Paper Info
Title
An FPGA-based people detection system
Abstract
This paper presents an FPGA-based system for detecting people from video. The system is designed to use JPEG-compressed frames from a network camera. Unlike previous approaches that use techniques such as background subtraction and motion detection, we use a machine-learning-based approach to train an accurate detector. We address the hardware design challenges involved in implementing such a detector, along with JPEG decompression, on an FPGA. We also present an algorithm that efficiently combines JPEG decompression with the detection process. This algorithm carries out the inverse DCT step of JPEG decompression only partially. Therefore, it is computationally more efficient and simpler to implement, and it takes up less space on the chip than the full inverse DCT algorithm. The system is demonstrated on an automated video surveillance application and the performance of both hardware and software implementations is analyzed. The results show that the system can detect people accurately at a rate of about 2.5 frames per second on a Virtex-II 2V1000 using a MicroBlaze processor running at 75 MHz, communicating with dedicated hardware over FSL links.
Year
DOI
Venue
2005
10.1155/ASP.2005.1047
EURASIP J. Adv. Sig. Proc.
Keywords
Field
DocType
use technique,fpga-based people,automated video surveillance application,jpeg decompression,detection system,dedicated hardware,hardware design,detection process,inverse dct step,full inverse dct algorithm,fpga-based system,accurate detector
MicroBlaze,Background subtraction,Computer vision,Motion detection,Computer science,Discrete cosine transform,Smart camera,Field-programmable gate array,JPEG,Frame rate,Artificial intelligence,Computer hardware
Journal
Volume
Issue
ISSN
2005,
7
1687-6180
Citations 
PageRank 
References 
19
1.74
5
Authors
3
Name
Order
Citations
PageRank
Vinod Nair11658134.40
Pierre-Olivier Laprise2191.74
James J. Clark340286.34