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
  • [1] Dynamic view selection for multi-camera action recognition
    Scott Spurlock
    Richard Souvenir
    [J]. Machine Vision and Applications, 2016, 27 : 53 - 63
  • [2] Dynamic view selection for multi-camera action recognition
    Spurlock, Scott
    Souvenir, Richard
    [J]. MACHINE VISION AND APPLICATIONS, 2016, 27 (01) : 53 - 63
  • [3] A MARKERLESS APPROACH FOR CONSISTENT ACTION RECOGNITION IN A MULTI-CAMERA SYSTEM
    Calderara, Simone
    Prati, Andrea
    Cucchiara, Rita
    [J]. 2008 SECOND ACM/IEEE INTERNATIONAL CONFERENCE ON DISTRIBUTED SMART CAMERAS, 2008, : 156 - +
  • [4] Action-Based Multi-Camera Synchronization
    Zini, Luca
    Cavallaro, Andrea
    Odone, Francesca
    [J]. IEEE JOURNAL ON EMERGING AND SELECTED TOPICS IN CIRCUITS AND SYSTEMS, 2013, 3 (02) : 165 - 174
  • [5] View-Invariant Feature Discovering for Multi-Camera Human Action Recognition
    Lin, Hong
    Chaisorn, Lekha
    Wong, Yongkang
    Liu, An-An
    Su, Yu-Ting
    Kankanhalli, Mohan S.
    [J]. 2014 IEEE 16TH INTERNATIONAL WORKSHOP ON MULTIMEDIA SIGNAL PROCESSING (MMSP), 2014,
  • [6] City-Scale Multi-Camera Vehicle Tracking by Semantic Attribute Parsing and Cross-Camera Tracklet Matching
    He, Yuhang
    Han, Jie
    Yu, Wentao
    Hong, Xiaopeng
    Wei, Xing
    Gong, Yihong
    [J]. 2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW 2020), 2020, : 2456 - 2465
  • [7] Caesar: Cross-camera Complex Activity Recognition
    Liu, Xiaochen
    Ghosh, Pradipta
    Ulutan, Oytun
    Manjunath, B. S.
    Chan, Kevin
    Govindan, Ramesh
    [J]. PROCEEDINGS OF THE 17TH CONFERENCE ON EMBEDDED NETWORKED SENSOR SYSTEMS (SENSYS '19), 2019, : 232 - 244
  • [8] The action control of a dexterous mechanical gripper by a multi-camera system
    Zhu, FW
    Gong, ZB
    [J]. PROCEEDINGS OF THE 3RD CHINA-JAPAN SYMPOSIUM ON MECHATRONICS, 2002, : 33 - 36
  • [9] Real-Time Multi-Camera Multi-Person Action Recognition using Pose Estimation
    Phang, Jonathan Then Sien
    Lim, King Hann
    [J]. PROCEEDINGS OF THE 3RD INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND SOFT COMPUTING (ICMLSC 2019), 2019, : 175 - 180
  • [10] A multi-camera dataset for depth estimation in an indoor scenario
    Marin, Giulio
    Agresti, Gianluca
    Minto, Ludovico
    Zanuttigh, Pietro
    [J]. DATA IN BRIEF, 2019, 27