Meeting in the Middle: A top-down and bottom-up approach to detect pedestrians
Shaukat, A, Gilbert, A, Windridge, D and Bowden, R (2012) Meeting in the Middle: A top-down and bottom-up approach to detect pedestrians In: 21st International Conference on Pattern Recognition, 2012-11-11 - 2012-11-15, Tsukuba, Japan.
Available under License : See the attached licence file.
This paper proposes a generic approach combining a bottom-up (low-level) visual detector with a top-down (high-level) fuzzy first-order logic (FOL) reasoning framework in order to detect pedestrians from a moving vehicle. Detections from the low-level visual corner based detector are fed into the logical reasoning framework as logical facts. A set of FOL clauses utilising fuzzy predicates with piecewise linear continuous membership functions associates a fuzzy confidence (a degree-of-truth) to each detector input. Detections associated with lower confidence functions are deemed as false positives and blanked out, thus adding top-down constraints based on global logical consistency of detections. We employ a state of the art visual detector on a challenging pedestrian detection dataset, and demonstrate an increase in detection performance when used in a framework that combines bottom-up detections with (fuzzy FOL-based) top-down constraints. © 2012 ICPR Org Committee.
|Item Type:||Conference or Workshop Item (Conference Paper)|
|Divisions :||Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing|
|Additional Information :||The original publication is available at http://www.springerlink.com|
|Depositing User :||Symplectic Elements|
|Date Deposited :||20 Sep 2013 13:07|
|Last Modified :||23 Sep 2013 20:17|
Actions (login required)
Downloads per month over past year