Real time motion estimation using a neural architecture implemented on GPUs

This work describes a neural network based architecture that represents and estimates object motion in videos. This architecture addresses multiple computer vision tasks such as image segmentation, object representation or characterization, motion analysis and tracking. The use of a neural network architecture allows for the simultaneous estimation of global and local motion and the representation of deformable objects. This architecture also avoids the problem of finding corresponding features while tracking moving objects. Due to the parallel nature of neural networks, the architecture has been implemented on GPUs that allows the system to meet a set of requirements such as: time constraints management, robustness, high processing speed and re-configurability. Experiments are presented that demonstrate the validity of our architecture to solve problems of mobile agents tracking and motion analysis.     

Massively parallel Lucas Kanade optical flow for real-time video processing applications

This paper deals with dense optical flow estimation from the perspective of the trade-off between quality of the estimated flow and computational cost which is required by real-world applications. We propose a fast and robust local method, denoted by eFOLKI, and describe its implementation on GPU. It leads to very high performance even on large image formats such as 4 K (3,840 × 2,160) resolution. In order to assess the interest of eFOLKI, we first present a comparative study with currently available GPU codes, including local and global methods, on a large set of data with ground truth. eFOLKI appears significantly faster while providing quite accurate and highly robust estimated flows. We then show, on four real-time video processing applications based on optical flow, that eFOLKI reaches the requirements both in terms of estimated flows quality and of processing rate.     

Effects of residual motion compensation errors on the performance of airborne along-track interferometric SAR

Two approximations, center-beam approximation and reference digital elevation model (DEM) approximation, are used in synthetic aperture radar (SAR) motion compensation procedures. They usually introduce residual motion compensation errors for airborne single-antenna SAR imaging and SAR interferometry. In this paper, we investigate the effects of residual uncompensated motion errors, which are caused by the above two approximations, on the performance of airborne along-track interferometric SAR (ATI-SAR). The residual uncompensated errors caused by center-beam approximation in the absence and in the presence of elevation errors are derived, respectively. Airborne simulation parameters are used to verify the correctness of the analysis and to show the impacts of residual uncompensated errors on the interferometric phase errors for ATI-SAR. It is shown that the interferometric phase errors caused by the center-beam approximation with an accurate DEM could be neglected, while the interferometric phase errors caused by the center-beam approximation with an inaccurate DEM cannot be neglected when the elevation errors exceed a threshold. This research provides theoretical bases for the error source analysis and signal processing of airborne ATI-SAR.     

Biologically inspired model of path integration based on head direction cells and grid cells

Some neurons in the brain of freely moving rodents show special firing pattern. The firing of head direction cells (HDCs) and grid cells (GCs) is related to the moving direction and distance, respectively. Thus, it is considered that these cells play an important role in the rodents’ path integration. To provide a bionic approach for the vehicle to achieve path integration, we present a biologically inspired model of path integration based on the firing characteristics of HDCs and GCs. The detailed implementation process of this model is discussed. Besides, the proposed model is realized by simulation, and the path integration performance is analyzed under different conditions. Simulations validate that the proposed model is effective and stable.     

Efficient identity-based signature over NTRU lattice

Identity-based signature has become an important technique for lightweight authentication as soon as it was proposed in 1984. Thereafter, identity-based signature schemes based on the integer factorization problem and discrete logarithm problem were proposed one after another. Nevertheless, the rapid development of quantum computers makes them insecure. Recently, many efforts have been made to construct identity-based signatures over lattice assumptions against attacks in the quantum era. However, their efficiency is not very satisfactory. In this study, an efficient identity-based signature scheme is presented over the number theory research unit (NTRU) lattice assumption. The new scheme is more efficient than other lattice- and identity-based signature schemes. The new scheme proves to be unforgeable against the adaptively chosen message attack in the random oracle model under the hardness of the γ-shortest vector problem on the NTRU lattice.     

