Deep Occlusion Reasoning for Multi-Camera Multi-Target Detection

Pierre Baque, Francois Fleuret, Pascal Fua; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp. 271-279

Abstract


People detection in 2D images has improved greatly in recent years. However, comparatively little of this progress has percolated into multi-camera multi-people tracking algorithms, whose performance still degrades severely when scenes become very crowded. In this work, we introduce a new architecture that combines Convolutional Neural Nets and Conditional Random Fields to explicitly resolve ambiguities. One of its key ingredients are high-order CRF terms that model potential occlusions and give our approach its robustness even when many people are present. Our model is trained end-to-end and we show that it outperforms several state-of-the-art algorithms on challenging scenes.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Baque_2017_ICCV,
author = {Baque, Pierre and Fleuret, Francois and Fua, Pascal},
title = {Deep Occlusion Reasoning for Multi-Camera Multi-Target Detection},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2017}
}