Latest revision as of 14:33, 12 February 2021

Abstract

Far-infrared pedestrian detection approaches for advanced driver-assistance systems based on high-dimensional features fail to simultaneously achieve robust and real-time detection. We propose a robust and real-time pedestrian detection system characterized by novel candidate filters, novel pedestrian features and multi-frame approval matching in a coarse-to-fine fashion. Firstly, we design two filters based on the pedestrians’ head and the road to select the candidates after applying a pedestrian segmentation algorithm to reduce false alarms. Secondly, we propose a novel feature encapsulating both the relationship of oriented gradient distribution and the code of oriented gradient to deal with the enormous variance in pedestrians’ size and appearance. Thirdly, we introduce a multi-frame approval matching approach utilizing the spatiotemporal continuity of pedestrians to increase the detection rate. Large-scale experiments indicate that the system works in real time and the accuracy has improved about 9% compared with approaches based on high-dimensional features only.

Document type: Article

Full document

Original document

The different versions of the original document can be found in:

• http://dx.doi.org/10.3390/s151229874 under the license https://creativecommons.org/licenses/by

• http://europepmc.org/articles/PMC4721794 under the license http://creativecommons.org/licenses/by/3.0/

• https://www.mdpi.com/1424-8220/15/12/29874/pdf

• http://www.mdpi.com/1424-8220/15/12/29874,

https://doaj.org/toc/1424-8220 under the license cc-by

• http://www.mdpi.com/1424-8220/15/12/29874/pdf,

http://dx.doi.org/10.3390/s151229874

• https://www.mdpi.com/1424-8220/15/12/29874/pdf,

https://www.mdpi.com/1424-8220/15/12/29874,

https://dblp.uni-trier.de/db/journals/sensors/sensors15.html#WangL15,

http://europepmc.org/articles/PMC4721794,

https://core.ac.uk/display/89231189,

http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4721794,

https://doi.org/10.3390/s151229874,

https://trid.trb.org/view/1409301,

https://academic.microsoft.com/#/detail/2214533396 under the license https://creativecommons.org/licenses/by/4.0/