Fast object instance search in videos from one example

Jingjing Meng, Junsong Yuan, Yap-Peng Tan, Gang Wang
2015 2015 IEEE International Conference on Image Processing (ICIP)  
We present an efficient approach to search for and locate all occurrences of a specific object in large video volumes, given a single query example. Locations of object occurrences are returned as spatio-temporal trajectories in the 3D video volume. Despite much work on object instance search in image datasets, these methods locate the object independently in each image, therefore do not preserve the spatio-temporal consistency in consecutive video frames. This results in suboptimal performance
more » ... optimal performance if directly applied to videos, as will be shown in our experiments. We propose to locate the object jointly across video frames using spatio-temporal search. The efficiency and effectiveness of the proposed approach is demonstrated on a consumer video dataset consisting of crawled YouTube videos and mobile captured consumer clips. Our method significantly improves the localized search accuracy over the baseline, which treats each frame independently. Moreover, it is able to find the top 100 object trajectories in the 5.5-hour dataset within 30 seconds. Index Termsspatio-temporal trajectory, object instance search in videos
doi:10.1109/icip.2015.7351634 dblp:conf/icip/MengYTW15 fatcat:yi6tycnjozabjctyxtdxt4syka