Shadow detection for moving objects based on texture analysis

Shadows detection is a fundamental step in visual surveillance and monitoring systems. Shadow points are often misclassified as object points causing errors in localization, segmentation, measurements, tracking and classification of moving objects. In order to detect potential shadow points an automatic segmentation procedure is performed and, for all moving pixels, the approach evaluates the compatibility of photometric properties with shadow characteristics. The approach is improved using a new method focused on the similarity between little textured patches: this method is based on the observation that shadow regions present same textural characteristics in each frame of the gray-level video-sequence and in the corresponding adaptive background model. We suggest a new approach to describe textural information in terms of redundant functions. The algorithm is designed to be unaffected by scene type, background type or light conditions. Results validate the algorithm 's performance on a benchmark suite of indoor and outdoor video sequences.

Shadow detection in very high spatial resolution aerial images: A comparative study

Moving shadows cause serious problem while segmenting and extracting foreground from video sequences, due to the misclassification of moving shadow as foreground. In order to detect the moving objects accurately, a method based on the similarity between little textured patches was proposed to remove the moving shadows. Firstly, the potential shadows were detected by analyzing the intensity and color properties. Secondly, the shadow detection approach was improved by evaluating the textural similarity between the current frame and the corresponding background model. Finally, the geometric heuristics were imposed to further improve the performance. Experimental results on both indoor and outdoor scenes exhibit that the proposed method succeeds in removing shadows robustly and achieves real-time performance.

Shadows cause problems in many remote sensing applications like images segmentation, objects extraction and stereo vision. This paper presents a new and an automatic approach to detect and remove shadows from pair of dense urban very high resolution (VHR) remote sensing images. The main contribution of this paper is twofold. First, a proposed approach is efficient to restore objects hidden by shadows, second, it improves a stereo matching process. We have chosen to operate on Ikonos pairs as an example of urban remote sensing images, for that, shadow detection is achieved using a new technique of property based method, operating directly in red. green and blue colour space (RGB). Shadow removal proposed technique aims to produce a needed amount of light to the shadow regions by multiplying the shadow regions by constants, after that, the shadow edge correction is applied to reduce the errors due to diffusion in the shadow boundary. Once pair of shadow free images is recovered, we apply a stereo matching process using a Hopfield neural technique in order to find homologous regions. Our results from different urban pairs show the effectiveness, the simplicity and the fastness of the proposed approach to reveal details hidden by shadows and to obtain a high stereo matching rate.

Shadows degrade image quality and complicate interpretation, underscoring the importance of accurate shadow detection for many image analysis tasks. However, due to the complex backgrounds and variable shadow characteristics of remote sensing images (RSIs), existing methods often struggle with accurately detecting shadows of various scales and misclassifying dark, non-shaded areas as shadows. To address these issues, we proposed a comprehensive shadow detection network called MAMNet. Firstly, we proposed a multi-scale spatial channel attention fusion module, which extracted multi-scale features incorporating both spatial and channel information, allowing the model to flexibly adapt to shadows of different scales. Secondly, to address the issue of false detection in non-shadow areas, we introduced a criss-cross attention module, enabling non-shadow pixels to be compared with other shadow and non-shadow pixels in the same row and column, learning similar features of pixels in the same category, which improved the classification accuracy of non-shadow pixels. Finally, to address the issue of important information from the other two modules being lost due to continuous upsampling during the decoding phase, we proposed an auxiliary branch module to assist the main branch in decision-making, ensuring that the final output retained the key information from all stages. The experimental results demonstrated that the model outperformed the current state-of-the-art RSI shadow detection method on the aerial imagery dataset for shadow detection (AISD). The model achieved an overall accuracy (OA) of 97.50%, an F1 score of 94.07%, an intersection over union (IOU) of 88.87%, a precision of 95.06%, and a BER of 4.05%, respectively. Additionally, visualization results indicated that our model could effectively detect shadows of various scales while avoiding false detection in non-shadow areas. Therefore, this model offers an efficient solution for shadow detection in aerial imagery.

