SynMVCrowd: A Large Synthetic Benchmark for Multi-view Crowd Counting and Localization
This addresses the issue of overfitting in existing methods for researchers in computer vision, though it is incremental as it focuses on dataset creation rather than a new method.
The paper tackles the problem of limited evaluation in multi-view crowd counting and localization by introducing SynMVCrowd, a large synthetic benchmark with up to 1000 people, 50 scenes, and multiple camera views, which improves domain transfer performance on real scenes.
Existing multi-view crowd counting and localization methods are evaluated under relatively small scenes with limited crowd numbers, camera views, and frames. This makes the evaluation and comparison of existing methods impractical, as small datasets are easily overfit by these methods. To avoid these issues, 3DROM proposes a data augmentation method. Instead, in this paper, we propose a large synthetic benchmark, SynMVCrowd, for more practical evaluation and comparison of multi-view crowd counting and localization tasks. The SynMVCrowd benchmark consists of 50 synthetic scenes with a large number of multi-view frames and camera views and a much larger crowd number (up to 1000), which is more suitable for large-scene multi-view crowd vision tasks. Besides, we propose strong multi-view crowd localization and counting baselines that outperform all comparison methods on the new SynMVCrowd benchmark. Moreover, we prove that better domain transferring multi-view and single-image counting performance could be achieved with the aid of the benchmark on novel new real scenes. As a result, the proposed benchmark could advance the research for multi-view and single-image crowd counting and localization to more practical applications. The codes and datasets are here: https://github.com/zqyq/SynMVCrowd.