Crowd Counting via Adversarial Cross-Scale Consistency Pursuit
| Autor: | Minsi Wang, Zan Shen, Bingbing Ni, Yi Xu, Xiaokang Yang, Jianguo Hu |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Scale (ratio)
business.industry Computer science Feature extraction Perspective (graphical) 020206 networking & telecommunications 02 engineering and technology Density estimation computer.software_genre Consistency (database systems) Kernel (statistics) 0202 electrical engineering electronic engineering information engineering Task analysis 020201 artificial intelligence & image processing Artificial intelligence Data mining business computer Crowd counting Subspace topology |
| Zdroj: | CVPR |
| DOI: | 10.1109/cvpr.2018.00550 |
| Popis: | Crowd counting or density estimation is a challenging task in computer vision due to large scale variations, perspective distortions and serious occlusions, etc. Existing methods generally suffer from two issues: 1) the model averaging effects in multi-scale CNNs induced by the widely adopted $$ regression loss; and 2) inconsistent estimation across different scaled inputs. To explicitly address these issues, we propose a novel crowd counting (density estimation) framework called Adversarial Cross-Scale Consistency Pursuit (ACSCP). On one hand, a U-net structured generation network is designed to generate density map from input patch, and an adversarial loss is directly employed to shrink the solution onto a realistic subspace, thus attenuating the blurry effects of density map estimation. On the other hand, we design a novel scale-consistency regularizer which enforces that the sum up of the crowd counts from local patches (i.e., small scale) is coherent with the overall count of their region union (i.e., large scale). The above losses are integrated via a joint training scheme, so as to help boost density estimation performance by further exploring the collaboration between both objectives. Extensive experiments on four benchmarks have well demonstrated the effectiveness of the proposed innovations as well as the superior performance over prior art. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|