80 results on '"Xiao, Chunxia"'
Search Results
2. Remote Sensing Image Classification Based on Neural Networks Designed Using an Efficient Neural Architecture Search Methodology.
- Author
-
Song, Lan, Ding, Lixin, Yin, Mengjia, Ding, Wei, Zeng, Zhigao, and Xiao, Chunxia
- Subjects
IMAGE recognition (Computer vision) ,NEURAL development ,MACHINE learning ,DISTANCE education ,REMOTE sensing ,DEEP learning ,NETWORK-attached storage - Abstract
Successful applications of machine learning for the analysis of remote sensing images remain limited by the difficulty of designing neural networks manually. However, while the development of neural architecture search offers the unique potential for discovering new and more effective network architectures, existing neural architecture search algorithms are computationally intensive methods requiring a large amount of data and computational resources and are therefore challenging to apply for developing optimal neural network architectures for remote sensing image classification. Our proposed method uses a differentiable neural architecture search approach for remote sensing image classification. We utilize a binary gate strategy for partial channel connections to reduce the sizes of the network parameters, creating a sparse connection pattern that lowers memory consumption and NAS computational costs. Experimental results indicate that our method achieves a 15.1% increase in validation accuracy during the search phase compared to DDSAS, although slightly lower (by 4.5%) than DARTS. However, we reduced the search time by 88% and network parameter size by 84% compared to DARTS. In the architecture evaluation phase, our method demonstrates a 2.79% improvement in validation accuracy over a manually configured CNN network. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
3. CRD-CGAN: category-consistent and relativistic constraints for diverse text-to-image generation.
- Author
-
Hu, Tao, Long, Chengjiang, and Xiao, Chunxia
- Abstract
Generating photo-realistic images from a text description is a challenging problem in computer vision. Previous works have shown promising performance to generate synthetic images conditional on text by Generative Adversarial Networks (GANs). In this paper, we focus on the category-consistent and relativistic diverse constraints to optimize the diversity of synthetic images. Based on those constraints, a category-consistent and relativistic diverse conditional GAN (CRD-CGAN) is proposed to synthesize K photo-realistic images simultaneously. We use the attention loss and diversity loss to improve the sensitivity of the GAN to word attention and noises. Then, we employ the relativistic conditional loss to estimate the probability of relatively real or fake for synthetic images, which can improve the performance of basic conditional loss. Finally, we introduce a category-consistent loss to alleviate the over-category issues between K synthetic images. We evaluate our approach using the Caltech-UCSD Birds-200-2011, Oxford 102 flower and MS COCO 2014 datasets, and the extensive experiments demonstrate superiority of the proposed method in comparison with state-of-the-art methods in terms of photorealistic and diversity of the generated synthetic images. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
4. Towards High-Resolution Specular Highlight Detection.
- Author
-
Fu, Gang, Zhang, Qing, Zhu, Lei, Lin, Qifeng, Wang, Yihao, Fan, Siyuan, and Xiao, Chunxia
- Subjects
COMPUTER vision ,DEEP learning ,APPLICATION software ,RESEARCH personnel ,INPAINTING ,IMAGE processing - Abstract
Specular highlight detection is an essential task with various applications in computer vision. This paper aims to detect specular highlights in single high-resolution images using deep learning while avoiding excessive GPU memory consumption. To achieve this, we present a high-resolution specular highlight detection dataset with manual annotations of specular highlights. Given our dataset, we propose a patch-level bidirectional refinement network for high-resolution specular highlight detection. The main idea is to utilize both the pathway from small-scale patch to large-scale patch and its reverse pathway to progressively refine the detection results of adjacent-scale specular highlight patches. Moreover, based on our detection network, we propose a modified inpainting framework for specular highlight removal as an application. Lastly, we provide ten potential research directions for specular highlight detection, inspiring researchers for further study. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
5. Facial Image Shadow Removal via Graph‐based Feature Fusion.
- Author
-
Zhang, Ling, Chen, Ben, Liu, Zheng, and Xiao, Chunxia
- Abstract
Despite natural image shadow removal methods have made significant progress, they often perform poorly for facial image due to the unique features of the face. Moreover, most learning‐based methods are designed based on pixel‐level strategies, ignoring the global contextual relationship in the image. In this paper, we propose a graph‐based feature fusion network (GraphFFNet) for facial image shadow removal. We apply a graph‐based convolution encoder (GCEncoder) to extract global contextual relationships between regions in the coarse shadow‐less image produced by an image flipper. Then, we introduce a feature modulation module to fuse the global topological relation onto the image features, enhancing the feature representation of the network. Finally, the fusion decoder integrates all the effective features to reconstruct the image features, producing a satisfactory shadow‐removal result. Experimental results demonstrate the superiority of the proposed GraphFFNet over the state‐of‐the‐art and validate the effectiveness of facial image shadow removal. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
6. Effect of Adding Fermented Proso Millet Bran Dietary Fiber on Micro-Structural, Physicochemical, and Digestive Properties of Gluten-Free Proso Millet-Based Dough and Cake.
- Author
-
Xiao, Jing, Li, Yinxia, Niu, Li, Chen, Ronghui, Tang, Jiayu, Tong, Zongbo, and Xiao, Chunxia
- Subjects
BROOMCORN millet ,FLOUR ,DIETARY fiber ,BRAN ,DOUGH ,FUNCTIONAL foods ,GUAR gum - Abstract
The increasing demand for functional foods has pushed the food industry to produce fiber-enriched products. In this study, rheological, microstructural, physicochemical, and functional characteristics were investigated for whole proso millet dough and cake, fortified with fermented proso millet bran dietary fiber flour (F-DF). Results showed that proso millet flour is less absorbent and stable than the control group. Adding proso millet flour and F-DF reduced the elasticity of the dough and increased its hardness, but had no significant effect on viscosity, cohesion, and resilience. The microstructure analysis exhibited an unformed continuous network formation in proso millet dough. Analyses suggested that proso millet flour combined with the fermented dietary fiber group had significantly higher total phenol content (0.46 GAE mg/g), DPPH• scavenging activity (66.84%), and ABTS•+ scavenging activity (87.01%) than did the other group. In addition, F-DF led to a significant reduction in the predicted released glucose contents of reformulated cakes. In summary, cakes prepared with the involvement of whole proso millet flour and F-DF exhibited less adverse sensory impact and possessed the potential to decrease postprandial blood glucose levels resulting purely from cake consumption. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
7. Monocular human depth estimation with 3D motion flow and surface normals.
- Author
-
Li, Yuanzhen, Luo, Fei, and Xiao, Chunxia
- Subjects
MONOCULARS ,HUMAN body ,HUMAN beings - Abstract
We propose a novel monocular human depth estimation method using video sequences as training data. We jointly train the depth and 3D motion flow networks with photometric and 3D geometric consistency constraints. Instead of depth ground truth, we take the surface normal as the pseudo-label to supervise the depth network learning. The estimated depth may exist texture copy artifact when the clothes on the human body have patterns and text marks (non-dominant color). Thus, we also propose an approach to alleviate the texture copy problem by estimating and adjusting the color of non-dominant color areas. Extensive experiments on public datasets and the Internet have been conducted. The comparison results prove that our method can produce competitive human depth estimation and has better generalization ability than state-of-the-art methods. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
