PS-RCNN: Detecting secondary human instances in a crowd via primary object suppression

Zheng Ge, Zequn Jie, Xin Huang, Rong Xu, Osamu Yoshie

研究成果: Conference contribution

1 被引用数 (Scopus)

抄録

Detecting human bodies in highly crowded scenes is a challenging problem. Two main reasons result in such a problem: 1). weak visual cues of heavily occluded instances can hardly provide sufficient information for accurate detection; 2). heavily occluded instances are easier to be suppressed by Non-Maximum-Suppression (NMS). To address these two issues, we introduce a variant of two-stage detectors called PS-RCNN. PS-RCNN first detects slightly/none occluded objects by an R-CNN [1] module (referred as P-RCNN), and then suppress the detected instances by human-shaped masks so that the features of heavily occluded instances can stand out. After that, PS-RCNN utilizes another R-CNN module specialized in heavily occluded human detection (referred as S-RCNN) to detect the rest missed objects by P-RCNN. Final results are the ensemble of the outputs from these two RCNNs. Moreover, we introduce a High Resolution RoI Align (HRRA) module to retain as much of fine-grained features of visible parts of the heavily occluded humans as possible. Our PS-RCNN significantly improves recall and AP by 4.49% and 2.92% respectively on CrowdHuman [2], compared to the baseline. Similar improvements on Widerperson [3] are also achieved by the PS-RCNN.

本文言語English
ホスト出版物のタイトル2020 IEEE International Conference on Multimedia and Expo, ICME 2020
出版社IEEE Computer Society
ISBN(電子版)9781728113319
DOI
出版ステータスPublished - 2020 7
イベント2020 IEEE International Conference on Multimedia and Expo, ICME 2020 - London, United Kingdom
継続期間: 2020 7 62020 7 10

出版物シリーズ

名前Proceedings - IEEE International Conference on Multimedia and Expo
2020-July
ISSN(印刷版)1945-7871
ISSN(電子版)1945-788X

Conference

Conference2020 IEEE International Conference on Multimedia and Expo, ICME 2020
国/地域United Kingdom
CityLondon
Period20/7/620/7/10

ASJC Scopus subject areas

  • コンピュータ ネットワークおよび通信
  • コンピュータ サイエンスの応用

フィンガープリント

「PS-RCNN: Detecting secondary human instances in a crowd via primary object suppression」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル