Occlusion-aware pedestrian detection

Christos Apostolopoulos; Kamal Nasrollahi; M. Hsuan Yang; Mohammad N. S. Jahromi; Thomas B. Moeslund

doi:10.1117/12.2523107

15 March 2019 Occlusion-aware pedestrian detection

Christos Apostolopoulos, Kamal Nasrollahi, M. Hsuan Yang, Mohammad N. S. Jahromi, Thomas B. Moeslund

Author Affiliations +

Proceedings Volume 11041, Eleventh International Conference on Machine Vision (ICMV 2018); 110410I (2019) https://doi.org/10.1117/12.2523107
Event: Eleventh International Conference on Machine Vision (ICMV 2018), 2018, Munich, Germany

Abstract

Failure in pedestrian detection systems can be extremely crucial, specifically in driverless driving. In this paper, failures in pedestrian detectors are refined by re-evaluating the results of state of the art pedestrian detection systems, via a fully convolutional neural network. The network is trained on a number of datasets which include a custom designed occluded pedestrian dataset to address the problem of occlusion. Results show that when applying the proposed network, detectors can not only maintain their state of the art performance, but they even decrease average false positives rate per image, especially in the case where pedestrians are occluded.

Citation Download Citation

Christos Apostolopoulos, Kamal Nasrollahi, M. Hsuan Yang, Mohammad N. S. Jahromi, and Thomas B. Moeslund "Occlusion-aware pedestrian detection", Proc. SPIE 11041, Eleventh International Conference on Machine Vision (ICMV 2018), 110410I (15 March 2019); https://doi.org/10.1117/12.2523107

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE