文档介绍：Designing an Embedded Video Processing Camera Using a 16-bit
Microprocessor for a Surveillance System
Koichi Sato*†, Brian L. Evans*‡ and J. K. Aggarwal*†
†Computer and Vision Research Center
‡Embedded Signal Processing Laboratory
*Department of Electrical puter Engineering
The University of Texas at Austin, Austin, TX 78712 USA
{ ******@alumni. , ******@ , ******@ }
Abstract
This paper describes the design and implementation of a hybrid intelligent surveillance system
that consists of an embedded system and a puter (PC)-based system. The
embedded system performs some of the image processing tasks and sends the processed data to
the PC. The PC tracks persons and recognizes two-person interactions by using a grayscale side
view image sequence captured by a stationary camera. Based on our previous research, we
explored the optimum division of tasks between the embedded system and the PC, simulated the
embedded system using dataflow models in Ptolemy, and prototyped the embedded system in
real-time hardware and software using a 16-bit CISC microprocessor. This embedded system
processes one 320x240 frame in 89 ms, which yields one-third of the rate of 30Hz video system.
In addition, the real-time embedded system prototype uses bytes of program memory,
854K bytes of internal data memory and 2M bytes external DRAM.
1. Introduction
Tracking, recognizing and detecting objects using a video sequence are topics of significant
interest puter vision. Cai and Aggarwal [1] reported a variety of methods for analyzing
human motion. In [2,3], Haritaoglu et al. tracked both single and multiple humans in outdoor
image sequences using a PC. In [4], Oliver, Rosario and Pentland recognized two-person
interactions from perspective-view image sequences. They tracked persons and recognized their
interaction using trajectory patterns. Meanwhile, some researchers developed applications that