Search

Shadow detection is essential for scene understanding and image restoration. Existing paradigms for producing shadow detection training data usually rely on densely labeling each image pixel, which will lead to a bottleneck when scaling up the number of images. To tackle this problem, by labeling shadow images with only a few strokes, this paper designs a learning framework for Weakly supervised Shadow Detection, namely WSD. Firstly, it creates two shadow detection datasets with scribble annotations, namely Scr-SBU and Scr-ISTD. Secondly, it proposes an uncertainty-guided label augmentation scheme based on graph convolutional networks, which can propagate the sparse scribble annotations to more reliable regions, and then avoid the model converging to an undesired local minima as intra-class discontinuity. Finally, it introduces a multi-task learning framework to jointly learn for shadow detection and edge detection, which encourages generated shadow maps to be comprehensive and well aligned with shadow boundaries. Experimental results on benchmark datasets demonstrate that our framework even outperforms existing semi-supervised and fully supervised shadow detectors requiring only 2% pixels to be labeled. [ABSTRACT FROM AUTHOR]

Solar energy plays an important role in renewable energy generation, with the advantages of low pollution, easy installation, and relatively easy access. However, photovoltaic (PV) modules are susceptible to cause localized shading from external factors such as leaves in the canopy, surrounding buildings, etc., which would affect power generation efficiency and even pose safety risks. Existing methods cannot perform well in real-time conditions. This paper proposes a real-time shading monitoring method for the PV module based on computer vision. The gamma transform and histogram matching were adopted to enhance key features and adjust the global gamut strength distribution in the image of the PV module; then the gray-level slicing method finished the segmentation to detect the shadow from the video. All processing can be realized in the real-time monitor camera and the detection results can be displayed on the HMI in PC with high efficiency and low cost. According to tests in the practical complex environment, the method can have enough detection performance and high real-time performance with an accuracy of 0.98, and the F0.5 and F2 values are 0.87 and 0.85, respectively. The metrics of the proposed method are higher than those of the existing Canny detection method, the Random Forest detection method, and the CNN detection method. In addition, the average time required by the proposed method to process a frame is 0.721 s. In addition, the average time required by the method to process an image frame is 0.721 s, which has good real-time performance. [ABSTRACT FROM AUTHOR]

Abstract Solar energy plays an important role in renewable energy generation, with the advantages of low pollution, easy installation, and relatively easy access. However, photovoltaic (PV) modules are susceptible to cause localized shading from external factors such as leaves in the canopy, surrounding buildings, etc., which would affect power generation efficiency and even pose safety risks. Existing methods cannot perform well in real-time conditions. This paper proposes a real-time shading monitoring method for the PV module based on computer vision. The gamma transform and histogram matching were adopted to enhance key features and adjust the global gamut strength distribution in the image of the PV module; then the gray-level slicing method finished the segmentation to detect the shadow from the video. All processing can be realized in the real-time monitor camera and the detection results can be displayed on the HMI in PC with high efficiency and low cost. According to tests in the practical complex environment, the method can have enough detection performance and high real-time performance with an accuracy of 0.98, and the F0.5 and F2 values are 0.87 and 0.85, respectively. The metrics of the proposed method are higher than those of the existing Canny detection method, the Random Forest detection method, and the CNN detection method. In addition, the average time required by the proposed method to process a frame is 0.721 s. In addition, the average time required by the method to process an image frame is 0.721 s, which has good real-time performance.

Sparsely annotated image segmentation has gained popularity due to its ability to significantly reduce the labeling burden on training data. However, existing methods still struggle to learn complete object structures, especially for complex shadow objects. This paper discusses two prevalent issues existing in previous methods, i.e., generating noisy pseudo labels and misdetecting ambiguous regions. To tackle these challenges, we propose a novel weakly-supervised learning framework to boost sparsely annotated shadow detection. Concretely, a reliable label propagation (RLP) scheme is first designed to diffuse sparse annotations into unlabeled regions, thereby generating denser pseudo shadow masks. This scheme effectively reduces the number of noisy labels by incorporating uncertainty analysis. Then, a multi-cue semantic calibration (MSC) strategy is presented to refine the semantic features extracted from the backbone by employing edge, global, and adjacent priors. Embedded with MSC, the detection network becomes more discriminative against ambiguous regions. By combining RLP and MSC, the proposed weakly-supervised framework can detect complete and accurate shadow regions from sparse annotations. Experimental results on three benchmark datasets demonstrate that our method achieves comparable performance to recent fully-supervised methods, while requiring only about 4.5% of the pixels to be labeled. Boosting sparsely annotated shadow detection [ABSTRACT FROM AUTHOR]

