There are four datasets included in the current BEST benchmark:
Based on this newly collected multi-task multi-camera on-using surveillance dataset, this benchmark aims at bringing together cutting-edge researches in the field of surveillance task aware based intelligent surveillance algorithms and applications. These datasets will be revised/expanded from time to time based on feedback from the academia and the industry.
If you use this facility in any publication, we request you to kindly acknowledge this website (http://best.sjtu.edu.cn) and cite the following overview paper:
Chongyang Zhang, Bingbing Ni, Li Song, Guangtao Zhai, Xiaokang Yang, and Wenjun Zhang, BEST: Benchmark and Evaluation of Surveillance Task, in the 13th Asian Conference on Computer Vision Workshop on Benchmark and Evaluation of Surveillance Task (BEST2016), Taipei ROC, November 20-24, 2016. (pdf)
|SPID: Surveillance Pedestrian Image Dataset||SHAD: Surveillance Human Action Dataset|
|SPRD: Surveillance Person Re-Identification Dataset||SVCD: Surveillance Video Coding Dataset|
2016 © SJTU-BEST 沪交ICP备20160083Support by : Wei Cheng