8. Involvement of intestinal flora and miRNA into the mechanism of coarse grains improving type 2 diabetes: an overview.
- Author
-
Deng, Xu, Niu, Li, Xiao, Jing, Guo, Qianqian, Liang, Jiayi, Tang, Jiayu, Liu, Xuebo, and Xiao, Chunxia
- Subjects
TYPE 2 diabetes ,BOTANY ,GRAIN ,MICRORNA ,INTESTINES ,GENE expression ,WHOLE grain foods - Abstract
The prevalence of type 2 diabetes has been growing at an increasing rate worldwide. Dietary therapy is probably the easiest and least expensive method to prevent and treat diabetes. Previous studies have reported that coarse grains have anti‐diabetic effects. Although considerable efforts have been made on the anti‐diabetic function of different grains, the mechanisms of coarse grains on type 2 diabetes have not been systematically compared and summarized so far. Intestinal flora, reported as the main 'organ' of action underlying coarse grains, is an important factor in the alleviation of type 2 diabetes by coarse grains. Furthermore, microRNA (miRNA), as a new disease marker and 'dark nutrient', plays a likely influential role in cross‐border communication among coarse grains, intestinal flora, and hosts. Given this context, this article reviews several possible mechanisms for the role of coarse grains on diabetes, incorporating resistance to inflammation and oxidative stress, repair of insulin signaling and β‐cell dysfunction, and highlights the regulation of intestinal flora disorders and miRNAs expression, along with some novel insights. © 2022 Society of Chemical Industry. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
9. Lactobacillus plantarum LLY-606 supplementation ameliorates hyperuricemia via modulating intestinal homeostasis and relieving inflammation.
- Author
-
Shi, Renjie, Ye, Jin, Fan, Hua, Xiao, Chunxia, Wang, Danna, Xia, Bing, Zhao, Zhenting, Zhao, Beita, Dai, Xiaoshuang, and Liu, Xuebo
- Published
- 2023
- Full Text
- View/download PDF
10. Unsupervised Intrinsic Image Decomposition Using Internal Self-Similarity Cues.
- Author
-
Zhang, Qing, Zhou, Jin, Zhu, Lei, Sun, Wei, Xiao, Chunxia, and Zheng, Wei-Shi
- Subjects
SUPERVISED learning ,ACOUSTIC surface waves ,DECOMPOSITION method - Abstract
Recent learning-based intrinsic image decomposition methods have achieved remarkable progress. However, they usually require massive ground truth intrinsic images for supervised learning, which limits their applicability on real-world images since obtaining ground truth intrinsic decomposition for natural images is very challenging. In this paper, we present an unsupervised framework that is able to learn the decomposition effectively from a single natural image by training solely with the image itself. Our approach is built upon the observations that the reflectance of a natural image typically has high internal self-similarity of patches, and a convolutional generation network tends to boost the self-similarity of an image when trained for image reconstruction. Based on the observations, an unsupervised intrinsic decomposition network (UIDNet) consisting of two fully convolutional encoder-decoder sub-networks, i.e., reflectance prediction network (RPN) and shading prediction network (SPN), is devised to decompose an image into reflectance and shading by promoting the internal self-similarity of the reflectance component, in a way that jointly trains RPN and SPN to reproduce the given image. A novel loss function is also designed to make effective the training for intrinsic decomposition. Experimental results on three benchmark real-world datasets demonstrate the superiority of the proposed method. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
11. Unsupervised Intrinsic Image Decomposition Using Internal Self-Similarity Cues.
- Author
-
Zhang, Qing, Zhou, Jin, Zhu, Lei, Sun, Wei, Xiao, Chunxia, and Zheng, Wei-Shi
- Subjects
SUPERVISED learning ,ACOUSTIC surface waves ,DECOMPOSITION method - Abstract
Recent learning-based intrinsic image decomposition methods have achieved remarkable progress. However, they usually require massive ground truth intrinsic images for supervised learning, which limits their applicability on real-world images since obtaining ground truth intrinsic decomposition for natural images is very challenging. In this paper, we present an unsupervised framework that is able to learn the decomposition effectively from a single natural image by training solely with the image itself. Our approach is built upon the observations that the reflectance of a natural image typically has high internal self-similarity of patches, and a convolutional generation network tends to boost the self-similarity of an image when trained for image reconstruction. Based on the observations, an unsupervised intrinsic decomposition network (UIDNet) consisting of two fully convolutional encoder-decoder sub-networks, i.e., reflectance prediction network (RPN) and shading prediction network (SPN), is devised to decompose an image into reflectance and shading by promoting the internal self-similarity of the reflectance component, in a way that jointly trains RPN and SPN to reproduce the given image. A novel loss function is also designed to make effective the training for intrinsic decomposition. Experimental results on three benchmark real-world datasets demonstrate the superiority of the proposed method. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
12. Self-supervised coarse-to-fine monocular depth estimation using a lightweight attention module.
- Author
-
Li, Yuanzhen, Luo, Fei, and Xiao, Chunxia
- Subjects
MONOCULARS ,MACHINE learning - Abstract
Self-supervised monocular depth estimation has been widely investigated and applied in previous works. However, existing methods suffer from texture-copy, depth drift, and incomplete structure. It is difficult for normal CNN networks to completely understand the relationship between the object and its surrounding environment. Moreover, it is hard to design the depth smoothness loss to balance depth smoothness and sharpness. To address these issues, we propose a coarse-to-fine method with a normalized convolutional block attention module (NCBAM). In the coarse estimation stage, we incorporate the NCBAM into depth and pose networks to overcome the texture-copy and depth drift problems. Then, we use a new network to refine the coarse depth guided by the color image and produce a structure-preserving depth result in the refinement stage. Our method can produce results competitive with state-of-the-art methods. Comprehensive experiments prove the effectiveness of our two-stage method using the NCBAM. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
13. NeuralRoom: Geometry-Constrained Neural Implicit Surfaces for Indoor Scene Reconstruction.
- Author
-
Wang, Yusen, Li, Zongcheng, Jiang, Yu, Zhou, Kaixuan, Cao, Tuo, Fu, Yanping, and Xiao, Chunxia
- Subjects
SURFACE reconstruction ,SPATIAL variation ,GEOMETRIC surfaces ,AMBIGUITY ,WINDOW blinds - Abstract
We present a novel neural surface reconstruction method called NeuralRoom for reconstructing room-sized indoor scenes directly from a set of 2D images. Recently, implicit neural representations have become a promising way to reconstruct surfaces from multiview images due to their high-quality results and simplicity. However, implicit neural representations usually cannot reconstruct indoor scenes well because they suffer severe shape-radiance ambiguity. We assume that the indoor scene consists of texture-rich and flat texture-less regions. In texture-rich regions, the multiview stereo can obtain accurate results. In the flat area, normal estimation networks usually obtain a good normal estimation. Based on the above observations, we reduce the possible spatial variation range of implicit neural surfaces by reliable geometric priors to alleviate shape-radiance ambiguity. Specifically, we use multiview stereo results to limit the NeuralRoom optimization space and then use reliable geometric priors to guide NeuralRoom training. Then the NeuralRoom would produce a neural scene representation that can render an image consistent with the input training images. In addition, we propose a smoothing method called perturbation-residual restrictions to improve the accuracy and completeness of the flat region, which assumes that the sampling points in a local surface should have the same normal and similar distance to the observation center. Experiments on the ScanNet dataset show that our method can reconstruct the texture-less area of indoor scenes while maintaining the accuracy of detail. We also apply NeuralRoom to more advanced multiview reconstruction algorithms and significantly improve their reconstruction quality. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
14. Targeted delivery of emamectin benzoate by functionalized polysuccinimide nanoparticles for the flowering cabbage and controlling Plutella xylostella.
