Hatem A. Rashwan

Illumination-Robust Optical Flow Using a Local Directional Pattern

Most of the variational optical flow methods are based on the well-known brightness constancy assumption or high-order constancy assumptions to implement the data term in the optimization energy function. Unfortunately, any variation in the lighting within the scene violates the brightness constancy constraint; in turn, the gradient constancy assumption does not work properly with large illumination changes. This paper proposes an illumination-robust constancy based on a robust texture descriptor rather than the brightness constancy. Thus, the similarity function used as a data term was obtained from extracting texture features through the local directional pattern descriptor for two consecutive frames within the duality total variational optical flow algorithm. In addition, a weighted nonlocal term that depends on both the color similarity and the occlusion state of pixels is integrated during the optimization process to increase the accuracy of the resulting flow field. The experimental results show a qualitative comparison with the proposed approach and yield state-of-the-art results on the KITTI, Midleburry, and MPI-sintel data sets.

Illumination Robust Optical Flow Model Based on Histogram of Oriented Gradients

The brightness constancy assumption has widely been used in variational optical flow approaches as their basic foundation. Unfortunately, this assumption does not hold when illumination changes or for objects that move into a part of the scene with different brightness conditions. This paper proposes a variation of the L1-norm dual total variational (TV-L1) optical flow model with a new illumination-robust data term defined from the histogram of oriented gradients computed from two consecutive frames. In addition, a weighted non-local term is utilized for denoising the resulting flow field. Experiments with complex textured images belonging to different scenarios show results comparable to state-of-the-art optical flow models, although being significantly more robust to illumination changes.

Analysis of tissue abnormality and breast density in mammographic images using a uniform local directional pattern

We propose a simple and robust local descriptor of breast tissues in mammograms called ULDP.ULDP is evaluated in the task of mass/normal breast tissue classification.ULDP is evaluated in the task of breast tissue density classification.The results are comparable to the state-of-the-art methods on two databases. This paper proposes a computer-aided diagnosis system to analyze breast tissues in mammograms, which performs two main tasks: breast tissue classification within a region of interest (ROI; mass or normal) and breast density classification. The proposed system consists of three steps: segmentation of the ROI, feature extraction and classification. Although many feature extraction methods have been used to characterize breast tissues, the literature shows no consensus on the optimal feature set for breast tissue characterization. Specifically, mass detection on dense breast tissues is still a challenge. In the feature extraction step, we propose a simple and robust local descriptor for breast tissues in mammograms, called uniform local directional pattern (ULDP). This descriptor can discriminate between different tissues in mammograms, yielding a significant improvement in the analysis of breast cancer. Classifiers based on support vector machines show a performance comparable to the state-of-the-art methods.

Variational Optical Flow Estimation Based on Stick Tensor Voting

Variational optical flow techniques allow the estimation of flow fields from spatio-temporal derivatives. They are based on minimizing a functional that contains a data term and a regularization term. Recently, numerous approaches have been presented for improving the accuracy of the estimated flow fields. Among them, tensor voting has been shown to be particularly effective in the preservation of flow discontinuities. This paper presents an adaptation of the data term by using anisotropic stick tensor voting in order to gain robustness against noise and outliers with significantly lower computational cost than (full) tensor voting. In addition, an anisotropic complementary smoothness term depending on directional information estimated through stick tensor voting is utilized in order to preserve discontinuity capabilities of the estimated flow fields. Finally, a weighted non-local term that depends on both the estimated directional information and the occlusion state of pixels is integrated during the optimization process in order to denoise the final flow field. The proposed approach yields state-of-the-art results on the Middlebury benchmark.

Towards a trustworthy privacy in pervasive video surveillance systems

The consideration of security and privacy is a linchpin of the social acceptance of pervasive technology. This paper paves the way to the development of trustworthy pervasive video surveillance systems, by emphasizing the need to properly combine different aspects that current systems do not manage. In particular, in this paper we propose the combination of the following issues into a common framework: proper people identification mainly based on computer vision techniques, content protection not only by using convenient cryptographic techniques, but also law enforcement and user cooperation in order to get feedback with regard to the whole video surveillance system. Furthermore, an analysis focused on the current computer vision techniques used for people identification is presented. Finally, a score to measure the trust offered by video surveillance systems is proposed.

