Detecting temporally consistent objects in videos through object class label propagation
Research output: Contribution to journal › Conference article › Research › peer-review
Object proposals for detecting moving or static video objects need to address issues such as speed, memory complexity and temporal consistency. We propose an efficient Video Object Proposal (VOP) generation method and show its efficacy in learning a better video object detector A deep-learning based video object detector learned using the proposed VOP achieves state-of-the-art detection performance on the Youtube-Objects dataset. We further propose a clustering of VOPs which can efficiently be used for detecting objects in video in a streaming fashion. As opposed to applying per-frame convolutional neural network (CNN) based object detection, our proposed method called Objects in Video Enabler thRough LAbel Propagation (OVERLAP) needs to classify only a small fraction of all candidate proposals in every video frame through streaming clustering of object proposals and class-label propagation. Source code for VOP clustering is available at https://github. com/subtri/streaming-VOP-clustering.
Original language | English |
---|---|
Journal | 2016 IEEE Winter Conference on Applications of Computer Vision, WACV 2016 |
DOIs | |
Publication status | Published - 23 May 2016 |
Externally published | Yes |
Event | IEEE Winter Conference on Applications of Computer Vision, WACV 2016 - Lake Placid, United States Duration: 7 Mar 2016 → 10 Mar 2016 |
Conference
Conference | IEEE Winter Conference on Applications of Computer Vision, WACV 2016 |
---|---|
Country | United States |
City | Lake Placid |
Period | 07/03/2016 → 10/03/2016 |
Bibliographical note
Publisher Copyright:
© 2016 IEEE.
ID: 301828559