Significant advancements have been made in colorization in recent years, especially with the introduction of deep learning technology. However, challenges remain in accurately colorizing images under certain lighting conditions, such as shadow. Shadows often cause distortions and inaccuracies in object recognition and visual data interpretation, impacting the reliability and effectiveness of colorization techniques. These problems often lead to unsaturated colors in shadowed images and incorrect colorization of shadows as objects. Our research proposes the first shadow-aware image colorization method, addressing two key challenges that previous studies have overlooked: integrating shadow information with general semantic understanding and preserving saturated colors while accurately colorizing shadow areas. To tackle these challenges, we develop a dual-branch shadow-aware colorization network. Additionally, we introduce our shadow-aware block, an innovative mechanism that seamlessly integrates shadow-specific information into the colorization process, distinguishing between shadow and non-shadow areas. This research significantly improves the accuracy and realism of image colorization, particularly in shadow scenarios, thereby enhancing the practical application of colorization in real-world scenarios. [ABSTRACT FROM AUTHOR]

The video synthetic aperture radar (ViSAR) system can utilize high-frame-rate scene motion target shadow information to achieve real-time monitoring of ground mobile targets. Modeling the characteristics of moving target shadows and analyzing shadow detection performance are of great theoretical and practical value for the optimization design and performance evaluation of ViSAR systems. Firstly, based on the formation mechanism and characteristics of video SAR moving target shadows, two types of shadow models based on critical size and shadow clutter ratio models are established. Secondly, for the analysis of moving target shadow detection performance in ViSAR systems, parameters such as the maximum detectable speed of moving targets, the minimum clutter backscatter coefficient, and the number of effective shadow pixels of moving targets are derived. Furthermore, the shadow characteristics of five typical airborne/spaceborne ViSAR systems are analyzed and compared. Finally, a set of simulation experiments on moving target shadow detection for the Hamas rocket launcher validates the correctness and effectiveness of the proposed models and methods. [ABSTRACT FROM AUTHOR]

ABSTRACTBuildings are one of the most important habitats for humans, and therefore, accurate identification and extraction of building information in remote sensing images are crucial. Buildings in remote sensing images vary in shape and color due to differences in sensor acquisition methods, geographical location, and other factors. However, they all share a common feature – the presence of shadows. Obtaining accurate data from building shadows can provide a wealth of reliable information for building research. Consequently, it is crucial to review various methods for extracting building shadows, especially deep learning-based methods, to illustrate shadow implementation scenarios in building research: 1) building detection in very high resolution remote sensing images (VHRRSI); 2) building detection in SAR; 3) building change detection; 4) building damage assessment; 5) building height estimation; 6) building shadow removal; 7) other methods (such as building shadow data enhancement, detection of building shadows in ghost images, and conservation of historic buildings). This study discusses the advantages and disadvantages of building shadow detection methods and provides an overview of the datasets and evaluation metrics commonly used in studies of building shadow applications. We hope that this study will serve as a valuable reference for researchers in the field of building shadow studies.

Shadows cause a reduction of text legibility and contrast of the overall document, leading to poor recognition rates by Optical Character Recognition (OCR). Shadows were cast during photo capturing because of object interferences due to projection angle from illumination sources and are challenging to handle by OCR. This work proposes an automated technique to detect the shadows caused by object interferences and eliminate them from document images. The proposed algorithm generates two reference masks of shadow and non-shadow regions using a global thresholding method to detect and remove shadow. Initially, the document image is pre-processed, followed by mask generation for shadow and non-shadow regions, and finally, a global thresholding strategy that removes the shadow using an image mapping technique. To evaluate the effectiveness of the proposed approach, a dataset of real-world smartphone-captured document images of about 300 is considered. The datasets encompass Mobile Dataset 3 and Mobile Dataset 4 from DIBCO datasets. Experiments are conducted to quantify the efficiency of the proposed approach using performance measures such as recognition rate by OCR, presentation score, legibility score, skew, and overall document quality score. From the results, the proposed approach collectively produces an average recognition rate of 87.15% and 81.50% towards word-level recognition of Mobile Datasets 3 and 4. The text quality of the document image post shadow removal procedure achieves a higher performance score with an average presentation score of 0.35, legibility score of 0.78, skew as 73.45 degrees from the horizontal axis, and overall document quality score above six towards datasets considered. Based on qualitative analysis, comparative analysis proves that the proposed is simple yet more proficient than existing methods. [ABSTRACT FROM AUTHOR]

Shadow, a natural phenomenon resulting from the absence of direct lighting, finds diverse real-world applications beyond computer vision, such as studying its effect on photosynthesis in plants and on the reduction of solar energy harvesting through photovoltaic panels. This article presents a dataset comprising 50,000 pairs of photorealistic computer-rendered images along with their corresponding physics-based shadow masks, primarily focused on agricultural settings with human activity in the field. The images are generated by simulating a scene in 3D modeling software to produce a pair of top-down images, consisting of a regular image and an overexposed image achieved by adjusting lighting parameters. Specifically, the strength of the light source representing the sun is increased, and all indirect lighting, including global illumination and light bouncing, is disabled. The resulting overexposed image is later converted into a physically accurate shadow mask with minimal annotation errors through post-processing techniques. This dataset holds promise for future research, serving as a basis for transfer learning or as a benchmark for model evaluation in the realm of shadow-related applications such as shadow detection and removal.