- Author
-
Ye, Xu, Liu, Meichen, Zhao, Ning, Xiao, Chunxia, Xu, Hanhong, and Jia, Jinliang
- Subjects
EMAMECTIN benzoate ,DIAMONDBACK moth ,TURNIPS ,PEST control ,CABBAGE ,NANOPARTICLES - Abstract
BACKGROUND: Plutella xylostella, one of the most destructive and cosmopolitan pests of cruciferous crops, is especially harmful to the young tissues of the flowering cabbage (Brassica campestris L.). Although emamectin benzoate (EB) has high insecticidal activity against P. xylostella, one major reason of low utilization for EB is the lack of internal transport in the young plants. RESULTS: In this study, four kinds of functional EB/polysuccinimide (PSI) with glycine methylester nanoparticles (EB@PGA NPs) were prepared. The obtained EB@PGA NPs could effectively protect EB from photolysis, and the degradation rate of EB@PGA NPs was <30% in 24 h. Simulating the intestinal pH = 9 of P. xylostella, the highest cumulative release rate of EB@PGA NPs could reach 89.61% in 24 h. Furthermore, EB@PGA NPs could delivery EB into the young tissues of the flowering cabbage through the nanocarrier, and the highest transport efficiency of EB@PGA25 reached 1.437%. The bioactivity of EB@PGA25 against P. xylostella larvae (LC50 = 0.34 μg mL−1) was 1.6‐fold higher than that of EB (LC50 = 0.53 μg mL−1). EB@PGA could easily become 'internalized' into the intestinal wall of P. xylostella, thus increasing the penetration of the drug and enhancing the insecticidal activity. CONCLUSION: The accurate delivery of insecticides by PGA nanocarriers into young tissues of plants could be a promising new method for the efficient management of field pests and diseases. © 2021 Society of Chemical Industry. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
15. Luminance Attentive Networks for HDR Image and Panorama Reconstruction.
- Author
-
Yu, Hanning, Liu, Wentao, Long, Chengjiang, Dong, Bo, Zou, Qin, and Xiao, Chunxia
- Subjects
IMAGE reconstruction ,PROBLEM solving ,HIGH dynamic range imaging ,REAL numbers ,SOURCE code ,WAGE payment systems - Abstract
It is very challenging to reconstruct a high dynamic range (HDR) from a low dynamic range (LDR) image as an ill‐posed problem. This paper proposes a luminance attentive network named LANet for HDR reconstruction from a single LDR image. Our method is based on two fundamental observations: (1) HDR images stored in relative luminance are scale‐invariant, which means the HDR images will hold the same information when multiplied by any positive real number. Based on this observation, we propose a novel normalization method called "HDR calibration "for HDR images stored in relative luminance, calibrating HDR images into a similar luminance scale according to the LDR images. (2) The main difference between HDR images and LDR images is in under‐/over‐exposed areas, especially those highlighted. Following this observation, we propose a luminance attention module with a two‐stream structure for LANet to pay more attention to the under‐/over‐exposed areas. In addition, we propose an extended network called panoLANet for HDR panorama reconstruction from an LDR panorama and build a dualnet structure for panoLANet to solve the distortion problem caused by the equirectangular panorama. Extensive experiments show that our proposed approach LANet can reconstruct visually convincing HDR images and demonstrate its superiority over state‐of‐the‐art approaches in terms of all metrics in inverse tone mapping. The image‐based lighting application with our proposed panoLANet also demonstrates that our method can simulate natural scene lighting using only LDR panorama. Our source code is available at https://github.com/LWT3437/LANet. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
16. Self-supervised monocular depth estimation based on image texture detail enhancement.
- Author
-
Li, Yuanzhen, Luo, Fei, Li, Wenjie, Zheng, Shenjie, Wu, Huan-huan, and Xiao, Chunxia
- Subjects
MONOCULARS ,TEXTURES - Abstract
We present a new self-supervised monocular depth estimation method with multi-scale texture detail enhancement. Based on the observation that the image texture detail and the semantic information have essential significance on the depth estimation, we propose to provide them to the network to learn more sharpness and structural integrity of depth. Firstly, we generate the filtered images and detail images by multi-scale decomposition and use a deep neural network to automatically learn their weights to construct the texture detail enhanced image. Then, we consider the semantic features by putting deep features from the VGG-19 network into a self-attention network, guide the depth decoder network to focus on the integrity of objects in the scene. Finally, we propose a scale-invariant smooth loss to improve the structural integrity of the predicted depth. We evaluate our method on the KITTI 2015 and Make3D datasets and apply the predicted depth to novel view synthesis. The experimental results show that it has achieved satisfactory results compared with the existing methods. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
17. An adaptive stacked hourglass network with Kalman filter for estimating 2D human pose in video.
- Author
-
Hu, Tao, Xiao, Chunxia, Min, Geyong, and Najjari, Noushin
- Subjects
DEEP learning ,KALMAN filtering ,STREAMING video & television ,IMAGE processing ,HUMAN beings ,COMPUTER science ,SINGLE people - Abstract
One of the main challenges in computer science and image processing is 2D human pose estimation. Specifically, occlusion and in particular occlusion of human joints caused by camera angle are of paramount importance. In this paper, a new highly accurate network was proposed that can estimate 2D human poses in video images using deep learning. We employ the Single Shot MultiBox Detector network to detect the centre position of each human within a video frame and then use the stacked hourglass network to estimate the 2D human pose. We approximate the human motion as a linear motion between different frames in a certain period; and optimize the human centres based on the local outlier factor and Kalman filters. The same method is applied to optimize the human pose estimations in video, which can address the inaccurate prediction caused by human joints occlusion. The proposed adaptive network is tested using the two well‐known benchmarks for human pose estimation (MPII and Joint‐annotated Human Motion Data Base datasets), and we also generate some 2D human pose estimating qualitative results of single and multiple people in Internet videos. The experimental results show that the proposed network has strong practicability and can achieve high accuracy on adaptive estimating the 2D human pose in video. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
18. A Novel Visual Representation on Text Using Diverse Conditional GAN for Visual Recognition.
- Author
-
Hu, Tao, Long, Chengjiang, and Xiao, Chunxia
- Subjects
GENERATIVE adversarial networks ,SOCIAL media ,TEXT recognition ,GALLIUM nitride ,IMAGE recognition (Computer vision) - Abstract
Automatic image visual recognition can make full use of largely available images with text descriptions on social media platforms to build large-scale image labeled datasets. In this paper, we propose a novel visual text representation, named DG-VRT (Diverse GAN-Visual Representation on Text), which extracts visual features from synthetic images generated by a diverse conditional Generative Adversarial Network (DCGAN) on the text, for visual recognition. The DCGAN incorporates the current state-of-the-art text-to-image GANs and generates multiple synthetic images with various prior noises conditioned on a text. Then we extract deep visual features from the generated synthetic images to explore the underlying visual concepts and provide a visual transformation on text in feature space. Finally, we combine image-level visual features, text-level features and visual features based on synthetic images together to recognize the images, and we also extend the proposed work to semantic segmentation. We conduct extensive experiments on two benchmark datasets and the experimental results demonstrate the efficacy of our proposed representation on text for visual recognition. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
19. Towards Interpretable Arrhythmia Classification With Human-Machine Collaborative Knowledge Representation.
- Author
-
Wang, Jilong, Li, Rui, Li, Renfa, Fu, Bin, Xiao, Chunxia, and Chen, Danny Z.
