Automatic detection of shadow regions in an image is a difficult task due to the lack of prior information about the illumination source and the dynamic of the scene objects. To address this problem, in this paper, a deep-learning based segmentation method is proposed that identifies shadow regions at the pixel-level in a single RGB image. We exploit a novel Convolutional Neural Network (CNN) architecture to identify and extract shadow features in an end-to-end manner. This network preserves learned contexts during the training and observes the entire image to detect global and local shadow patterns simultaneously. The proposed method is evaluated on two publicly available datasets of SBU and UCF. We have improved the state-of-the-art Balanced Error Rate (BER) on these datasets by 22\% and 14\%, respectively.
Shadows are common aspect of images and when left undetected can hinder scene understanding and visual processing. We propose a simple yet effective approach based on reflectance to detect shadows from single image. An image is first segmented and based on the reflectance, illumination and texture characteristics, segments pairs are identified as shadow and non-shadow pairs. The proposed method is tested on two publicly available and widely used datasets. Our method achieves higher accuracy in detecting shadows compared to previous reported methods despite requiring fewer parameters. We also show results of shadow-free images by relighting the pixels in the detected shadow regions.
Efficient security management has become an important parameter in todays world. As the problem is growing, there is an urgent need for the introduction of advanced technology and equipment to improve the state-of art of surveillance. In this paper we propose a model for real time background subtraction using AGMM. The proposed model is robust and adaptable to dynamic background, fast illumination changes, repetitive motion. Also we have incorporated a method for detecting shadows using the Horpresert color model. The proposed model can be employed for monitoring areas where movement or entry is highly restricted. So on detection of any unexpected events in the scene an alarm can be triggered and hence we can achieve real time surveillance even in the absence of constant human monitoring.
Synthetic aperture radar (SAR) images are widely used in target recognition tasks nowadays. In this letter, we propose an automatic approach for radar shadow detection and extraction from SAR images utilizing geometric projections along with the digital elevation model (DEM) which corresponds to the given geo-referenced SAR image. First, the DEM is rotated into the radar geometry so that each row would match that of a radar line of sight. Next, we extract the shadow regions by processing row by row until the image is covered fully. We test the proposed shadow detection approach on different DEMs and a simulated 1D signals and 2D hills and volleys modeled by various variance based Gaussian functions. Experimental results indicate the proposed algorithm produces good results in detecting shadows in SAR images with high resolution.
We propose a novel GAN-based framework for detecting shadows in images, in which a shadow detection network (D-Net) is trained together with a shadow attenuation network (A-Net) that generates adversarial training examples. The A-Net modifies the original training images constrained by a simplified physical shadow model and is focused on fooling the D-Net's shadow predictions. Hence, it is effectively augmenting the training data for D-Net with hard-to-predict cases. The D-Net is trained to predict shadows in both original images and generated images from the A-Net. Our experimental results show that the additional training data from A-Net significantly improves the shadow detection accuracy of D-Net. Our method outperforms the state-of-the-art methods on the most challenging shadow detection benchmark (SBU) and also obtains state-of-the-art results on a cross-dataset task, testing on UCF. Furthermore, the proposed method achieves accurate real-time shadow detection at 45 frames per second.
Shadow detection is a fundamental and challenging task, since it requires an understanding of global image semantics and there are various backgrounds around shadows. This paper presents a novel network for shadow detection by analyzing image context in a direction-aware manner. To achieve this, we first formulate the direction-aware attention mechanism in a spatial recurrent neural network (RNN) by introducing attention weights when aggregating spatial context features in the RNN. By learning these weights through training, we can recover direction-aware spatial context (DSC) for detecting shadows. This design is developed into the DSC module and embedded in a CNN to learn DSC features at different levels. Moreover, a weighted cross entropy loss is designed to make the training more effective. We employ two common shadow detection benchmark datasets and perform various experiments to evaluate our network. Experimental results show that our network outperforms state-of-the-art methods and achieves 97% accuracy and 38% reduction on balance error rate.