The undulating terrain in mountainous and hilly regions results in a greater variety and complexity of shadows. Efficient methods for shadow detection and reconstruction in high-resolution remote sensing images are particularly important in such hilly areas. The accurate detection of shadow masks is a prerequisite for shadow reconstruction. By utilizing the features of high hue and low intensity in shadow areas, an initial spectral ratio is constructed based on the CIELCh color space model. Simple linear iterative clustering is employed to perform superpixel segmentation on the image, and the segmented results are spatially constrained to reconstruct the initial spectral ratio. Afterward, an automatic multilevel global thresholding approach is applied to obtain the shadow mask and eliminate the influence of interfering objects. For shadow reconstruction, the segmented superpixels are treated as the smallest processing units. Similar neighboring objects have similar ambient light intensities. Based on this, we propose a shadow reconstruction method, which compensates shadow superpixels using adjacent nonshadow superpixels and determines compensation weights based on their similarity. Furthermore, the shadow boundaries are dilated to obtain penumbra, and mean filtering is performed to compensate for the illumination in the penumbra. Finally, the proposed method is qualitatively and quantitatively compared with existing shadow detection and reconstruction methods. Experimental results demonstrate that this method can accurately detect shadows in high-resolution remote sensing images in mountainous and hilly environments, and effectively reconstruct the spectral information of shadow areas. This has significant implications for subsequent feature extraction and further analysis in mountainous and hilly regions.

Accurate and rapid detection of building changes is of great significance to identify latent areas along transmission lines. With the development and progress of satellite remote sensing technology, building change detection based on high resolution remote sensing image has become a research hotspot. A Gaussian probability model integrating features such as shadow, building index, texture and shape was proposed to realize initial extraction of buildings at the pixel level. Based on this, object-level change detection of buildings was realized by combining multi-scale segmentation results. Finally, the spatial superposition analysis was carried out on the extraction results of object-level buildings in the front and back phases, and the superposition results were divided into three categories: building addition, building demolition and building reconstruction. Remote sensing images with different resolutions were used in the research area and the verification area respectively for experiments and verification. The results show that the proposed method achieves practical results and detection accuracy under different scales and image resolutions, and can provide good technical support for the detection of building changes along the transmission line. [ABSTRACT FROM AUTHOR]

Shadow detection is a common computer vision task that identifies the location of shadows. It has been used as a key primitive for many high-level tasks such as object segmentation and video tracking. Due to the complexity and variety of shadows, it is challenging to design a one-size-fits-all shadow detection algorithm in real-world scenarios. Instead, it is often necessary in practice to pick the best shadow detection algorithm for a particular vision application. While shadow detection algorithms can be assessed by comparing the detected shadow with the ground truth, such ground truth is often unavailable in real-world vision systems consistently generating new data. In this paper, we propose a no-reference shadow detection quality assessment network (NSDQA-Net) to rank shadow detection algorithms without needing the ground truth. For a given image, the proposed assessment network first learns a reference map that compensates the false positives and false negatives of multiple input shadow detection algorithms. The reference map, as well as the original image and the input shadow detection results, are then used to regress the quality scores of the shadow detection methods. Our framework supports the assessment of one, two, or multiple algorithms in a single run, making it easier for deployment in practical scenarios. Experiments results show that the proposed network achieves optimal accuracy in no-reference shadow detection assessment. Relying on it for adaptive algorithm selection also improves the performance of shadow detection using a fixed algorithm on benchmark datasets. [Display omitted] • We identify a task of no-reference quality assessment in shadow detection. • We design a novel no-reference shadow detection quality assessment network (NSDQA-Net). • We experimentally demonstrate the state-of-the-art performance of the proposed network. [ABSTRACT FROM AUTHOR]

With the continuous increase in the resolution of high-resolution remote sensing satellite images, shadows have increasingly impacted feature target recognition and classification in images, urban reconstruction, and image interpretation. Although various shadow detection methods exist for different features, undetected small shadowed areas, misclassified dark areas, and highlighted non-shadowed areas remain. Moreover, it is still difficult to distinguish waters from shadowed regions owing to their similar characteristics. To further solve these problems, we propose a novel mixed shadow detection index (MSDI) for extracting urban feature shadows, using the original information of the first principal component that contains the differences between most of the different objects in the image, as well as the difference features in the shadowed areas and water bodies. We evaluated the effectiveness and robustness of our method by conducting comparison experiments using Gaofen-1, Gaofen-2, and WorldView-3 images from different scenes, times, and acquisition locations. Through visual analysis and data analysis of our method, we found that the method achieved excellent shadow detection results, with an average total accuracy 94% for shadow detection. The proposed shadow detection algorithm could accurately recognize waters, and it could also accurately recognize easily missed small shadowed areas and easily confused non-shadowed areas.