- Subjects
KNOWLEDGE representation (Information theory) ,DEEP learning ,ARRHYTHMIA ,DIAGNOSIS ,CLASSIFICATION ,HUMAN-machine systems - Abstract
Arrhythmia detection and classification is a crucial step for diagnosing cardiovascular diseases. However, deep learning models that are commonly used and trained in end-to-end fashion are not able to provide good interpretability. In this paper, we address this deficiency by proposing the first novel interpretable arrhythmia classification approach based on a human-machine collaborative knowledge representation. Our approach first employs an AutoEncoder to encode electrocardiogram signals into two parts: hand-encoding knowledge and machine-encoding knowledge. A classifier then takes as input the encoded knowledge to classify arrhythmia heartbeats with or without human in the loop (HIL). Experiments and evaluation on the MIT-BIH Arrhythmia Database demonstrate that our new approach not only can effectively classify arrhythmia while offering interpretability, but also can improve the classification accuracy by adjusting the hand-encoding knowledge with our HIL mechanism. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
20. Effects of insoluble dietary fiber from kiwi fruit pomace on the physicochemical properties and sensory characteristics of low-fat pork meatballs.
- Author
-
Zhao, Dingwei, Guo, Chenxi, Liu, Xuebo, and Xiao, Chunxia
- Abstract
As beverage industry by product, kiwi fruit pomace is potential but underutilized. In this study, insoluble dietary fiber from kiwi fruit pomace was modified via ultra-fine pulverization. The physicochemical and functional properties of kiwi fruit insoluble dietary fiber (KWIDF) superfine powder and its application in pork meatballs as a fat substitute were investigated. The SEM and droplet size measurement results revealed that the specific surface area of KWIDF increased from 44.4 to 192.9 m
2 kg−1 . The swelling capacity, water-, oil- and fat-holding capacities increased by 51.61%, 40.21%, 46.09% and 47.01%, respectively. The poisonous substances adsorbing abilities and the inhibition of enzyme activities were also improved. Similarly, KWIDF adsorbed cholesterol and glucose preferably. In addition, KWIDF revealed significant dose–response effects on the nutritional within a meat matrix, quality and sensory characteristics in meatballs (P < 0.05). The addition of 3% KWIDF superfine powder was found most suitable with high acceptability overall. [ABSTRACT FROM AUTHOR]- Published
- 2021
- Full Text
- View/download PDF
21. Online MECG Compression Based on Incremental Tensor Decomposition for Wearable Devices.
- Author
-
Xiao, Ling, Zhang, Qian, Xie, Kun, and Xiao, Chunxia
- Subjects
DATA compression ,ROBOTIC exoskeletons ,ELECTROCARDIOGRAPHY - Abstract
Lightweight and real-time multi-lead electrocardiogram (MECG) compression on wearable devices is important and challenging for long-term health monitoring. To utilize all three kinds of correlations of MECG data simultaneously, we construct 3-order incremental tensor and formulate data compression problem as tensor decomposition. However, the conventional tensor decomposition algorithms for large-scale tensor are usually too computationally expensive to apply to wearable devices. To reduce the computation complexity, we develop online compression approach by incremental tracking the CANDECOMP/PARAFAC (CP) decomposition of dynamic incremental tensors, which can efficiently utilize the tensor compression result based on the previous MECG data to derive the tensor compression upon arriving of new data. We evaluate the performance of our method with the Physikalisch-Technische Bundesanstalt MECG diagnostic dataset. Our method can achieve the averaged percentage root-mean-square difference (PRD) of 8.35% ± 2.28% and the compression ratio (CR) of 43.05 ± 2.01, which is better than five state-of-the-art of methods. Additionally, it can also well preserve the information of R-peak. Our method is suitable for near real-time MECG compression on wearable devices. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
22. Dense multiview stereo based on image texture enhancement.
- Author
-
Liao, Jie, Wei, Mengqiang, Fu, Yanping, Yan, Qingan, and Xiao, Chunxia
- Subjects
STEREO image ,IMAGE intensifiers ,POINT cloud ,GEOMETRY - Abstract
In this paper, we propose a novel Multiview Stereo (MVS) method which can effectively estimate geometry in low‐textured regions. Conventional MVS algorithms predict geometry by performing dense correspondence estimation across multiple views under the constraint of epipolar geometry. As low‐textured regions contain less feature information for reliable matching, estimating geometry for low‐textured regions remains hard work for previous MVS methods. To address this issue, we propose an MVS method based on texture enhancement. By enhancing texture information for each input image via our multiscale bilateral decomposition and reconstruction algorithm, our method can estimate reliable geometry for low‐textured regions that are intractable for previous MVS methods. To densify the final output point cloud, we further propose a novel selective joint bilateral propagation filter, which can effectively propagate reliable geometry estimation to neighboring unpredicted regions. We validate the effectiveness of our method on the ETH3D benchmark. Quantitative and qualitative comparisons demonstrate that our method can significantly improve the quality of reconstruction in low‐textured regions. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
23. Thin Cloud Removal for Single RGB Aerial Image.
- Author
-
Song, Chengfang, Xiao, Chunxia, Zhang, Yeting, and Sui, Haigang
- Subjects
ATMOSPHERIC models ,COMPUTATIONAL photography ,HAZE ,COLOR - Abstract
Acquired above variable clouds, aerial images contain the components of ground reflection and cloud effect. Due to the non‐uniformity, clouds in aerial images are even harder to remove than haze in terrestrial images. This paper proposes a divide‐and‐conquer scheme to remove the thin translucent clouds in a single RGB aerial image. Based on colour attenuation prior, we design a kind of veiling metric that indicates the local concentration of clouds effectively. By this metric, an aerial image containing thickness‐varied clouds is segmented into multiple regions. Each region is veiled by clouds of nearly‐equal concentration, and hence subject to common assumptions, such as boundary constraint on transmission. The atmospheric light in each region is estimated by the modified local colour‐line model and composed into a spatially‐varying airlight map for the entire image. Then scene transmission is estimated and further refined by a weighted L1‐norm based contextual regularization. Finally, we recover ground reflection via the atmospheric scattering model. We verify our cloud removal method on a number of aerial images containing thin clouds and compare our results with classical single‐image dehazing methods and the state‐of‐the‐art learning‐based declouding method, respectively. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
24. Shading-aware shadow detection and removal from a single image.
- Author
-
Fan, Xinyun, Wu, Wenjun, Zhang, Ling, Yan, Qingan, Fu, Gang, Chen, Zipei, Long, Chengjiang, and Xiao, Chunxia
- Subjects
SHADES & shadows ,ALGORITHMS ,IMAGE - Abstract
Shadow removal is a challenging problem due to its sensitivity to lighting and material conditions. In this paper, we propose a shading-aware shadow processing algorithm, which can automatically detect and remove complex shadows from a single color image. Our framework consists of two key steps. We firstly conduct a shadow-preserving filter upon the image which will effectively remove the image texture while preserving the shadow and shading information. Shadow regions are estimated by establishing a confidence map from the filtered image incorporating depth cue. We then develop a shading-aware optimization framework to remove shadows and recover shading in these regions. The extensive experimental results show that the proposed algorithm produces visually compelling results in a series of challenging images and it can handle complex shadows in both indoor and outdoor scenes. Quantitative and qualitative comparisons with current state-of-the-art methods strongly demonstrate the efficacy of our proposed approach. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF
