Hardware Acceleration of Background Modeling in the Compressed Domain

Abstract

In intelligent video surveillance systems, scalability (of the number of simultaneous video streams) is important. Two key factors which hinder scalability are the time spent in decompressing the input video streams, and the limited computational power of the processor. This paper demonstrates how a combination of algorithmic and hardware techniques can overcome these limitations, and significantly increase the number of simultaneous streams. The techniques used are processing in the compressed domain, and exploitation of the multicore and vector processing capability of modern processors. The paper presents a system which performs background modeling, using a Mixture of Gaussians approach. This is an important first step in the segmentation of moving targets. The paper explores the effects of reducing the number of coefficients in the compressed domain, in terms of throughput speed and quality of the background modeling. The speedups achieved by exploiting compressed domain processing, multicore and vector processing are explored individually. Experiments show that a combination of all these techniques can give a speedup of 170 times on a single CPU compared to a purely serial, spatial domain implementation, with a slight gain in quality.

A Content-Adaptive Resizing Framework for Boosting Computation Speed of Background Modeling Methods

“…Because of the practical real-time issue of BM methods, hardware-based acceleration methods implemented using CPU and GPU are proposed. For example, Popa et al [16] applied multicores and vector processing of CPUs to implement GMM [17] in the compressed domain. Recently, GPUbased implementations of BM methods have become a new trend due to the parallel processing ability of GPU cores.…”

Fast convergence of regularised Region-based Mixture of Gaussians for dynamic background modelling

“…We show the results for two different values of the neighbourhood term r in the RMoG algorithm, r = 1 and r = 8. r = 1 corresponds to the standard MoG approach while r = 8 is the RMoG with 8 Â 8 regions. We fix the neighbourhood size r as 8 because it is a standard neighbourhood size that can also be applied to background modelling in the compressed domain as in [50]. We also found empirically that r = 8 produced the best results for the RMoG algorithm without compromising too much on the quality of the output.…”

SoC Hardware Implementation of Real-Time Video Segmentation based on the Mixture of Gaussian Algorithm

“…In the past years, some work has been reported on hardware implementation/acceleration of MoG algorithm for video segmentation [7][8][9][10][11][12][13][14]. Early work on hardware implementation of MoG algorithm was conducted in [8,9].…”

“…[11] presents a customized implementation of the MoG algorithm for full high-definition videos to reduce power consumption and hardware resources after simplifying/modifying the MoG algorithm. To further increase the performance of MoG hardware implementation, recent work in [12][13][14] explored to leverage the power of modern multi-core processors and graphic-processing-units (GPU) with parallel or vector processing techniques. The MoG algorithm in [9][10][11] was implemented mainly from a custom design perspective so that it achieves relatively high performance with a relatively low hardware complexity and small amount of hardware resources.…”