The video synthetic aperture radar (ViSAR) system can utilize high-frame-rate scene motion target shadow information to achieve real-time monitoring of ground mobile targets. Modeling the characteristics of moving target shadows and analyzing shadow detection performance are of great theoretical and practical value for the optimization design and performance evaluation of ViSAR systems. Firstly, based on the formation mechanism and characteristics of video SAR moving target shadows, two types of shadow models based on critical size and shadow clutter ratio models are established. Secondly, for the analysis of moving target shadow detection performance in ViSAR systems, parameters such as the maximum detectable speed of moving targets, the minimum clutter backscatter coefficient, and the number of effective shadow pixels of moving targets are derived. Furthermore, the shadow characteristics of five typical airborne/spaceborne ViSAR systems are analyzed and compared. Finally, a set of simulation experiments on moving target shadow detection for the Hamas rocket launcher validates the correctness and effectiveness of the proposed models and methods.

Recent improvements in remote sensing technologies have boosted building detection techniques from rough classifications using moderate resolution imagery to precise extraction from high-resolution imagery. Shadows frequently emerge in high-resolution urban images. To exploit shadow information, we developed a novel building detection and classification algorithm for images of urban areas with large-size shadows, employing only the visible spectral bands to determine the height levels of buildings. The proposed method, building general-classified by height (BGCH), calculates shadow orientation, detects buildings using seed-blocks, and classifies the buildings into different height groups. Our proposed approach was tested on complex urban scenes from Toronto and Beijing. The experimental results illustrate that our proposed method accurately and efficiently detects and classifies buildings by their height levels; the building detection rate exceeded 95%. The precision of classification by height levels was over 90%. This novel building-height-level detection method provides rich information at low cost and is suitable for further city scene analysis, flood disaster risk assessment, population estimation, and building change detection applications. [ABSTRACT FROM AUTHOR]

Remote sensing images (RSI) of urban regions often exhibit shadows cast by buildings and other objects, which may result in imprecise analysis and interpretation. Therefore, shadow detection plays a significant role in RSI scene understanding. Current approaches have paid little attention to the presence of pseudo shadows and their confounding effects on detection results. We tackle these questions in the spatial context of orientation-awareness, effectively capturing the intricate relationships between shadows and ground objects. Here, we introduce a novel deep learning network named the Orientation-Aware and Multi-Scale Feature Fusion Network (OAMSFNet) due to noise reduction considerations. The proposed OAMSFNet comprises Shadow Aware Feature Encoder (SFE), Orientation-Aware Context Module (OCM), and Multi-Scale Feature Pyramid (MFP). Furthermore, a multi-scale feature fusion algorithm has been devised to enhance the detection and segmentation capabilities of the model in shadow regions. Finally, a comparative study was conducted on the Aerial Imagery dataset for Shadow Detection (AISD) in both quantitative and qualitative aspects. The experimental results show that our method outperforms state-of-the-art methods while maintaining a lightweight model design, indicating that our approach exhibits remarkable accuracy and stability in excellent agreement with predictions. OAMSFNet achieved an average F-score of 89.85%, surpassing the straightforward semantic segmentation model SegNet by 9.94%, and demonstrated remarkable efficiency enhancements, with FLOPs reduced to as low as 11.48 G, resulting in efficiency improvements of 66.7%-96.5% compared to other shadow detection models. [ABSTRACT FROM AUTHOR]

Although current methods based on deep learning (DL) have been widely employed in shadow detection tasks, the cluttered background and complex shadow features in remote sensing images (RSIs) make shadow detection still a challenging task. In this paper, we apply a neural network combined with a distance transformation algorithm to RSI shadow detection for the first time and propose a novel slice-to-slice context transfer and uncertainty region calibration network (SCUCNet). First, an interslice context semantic transfer (SCT) module is proposed to explore the connections among spatial pixel information and extract sufficient global contextual information via interslice feature transfer. This process helps alleviate the interference of multiscale differences and complex backgrounds on the detection results. Second, to further optimize the initial output mapping, calibrate the uncertainty region, and enhance the feature representation, we propose a plug-and-play uncertainty region awareness and calibration (URAC) module combined with a distance transform algorithm, which introduces only 0.09 M parameters. The quantitative results show that the proposed model outperforms state-of-the-art methods for shadow detection in RSIs, achieving an Intersection over Union (IoU) of 88.33% on the aerial imagery dataset for shadow detection (AISD). In addition, extensive experiments and visualizations further prove the validity and interpretability of our method, and the proposed method can effectively mitigate the interference caused by multiscale differences, morphological diversity, spectral similarity and heterogeneity. [ABSTRACT FROM AUTHOR]