25. Real-time dense 3D reconstruction and camera tracking via embedded planes representation.
- Author
-
Fu, Yanping, Yan, Qingan, Liao, Jie, Chow, Alix L. H., and Xiao, Chunxia
- Subjects
ALGORITHMS ,CAMERAS ,POINT cloud ,AEROSPACE planes ,POSE estimation (Computer vision) ,TOPOLOGY ,ARTIFICIAL satellite tracking - Abstract
This paper proposes a novel approach for robust plane matching and real-time RGB-D fusion based on the representation of plane parameter space. In contrast to previous planar-based SLAM algorithms estimating correspondences for each plane-pair independently, our method instead explores the holistic topology of all relevant planes. We note that by adopting the low-dimensionality parameter space representation, the plane matching can be intuitively reformulated and solved as a point cloud registration problem. Besides estimating the plane correspondences, we contribute an efficient optimization framework, which employs both frame-to-frame and frame-to-model planar consistency constraints. We propose a global plane map to dynamically represent the reconstructed scene and alleviate accumulation errors that exist in camera pose tracking. We validate the proposed algorithm on standard benchmark datasets and additional challenging real-world environments. The experimental results demonstrate its outperformance to current state-of-the-art methods in tracking robustness and reconstruction fidelity. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF
26. CLA‐GAN: A Context and Lightness Aware Generative Adversarial Network for Shadow Removal.
- Author
-
Zhang, Ling, Long, Chengjiang, Yan, Qingan, Zhang, Xiaolong, and Xiao, Chunxia
- Subjects
SHADES & shadows ,COST functions - Abstract
In this paper, we propose a novel context and lightness aware Generative Adversarial Network (CLA‐GAN) framework for shadow removal, which refines a coarse result to a final shadow removal result in a coarse‐to‐fine fashion. At the refinement stage, we first obtain a lightness map using an encoder‐decoder structure. With the lightness map and the coarse result as the inputs, the following encoder‐decoder tries to refine the final result. Specifically, different from current methods restricted pixel‐based features from shadow images, we embed a context‐aware module into the refinement stage, which exploits patch‐based features. The embedded module transfers features from non‐shadow regions to shadow regions to ensure the consistency in appearance in the recovered shadow‐free images. Since we consider pathces, the module can additionally enhance the spatial association and continuity around neighboring pixels. To make the model pay more attention to shadow regions during training, we use dynamic weights in the loss function. Moreover, we augment the inputs of the discriminator by rotating images in different degrees and use rotation adversarial loss during training, which can make the discriminator more stable and robust. Extensive experiments demonstrate the validity of the components in our CLA‐GAN framework. Quantitative evaluation on different shadow datasets clearly shows the advantages of our CLA‐GAN over the state‐of‐the‐art methods. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF
27. S3D: Scalable Pedestrian Detection via Score Scale Surface Discrimination.
- Author
-
Wang, Xiao, Liang, Chao, Chen, Chen, Chen, Jun, Wang, Zheng, Han, Zhen, and Xiao, Chunxia
- Subjects
PEDESTRIANS ,VIDEO surveillance ,COMPUTER vision - Abstract
Pedestrian detection has remained an important research topic in both the computer vision and multimedia communities because of its importance in practical applications, such as driving assistance and video surveillance. Existing methods compare the response score with a fixed threshold to determine whether a candidate region contains pedestrians and produce dissatisfactory results that contain either missed detections or false detections, which are difficult to balance. This situation has a serious impact under the condition of variable scale. This paper investigates the functional relationship between the scores and scales of pedestrians. By designing experiments with multiple scales, we have found a discriminant surface in the score scale space. Pedestrians can be distinguished at various scale levels according to their locations on the discriminant surface. The proposed approach is evaluated using four challenging pedestrian detection datasets, including Caltech, INRIA, ETH, and KITTI, and the superior experimental results are achieved when compared with baseline methods. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF
28. Effect of silane coupling agent on properties of silane modified polyether waterproof sealant.
- Author
-
XIAO Chunxia, HUANG Kun, SHEN Peiliang, WANG Xiaoli, and YANG Sheng
- Abstract
Low modulus single component silane modified polyether sealant is prepared with self -made silane modified polyether resin. The tensile modulus, elongation at break and elastic recovery rate of the sealant were studied. The effects of silane coupling agent on water adhesion, surface drying time and tensile modulus were investigated. The most appropriate type and dosage of silane coupling agent was determined. The results show that KH792 is the optimal silane coupling agent in the formulation system. When the dosage is 5, the surface drying time of the prepared sealant is 20 min, the elastic recovery rate is 82.03%, the tensile modulus is 0.25 MPa, and the elongation at break is 626%. [ABSTRACT FROM AUTHOR]
- Published
- 2021
29. Transparent object segmentation from casually captured videos.
- Author
-
Liao, Jie, Fu, Yanping, Yan, Qingan, and Xiao, Chunxia
- Subjects
IMAGE segmentation ,COMPUTER vision ,APPLICATION software ,VIDEOS ,VIDEO processing - Abstract
Segmentation of transparent objects from sequences can be very useful in computer vision applications. However, without additional auxiliary information it can be hard work for traditional segmentation methods, as light in the transparent area captured by RGB cameras mostly derive from the background and the appearance of transparent objects changes with surroundings. In this article, we present a from‐coarse‐to‐fine transparent object segmentation method, which utilizes trajectory clustering to roughly distinguish the transparent from the background and refine the segmentation based on combination information of color and distortion. We further incorporate the transparency saliency with color and trajectory smoothness throughout the video to acquire a spatiotemporal segmentation based on graph‐cut. We conduct our method on various datasets. The results demonstrate that our method can successfully segment transparent objects from the background. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF
30. Folding patch correspondence for multiview stereo.
- Author
-
Liao, Jie, Fu, Yanping, Yan, Qingan, and Xiao, Chunxia
- Subjects
PLANT surfaces ,GEOMETRIC surfaces ,LETTERS ,TRACKING algorithms ,ISOGEOMETRIC analysis - Abstract
In this article, we propose the novel folding patch model which can replace the traditional patch model utilized in patch‐based multiview stereo (MVS) methods to significantly improve the reconstruction results. The patch model is applied as an approximation of the scene surface differential in the geometric estimation procedure. By minimizing the photometric discrepancy of the projection of the patch model on multiple source images, patch‐based MVS algorithms optimize the position and normal values for the 3D hypothesis of the target pixel. The optimization is based on the assumption that the patch model can fit the target scene surface perfectly. However, when it comes to complex scenes crowded with sharp edges, splintery surfaces, or round surfaces, the patch model is inherently not suitable since even from the microscopic perspective these surfaces are not entirely flat. We construct the folding patch model by folding the traditional patch model from the middle line. By adjusting the folding angle and direction, the folding patch model can fit complex surfaces more flexibly. We apply our folding patch model to the representative open‐source patch based multiview stereo (PMVS) and COLMAP, and validate the effectiveness on ETH3D benchmark and data sets captured in nature. The results demonstrate that utilizing the folding patch model can significantly improve the behavior of PMVS and COLMAP, especially on data sets mainly consist of complex surfaces from plants. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF
31. Antifeeding effects of azadirachtin on the fifth instar Spodoptera litura larvae and the analysis of azadirachtin on target sensilla around mouthparts.
- Author
-
Qin, Deqiang, Zhang, Peiwen, Zhou, You, Liu, Benju, Xiao, Chunxia, Chen, Weibin, and Zhang, Zhixiang
- Published
- 2020
- Full Text
- View/download PDF
32. Fabrication of capsaicin emulsions: improving the stability of the system and relieving the irritation to the gastrointestinal tract of rats.
