Feature-aware Adaptation and Density Alignment for Crowd Counting in Video Surveillance
arXiv:1912.03672
Abstract
With the development of deep neural networks, the performance of crowd counting and pixel-wise density estimation are continually being refreshed. Despite this, there are still two challenging problems in this field: 1) current supervised learning needs a large amount of training data, but collecting and annotating them is difficult; 2) existing methods can not generalize well to the unseen domain. A recently released synthetic crowd dataset alleviates these two problems. However, the domain gap between the real-world data and synthetic images decreases the models' performance. To reduce the gap, in this paper, we propose a domain-adaptation-style crowd counting method, which can effectively adapt the model from synthetic data to the specific real-world scenes. It consists of Multi-level Featureaware Adaptation (MFA) and Structured Density map Alignment (SDA). To be specific, MFA boosts the model to extract domain-invariant features from multiple layers. SDA guarantees the network outputs fine density maps with a reasonable distribution on the real domain. Finally, we evaluate the proposed method on four mainstream surveillance crowd datasets, Shanghai Tech Part B, WorldExpo'10, Mall and UCSD. Extensive experiments evidence that our approach outperforms the state-of-the-art methods for the same cross-domain counting problem.
arXiv commentaccepted by IEEE T-CYB
References in corpus (15)
- Adam: A Method for Stochastic Optimization
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
- NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization
- Crowded Scene Analysis: A Survey
- SCAR: Spatial-/Channel-wise Attention Regression Networks for Crowd Counting
- Weakly Supervised Adversarial Domain Adaptation for Semantic Segmentation in Urban Scenes
- Top-Down Feedback for Crowd Counting Convolutional Neural Network
- Tracking as A Whole: Multi-Target Tracking by Modeling Group Behavior with Sequential Detection
- Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds
- Learning from Synthetic Data for Crowd Counting in the Wild
- Fine-Grained Crowd Counting
- Crowd Counting with Deep Structured Scale Integration Network
- C^3 Framework: An Open-source PyTorch Code for Crowd Counting
- Leveraging Unlabeled Data for Crowd Counting by Learning to Rank