Dualbox: Generating Bbox pair with strong correspondence via occlusion pattern clustering and proposal refinement

Zheng Ge, Chuyu Hu, Xin Huang, Baiqiao Qiu, Osamu Yoshie

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Despite the rapid development of pedestrian detection, the problem of dense pedestrian detection is still unsolved, especially the upper limit of Recall caused by Non-Maximum-Suppression (NMS). Out of this reason, R2NMS [1] is proposed to simultaneously detect full and visible body bounding boxes, by replacing the full body BBoxes with less occluded visible body BBoxes in the NMS algorithm, achieving a higher recall. However, the P-RPN and P-RCNN modules proposed in R2NMS for simultaneous high quality full and visible body prediction require non-trivial positive/negative assigning strategies for anchor BBoxes. To simplify the prerequisites and improve the utility of R2NMS, we incorporate clustering analysis into the learning of visible body proposals from full body proposals. Furthermore, to reduce the computation complexity caused by the large number of potential visible body proposals, we introduce a novel occlusion pattern prediction branch on top of the R-CNN module (i.e. F-RCNN) to select the best matched visible proposals for each full body proposals and then feed them into another R-CNN module (i.e. V-RCNN). Incorporated with R2NMS, our DualBox model can achieve competitive performance while only requires few hyper-parameters. We validate the effectiveness of the proposed approach on the CrowdHuman [2] and CityPersons [3] datasets. Experimental results show that our approach achieves promising performance for detecting both non-occluded and occluded pedestrians, especially heavily occluded ones.

Original languageEnglish
Title of host publicationProceedings of ICPR 2020 - 25th International Conference on Pattern Recognition
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2097-2102
Number of pages6
ISBN (Electronic)9781728188089
DOIs
Publication statusPublished - 2020
Event25th International Conference on Pattern Recognition, ICPR 2020 - Virtual, Milan, Italy
Duration: 2021 Jan 102021 Jan 15

Publication series

NameProceedings - International Conference on Pattern Recognition
ISSN (Print)1051-4651

Conference

Conference25th International Conference on Pattern Recognition, ICPR 2020
Country/TerritoryItaly
CityVirtual, Milan
Period21/1/1021/1/15

Keywords

  • Dense pedestrian detection
  • Non-maximum-suppression
  • Occlusion patterns

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Dualbox: Generating Bbox pair with strong correspondence via occlusion pattern clustering and proposal refinement'. Together they form a unique fingerprint.

Cite this