- Author
-
Han, Jingjing, Zhang, Shuhan, Liu, Xuebo, and Xiao, Chunxia
- Subjects
EMULSIONS ,POLYETHYLENE glycol ,ZETA potential ,RATS ,CAPSAICIN ,GASTROINTESTINAL system - Abstract
BACKGROUND: Capsaicin, as a major pungent ingredient of peppers, has many health benefits. However, the strong irritation effect of capsaicin inhibits its application in the food industry. Emulsions can be an effective approach to alleviate the irritation. RESULTS: In this study, we used tocopheryl polyethylene glycol 1000 succinate (TPGS) as an emulsifier to prepare capsaicin emulsions through high‐pressure homogenization. Capsaicin emulsions with a particle size of about 100 nm, −36.4 mV zeta potential, and 91.9% encapsulation efficiency were prepared successfully and showed better environmental stability and higher antioxidant activity. Emulsions reduced the cumulative release of capsaicin and had no toxic effect on buffalo rat liver (BRL‐3A) cells. Moreover, the gastrointestinal injury model of rats showed that emulsions reduced the strong irritation of capsaicin. CONCLUSION: This work provides a theoretical basis for the application of irritant ingredients in food industry. © 2019 Society of Chemical Industry [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF
33. Wavelet Flow: Optical Flow Guided Wavelet Facial Image Fusion.
- Author
-
Ding, Hong, Yan, Qingan, Fu, Gang, and Xiao, Chunxia
- Subjects
IMAGE fusion ,OPTICAL flow ,OPTICAL computing ,OPTICAL images ,COMPUTATIONAL photography ,REVUES - Abstract
Estimating the correspondence between the images using optical flow is the key component for image fusion, however, computing optical flow between a pair of facial images including backgrounds is challenging due to large differences in illumination, texture, color and background in the images. To improve optical flow results for image fusion, we propose a novel flow estimation method, wavelet flow, which can handle both the face and background in the input images. The key idea is that instead of computing flow directly between the input image pair, we estimate the image flow by incorporating multi‐scale image transfer and optical flow guided wavelet fusion. Multi‐scale image transfer helps to preserve the background and lighting detail of input, while optical flow guided wavelet fusion produces a series of intermediate images for further fusion quality optimizing. Our approach can significantly improve the performance of the optical flow algorithm and provide more natural fusion results for both faces and backgrounds in the images. We evaluate our method on a variety of datasets to show its high outperformance. [ABSTRACT FROM AUTHOR]
- Published
- 2019
- Full Text
- View/download PDF
34. Shadow Inpainting and Removal Using Generative Adversarial Networks with Slice Convolutions.
- Author
-
Wei, Jinjiang, Long, Chengjiang, Zou, Hua, and Xiao, Chunxia
- Subjects
PIXELS ,INPAINTING ,SHADES & shadows ,DEEP learning ,MATHEMATICAL convolutions - Abstract
In this paper, we propose a two‐stage top‐down and bottom‐up Generative Adversarial Networks (TBGANs) for shadow inpainting and removal which uses a novel top‐down encoder and a bottom‐up decoder with slice convolutions. These slice convolutions can effectively extract and restore the long‐range spatial information for either down‐sampling or up‐sampling. Different from the previous shadow removal methods based on deep learning, we propose to inpaint shadow to handle the possible dark shadows to achieve a coarse shadow‐removal image at the first stage, and then further recover the details and enhance the color and texture details with a non‐local block to explore both local and global inter‐dependencies of pixels at the second stage. With such a two‐stage coarse‐to‐fine processing, the overall effect of shadow removal is greatly improved, and the effect of color retention in non‐shaded areas is significant. By comparing with a variety of mainstream shadow removal methods, we demonstrate that our proposed method outperforms the state‐of‐the‐art methods. [ABSTRACT FROM AUTHOR]
- Published
- 2019
- Full Text
- View/download PDF
35. Pyramid Multi‐View Stereo with Local Consistency.
- Author
-
Liao, Jie, Fu, Yanping, Yan, Qingan, and Xiao, Chunxia
- Subjects
PIXELS ,PYRAMIDS ,TECHNOLOGY convergence ,GEOMETRY - Abstract
In this paper, we propose a PatchMatch‐based Multi‐View Stereo (MVS) algorithm which can efficiently estimate geometry for the textureless area. Conventional PatchMatch‐based MVS algorithms estimate depth and normal hypotheses mainly by optimizing photometric consistency metrics between patch in the reference image and its projection on other images. The photometric consistency works well in textured regions but can not discriminate textureless regions, which makes geometry estimation for textureless regions hard work. To address this issue, we introduce the local consistency. Based on the assumption that neighboring pixels with similar colors likely belong to the same surface and share approximate depth‐normal values, local consistency guides the depth and normal estimation with geometry from neighboring pixels with similar colors. To fasten the convergence of pixelwise local consistency across the image, we further introduce a pyramid architecture similar to previous work which can also provide coarse estimation at upper levels. We validate the effectiveness of our method on the ETH3D benchmark and Tanks and Temples benchmark. Results show that our method outperforms the state‐of‐the‐art. [ABSTRACT FROM AUTHOR]
- Published
- 2019
- Full Text
- View/download PDF
36. Specular Highlight Removal for Real‐world Images.
- Author
-
Fu, Gang, Zhang, Qing, Song, Chengfang, Lin, Qifeng, and Xiao, Chunxia
- Subjects
COMPUTER vision ,COLORING matter ,COMPUTATIONAL photography ,IMAGE ,COMPUTER graphics - Abstract
Removing specular highlight in an image is a fundamental research problem in computer vision and computer graphics. While various methods have been proposed, they typically do not work well for real‐world images due to the presence of rich textures, complex materials, hard shadows, occlusions and color illumination, etc. In this paper, we present a novel specular highlight removal method for real‐world images. Our approach is based on two observations of the real‐world images: (i) the specular highlight is often small in size and sparse in distribution; (ii) the remaining diffuse image can be represented by linear combination of a small number of basis colors with the sparse encoding coefficients. Based on the two observations, we design an optimization framework for simultaneously estimating the diffuse and specular highlight images from a single image. Specifically, we recover the diffuse components of those regions with specular highlight by encouraging the encoding coefficients sparseness using L0 norm. Moreover, the encoding coefficients and specular highlight are also subject to the non‐negativity according to the additive color mixing theory and the illumination definition, respectively. Extensive experiments have been performed on a variety of images to validate the effectiveness of the proposed method and its superiority over the previous methods. [ABSTRACT FROM AUTHOR]
- Published
- 2019
- Full Text
- View/download PDF
37. Scale‐adaptive Structure‐preserving Texture Filtering.
- Author
-
Song, Chengfang, Xiao, Chunxia, Lei, Ling, and Sui, Haigang
- Subjects
TEXTURES ,ADAPTIVE filters ,COMPUTATIONAL photography ,PIXELS - Abstract
This paper proposes a scale‐adaptive filtering method to improve the performance of structure‐preserving texture filtering for image smoothing. With classical texture filters, it usually is challenging to smooth texture at multiple scales while preserving salient structures in an image. We address this issue in the concept of adaptive bilateral filtering, where the scales of Gaussian range kernels are allowed to vary from pixel to pixel. Based on direction‐wise statistics, our method distinguishes texture from structure effectively, identifies appropriate scope around a pixel to be smoothed and thus infers an optimal smoothing scale for it. Filtering an image with varying‐scale kernels, the image is smoothed according to the distribution of texture adaptively. With commendable experimental results, we show that, needing less iterations, our proposed scheme boosts texture filtering performance in terms of preserving the geometric structures of multiple scales even after aggressive smoothing of the original image. [ABSTRACT FROM AUTHOR]
- Published
- 2019
- Full Text
- View/download PDF
38. Eriodictyol alleviates lipopolysaccharide‐triggered oxidative stress and synaptic dysfunctions in BV‐2 microglial cells and mouse brain.
