Journal
2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
Volume -, Issue -, Pages 2539-2543Publisher
IEEE
DOI: 10.1109/ICASSP43922.2022.9747070
Keywords
Crowd Counting; Crowd Density Estimation; Synthetic Data; Domain Transfer
Funding
- National Key R&D Program of China [2021ZD0109802]
- National Science Foundation of China [61971047]
Ask authors/readers for more resources
In this article, a simulated crowd counting dataset CrowdX is proposed, which enhances the performance of existing algorithms in crowd counting. The analysis of the dataset reveals the impact of factors such as background, camera angle, human density, and resolution on crowd counting.
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 pm-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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available