Part-Level Convolutional Neural Networks for Pedestrian Detection Using Saliency and Boundary Box Alignment

Pedestrians in videos have a wide range of appearances such as body poses, occlusions, and complex backgrounds, and there exists the proposal shift problem in pedestrian detection that causes the loss of body parts such as head and legs. To address it, we propose part-level convolutional neural networks (CNN) for pedestrian detection using saliency and boundary box alignment in this paper... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Pedestrian Detection Caltech Part-level CNN + saliency and bounding box alignment Reasonable Miss Rate 12.4 # 20

Methods used in the Paper