Effective shadow detection and shadow removal can improve the performance of fruit recognition in natural environments and provide technical support for agricultural intelligence. In this study, a superpixel segmentation method was used to divide an image into multiple small regions. Based on the superpixel segmentation results, the shadow regions and the shadowless regions of the orchard images under natural light were compared and studied. Seven shadow saliency features (SSF) were explored and analyzed for shadow detection. The SSF were used to enhance the shadow characteristics. Then, the genetic algorithm (GA) was used to optimize the parameters, and support vector machine recursive feature elimination (SVM-RFE) was used to determine the best feature combination for shadow detection. According to the best feature combination, the support vector machine (SVM) algorithm was used to determine whether each segment of the superpixel segmentation results belonged to the shadow region. Shadow removal was carried out on each detected shadow region, and a natural light image after shadow removal was obtained. Finally, the accuracy of shadow detection was tested. The experimental results showed that the average accuracy of the shadow detection algorithm in this study was 91.91%. As a result, the precision and recall for fruits recognition after shadow removal generally improved.

Intelligent video surveillance systems detect pre-configured surveillance events through background modeling, foreground and object extraction, object tracking, and event detection. Shadow regions inside video frames sometimes appear as foreground objects, interfere with ensuing processes, and finally degrade the event detection performance of the systems. Conventional studies have mostly used intensity, color, texture, and geometric information to perform shadow detection in daytime video, but these methods lack the capability of removing shadows in nighttime video. In this paper, a novel shadow detection algorithm for nighttime video is proposed; this algorithm partitions each foreground object based on the object’s vertical histogram and screens out shadow objects by validating their orientations heading toward regions of light sources. From the experimental results, it can be seen that the proposed algorithm shows more than 93.8% shadow removal and 89.9% object extraction rates for nighttime video sequences, and the algorithm outperforms conventional shadow removal algorithms designed for daytime videos.

In this paper, for the modern intelligent video surveillance, we introduce an optimizing motion detection algorithm aim at overcoming the flaw of conventional background subtraction algorithm. We combine adaptive background model in HSV color space with moving object segmentation based on fuzzy clustering to extract moving objects from frame. The adaptive background model is able to restoring the background due to the accurate description of the HSV color space, and then the moving object segmentation based on fuzzy clustering is used to distinguish the moving area and noise area by the adaptive selection of threshold. We also consider SIFT feature to improve the performance of motion detection algorithm. The experiment show that the algorithm alleviates the impairment of noise and time complexity of the motion detection algorithm is low.

In low or moderate ambient light conditions, flash image is sharp and less noisy as compared to no-flash image; however, it contains unwanted sharp shadows at silhouettes. In our previous work, we proposed a new flash image shadow detection method which utilizes a pair of flash/no-flash images to detect sharp shadows at silhouettes; however, the method often leads to false shadow detection due its inability to effectively discriminate dark background areas. In this paper, we present an enhanced shadow detection algorithm which shows significant improvement in detection results. A seamless cloning method is used to fill detected shadow regions using no-flash image information. A quantitative as well as qualitative comparison of the proposed shadow detection method on our flash/no-flash image dataset shows that it outperforms current state-of-the-art shadow detection algorithms, both in terms of accuracy as well as speed. The qualitative results of proposed shadow recovery technique show that it generates good quality resultant flash images without sharp shadows.

Shadow detection is useful in a variety of image analysis applications, as it can improve scene understanding. Most of the recent shadow detection approaches use near-infrared (NIR) cameras and deep learning to provide enhanced segmentation of the shadow areas in images. In this paper a novel shadow detection method is proposed, exploiting the perceptual color representation of the HSV color space and a physics-inspired optimization algorithm for image segmentation. The comparative advantage of this method over the state-of-the-art ones is that its performance is comparable without requiring any special equipment, such as NIR cameras, while it is simpler. Quantitative and qualitative experiments on publicly available datasets in comparison with three state-of-the-art methods, validate its effectiveness.

