Abstract | ||
---|---|---|
As the post-processing step for object detection, non-maximum suppression (GreedyNMS) is widely used in most of the detectors for many years. It is efficient and accurate for sparse scenes, but suffers an inevitable trade-off between precision and recall in crowded scenes. To overcome this drawback, we propose a Pairwise-NMS to cure GreedyNMS. Specifically, a pairwise-relationship network that is based on deep learning is learned to predict if two overlapping proposal boxes contain two objects or zero/one object, which can handle multiple overlapping objects effectively. Through neatly coupling with GreedyNMS without losing efficiency, consistent improvements have been achieved in heavily occluded datasets including MOT15, TUD-Crossing and PETS. In addition, Pairwise-NMS can be integrated into any learning based detectors (Both of Faster-RCNN and DPM detectors are tested in this paper), thus building a bridge between GreedyNMS and end-to-end learning detectors. |
Year | Venue | DocType |
---|---|---|
2019 | arXiv: Computer Vision and Pattern Recognition | Journal |
Volume | Citations | PageRank |
abs/1901.03796 | 0 | 0.34 |
References | Authors | |
0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yu Liu | 1 | 15 | 2.97 |
Lingqiao Liu | 2 | 592 | 37.69 |
Seyed Hamid Rezatofighi | 3 | 149 | 13.36 |
Thanh-Toan Do | 4 | 173 | 24.22 |
Qinfeng Shi | 5 | 1564 | 74.85 |
Ian D. Reid | 6 | 5864 | 364.59 |