Understanding trust in privacy-aware video surveillance systems

Recent advances in pervasive video surveillance systems pave the way for a comprehensive surveillance of every aspect of our lives, hence, leading us to a state of dataveillance. Computerized and interconnected systems of cameras could be used to profile, track and monitor individuals for the sake of security. Notwithstanding, these systems clearly interfere with the fundamental right of the individuals to privacy. Most literature on privacy in video surveillance systems concentrates on the goal of detecting faces and other regions of interest and in proposing different methods to protect them. However, the trustworthiness of those systems and, by extension, of the privacy they provide are mostly neglected. In this article, we define the concept of trustworthy privacy-aware video surveillance system. Moreover, we assess the techniques proposed in the literature according to their suitability for such a video surveillance system. Finally, we describe the properties that a deployment of a trustworthy video surveillance system must fulfill.

Improving the robustness of variational optical flow through tensor voting

Differential optical flow methods allow the estimation of optical flow fields based on the first-order and even higher-order spatio-temporal derivatives (gradients) of sequences of input images. If the input images are noisy, for instance because of the limited quality of the capturing devices or due to poor illumination conditions, the use of partial derivatives will amplify that noise and thus end up affecting the accuracy of the computed flow fields. The typical approach in order to reduce that noise consists of smoothing the required gradient images with Gaussian filters, for instance by applying structure tensors. However, that filtering is isotropic and tends to blur the discontinuities that may be present in the original images, thus likely leading to an undesired loss of accuracy in the resulting flow fields. This paper proposes the use of tensor voting as an alternative to Gaussian filtering, and shows that the discontinuity preserving capabilities of the former yield more robust and accurate results. In particular, a state-of-the-art variational optical flow method has been adapted in order to utilize a tensor voting filtering approach. The proposed technique has been tested upon different datasets of both synthetic and real image sequences, and compared to both well known and state-of-the-art differential optical flow methods.

On improving the robustness of variational optical flow against illumination changes

The brightness constancy assumption is the base of estimating the flow fields in most differential optical flow approaches. However, the brightness constancy constraint easily violates with any variation in the lighting conditions in the scene. Thus, this work proposes a robust data term against illumination changes based on a rich descriptor. This descriptor extracts the textures features for each image in the two consecutive images using local edge responses. In addition, a weighted non-local term depending on the intensity similarity, the spatial distance and the occlusion state of pixels is integrated within the adapted duality total variational optical flow algorithm in order to obtain accurate flow fields. The proposed model yields state-of-the-art results on the the KITTI optical flow database and benchmark.

On improving the robustness of differential optical flow

Differential optical flow techniques estimate flow fields based on the derivatives of consecutive images. However, the use of partial derivatives amplifies the possible noise present in those images, thus degrading the accuracy of the computed flow fields. This problem is usually overcome by smoothing the gradient images with Gaussian filters. However, the latter tends to blur discontinuities, yielding an undesired loss of accuracy. This paper proposes tensor voting as an alternative to Gaussian filtering that yields more robust and accurate optical flow fields. The proposed model yields state-of-the-art results on the Middlebury optical flow database and benchmark.

Trustworthy Video Surveillance: An Approach Based on Guaranteeing Data Privacy

Thousands of video files are stored in surveillance databases. Pictures of individuals are considered personal data and, thus, their disclosure must be prevented. Although video surveillance is done for the sake of security, the privacy of individuals could be endangered if the proper measures are not taken. In this chapter we claim that a video-surveillance system could protect our safety and, at the same time, guarantee our privacy. Most literature on privacy in video surveillance systems concentrates on the goal of detecting faces and other regions of interest, and in proposing different methods to protect them. However, the trustworthiness of those systems and, by extension, of the privacy they provide are neglected. Hence, we define the concept of Trustworthy Video Surveillance System (T-VSS), which tackles the issue of protecting the privacy of the individuals. In this chapter, we assess the techniques proposed in the literature according to their suitability in a T-VSS. Moreover, we describe a privacy-aware video-surveillance platform that fulfils those properties and we detail all its components. We have implemented and tested the proposed platform to show the feasibility of our proposal.