With the continuous increase in the resolution of high-resolution remote sensing satellite images, shadows have increasingly impacted feature target recognition and classification in images, urban reconstruction, and image interpretation. Although various shadow detection methods exist for different features, undetected small shadowed areas, misclassified dark areas, and highlighted non-shadowed areas remain. Moreover, it is still difficult to distinguish waters from shadowed regions owing to their similar characteristics. To further solve these problems, we propose a novel mixed shadow detection index (MSDI) for extracting urban feature shadows, using the original information of the first principal component that contains the differences between most of the different objects in the image, as well as the difference features in the shadowed areas and water bodies. We evaluated the effectiveness and robustness of our method by conducting comparison experiments using Gaofen-1, Gaofen-2, and WorldView-3 images from different scenes, times, and acquisition locations. Through visual analysis and data analysis of our method, we found that the method achieved excellent shadow detection results, with an average total accuracy 94% for shadow detection. The proposed shadow detection algorithm could accurately recognize waters, and it could also accurately recognize easily missed small shadowed areas and easily confused non-shadowed areas. [ABSTRACT FROM AUTHOR]

Recent shadow detectors excel on simple datasets but encounter difficulties with facial shadow images under complex lighting due to the lack of annotated shadow masks, varying shadow sizes, and imbalances between the target and background. This leads to training difficulties, reduced accuracy, and slower processing, posing a significant challenge for precise and fast detection framework development. We collected images and created Extended Yale Shadow Detection Dataset (EYSDD). In comparison to other datasets, this dataset includes additional manually annotated shadow masks, making it suitable for training convolutional neural networks. To address this problem, we propose incorporating Channel Spatial Direction-aware Spatial Context (CSDSC) module into Fast Shadow Detection Network (FSDNet). Additionally, we introduce Selective Attention Inverted Residual Bottleneck (SAIRB) with Selective Attention Mechanism (SAM). Furthermore, we integrate Detail Enhancement Module (DEM), which refines low-level features, into Fast Face Shadow Detection Framework (FFSDF). Finally, compared to other methods, our model surpasses the baseline method FSDNet and the advanced method EVP by 3.5% and 1.9% in terms of IoU, and 1.8% and 4.3% in terms of Dice score, respectively. Our model has only 4.31 M parameters and achieves a computing speed of 0.022 sec/image, demonstrating superior efficiency compared to other methods.

Due to the complexity and lack of transparency of recent advances in artificial intelligence, Explainable AI (XAI) emerged as a solution to enable the development of causal image-based models. This study examines shadow detection across several fields, including computer vision and visual effects. Three-fold approaches were used to construct a diverse dataset, integrate structural causal models with shadow detection, and apply interventions simultaneously for detection and inferences. While confounding factors have only a minimal impact on cause identification, this study illustrates how shadow detection enhances understanding of both causal inference and confounding variables. [ABSTRACT FROM AUTHOR]

Background subtraction approaches are used to detect moving objects with a high recognition rate and less computation time. These methods face two challenges: selecting the appropriate threshold value and removing shadow pixels for correct foreground detection. In this paper, we solve these challenges by proposing a new background subtraction method called ABGS Segmenter, which is based on a two-level adaptive thresholding approach where a reference frame is created using mean-based thresholding to generate the initial value of the threshold and accelerates the process of foreground segmentation for remaining frames by adaptively updating the threshold value at the pixel level. ABGS Segmenter is also capable of removing shadow pixels by fusing the chromaticity-based YCbCr color space model with the intensity ratio method for improving the percentage of correct pixels' classification measure. Comprehensive experiments are evaluated on three benchmark datasets (Highway, PETS 2006, and SBU) and observed that the proposed work achieves better results than existing methods. [ABSTRACT FROM AUTHOR]

The majority of photovoltaic (PV) systems in the Netherlands are small scale, installed on rooftops, where the lack of onsite global tilted irradiance (GTI) measurements and the frequent presence of shadow due to objects in the close vicinity oppose challenge in their monitoring process. In this study, a new algorithmic tool is introduced that creates a reference data‐set through the combination of data‐sets of the unshaded PV systems in the surrounding area. It subsequently compares the created reference data‐set with the one of the PV system of interest, detects any energy loss and clusters the distinctive loss due to shadow, created by the surrounding objects. The new algorithm is applied successfully to a number of different cases of shaded PV systems. Finally, suggestions on the unsupervised use of the algorithm by any monitoring platform are discussed, along with its limitations algorithm and suggestions for further research. [ABSTRACT FROM AUTHOR]

