Switching Convolutional Neural Network for Crowd Counting

CVPR 2017 • Deepak Babu Sam • Shiv Surya • R. Venkatesh Babu

We propose a novel crowd counting model that maps a given crowd scene to its density. Crowd analysis is compounded by myriad of factors like inter-occlusion between people due to extreme crowding, high similarity of appearance between people and background elements, and large variability of camera view-points... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Crowd Counting ShanghaiTech A Switch-CNN MAE 90.4 # 11
Crowd Counting ShanghaiTech B Switch-CNN MAE 21.6 # 13
Crowd Counting UCF CC 50 Switch-CNN MAE 318.1 # 11
Crowd Counting WorldExpo’10 Switch-CNN Average MAE 9.4 # 9

Results from Other Papers


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK SOURCE PAPER COMPARE
Crowd Counting UCF-QNRF Switch-CNN MAE 228 # 5
Crowd Counting Venice Switch-CNN MAE 52.8 # 4