Citation

Guo Z, Liao W, Xiao Y, Veelaert P, Philips W. Sensors (Basel) 2018; 18(7): s18072272.

Affiliation

Department of Telecommunications and Information Processing, Ghent University-Interuniversitair Micro-Elektronica Centrum (IMEC), Sint-Pietersnieuwstraat 41, 9000 Gent, Belgium. Wilfried.Philips@UGent.be.

Copyright

(Copyright © 2018, MDPI: Multidisciplinary Digital Publishing Institute)

DOI

10.3390/s18072272

PMID

30011869

Abstract

Better features have been driving the progress of pedestrian detection over the past years. However, as features become richer and higher dimensional, noise and redundancy in the feature sets become bigger problems. These problems slow down learning and can even reduce the performance of the learned model. Current solutions typically exploit dimension reduction techniques. In this paper, we propose a simple but effective feature selection framework for pedestrian detection. Moreover, we introduce occluded pedestrian samples into the training process and combine it with a new feature selection criterion, which enables improved performances for occlusion handling problems. Experimental results on the Caltech Pedestrian dataset demonstrate the efficiency of our method over the state-of-art methods, especially for the occluded pedestrians.

Language: en

Keywords

deep learning; feature selection; occlusion handling; pedestrian detection