Residual image and illumination estimation have been proven to be helpful for image enhancement. In this article, we propose a general framework, called RI-GAN, that exploits residual and illumination using generative adversarial networks (GANs). The proposed framework detects and removes shadows in a coarse-to-fine fashion. At the coarse stage, we employ three generators to produce a coarse shadow-removal result, a residual image, and an inverse illumination map. We also incorporate two indirect shadow-removal images via the residual image and the inverse illumination map. With the residual image, the illumination map, and the two indirect shadow-removal images as auxiliary information, the refinement stage estimates a shadow mask to identify shadow regions in the image, and then refines the coarse shadow-removal result to the fine shadow-free image. We introduce a cross-encoding module to the refinement generator, in which the use of feature-crossing can provide additional details to promote the shadow mask and the high-quality shadow-removal result. In addition, we apply data augmentation to the discriminator to reduce the dependence between representations of the discriminator and the quality of the predicted image. Experiments for shadow detection and shadow removal demonstrate that our method outperforms state-of-the-art methods. Furthermore, RI-GAN exhibits good performance in terms of image dehazing, rain removal, and highlight removal, demonstrating the effectiveness and flexibility of the proposed framework. [ABSTRACT FROM AUTHOR]

Fatigue detection has many applications, one of them is intelligent transportation for accident prevention. It is challenging to detect driver fatigue adopting photometric stereo and 3D fatigue-related facial action unit identification. During 3D reconstruction shadows are encountered, causing reconstruction error, therefore, for accurate fatigue detection shadow removal is crucial. This study presents a novel snake based approach for shadow handling in photometric stereo. Seven light sources were employed and region visibility of the light source for each region of interest (ROI) was deduced. Surface normal estimation enhancement was achieved via snake model based shadow labeling. Discrepancies measured among shadowed regions and ROIs were recorded. Light sources having high intersection with the shadow map were excluded from the reconstruction process at pixel level. This results in an automatic driver fatigue related action unit detection employing uncalibrated Lambertian surface under shadow conditions. The developed method was tested and compared with other established driver fatigue detection methods and higher performance in terms of accuracy (i.e. 97.85%) was achieved. The developed method proves to be well suited for driver fatigue detection under uncalibrated conditions.

Shadow detection is a significant preprocessing work that soil species are classified with machine vision because shadow may affect the accuracy of identifying soil species. To judge the number of shadows in a soil image used for soil species identification, density peak clustering for shadow detection of soil image (DPCSDSI) is proposed to segment shadows. Firstly, the Bright histogram of a soil image is built and its Gaussian smoothing is done. Then a new parameter-free density formula and decision value measure are reconstructed. Because shadow detection is a typical binary classification problem, the two x i points with the largest decision value γ i are chosen as the cluster centers of shadow and non-shadow. And the clustering labels gray levels are initialized by the original DPC algorithm with the cluster centers. Next, the Bright histogram is fitted with Fourier series to search valleys and update the clustering labels. Finally, the clustering labels are corrected with uncertainty coefficient until Eq. (21) is satisfied, which finishes the segmentation of shadow and non-shadow in a soil image. The simulation results show that DPCSDSI is better than the contrast algorithms and its average brightness standard deviations of the shadow and non-shadow are, respectively, 20.5484 and 20.9024. It can detect adaptively shadows in a soil image and there is not the "domino" error propagation in it, so it is effective. [ABSTRACT FROM AUTHOR]

Shadow detection is a new method for video synthetic aperture radar moving target indication (ViSAR-GMTI). The shadow formed by the target occlusion will reflect its real position, preventing the defocusing or offset of the moving target from making it difficult to identify the target during imaging. To achieve high-precision shadow detection, this paper proposes a video SAR moving target shadow-detection algorithm based on low-rank sparse decomposition combined with trajectory area extraction. Based on the low-rank sparse decomposition (LRSD) model, the algorithm creates a new decomposition framework combined with total variation (TV) regularization and coherence suppression items to improve the decomposition effect, and a global constraint is constructed to suppress interference using feature operators. In addition, it cooperates with the double threshold trajectory segmentation and error trajectory elimination method to further improve the detection performance. Finally, an experiment was carried out based on the video SAR data released by Sandia National Laboratory (SNL); the results prove the effectiveness of the proposed method, and the detection performance of the method is proved by comparative experiments. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Zhengzhou University (Natural Science Edition) is the property of Journal of Zhengzhou University (Natural Science Edition) Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Illumination pattern recognition of face image has always been a hot research topic in the field of human-computer interaction, and has been widely used in lighting recovery, virtual scene construction and other multimedia fields. Most of the traditional methods achieve this task by analyzing the illumination components from the image texture and structure information, which is often considered to be indirect, complex and time-consuming. This paper introduces a Double-inputs Illumination Pattern Recognizing Model (DIPRM) with Automatic Shadow Detection Network (ASDN) based on Convolution Neural Networks (CNNs). In the proposed coherent system framework, we first annotate the shadow regions of face images with uneven illumination to obtain the face shadow detection dataset. Second, an ASDN which has the encoder-decoder structure is designed. The main architecture of the ASDN is based on the nested U-Net, and for this nesting, the attention mechanism is applied to fuse the output of each sublayer. Third, a double-inputs Facial Illumination Pattern Recognizing Network (FIPRN) following the ASDN is organized, which consists of AlexNet and the attention module. As the double-inputs, the binary image after the shadow segmentation from the ASDN and the original image are input into the FIPRN to make the whole network converge to a good collaboration state eventually. For shadow detection task, the ASDN was evaluated in comparisons with U-Net and UNet++. Experimental results demonstrated that the ASDN achieved an average IoU and Dice gains of 1.9 and 1.2 points over the base-line model with best results. Moreover, the FIPRN was tested in comparison with some baseline models in illumination pattern recognizing task, where the results demonstrated that it achieved an accuracy rate gain of 1.0 points than the AlexNet with a signal-input. [ABSTRACT FROM AUTHOR]