- Author
-
He, Pandi, Yan, Shikai, Wen, Xin, Zhang, Shuhan, Liu, Zhigang, Liu, Xuebo, and Xiao, Chunxia
- Published
- 2019
- Full Text
- View/download PDF
39. Joint bilateral propagation upsampling for unstructured multi-view stereo.
- Author
-
Wei, Mengqiang, Yan, Qingan, Luo, Fei, Song, Chengfang, and Xiao, Chunxia
- Subjects
THREE-dimensional display systems ,GEOMETRY ,ALGORITHMS ,VIDEO coding - Abstract
In this paper, we explore a new way to accelerate and densify unstructured multi-view stereo (MVS). While many unstructured MVS algorithms have been proposed, we discover that the image-guided resizing can easily and significantly benefit their 3D reconstruction results in both efficiency and completeness. Therefore, we build our framework upon a novel selective joint bilateral upsampling and depth propagation strategy. First, we downsample the input unstructured images into lower resolution ones and perform the MVS calculation to efficiently obtain depth and normal maps from these resized pictures. Then, the proposed algorithm upsamples the normal maps with the guidance of input images, and jointly take them into consideration to recover the low-resolution depth maps into high resolution with geometry details simultaneously enriched. Finally by adaptively fusing the reconstructed depth and normal maps, we construct the final dense 3D scene. Quantitative results validate the efficiency and effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]
- Published
- 2019
- Full Text
- View/download PDF
40. Effective shadow removal via multi-scale image decomposition.
- Author
-
Zhang, Ling, Yan, Qingan, Zhu, Yao, Zhang, Xiaolong, and Xiao, Chunxia
- Subjects
SHADES & shadows ,SURFACES (Technology) - Abstract
Shadow removal is a fundamental and challenging problem in image processing field. Current approaches can only process shadows with simple scenes. For complex texture and illumination, the performance is less impressive. In this paper, we propose a novel shadow removal algorithm based on multi-scale image decomposition, which can recover the illumination for complex shadows with inconsistent illumination and different surface materials. Independent of shadow detection, our algorithm only requires a rough boundary distinguishing shadow regions from non-shadow regions. It first performs a multi-scale decomposition for the input image based on an illumination-sensitive smoothing process and then removes shadows in the basic layer using a local-to-global optimization strategy, which fuses all local shadow-free results in a global manner. Finally, we recover the texture details for the shadow-free basic layer and obtain the final shadow-free image. We validate the performance of the proposed method under various lighting and texture conditions and show consistent illumination between shadow and surrounding regions in the shadow removal results. [ABSTRACT FROM AUTHOR]
- Published
- 2019
- Full Text
- View/download PDF
41. Narrative Collage of Image Collections by Scene Graph Recombination.
- Author
-
Fang, Fei, Yi, Miao, Feng, Hui, Hu, Shenghong, and Xiao, Chunxia
- Subjects
COLLAGE ,DIGITAL image editing ,ACQUISITION of data ,DIGITAL image processing ,DATA extraction - Abstract
A narrative collage is an interesting image editing method for summarizing the main theme or storyline behind an image collection. We present a novel method to generate narrative images with plausible semantic scene structures. To achieve this goal, we introduce a layer graph and a scene graph to represent the relative depth order and semantic relationship between image objects, respectively. We first cluster the input image collection to select representative images, and then we extract a group of semantic salient objects from each representative image. Both layer graphs and scene graphs are constructed and combined according to our specific rules for reorganizing the extracted objects in every image. We design an energy model to appropriately locate every object on the final canvas. The experimental results show that our method can produce competitive narrative collage results and that it performs well on a wide range of image collections. [ABSTRACT FROM AUTHOR]
- Published
- 2018
- Full Text
- View/download PDF
42. Surface Reconstruction via Fusing Sparse-Sequence of Depth Images.
- Author
-
Yang, Long, Yan, Qingan, Fu, Yanping, and Xiao, Chunxia
- Subjects
IMAGE reconstruction ,ALGORITHMS ,MATHEMATICAL programming ,IMAGE processing ,ALGEBRA - Abstract
Handheld scanning using commodity depth cameras provides a flexible and low-cost manner to get 3D models. The existing methods scan a target by densely fusing all the captured depth images, yet most frames are redundant. The jittering frames inevitably embedded in handheld scanning process will cause feature blurring on the reconstructed model and even trigger the scan failure (i.e., camera tracking losing). To address these problems, in this paper, we propose a novel sparse-sequence fusion (SSF) algorithm for handheld scanning using commodity depth cameras. It first extracts related measurements for analyzing camera motion. Then based on these measurements, we progressively construct a supporting subset for the captured depth image sequence to decrease the data redundancy and the interference from jittering frames. Since SSF will reveal the intrinsic heavy noise of the original depth images, our method introduces a refinement process to eliminate the raw noise and recover geometric features for the depth images selected into the supporting subset. We finally obtain the fused result by integrating the refined depth images into the truncated signed distance field (TSDF) of the target. Multiple comparison experiments are conducted and the results verify the feasibility and validity of SSF for handheld scanning with a commodity depth camera. [ABSTRACT FROM AUTHOR]
- Published
- 2018
- Full Text
- View/download PDF
43. Distance field guided L1-median skeleton extraction.
- Author
-
Song, Chengfang, Pang, Zhiqiang, Jing, Xiaoyuan, and Xiao, Chunxia
- Subjects
CLOUD storage ,CLOUD computing ,DATA extraction ,AUTOMATIC extracting (Information science) ,TOPOLOGY - Abstract
We introduce a distance field guided L1
-median method to extract topologically clean 1D curve skeleton from the point cloud model. We first voxelize the input point cloud, and compute the distance field for the point cloud. Then with the distance field, we extract the initial skeleton of the model using a multi-scale parameter controlled thinning method. Finally, we incorporate the initial skeleton into the L1 -median optimization, and develop a distance field guided L1 -median to effectively extract the complete skeleton from the point cloud. Our method exhibits the advantages of both the distance field based skeleton extraction methods and the L1 -median skeleton extraction methods. Our skeleton extraction system is robust and effective, and can be applied to the raw scanned point cloud data. [ABSTRACT FROM AUTHOR] - Published
- 2018
- Full Text
- View/download PDF
44. High glucose levels impact visual response properties of retinal ganglion cells in C57 mice-An in vitro physiological study.
- Author
-
Zhou, Yuan, Xiao, Chunxia, and Pu, Mingliang
- Abstract
This study investigated visual response properties of retinal ganglion cells (RGCs) under high glucose levels. Extracellular single-unit responses of RGCs from mouse retinas were recorded. And the eyecup was prepared as a flat mount in a recording chamber and superfused with Ames medium. The averaged RF size of the ON RGCs (34.1±2.9, n=14) was significantly smaller than the OFF RGCs under the HG (49.3±0.3, n=12) ( P<0.0001) conditions. The same reduction pattern was also observed in the osmotic control group (HM) between ON and OFF RGCs ( P<0.0001). The averaged luminance threshold (LT) of ON RGCs increased significantly under HG or HM (HG: P<0.0001; HM: P<0.0002). OFF RGCs exhibited a similar response pattern under the same conditions (HG: P<0.01; HM: P<0.0002). The averaged contrast gain of ON cells was significantly lower than that of OFF cells with the HM treatment ( P<0.015, unpaired Student's t test). The averaged contrast gain of ON cells was significantly higher than OFF cells with the HG treatment ( P<0.0001). The present results suggest that HG reduced receptive field center size, suppressed luminance threshold, and attenuated contrast gain of RGCs. The impact of HG on ON and OFF RGCs may be mediated via different mechanisms. [ABSTRACT FROM AUTHOR]