A competitive study of the pseudoflow algorithm for the minimum <Emphasis Type="Italic">s</Emphasis>–<Emphasis Type="Italic">t</Emphasis> cut problem in vision applications

Rapid advances in image acquisition and storage technology underline the need for real-time algorithms that are capable of solving large-scale image processing and computer-vision problems. The minimum s–t cut problem, which is a classical combinatorial optimization problem, is a prominent building block in many vision and imaging algorithms such as video segmentation, co-segmentation, stereo vision, multi-view reconstruction, and surface fitting to name a few. That is why finding a real-time algorithm which optimally solves this problem is of great importance. In this paper, we introduce to computer vision the Hochbaum’s pseudoflow (HPF) algorithm, which optimally solves the minimum s–t cut problem. We compare the performance of HPF, in terms of execution times and memory utilization, with three leading published algorithms: (1) Goldberg’s and Tarjan’s Push-Relabel; (2) Boykov’s and Kolmogorov’s augmenting paths; and (3) Goldberg’s partial augment-relabel. While the common practice in computer-vision is to use either BK or PRF algorithms for solving the problem, our results demonstrate that, in general, HPF algorithm is more efficient and utilizes less memory than these three algorithms. This strongly suggests that HPF is a great option for many real-time computer-vision problems that require solving the minimum s–t cut problem.     

Multigrid gradient vector flow computation on the GPU

Gradient vector flow (GVF) is a feature-preserving spatial diffusion of image gradients. It was introduced to overcome the limited capture range in traditional active contour segmentation. However, the original iterative solver for GVF, using Euler’s method, converges very slowly. Thus, many iterations are needed to achieve the desired capture range. Several groups have investigated the use of graphic processing units (GPUs) to accelerate the GVF computation. Still, this does not reduce the number of iterations needed. Multigrid methods, on the other hand, have been shown to provide a much better capture range using considerable less iterations. However, non-GPU implementations of the multigrid method are not as fast as the Euler method when executed on the GPU. In this paper, a novel GPU implementation of a multigrid solver for GVF written in OpenCL is presented. The results show that this implementation converges and provides a better capture range about 2–5 times faster than the conventional iterative GVF solver on the GPU.     

Buffer overflow vulnerabilities in CUDA: a preliminary analysis

We present a preliminary study of buffer overflow vulnerabilities in CUDA software running on GPUs. We show how an attacker can overrun a buffer to corrupt sensitive data or steer the execution flow by overwriting function pointers, e.g., manipulating the virtual table of a C++ object. In view of a potential mass market diffusion of GPU accelerated software this may be a major concern.     

Subroutine based detection of APT malware

Statistical detection of mass malware has been shown to be highly successful. However, this type of malware is less interesting to cyber security officers of larger organizations, who are more concerned with detecting malware indicative of a targeted attack. Here we investigate the potential of statistically based approaches to detect such malware using a malware family associated with a large number of targeted network intrusions. Our approach is complementary to the bulk of statistical based malware classifiers, which are typically based on measures of overall similarity between executable files. One problem with this approach is that a malicious executable that shares some, but limited, functionality with known malware is likely to be misclassified as benign. Here a new approach to malware classification is introduced that classifies programs based on their similarity with known malware subroutines. It is illustrated that malware and benign programs can share a substantial amount of code, implying that classification should be based on malicious subroutines that occur infrequently, or not at all in benign programs. Various approaches to accomplishing this task are investigated, and a particularly simple approach appears the most effective. This approach simply computes the fraction of subroutines of a program that are similar to malware subroutines whose likes have not been found in a larger benign set. If this fraction exceeds around 1.5 %, the corresponding program can be classified as malicious at a 1 in 1000 false alarm rate. It is further shown that combining a local and overall similarity based approach can lead to considerably better prediction due to the relatively low correlation of their predictions.     

Building 3D semantic maps for mobile robots using RGB-D camera

The wide availability of affordable RGB-D sensors changes the landscape of indoor scene analysis. Years of research on simultaneous localization and mapping (SLAM) have made it possible to merge multiple RGB-D images into a single point cloud and provide a 3D model for a complete indoor scene. However, these reconstructed models only have geometry information, not including semantic knowledge. The advancements in robot autonomy and capabilities for carrying out more complex tasks in unstructured environments can be greatly enhanced by endowing environment models with semantic knowledge. Towards this goal, we propose a novel approach to generate 3D semantic maps for an indoor scene. Our approach creates a 3D reconstructed map from a RGB-D image sequence firstly, then we jointly infer the semantic object category and structural class for each point of the global map. 12 object categories (e.g. walls, tables, chairs) and 4 structural classes (ground, structure, furniture and props) are labeled in the global map. In this way, we can totally understand both the object and structure information. In order to get semantic information, we compute semantic segmentation for each RGB-D image and merge the labeling results by a Dense Conditional Random Field. Different from previous techniques, we use temporal information and higher-order cliques to enforce the label consistency for each image labeling result. Our experiments demonstrate that temporal information and higher-order cliques are significant for the semantic mapping procedure and can improve the precision of the semantic mapping results.