Detecting Pedestrians Using Patterns of Motion and Appearance

DMCA

Detecting Pedestrians Using Patterns of Motion and Appearance (2003)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Paul Viola , Michael J. Jones , Daniel Snow

Venue:	IN ICCV
Citations:	575 - 3 self

BibTeX

@INPROCEEDINGS{Viola03detectingpedestrians,
    author = {Paul Viola and Michael J. Jones and Daniel Snow},
    title = {Detecting Pedestrians Using Patterns of Motion and Appearance},
    booktitle = {IN ICCV},
    year = {2003},
    pages = {734--741},
    publisher = {}
}

OpenURL

Abstract

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 motion information or 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 20x15 pixels), and has a very low false positive rate

Keyphrases

appearance information motion information consecutive frame video sequence past approach low false positive rate small scale single detector image intensity information pedestrian detection system detection style algorithm detects pedestrian

DMCA