Enhancing and Dissecting Crowd Counting By Synthetic Data
This work addresses data scarcity and variability in crowd counting for computer vision applications, though it is incremental as it builds on existing methods with new synthetic data.
The authors tackled the problem of limited and varied data in crowd counting by creating a synthetic dataset, CrowdX, which improved the performance of their benchmark network by 8.4% and enhanced other architectures.
In this article, we propose a simulated crowd counting dataset CrowdX, which has a large scale, accurate labeling, parameterized realization, and high fidelity. The experimental results of using this dataset as data enhancement show that the performance of the proposed streamlined and efficient benchmark network ESA-Net can be improved by 8.4\%. The other two classic heterogeneous architectures MCNN and CSRNet pre-trained on CrowdX also show significant performance improvements. Considering many influencing factors determine performance, such as background, camera angle, human density, and resolution. Although these factors are important, there is still a lack of research on how they affect crowd counting. Thanks to the CrowdX dataset with rich annotation information, we conduct a large number of data-driven comparative experiments to analyze these factors. Our research provides a reference for a deeper understanding of the crowd counting problem and puts forward some useful suggestions in the actual deployment of the algorithm.