Video Synthetic Aperture Radar (SAR) presents great potential in ground moving target detection and tracking through high frame rate and high-resolution imaging. Target Doppler energy is essential for traditional SAR Ground Moving Target Indication (SAR-GMTI), as the target shadow can also be used for detection in video SAR. However, neither of these detection methods can stand alone to achieve robust detection in video SAR, owing to the distortion or smearing of target energy and its shadow. This paper presents the processing results of airborne video SAR real data using the Faster Region-based Convolutional Neural Network (Faster R-CNN) and the traditional track association based on dual-domain joint detection as proposed in the literature. These two approaches successfully utilize the feature and space time information of target Doppler energy and shadow in the detection of a maneuvering target.

High dynamic range images have higher contrast, which can provide more dynamic range and image details to reflect the visual effects in the real environment better, while dark objects tend to have higher near-infrared reflectivity in the near-infrared spectrum. After studying these two tasks in depth, we propose a novel method for detecting shadows based on high dynamic range images and near-infrared information. The proposed method takes advantage of the characteristics of high dynamic range images for pre-processing before shadow detection. The low dynamic range images are firstly converted into high dynamic range images by increasing the dynamic range and contrast enhancement, and then proceeding to the next step of shadow detection. In this way, we can further perform shadow detection on the basis of establishing an accurate and clear shadow map. The key point of shadow detection is to distinguish between shadows and dark objects, which can be improved by the near-infrared information of images. In the process of shadow detection, high dynamic range image obtained in the previous step and the corresponding near-infrared image undergo some operations to obtain a determined shadow map, which includes the process of images' multiplication and division. Finally, the shadow mask is obtained through adaptive thresholding. Quantitative comparison and qualitative analysis show that our method is superior to other shadow detection methods in accuracy and computational efficiency. [ABSTRACT FROM AUTHOR]

Abstract Shadow has been increasingly a kind of significant aid information for object extraction and scene interpretation in synthetic aperture radar images, which makes SAR shadow detection an important issue. In this paper, we propose a feed‐forward framework integrating saliency and geometry discrimination for shadow detection in SAR images. We firstly develop a global contrast based shadow saliency model to extract suspected shadows. Considering that such suspected regions mostly contain some non‐shadow areas, a discrimination strategy based on geometric relationships between objects and shadows is designed to remove falsely detected areas. Then the remaining regions become the final shadow detection results. Several experiments are carried out on images from two real datasets, Moving and Stationary Target Acquisition Recognition and MiniSAR, to evaluate the performance of our method. From the perspectives of three commonly used metrics, the proposed algorithm comprehensively outperforms two other classic methods, presenting reliable shadow detection ability. Moreover, the detection results of the two classic methods are significantly enhanced in controlling false alarms after the discrimination module is introduced. The results demonstrate that our algorithm is practically applicable to shadow detection in SAR images, and the discrimination strategy can be flexibly extended for related tasks.

Recent improvements in remote sensing technologies have boosted building detection techniques from rough classifications using moderate resolution imagery to precise extraction from high-resolution imagery. Shadows frequently emerge in high-resolution urban images. To exploit shadow information, we developed a novel building detection and classification algorithm for images of urban areas with large-size shadows, employing only the visible spectral bands to determine the height levels of buildings. The proposed method, building general-classified by height (BGCH), calculates shadow orientation, detects buildings using seed-blocks, and classifies the buildings into different height groups. Our proposed approach was tested on complex urban scenes from Toronto and Beijing. The experimental results illustrate that our proposed method accurately and efficiently detects and classifies buildings by their height levels; the building detection rate exceeded 95%. The precision of classification by height levels was over 90%. This novel building-height-level detection method provides rich information at low cost and is suitable for further city scene analysis, flood disaster risk assessment, population estimation, and building change detection applications.

