Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd

ECCV 2018 Shifeng ZhangLongyin WenXiao BianZhen LeiStan Z. Li

Pedestrian detection in crowded scenes is a challenging problem since the pedestrians often gather together and occlude each other. In this paper, we propose a new occlusion-aware R-CNN (OR-CNN) to improve the detection accuracy in the crowd... (read more)

PDF Abstract

Code


No code implementations yet. Submit your code now

Results from the Paper


#5 best model for Pedestrian Detection on Caltech (using extra training data)

     Get a GitHub badge
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
RESULT LEADERBOARD
Pedestrian Detection Caltech OR-CNN + CityPersons dataset Reasonable Miss Rate 4.1 # 5
Pedestrian Detection CityPersons OR-CNN Reasonable MR^-2 12.8 # 7
Heavy MR^-2 55.7 # 8
Partial MR^-2 15.3 # 6
Bare MR^-2 6.7 # 4

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet