Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

ADCrowdNet: An Attention-injective Deformable Convolutional Network for Crowd Understanding

About

We propose an attention-injective deformable convolutional network called ADCrowdNet for crowd understanding that can address the accuracy degradation problem of highly congested noisy scenes. ADCrowdNet contains two concatenated networks. An attention-aware network called Attention Map Generator (AMG) first detects crowd regions in images and computes the congestion degree of these regions. Based on detected crowd regions and congestion priors, a multi-scale deformable network called Density Map Estimator (DME) then generates high-quality density maps. With the attention-aware training scheme and multi-scale deformable convolutional scheme, the proposed ADCrowdNet achieves the capability of being more effective to capture the crowd features and more resistant to various noises. We have evaluated our method on four popular crowd counting datasets (ShanghaiTech, UCF_CC_50, WorldEXPO'10, and UCSD) and an extra vehicle counting dataset TRANCOS, and our approach beats existing state-of-the-art approaches on all of these datasets.

Ning Liu, Yongchao Long, Changqing Zou, Qun Niu, Li Pan, Hefeng Wu• 2018

Related benchmarks

TaskDatasetResultRank
Crowd CountingShanghaiTech Part B
MAE7.6
160
Crowd CountingShanghaiTech Part A
MAE63.2
138
Crowd CountingWorldExpo'10 (test)
Scene 1 Error1.6
80
Crowd CountingUCF_CC_50
MAE257.1
60
Crowd CountingUCSD crowd-counting (test)
MAE0.98
36
Vehicle CountingTRANCOS
GAME0 Error2.39
7
Vehicle CountingTRANCOS 34
MAE2.44
6
Density Map EstimationShanghaiTech Part_A
PSNR24.48
2
Density Map EstimationShanghaiTech Part B
PSNR29.35
2
Density Map EstimationUCF_CC_50
PSNR20.08
2
Showing 10 of 13 rows

Other info

Follow for update