Detecting pedestrians using patterns of motion and appearance

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 This work may not be copied or reproduced in whole or in part for any commercial purpose. Permission to copy in whole or in part without payment of fee is granted for nonprofit educational and research purposes provided that all such whole or partial copies include the following: a notice that such copying is by permission of Mitsubishi Electric Research Laboratories, Inc.; an acknowledgment of the authors and individual contributions to the work; and all applicable portions of the copyright notice. Copying, reproduction, or republishing for any other purpose shall require a license with payment of fee to Mitsubishi Electric Research Laboratories, Inc. All rights reserved. Detecting Pedestrians Using Patterns of Motion and Appearance

Geography and computational social science

“…Wireless Internet access points can be used to triangulate the movement of laptop users in urban environments (Torrens 2008). Behavior can also be inferred from movements detected in video using pattern-matching (Viola et al 2005). The geography of these patterns and behaviors is also being used to develop location-based services (Schiller and Voisard 2004) that make use of information regarding where people are, where they have been, and what they have done (or what other people with similar geographical history have done), to deliver information to mobile, location-aware devices carried in pockets and handbags (portable music players, cellphones, handheld computers, cameras) or embedded in objects (vehicles, assets, casino chips).…”

Particle swarm optimisation based AdaBoost for object detection

“…This system has three main characteristics: using the AdaBoost boosting algorithm to combine simple weak classifiers into a more effective strong classifier; use of an integral image to rapidly compute simple features; and using a cascade of AdaBoost classifiers to quickly eliminate most negative images from consideration. Due to its robustness, it has been used in different applications including face and pedestrian detection (Viola et al 2003), gender classification (Verschae et al 2006), text detection (Bargeron et al 2005) and others.…”

Pre-Attentive and Attentive Detection of Humans in Wide-Field Scenes

“…We perform a rigorous comparison between our proposed Bayesian cue integration technique and four state-of-the-art methods from the literature (Viola and Jones, 2001;Viola et al, 2003;Abramson and Freund, 2005;Xiong and Jaynes, 2003). 6.…”