Search

Image semantic segmentation technology is one of the core research contents in the field of computer vision. With the improvement of computer performance and the continuous development of deep learning technology, researchers have more and more enthusiasm to study the actual effect and performance of image semantic segmentation. The results of deep semantic segmentation allow computers to have a more detailed and accurate understanding of images, and have a wide range of application needs in the fields of autonomous driving, intelligent security, medical imaging, remote sensing images, etc. However, the existing image semantic segmentation algorithms have the disadvantages of easy discontinuous results and insufficient prediction accuracy. In this paper, we take deep learning-based image semantic segmentation technology as the research object to explore the improvement of the image semantic segmentation algorithm and its application in road scenarios. First, this paper proposes MCU-Net method based on residual fusion and multi-scale contextual information. MCU-Net uses residual fusion module to deepen the network structure and improve the ability of U-Net to acquire deeper features. Then a top-down and bottom-up path is constructed for feature information between different levels, and the spatial and semantic information contained in shallow and deep features in the network is fully utilized by fusing features from different levels. In addition, an enhanced void space pyramid pooling module is added for feature information between the same levels, which enables the output features to have a larger range of semantic information. Second, this paper proposes the DAMCU-Net method based on attention mechanism and edge detection based on MCU-Net. DAMCU-Net extracts global contextual information by the attention mechanism optimization module, while fusing features using dense jump connections to facilitate the network to recover more spatial detail information during upsampling, and uses the FReLU activation function to improve the segmentation capability of the network for complex targets. For the edge information lost in the feature extraction process, the edge detection branch is added to supplement the feature information of the main path by feature fusion to achieve the optimization of the edge information. [ABSTRACT FROM AUTHOR]

In this paper, we focus on two tasks: semantic segmentation and target detection in the visual semantic understanding of tennis sports images and we optimize the network structure to achieve a more complete location contour information mining of the target. In detail, we focus on a weakly supervised image semantic segmentation method based on null convolution pixel relations. To address the problem of incomplete pixel-level pseudo-labeling, we introduce a cavity convolution unit with multiple cavity rates and a self-attentive mechanism in the classification model to adaptively enhance the target regions and suppress other irrelevant regions while expanding the perceptual field to generate high-quality pixel-level pseudo-labeling and then train the semantic segmentation model. The final experimental results show that the hierarchical fusion algorithm proposed in this paper significantly outperforms other algorithms, and the overall classification accuracy of the tandem cavity neural network algorithm reaches 81% with good overall classification results. The recognition accuracy of static movements is higher than that of dynamic movements. [ABSTRACT FROM AUTHOR]

Industrial fume emissions are a major contributor to global warming, and accurate monitoring is necessary. However, current segmentation techniques for video monitoring of industrial fumes are limited by ineffective edge segmentation, lack of consideration of dynamic characteristics, and poor segmentation accuracy. To address these issues, a deep learning-based semantic video segmentation network is proposed in this paper. The network combines fume deformation information, employs LR-ASPP design for real-time performance, and spatio-temporal consistency to enhance semantic information in the dynamic region. A residual hybrid attention network is constructed for the motion region to minimize loss of motion information. The proposed network demonstrates strong anti-interference capability in complex environments, achieving over 10% improvement in IoU and F -score under a high-speed segmentation of 53 FPS. This technology can be integrated with automated systems to enable timely responses to hazardous situations, minimizing risks to workers and nearby communities. In summary, the proposed deep learning-based semantic video segmentation network has significant implications for improving environmental monitoring and management practices in industrial settings. [ABSTRACT FROM AUTHOR]

At present, there are many semantic segmentation algorithms with excellent performance for intelligent driving vehicles, but most of them only work well on scenes with good illumination. In order to solve the problem of scene segmentation under low illumination, this paper proposes a novel semantic segmentation algorithm that combines visible and infrared images. In this algorithm, two parallel encoders are designed as the input of the images, and the decoder divides the fused images output from the encoder. The model is based on ResNet algorithm, and the residual attention module is used in each branch to mine and enhance the spatial features of multilevel channels to extract images information. Experiments are carried out on publicly available thermal infrared and visible datasets. The results show that the algorithm proposed in this paper is superior to the algorithm using only visible images in semantic segmentation of traffic environment. [ABSTRACT FROM AUTHOR]

In recent years, solar photovoltaic-based power generation technology has become the key planning direction of many countries around the world. In the process of making solar cells, the quality inspection requirements are very particular, such as physical damages, surface scratches, broken grids and microcracks. In traditional factory production, the detection of the above defects requires professional inspectors to carry out visual inspection, which often leads to low detection efficiency, subjective assumption and fatigue, as well as some detection errors. In recent years, the rapid development of computer vision makes it possible to be used to detect the defects in solar cells. To overcome existing barriers, this paper proposes a method for detecting surface defects in solar cells based on deep neural network. Specifically, a specified image segmentation model named U-Net is developed for this purpose. By automatically segmenting little objects using the proposed recognition approach, surface defects detection can be realized. At last, we use a set of experiments on images from real scenes to verify the proposed method. [ABSTRACT FROM AUTHOR]