Approximation-free running SVD and its application to motion detection

Background modeling techniques for embedded computer vision applications must balance accuracy, speed, and power. Basic background modeling techniques run quickly, but their accuracy is not sufficient for computer vision problems involving dynamic background. In contrast, adaptive background modeling techniques are more robust, but run more slowly. Due to its high inherent fine-grain parallelism, robust adaptive background modeling has been implemented on GPUs with significant performance improvements over CPUs. However, these implementations are infeasible in embedded applications due to the high power ratings of the targeted general-purpose GPU platforms. This paper focuses on exploiting fine-grain data parallelism and optimizing memory access patterns to target a low-cost adaptive background modeling algorithm multimodal mean (MMM) to a low-power GPU with thermal design power (TDP) of only 12 watts. The algorithm has comparable accuracy with the Gaussian mixture model (GMM) algorithm, but less computational and memory cost. It achieves a frame rate of 392 fps with a full VGA resolution (640x480) frame on the low-power integrated GPU NVIDIA ION. This is a 20x speed-up of the MMM algorithm compared to the embedded CPU platform Intel Atom of comparable TDP. In addition, the MMM algorithm attains a 5-6x speed up over the GMM implementation on the ION GPU platform.

The changes of active ingredients content, moisture status and texture characteristics during the moistening of Paeoniae Radix Alba were studied by low-field NMR and imaging(LF-NMR/MRI) and texture analyzer, so as to analyze the correlation between LF-NMR parameters, texture characteristics and active ingredient content of Paeoniae Radix Alba during the moistening at diffe-rent times. The results showed that MRI technology could directly, vividly and accurately characterize the degree of moistening and the process of water migration, and the degree of moistening was consistent with the judgment results of traditional experience. The characteristics of moisture migration and moisture phase state in the moistening process of Paeoniae Radix Alba were that the total water content increased and existed in the form of free water, with an increased moisture mobility. In the case of dampening, the total water content did not increase, but the more watery part of the medicinal material was distributed to the less watery part, with a reduced fluidity. Finally, the medicinal materials were moistened, which can be mutually verified with the MRI results. The free water content and the total water content of Paeoniae Radix Alba had extremely negative correlations with hardness, surface toughness, internal toughness, Paeoniflorin and albiflorin contents(P<0.01). It showed that the use of LF-NMR/MRI and texture analyzer could better characterize the moistening process. It provides data characterization for the scientific connotation of "less soaking and more moisturizing, and the drug is completely saturated with water", and the traditional experience of "observing the water head". The feasible and objective evaluation method was helpful to optimize the softening process parameters, scientifically standardize the operating specifications, define the scienti-fic connotation of traditional Chinese medicine softening, and promote the inheritance and innovation of traditional Chinese medicine processing.

Moving shadows constitute problems in various applications such as image segmentation and object tracking. The main cause of these problems is the misclassification of the shadow pixels as target pixels. Therefore, the use of an accurate and reliable shadow detection method is essential to realize intelligent video processing applications. In this paper, a cepstrum-based method for moving shadow detection is presented. The proposed method is tested on outdoor and indoor video sequences using well-known benchmark test sets. To show the improvements over previous approaches, quantitative metrics are introduced and comparisons based on these metrics are made.

Various computer vision applications required Shadow detection and removal for example object tracking and recognition, scene interpretation, and video supervision. Since shadows have similar characteristics as that of the objects shadow pixels can be classified as part of object. This may cause problems such as merging or loss of object, alternation, and misinterpretation of object shape. To deal with this problem, we represent a deep learning based framework to automatically detect shadows in images. Our method learns many significant features automatically using supervised approach in Convolutional Neural Networks (ConvNets). The approach also makes use of drop out to improve results. The proposed methodology is tested on SBU dataset and results are promising.