- Published
- 2017
- Full Text
- View/download PDF
45. Video Shadow Removal Using Spatio-temporal Illumination Transfer.
- Author
-
Zhang, Ling, Zhu, Yao, Liao, Bin, and Xiao, Chunxia
- Subjects
SHADES & shadows ,VIDEO editing ,DIGITAL video editing ,SPATIOTEMPORAL processes ,COMPUTER algorithms - Abstract
Shadow removal for videos is an important and challenging vision task. In this paper, we present a novel shadow removal approach for videos captured by free moving cameras using illumination transfer optimization. We first detect the shadows of the input video using interactive fast video matting. Then, based on the shadow detection results, we decompose the input video into overlapped 2D patches, and find the coherent correspondences between the shadow and non-shadow patches via discrete optimization technique built on the patch similarity metric. We finally remove the shadows of the input video sequences using an optimized illumination transfer method, which reasonably recovers the illumination information of the shadow regions and produces spatio-temporal shadow-free videos. We also process the shadow boundaries to make the transition between shadow and non-shadow regions smooth. Compared with previous works, our method can handle videos captured by free moving cameras and achieve better shadow removal results. We validate the effectiveness of the proposed algorithm via a variety of experiments. [ABSTRACT FROM AUTHOR]
- Published
- 2017
- Full Text
- View/download PDF
46. Illumination Decomposition for Photograph With Multiple Light Sources.
- Author
-
Zhang, Ling, Yan, Qingan, Liu, Zheng, Zou, Hua, and Xiao, Chunxia
- Subjects
PHOTOGRAPHS ,IMAGE processing ,LIGHT sources ,IMAGE reconstruction ,IMAGE analysis - Abstract
Illumination decomposition for a single photograph is an important and challenging problem in image editing operation. In this paper, we present a novel coarse-to-fine strategy to perform illumination decomposition for photograph with multiple light sources. We first reconstruct the lighting environment of the image using the estimated geometry structure of the scene. With the position of lights, we detect the shadow regions as well as the highlights in the projected image for each light. Then, using the illumination cues from shadows, we estimate the coarse illumination decomposed image emitted by each light source. Finally, we present a light-aware illumination optimization model, which efficiently produces the finer illumination decomposition results, as well as recover the texture detail under the shadow. We validate our approach on a number of examples, and our method effectively decomposes the input image into multiple components corresponding to different light sources. [ABSTRACT FROM AUTHOR]
- Published
- 2017
- Full Text
- View/download PDF
47. Shape-controllable geometry completion for point cloud models.
- Author
-
Yang, Long, Yan, Qingan, and Xiao, Chunxia
- Subjects
FEATURE extraction ,BOUNDARY value problems ,ALGORITHMS ,STATISTICAL sampling ,CLOUD computing - Abstract
Geometry completion is an important operation for generating a complete model. In this paper, we present a novel geometry completion algorithm for point cloud models, which is capable of filling holes on either smooth models or surfaces with sharp features. Our method is built on the physical diffusion pattern. We first decompose each pass hole-boundary contraction into two steps, namely normal propagation and position sampling. Then the normal dissimilarity constraint is incorporated into these two steps to fill holes with sharp features. Our algorithm implements these two steps alternately and terminates until generating no new hole boundary. Experimental results demonstrate its feasibility and validity of recovering the potential geometry shapes. [ABSTRACT FROM AUTHOR]
- Published
- 2017
- Full Text
- View/download PDF
48. Person Reidentification via Ranking Aggregation of Similarity Pulling and Dissimilarity Pushing.
- Author
-
Ye, Mang, Liang, Chao, Yu, Yi, Wang, Zheng, Leng, Qingming, Xiao, Chunxia, Chen, Jun, and Hu, Ruimin
- Abstract
Person reidentification is a key technique to match different persons observed in nonoverlapping camera views. Many researchers treat it as a special object-retrieval problem, where ranking optimization plays an important role. Existing ranking optimization methods mainly utilize the similarity relationship between the probe and gallery images to optimize the original ranking list, but seldom consider the important dissimilarity relationship. In this paper, we propose to use both similarity and dissimilarity cues in a ranking optimization framework for person reidentification. Its core idea is that the true match should not only be similar to those strongly similar galleries of the probe, but also be dissimilar to those strongly dissimilar galleries of the probe. Furthermore, motivated by the philosophy of multiview verification, a ranking aggregation algorithm is proposed to enhance the detection of similarity and dissimilarity based on the following assumption: the true match should be similar to the probe in different baseline methods. In other words, if a gallery blue image is strongly similar to the probe in one method, while simultaneously strongly dissimilar to the probe in another method, it will probably be a wrong match of the probe. Extensive experiments conducted on public benchmark datasets and comparisons with different baseline methods have shown the great superiority of the proposed ranking optimization method. [ABSTRACT FROM PUBLISHER]
- Published
- 2016
- Full Text
- View/download PDF
49. Geometrically Based Linear Iterative Clustering for Quantitative Feature Correspondence.
- Author
-
Yan, Qingan, Yang, Long, Liang, Chao, Liu, Huajun, Hu, Ruimin, and Xiao, Chunxia
- Subjects
CORRESPONDENCE analysis (Communications) ,DISCOURSE analysis ,ITERATIVE methods (Mathematics) ,NUMERICAL analysis ,HEURISTIC - Abstract
A major challenge in feature matching is the lack of objective criteria to determine corresponding points. Recent methods find match candidates first by exploring the proximity in descriptor space, and then rely on a ratio-test strategy to determine final correspondences. However, these measurements are heuristic and subjectively excludes massive true positive correspondences that should be matched. In this paper, we propose a novel feature matching algorithm for image collections, which is capable of providing quantitative depiction to the plausibility of feature matches. We achieve this by exploring the epipolar consistency between feature points and their potential correspondences, and reformulate feature matching as an optimization problem in which the overall geometric inconsistency across the entire image set ought to be minimized. We derive the solution of the optimization problem in a simple linear iterative manner, where a k-means-type approach is designed to automatically generate consistent feature clusters. Experiments show that our method produces precise correspondences on a variety of image sets and retrieves many matches that are subjectively rejected by recent methods. We also demonstrate the usefulness of the framework in structure from motion task for denser point cloud reconstruction. [ABSTRACT FROM AUTHOR]
- Published
- 2016
- Full Text
- View/download PDF
50. Rapid Determination of Trace Sulfonamides in Milk by Graphene Oxide-Based Magnetic Solid Phase Extraction Coupled with HPLC-MS/MS.
- Author
-
Wang, Yutang, Liu, Laping, Xiao, Chunxia, Chen, Lin, Yang, Peng, Liu, Qian, Wang, Jianlong, and Liu, Xuebo
- Abstract
A simple and rapid method based on magnetic solid-phase extraction (MSPE) combined with high-performance liquid chromatography coupled with triple quadrupole mass spectrometry (HPLC-MS/MS) was used for the determination of 15 sulfonamides from milk samples. The extraction and cleanup used a graphene oxide-based magnetic nanocomposite (FeO@GO) as an adsorbent. Various experimental parameters that could affect the extraction efficiencies, such as the amount of FeO@GO, the extraction time, the ionic strength of sample solution, and the type of eluent, were investigated. Under optimized experimental conditions, good linearity was observed in the range of 2.0 to 100.0 μg L for all of the analytes, with correlation coefficients (R) ranging from 0.994 to 0.999. The limits of detection for the method ranged between 0.02 and 0.13 μg L. Mean values of the relative standard deviation of intraday and interday precision ranging from 1.0 to 7.3 % and from 1.7 to 8.1 % were obtained, respectively. The average recoveries were between 73.4 and 97.4 % at three different spiked levels. It was confirmed that the FeO@GO nanocomposite was an effective MSPE material for use in sulfonamide analyses in milk samples. [ABSTRACT FROM AUTHOR]
- Published
- 2016
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.