Home // PATTERNS 2015, The Seventh International Conferences on Pervasive Patterns and Applications // View article

Pedestrian Detection with Occlusion Handling

Authors:
Yawar Rehman
Irfan Riaz
Fan Xue
Piao Jingchun
Jameel Ahmed Khan
Shin Hyunchul

Keywords: Pedestrian detection; occlusion handling

Abstract:
Pedestrian detection in a crowded environment under occlusion constraint is a challenging task. We have addressed this task by exploiting the properties of rich feature set which gives almost all cues necessary for recognizing pedestrians. Using rich feature set results in higher dimensional space. We have used partial least square regression to work with more discriminative (lower dimensional) features than (higher dimensional) rich feature set. Part model is further applied to deal with occlusions. Our proposed method gives the accuracy of 98% at 10-4 false positives per window on INRIA pedestrian database, which is the best result reported so far, under the same false positives per window.

Pages: 15 to 20

Copyright: Copyright (c) IARIA, 2015

Publication date: March 22, 2015

Published in: conference

ISSN: 2308-3557

ISBN: 978-1-61208-393-3

Location: Nice, France

Dates: from March 22, 2015 to March 27, 2015