A modular system for global and local abnormal event detection and categorization in videos

This paper presents a modular system for both abnormal event detection and categorization in videos. Complementary normalcy models are built both globally at the image level and locally within pixels blocks. Three features are analyzed: (1) spatio-temporal evolution of binary motion where foreground pixels are detected using an enhanced background subtraction method that keeps track of temporarily static pixels; (2) optical flow, using a robust pyramidal KLT technique; and (3) motion temporal derivatives. At the local level, a normalcy MOG model is built for each block and for each flow feature and is made more compact using PCA. Then, the activity is analyzed qualitatively using a set of compact hybrid histograms embedding both optical flow orientation (or temporal gradient orientation) and foreground statistics. A compact binary signature of maximal size 13 bits is extracted from these different features for event characterization. The performance of the system is illustrated on different datasets of videos recorded on static cameras. The experiments show that the anomalies are well detected even if the method is not dedicated to one of the addressed scenarios.     

Color tracking with contextual switching: real-time implementation on CPU

Journal of Real-Time Image Processing - The paper proposes contributions for mean-shift (MS) and covariance tracking (CT), and makes these two complementary methods cooperate. While MS runs fast...     

Parallel Light Speed Labeling: an efficient connected component algorithm for labeling and analysis on multi-core processors

In the last decade, many papers have been published to present sequential connected component labeling (CCL) algorithms. As modern processors are multi-core and tend to many cores, designing a CCL algorithm should address parallelism and multithreading. After a review of sequential CCL algorithms and a study of their variations, this paper presents the parallel version of the Light Speed Labeling for connected component analysis (CCA) and compares it to our parallelized implementations of State-of-the-Art sequential algorithms. We provide some benchmarks that help to figure out the intrinsic differences between these parallel algorithms. We show that thanks to its run-based processing, the LSL is intrinsically more efficient and faster than all pixel-based algorithms. We show also, that all the pixel-based are memory-bound on multi-socket machines and so are inefficient and do not scale, whereas LSL, thanks to its RLE compression can scale on such high-end machines. On a 4 × 15-core machine, and for 8192 × 8192 images, LSL outperforms its best competitor by a factor ×10.8 and achieves a throughput of 42.4 gigapixel labeled per second.     

Un indicateur psychosocial: la position syntaxique.

Studied the function of syntactic variables as indicators of psychosocial status. Human Ss: 18 normal male and female French adults (aged 45–64 yrs) (farmers). Ss' discourses on a "strong" nationality (German) vs a "weak" nationality (Portuguese) were analyzed with regard to the syntactic position of phrases referring to representatives of these nationalities. (English abstract) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Les groupes de supporters ultras à Marseille: Des modes de gestion identitaire différents?

This article proposes a study of the identity management strategies of two French ultra groups, South Winners (SW) and the Commando Ultra (CU), who support the same team of Marseille. The Social Identity Theory and the Self Categorization Theory constitute our frame of analysis. We loosened the socio-structural characteristics of status, legitimacy and stability of SW and CU from socio-historic information. Accounts of 40 games between 1997 and 2003 diffused in the fanzines of both groups were analyzed using language social psychology. The obtained results allowed us to put in evidence two different identity management strategy, type "egocentric" for the CU characterized mainly by a Comparison with Standard strategy and of "regionalist type" for the SW, basing essentially on a Supra Ordinate Recategorization. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Light speed labeling: efficient connected component labeling on RISC architectures

This article introduces two fast algorithms for connected component Labeling of binary images, a peculiar case of coloring. The first one, Selkow _DT is pixel-based and a Selkow’s algorithm combined with the decision tree optimization technique. The second one called light speed labeling is segment-based line-relative labeling and was especially thought for commodity RISC architectures. An extensive benchmark on both structured and unstructured images substantiates that these two algorithms, the way they were designed, run faster than Wu’s algorithm claimed to be the world fastest in 2007. Also they both show greater data independency hence runtime predictability.     

POD analysis of oscillating grid turbulence in water and shear thinning polymer solution

Oscillating grids are frequently used with water and Newtonian fluids to generate controlled turbulence and mixing. Yet, their use with shear thinning fluids still requires experimental characterization. Proper orthogonal decomposition (POD) is applied to PIV measurements of the flow generated by an oscillating grid in water and a shear thinning dilute polymer solution (DPS) of xanthan gum. The aims are to investigate the ability of POD to isolate periodic flow structures, and to use it to describe the effects of the shear thinning property. A dominance of the low order POD modes is evidenced in DPS. The methods applied in blade stirred tanks to identify oscillatory motion fail here. However, a strong mode coupling in the grid swept region is observed, determined by the working fluid and by an underlying chaotic nature of the flow. Possibilities of reconstructing turbulence properties using high order modes are discussed.     

High performance motion detection: some trends toward new embedded architectures for vision systems

The goal of this article is to compare some optimised implementations on current high performance platforms in order to highlight architectural trends in the field of embedded architectures and to get an estimation of what should be the components of a next generation vision system. We present some implementations of robust motion detection algorithms on three architectures: a general purpose RISC processor—the PowerPC G4—a parallel artificial retina dedicated to low level image processing—Pvlsar34—and the Associative Mesh, a specialized architecture based on associative net. To handle the different aspects and constraints of embedded systems, execution time and power consumption of these architectures are compared.

Image Processing Vision Systems: Standard Image Sensors Versus Retinas

To decrease the computational complexity of computer vision algorithms, one of the solutions is to achieve some low-level image processing on the sensor focal plan. It becomes a smart sensor device called a retina. This concept makes the vision systems more compact. It increases performances thanks to the reduction of data flow exchanges with external circuits. This paper presents a comparison relating two different vision system architectures. The first one implements a logarithmic complimentary metal-oxide-semiconductor (CMOS)/active pixel sensor interfaced to a microprocessor, where all computations are carried out. The second involves a CMOS sensor including analog processors allowing on-chip image processing. An external microprocessor is used to control the on-chip data flow and integrated operators. We have designed two vision systems as proof-of-concept. The comparison is related to image processing computation time, processing reliability, programmability, precision, bandwidth, and subsequent stages of computations.