H.264-based Wireless Surveillance Sensors in Application to Target Identification and Tracking

Vol.4 No.2

Year: 2009

Issue: October - December

Title: H.264-based Wireless Surveillance Sensors in Application to Target Identification and Tracking   

Author Name: Wei Zhao, Jeffrey Fan, Asad Davari   

Synopsis:   

In this paper, we propose a hardware-based microstructure inside the architecture of H.264 encoder, called Vector Bank (VB), which can dramatically reduce the bandwidth, memory, and computation time of a multi-camera video surveillance system. VB is a memory-based structure that contains the vector information for every single Macro Block (MB) of the video frame from the Motion Estimation module of the H.264 encoder. After extraction of these vectors from several frames, a dedicated Digital Signal Processor (DSP) can be assigned to analyze and predict the trajectories of the objects in motion. With the application of 2-D edge detectors, such as Sobel or Laplacian of Gaussian (LoG) operators, the objects in motion can be isolated from the background and thus be easily identified. In addition, a middleware-based technique derived from Directional Discrete Cosine Transform (DDCT) is introduced to improve the image quality without sacrificing the system performance. We propose four new modes of operations in DDCT for better image compression ratio. The experimental results show that we can improve the image quality of the targets, isolate them from the background, and track them easily in both linear and exponential trajectories of the motion.