Detecting pedestrians using patterns of motion and appearance

This paper describes a pedestrian detection system that integrates image intensity information with motion information. We use a detection style algorithm that scans a detector over two consecutive frames of a video sequence. The detector is trained (using AdaBoost) to take advantage of both motion...

Full description

Saved in:
Bibliographic Details
Published in:Computer Vision, 9th IEEE International Conference On pp. 734 - 741 vol.2
Main Authors: Viola, Jones, Snow
Format: Conference Proceeding
Language:English
Published: IEEE 2003
Subjects:
Detectors
Face detection
Humans
Image resolution
Motion analysis
Motion detection
Object detection
Pattern recognition
Rain
Snow
ISBN:9780769519500, 0769519504
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper describes a pedestrian detection system that integrates image intensity information with motion information. We use a detection style algorithm that scans a detector over two consecutive frames of a video sequence. The detector is trained (using AdaBoost) to take advantage of both motion and appearance information to detect a walking person. Past approaches have built detectors based on appearance information, but ours is the first to combine both sources of information in a single detector. The implementation described runs at about 4 frames/second, detects pedestrians at very small scales (as small as 20/spl times/15 pixels), and has a very low false positive rate. Our approach builds on the detection work of Viola and Jones. Novel contributions of this paper include: i) development of a representation of image motion which is extremely efficient, and ii) implementation of a state of the art pedestrian detection system which operates on low resolution images under difficult conditions (such as rain and snow).
ISBN:9780769519500
0769519504
DOI:10.1109/ICCV.2003.1238422