person re identification
play

Person Re-Identification Yiheng Liu Outli line Background - PowerPoint PPT Presentation

Person Re-Identification Yiheng Liu Outli line Background Image-Based Person Re-Identification Partial Person Re-identification Video-Based Person Re-Identification Our Methods Outli line Background Image-Based


  1. Person Re-Identification Yiheng Liu

  2. Outli line • Background • Image-Based Person Re-Identification • Partial Person Re-identification • Video-Based Person Re-Identification • Our Methods

  3. Outli line • Background • Image-Based Person Re-Identification • Partial Person Re-identification • Video-Based Person Re-Identification • Our Methods

  4. Person Re-id identif ification • Person re-identification aims to match persons across non-overlapping surveillance camera views. 数据 检测 跟踪 匹配 Images : https://www.tugraz.at/institute/icg/research/team-bischof/lrs/downloads/prid11/

  5. Datasets and Protocols ls Dataset ID Images Market1501 1501 32217 DukeMTMC-reID 1812 36441 Image Cumulated Matching Characteristics (CMC) : Rank-1, Rank-5 • CUHK03 1467 13164 • mean Average Precision (mAP) MSMT17 4101 126441 iLIDS-VID 300 42495 Video PRID2011 934 24541 MARS 1261 1191003

  6. Outli line • Background • Image-Based Person Re-Identification • Partial Person Re-identification • Video-Based Person Re-Identification • Our Methods

  7. Learning Dis iscrim iminative Features wit ith Mult ltiple Granularitie ies for Person Re-Id Identification

  8. Beyond Part Models ls: Person Retrie ieval l wit ith Refin ined Part Poolin ing (and A Strong Convolutional l Baseline)

  9. Refin ined Part Poolin ing

  10. Horiz izontal l Pyramid Matchin ing for Person Re-id identific ication

  11. Learning In Incremental Trip iple let Margin for Person Re-id identific ication

  12. Outli line • Background • Image-Based Person Re-Identification • Partial Person Re-identification • Video-Based Person Re-Identification • Our Methods

  13. Perceive Where to Focus: Learning Vis isibilit ity-aware Part-le level Features for Partial l Person Re-id identif ification

  14. Overall distance: Region feature:

  15. • The training of region locator • Cross-entropy loss • Triplet loss

  16. Outli line • Background • Image-Based Person Re-Identification • Partial Person Re-identification • Video-Based Person Re-Identification • Our Methods

  17. STA: Spatial-Temporal l Attention for Large-Scale le Vid ideo-based Person Re-Id Identif ification Inter-Frame Regularization

  18. Feature Fusion Strategy

  19. THANK YOU FOR LISTENING

Recommend


More recommend