Services on Demand
Journal
Article
Indicators
- Cited by SciELO
- Access statistics
Related links
- Similars in SciELO
Share
Ingenius. Revista de Ciencia y Tecnología
On-line version ISSN 1390-860XPrint version ISSN 1390-650X
Abstract
GALARZA BRAVO, Michelle and FLORES CALERO, Marco. PEDESTRIAN DETECTION AT NIGHT BY USING FASTER R-CNN Y INFRARED IMAGES. Ingenius [online]. 2018, n.20, pp.48-57. ISSN 1390-860X. https://doi.org/10.17163/ings.n20.2018.05.
In this paper we present a system for pedestrian detection at nighttime conditions for vehicular safety applications. For this purpose, we analyze the performance of the algorithm Faster R-CNN [1] for infrared images. So that we note that Faster R-CNN [1] has problems to detect small scale pedestrians. For this reason, we present a new Faster R-CNN architecture focused on multi-scale detection, through two ROI’s generators for large size and small size pedestrians, RPNCD and RPNLD respectively. This architecture has been compared with the best Faster R-CNN [1] baseline models, VGG-16 [2] and Resnet 101 [3], which present the best results. The experimental results have been development on CVC-09 [4] and LSIFIR [5] databases, which show improvements specially when detecting pedestrians that are far away, over the DET curve presents the miss rate versus FPPI of 16% and over the Precision vs Recall the AP of 89.85% for pedestrian class and the mAP of 90% over LSIFIR [5] and CVC-09 [4] test sets.
Keywords : pedestrian; infrared; Faster R-CNN; RPN; multi-scale; nighttime.