CUED Publications database

Co-occurrence flow for pedestrian detection

Maki, A and Seki, A and Watanabe, T and Cipolla, R (2011) Co-occurrence flow for pedestrian detection. Proceedings - International Conference on Image Processing, ICIP. pp. 1889-1892. ISSN 1522-4880

Full text not available from this repository.

Abstract

The last few years have seen considerable progress in pedestrian detection. Recent work has established a combination of oriented gradients and optic flow as effective features although the detection rates are still unsatisfactory for practical use. This paper introduces a new type of motion feature, the co-occurrence flow (CoF). The advance is to capture relative movements of different parts of the entire body, unlike existing motion features which extract internal motion in a local fashion. Through evaluations on the TUD-Brussels pedestrian dataset, we show that our motion feature based on co-occurrence flow contributes to boost the performance of existing methods. © 2011 IEEE.

Item Type: Article
Uncontrolled Keywords: flow HOG motion feature pedestrian
Subjects: UNSPECIFIED
Divisions: Div F > Machine Intelligence
Depositing User: Cron Job
Date Deposited: 07 Mar 2014 12:30
Last Modified: 08 Dec 2014 02:39
DOI: 10.1109/ICIP.2011.6115837