Shadow detection provides worthwhile information for remote sensing applications, e.g. building height estimation. Shadow areas are formed in the opposite side of the sunlight radiation to tall objects, and thus, solar illumination angle is required to find probable shadow areas. In recent years, Very High Resolution (VHR) imagery provides more detailed data from objects including shadow areas. In this regard, the motivation of this paper is to propose a reliable feature, Shadow Low Gradient Direction (SLGD), to automatically determine shadow and solar illumination direction in VHR data. The proposed feature is based on inherent spatial feature of fine-resolution shadow areas. Therefore, it can facilitate shadow-based operations, especially when the solar illumination information is not available in remote sensing metadata. Shadow intensity is supposed to be dependent on two factors, including the surface material and sunlight illumination, which is analyzed by directional gradient values in low gradient magnitude areas. This feature considers the sunlight illumination and ignores the material differences. The method is fully implemented on the Google Earth Engine cloud computing platform, and is evaluated on VHR data with 0.3m resolution. Finally, SLGD performance is evaluated in determining shadow direction and compared in refining shadow maps.

Video synthetic aperture radar (ViSAR) has been found very useful for the surveillance of ground moving targets. The target energy can be utilized for ground moving target tracking, while the dynamic shadows of moving targets enable an alternative tracking approach. However, neither of these two approaches can stand alone to provide reliable target tracking. The smeared shadow and energy both degrade the tracking performance when the target is maneuvering. A moving target tracking framework based on the joint kernelized correlation filter (JKCF) has been developed. Based on the feature training of JKCF, the target is tracked by combining its shadow in the sequential SAR imagery and the corresponding energy in the range-Doppler (RD) spectra. Aiming at the problems of tracking drift and collapse, interactive processing is adopted to enhance the target positioning and feature update based on the confidence assessment. By cooperating with the initialization and feature update strategy, the tracking success rate and precision can be improved significantly.

Shadow leads to failure of moving target positioning, segmentation, tracking, and classification in the video surveillance system thus shadow detection and removal is essential for further computer vision process. The existing state-of-the-art methods for dynamic shadow detection have produced a high discrimination rate but a poor detection rate (foreground pixels are classified as shadow pixels). This paper proposes an effective method for dynamic shadow detection and removal based on intensity ratio along with frame difference, gamma correction, and morphology operations. The performance of the proposed method has been tested on two outdoor ATON datasets, namely, highway-I and highway-III for vehicle tracking systems. The proposed method has produced a discrimination rate of 89.07% and a detection rate of 80.79% for highway-I video sequences. Similarly, for a highway-III video sequence, the discrimination rate of 85.60% and detection rate of 84.05% have been obtained. Investigational outcomes show that the proposed method is the simple, steadiest, and robust for dynamic shadow detection on the dataset used in this work. [ABSTRACT FROM AUTHOR]

One of the fundamental functions of traffic monitoring systems is vehicle detection. However, vehicle detection is typically hampered by the shadow problem. Objects are sometimes lost or their shapes are distorted because shadows are misunderstood to be elements of a vehicle. Shadows are a major problem for the current vehicle detecting technology. For video target segmentation, a moving shadow can be easily mistaken for a portion of the object due to their similarity, and the processing speed of classic shadow eradication methods is insufficient for a real-time intelligent transport system. For the purpose of removing shadows, a novel technique is suggested in this research. There are a number of issues that arise as a result of this, including the destruction of objects and the warping of their original shapes. Many algorithms, including deep learning ones, ignore the shadow problem, which contributes to the poor accuracy of vehicle recognition. The shadow problem can reduce the accuracy of vehicle detection, hence traditionally, vehicle detection has been a part of traffic monitoring structures. Vehicle components cast in a shadow may be misidentified, and users may have to deal with the loss of items or the distorting of their shapes. Since the problem could be caused by inaccurate data, the shadow reduction technique is the primary method for improving precision during the vehicle detection procedure. This research presents a method for removing shadows from an image by first identifying the foreground regions using edge data, and then detecting and removing the shadows using prior knowledge based on the image's grayscale data. According to the results of the performance analysis, the suggested method outperforms similar methods in detecting vehicles, hence it will be used in future Intelligent Transportation System deployments. [ABSTRACT FROM AUTHOR]

Shadow detection is a significant preprocessing work that soil type is classified with machine vision. Thus, Density peak clustering based on histogram fitting(DPCHF) is proposed to segment soil image shadows. First, its clustering centers are adaptively obtained by constructing a new parameterless density formula and decision value measure. Then the Fourier series are drawn into it to approximate the gray histogram and a part of gray-levels are allocated by valley points of the histogram fitting curve. Finally, an optimization model is established to optimize the threshold of detecting the shadow in the soil image, and the remaining gray-levels are clustered by the threshold. The simulation results show that DPCHF is better than the contrast algorithm. The average brightness standard deviations of the shadow and non-shadow are respectively 20.9348 and 20.3081 with DPCHF. It can realize the adaptive shadow detection of soil images and there is not the "domino" error propagation in it. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)