In medical image examination, image segmentation is the broadly used method. Currently, the efficient segmentation of mammogram images is the main challenge. Many methods were presented for segmenting the mammogram images, but the results are not satisfactory. In this paper, an efficient segmentation of mammogram images-based Multilevel Thresholding (MLT) method is proposed. Initially, the preprocessing step is executed for eliminating the unnecessary noises. For gaining the useful features from the mammogram images, mammogram image segmentation is carried out using multilevel thresholding method. In this paper, a novel Multi-Objective Emperor Penguin Optimization (MOEPO) algorithm is proposed for searching the multilevel greatest thresholds that segment the images into background and objects. The objective functions of the MLT are Otsu's method, Kapur and Tsallis entropy. The effectiveness of the proposed method is analyzed using several performances evaluating metrics, like PSNR, FSIM and SSIM. The experimental outcomes show that the performance of the proposed technique is superior to other state-of-the-art methods. The proposed technique is likened to three existing models, viz. ScPSO-MT, Double Threshold and IWO-SUSAN. The SSIM of the proposed technique is 24.99%, 27.83% and 26.95% better than ScPSO-MT, Double Threshold and IWO-SUSAN existing approaches. The PSNR of the proposed technique is 25.27%, 40% and 50.74% better than ScPSO-MT, Double Threshold and IWO-SUSAN approaches. The FSIM of the proposed technique is 28.57%, 34.12% and 34.12% better than ScPSO-MT, Double Threshold and IWO-SUSAN methods. [ABSTRACT FROM AUTHOR]

Hardware/software partitioning is a typical multi-stage decision optimization problem; most existing hardware/software partitioning methods ignore a fact that real-life decisions are usually made in an uncertain state. We should model the hardware/software partitioning problem in uncertain environments and deal with uncertainty. The state-of-the-art work proposed an uncertainty conversion method for hardware/software partitioning, but this method does not include the equivalent deterministic model and is not suitable for dealing with different types of uncertainties. In order to cope with different situations with various uncertainties, we should apply uncertain programming to build a model in uncertain environments and give different equivalent deterministic models to convert different uncertainties theoretically. In this paper, we present the process of applying uncertain programming to solve the hardware/software partitioning problem, including the model and algorithm. We convert the uncertain programming model into its equivalent deterministic models, including the expected value model and the chance-constrained programming model; we give details for the conversion methods of these two models. We present the custom genetic algorithm to solve the converted model, by incorporating a greedy idea in two steps of the genetic algorithm. Experimental results show that the custom genetic algorithm can find a high-quality approximate solution while running much faster for large input scales, compared with the exact algorithm. [ABSTRACT FROM AUTHOR]

This paper constructs a low-resolution model for face recognition and sports training actions based on wireless sensors. The model obtains the distribution of the information size in the face image by calculating the image entropy value, and assigns different weights according to the size of the information to perform face recognition calculation, so that the original module-based algorithm is simply based on image segmentation into one based on entropy. The size of the value is divided into blocks, which solves the problem of computational quantification of category information. In the test stage, the traditional orthogonal matching pursuit algorithm is used to solve the coding coefficients, and the excellent classification and recognition results are obtained by calculating the intra-class matrix of the face image and the inter-class matrix of the sports training action image. Methods that perform well on classification problems further improve face recognition rates. The specific processing process is to add Gaussian noise, salt and pepper noise to the input face image and reduce the size of the face image in the input image, so that the improved algorithms are improved. The experimental results show that the high-efficiency resolution sensing technology is used to learn the sports training actions corresponding to the two modalities, and the matrix coefficient between the obtained high-resolution modal and low-resolution modal images reaches 0.971, and the iteration rate is improved by 71.5%, effectively promoting the high recognition rate of faces and actions. [ABSTRACT FROM AUTHOR]

As one of the fatal human diseases, early detection of brain tumors can effectively save patients' lives. Brain tumor image segmentation is of great practical importance for physicians to perform brain tumor diagnoses quickly. Due to the data complexity of 3D brain images, it is impractical to segment out tumor regions manually, so automatic and reliable methods can be utilized instead of manual work to achieve accurate segmentation of tumor regions. In this paper, we propose an end-to-end, more efficient brain tumor MRI segmentation model, REMU-Net, for the problems of multi-scale feature extraction and difficulty in small target feature extraction in 3D brain tumor image segmentation. Firstly, design and use the multi-channel parallel M-RepVGG module as a decoder to achieve multi-scale feature fusion. Secondly, embedding dilated convolution with different dilated rates in the DM-RepVGG module of the encoder to better extract features at different scales. Finally, introduce the expectation-maximizing attention in the network to better extract the features of the internal details of the tumor. The experimental results on the BraTS2018 validation dataset are Dice scores of 80.93%, 90.13%, and 86.15%, respectively. Experimental results on the BraTS2019 validation dataset can be achieved with Dice scores of 78.29%, 90.65%, and 82.77%, respectively. [ABSTRACT FROM AUTHOR]

