Two-level Data Augmentation for Calibrated Multi-view Detection

Abstract

Data augmentation has proven its usefulness to improve model generalization and performance. While it is commonly applied in computer vision application when it comes to multi-view systems, it is rarely used. Indeed geometric data augmentation can break the alignment among views. This is problematic since multi-view data tend to be scarce and it is expensive to annotate. In this work we propose to solve this issue by introducing a new multi-view data augmentation pipeline that preserves alignment among views. Additionally to traditional augmentation of the input image we also propose a second level of augmentation applied directly at the scene level. When combined with our simple multi-view detection model, our two-level augmentation pipeline outperforms all existing baselines by a significant margin on the two main multi-view multi-person detection datasets WILDTRACK and MultiviewX.

Links

Paper Suppl. Code

Citation

If you found this work useful, please cite the associated paper:

@inproceedings{engilber2023two,
  title={Two-level Data Augmentation for Calibrated Multi-view Detection},
  author={Engilberge, Martin and Shi, Haixin and Wang, Zhiye and Fua, Pascal},
  booktitle={Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
  year={2023}
}