Abstract | ||
---|---|---|
Since objects usually keep a certain distance from the surveillance camera, small object detection is a practical issue. Detecting small objects is also one of the remaining challenges in the computer vision community. The current detectors usually leverage a more robust backbone network, build one or more multi-scale feature pyramids, or define a more precise anchor-box screening criteria. However, the distinguishable features are scarce due to the appearance degradation and a shallow resolution. In this paper, we leverage high-level context to enhance anchor-based detectors’ capabilities for small and crowded face detection. We first define face co-occurrence prior based on density maps (FCP-DM) to explore extensive high-level contextual information. We propose a score-size-specific non-maximum suppression (S3NMS) to replace the traditional non-maximum suppression at the end of anchor-based detectors. Our approach is plug and play and model-independent, which could be concatenated into the existing anchor-based face detectors without extra learning. Compared to the prior art on the WIDER FACE hard set, our method increases an Average Precision of 0.1%-1.3%, while on Crowd Face, which we make for testing small and crowded face detection, it raises an Average Precision of 1% - 6%. Codes and dataset have been available online. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1007/s11042-022-12319-y | Multimedia Tools and Applications |
Keywords | DocType | Volume |
Object detection, Degraded face, Video surveillance | Journal | 81 |
Issue | ISSN | Citations |
24 | 1380-7501 | 0 |
PageRank | References | Authors |
0.34 | 4 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Liang Dong | 1 | 326 | 52.32 |
Geng Qixiang | 2 | 0 | 0.34 |
Sun Han | 3 | 0 | 0.34 |
Huiyu Zhou | 4 | 1303 | 111.91 |
Shun'ichi Kaneko | 5 | 230 | 35.34 |