Image segmentation is an important processing technology, which is the basis of image recognition and has been widely used in many fields. In this paper, we propose a method, termed coarse-to-fine strategy-based image segmentation (CSIS), for color image segmentation. The basic idea is to segment an image by three phases: (1) the original image is first segmented into several distinct regions by using the mean shift method; (2) the segmented regions are converted to a weighted region adjacency graph (RAG), and a new graph cut method, called multi-cut algorithm, is proposed to partition the RAG into multiple regions; (3) a one-step Chan–Vese algorithm is applied to smooth the boundaries of the segmented objectives. In each of the last two phases, a method is applied to refine the result obtained in the previous phase. By carefully balancing the efforts used in each phase, CSIS could segment color images both efficiently and effectively. These advantages are demonstrated by applying the proposed method to a variety of test instances, and the statistical results also show that it is comparable with some state-of-the-art methods. [ABSTRACT FROM AUTHOR]

This paper discusses how to efficiently recognize flowers based on a convolutional neural network (CNN) using multiple features. Our proposed work consists of three phases including segmentation by Otsu thresholding with particle swarm optimization algorithms, feature extraction of color, shape, texture and recognition with the LeNet-5 neural network. In the feature extraction, an improved H component with the definition of WGB value is applied to extract the color feature, and a new algorithm based on local binary pattern (LBP) is proposed to enhance the accuracy of texture extraction. Besides this, we replace ReLU with Mish as activation function in the network design, and therefore increase the accuracy by 8% accuracy according to our comparison. The Oxford-102 and Oxford-17 datasets are adopted for benchmarking. The experimental results show that the combination of color features and texture features generates the highest recognition accuracy as 92.56% on Oxford-102 and 93% on Oxford-17. [ABSTRACT FROM AUTHOR]

The one-dimensional Otsu method is an adaptive threshold method. It obtains the optimal threshold for image segmentation by the maximum between-class variance, without considering the minimum within-class variance. As the background of water surface image is mostly uniform, using this feature, the threshold selection tactics adopt the combination of the one-dimensional Otsu method and the uniformity measurement, proposes the threshold segmentation method based on uniformity measurement, and adopts the performance evaluation method based on GT image to compare the segmentation result. Experimental results demonstrate that effectiveness of the improved Otsu method is generally better than the traditional Otsu method, and the other four commonly used threshold segmentation methods for the water surface image, which improves the segmentation accuracy of such images and reduces the segmentation error rate. At the same time, as the water surface image is usually affected by light intensity, water ripple and other factors, this paper also adopts the relevant correction algorithm to further improve the segmentation accuracy. [ABSTRACT FROM AUTHOR]

Multimodal Magnetic Resonance Imaging (MRI) is an imaging technique widely used in the diagnosis and treatment planning of patients. Lesion segmentation of brain MRI is one of the most important image analysis task in medical imaging. In this paper, a new method for the supervised segmentation of the lesion in brain MRI using Grammatical Bee Colony (GBC) is proposed. The segmentation process is adversely affected by the presence of noises and intensity inhomogeneities in the Magnetic Resonance (MR) images. Therefore, noises are removed from the images and intensity inhomogeneities are corrected in the pre-processing steps. A set of stationary wavelet features are extracted from the co-registered 1-weighted (-), 2-weighted (-) and Fluid-Attenuated Inversion Recovery (FLAIR) images after skull stripping. A classifier is evolved using the GBC to classify the tissues as healthy tissues or lesions. The GBC classifier is trained with extracted features. The trained classifier is used to segment the test Magnetic Resonance (MR) image into healthy tissues or lesion regions. Finally, the connected component labeling algorithm is used to extract the lesions from the segmented images in the post-processing step. Effectiveness of the proposed method is tested by identifying the brain lesions from a set of MR images. [ABSTRACT FROM AUTHOR]

The segmented channel routing problem is fundamental to the routing of row-based field programmable gate arrays (FPGAs) and is proven to be nondeterministic polynomial time (NP) complete. In this paper, we capitalize on the compelling advancements in satisfiability (SAT) solvers to propose a multilevel pseudo-Boolean SAT-based approach. We construct several levels of hierarchy amongst the nets and the routing problem of each level is formulated as a pseudo-Boolean optimization (PBO) problem. Moreover, an optimization technique of reducing the number of variables in PBO problems is described to improve the scalability of the proposed method. Similar to the SAT-based routing, the unroutability of a given circuit can be proved by the approach. Experimental results show that the proposed method compares very favorably with existing algorithms and achieves the best convergence rate. [ABSTRACT FROM AUTHOR]

In this research paper, we propose an automatic segmentation method of multispectral magnetic resonance image (MRI) of the human brain using an information fusion approach through the framework of the possibility theory. The fusion process is summarized into three essential steps. First, a data is extracted from the various images and modeled in a common mathematical framework, in this step the fuzzy C-means (FCM) algorithm is chosen. The combination rule is used to combine this information in the second step. A final segmented image is the result of the last phase. Our experimental results using simulated brain MRI datasets show that the pro-posed approach overcome the impact of the noise and substantially improve the accuracy of image segmentation. [ABSTRACT FROM AUTHOR]