Flow-Guided Feature Aggregation for Video Object Detection

Extending state-of-the-art object detectors from image to video is challenging. The accuracy of detection suffers from degenerated object appearances in videos, e.g., motion blur, video defocus, rare poses, etc. Existing work attempts to exploit temporal information on box level, but such methods ar...

Full description

Saved in:
Bibliographic Details
Published inProceedings / IEEE International Conference on Computer Vision pp. 408 - 417
Main Authors Xizhou Zhu, Yujie Wang, Jifeng Dai, Lu Yuan, Yichen Wei
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.10.2017
Subjects
Detectors
Feature extraction
Object detection
Optical imaging
Target tracking
Training
Online AccessGet full text

Cover

More Information
Summary:Extending state-of-the-art object detectors from image to video is challenging. The accuracy of detection suffers from degenerated object appearances in videos, e.g., motion blur, video defocus, rare poses, etc. Existing work attempts to exploit temporal information on box level, but such methods are not trained end-to-end. We present flow-guided feature aggregation, an accurate and end-to-end learning framework for video object detection. It leverages temporal coherence on feature level instead. It improves the per-frame features by aggregation of nearby features along the motion paths, and thus improves the video recognition accuracy. Our method significantly improves upon strong singleframe baselines in ImageNet VID [33], especially for more challenging fast moving objects. Our framework is principled, and on par with the best engineered systems winning the ImageNet VID challenges 2016, without additional bells-and-whistles. The code would be released.
ISSN:2380-7504
DOI:10.1109/ICCV.2017.52