Multi-Camera Action Dataset for Cross-Camera Action Recognition Benchmarking

被引:13
|
作者
Li, Wenhui [1 ]
Wong, Yongkang [2 ]
Liu, An-An [1 ]
Li, Yang [1 ]
Su, Yu-Ting [1 ]
Kankanhalli, Mohan [2 ,3 ]
机构
[1] Tianjin Univ, Sch Elect Informat Engn, Tianjin, Peoples R China
[2] Natl Univ Singapore, Interact & Digital Media Inst, Singapore, Singapore
[3] Natl Univ Singapore, Sch Comp, Singapore, Singapore
基金
新加坡国家研究基金会;
关键词
D O I
10.1109/WACV.2017.28
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Action recognition has received increasing attention from the computer vision and machine learning communities in the last decade. To enable the study of this problem, there exist a vast number of action datasets, which are recorded under controlled laboratory settings, real-world surveillance environments, or crawled from the Internet. Apart from the "in-the-wild" datasets, the training and test split of conventional datasets often possess similar environments conditions, which leads to close to perfect performance on constrained datasets. In this paper, we introduce a new dataset, namely Multi-Camera Action Dataset (MCAD), which is designed to evaluate the open view classification problem under the surveillance environment. In total, MCAD contains 14,298 action samples from 18 action categories, which are performed by 20 subjects and independently recorded with 5 cameras. Inspired by the well received evaluation approach on the LFW dataset, we designed a standard evaluation protocol and benchmarked MCAD under several scenarios. The benchmark shows that while an average of 85% accuracy is achieved under the closed-view scenario, the performance suffers from a significant drop under the cross-view scenario. In the worst case scenario, the performance of 10-fold cross validation drops from 87.0% to 47.4%.
引用
收藏
页码:187 / 196
页数:10
相关论文
共 50 条
  • [31] Computing camera positions from a multi-camera head
    Roth, G
    [J]. THIRD INTERNATIONAL CONFERENCE ON 3-D DIGITAL IMAGING AND MODELING, PROCEEDINGS, 2001, : 135 - 142
  • [32] Human Action Recognition using Prominent Camera
    Kavimandan, P. S.
    Kapoor, R.
    Yadav, K.
    [J]. INTERNATIONAL JOURNAL OF ENGINEERING, 2021, 34 (02): : 427 - 432
  • [33] Human action recognition using prominent camera
    Kavimandan P.S.
    Kapoor R.
    Yadav K.
    [J]. International Journal of Engineering, Transactions B: Applications, 2021, 34 (02): : 427 - 432
  • [34] Multi-Camera Cinematography and Production
    不详
    [J]. SIGHT AND SOUND, 2024, 34 (03): : 66 - 66
  • [35] Multi-camera video surveillance
    Ellis, T
    [J]. 36TH ANNUAL 2002 INTERNATIONAL CARNAHAN CONFERENCE ON SECURITY TECHNOLOGY, PROCEEDINGS, 2002, : 228 - 233
  • [36] Multi-camera colour tracking
    Orwell, J
    Remagnino, P
    Jones, GA
    [J]. SECOND IEEE WORKSHOP ON VISUAL SURVEILLANCE (VS'99), PROCEEDINGS, 1999, : 14 - 21
  • [37] Calibration of Multi-Camera Systems
    Dondo, Diego Gonzalez
    Trasobares, Fernando
    Yoaquino, Leandro
    Padilla, Julian
    Redolfi, Javier
    [J]. 2015 XVI WORKSHOP ON INFORMATION PROCESSING AND CONTROL (RPIC), 2015,
  • [38] Multi-camera face recognition by reliability-based selection
    Xie, Binglong
    Boult, Terry
    Ramesh, Visvanathan
    Zhu, Ying
    [J]. 2006 IEEE INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE FOR HOMELAND SECURITY AND PERSONAL SAFETY, 2006, : 18 - +
  • [39] Overhead Projection Approach For Multi-Camera Vessel Activity Recognition
    Strauch, George E.
    Lin, Jiajian
    Tesic, Jelena
    [J]. 2021 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA), 2021, : 5626 - 5632
  • [40] CALIBRATION OF A MULTI-CAMERA ROVER
    Brunn, A.
    Meyer, Th.
    [J]. XXIII ISPRS Congress, Commission V, 2016, 41 (B5): : 445 - 452