Tracking Assisted Faster Video Object Detection
Authors:
- 1 July 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1750-1755
Abstract
Recent approaches have achieved great success on still image object detection. Despite the high accuracy, directly applying image object detectors for video object detection is rather slow. Inspired from the fact that object tracking is much more efficient than object detection, we propose to combine object detection and tracking for fast video object detection. Computational expensive detection network is applied on sparsely arranged key frames, while proposals of non-key frames are obtained through tracking and regression of previous frame's proposals. Assisted with an adaptive key-frame arrangement module, our method can adaptively decide whether to track or to detect based on tracking quality. Extensive experiments show that the proposed method can significantly boost detection speed with a rather small drop in detection accuracy.Keywords
This publication has 10 references indexed in Scilit:
- Video Object Detection with an Aligned Spatial-Temporal Memory2018
- Object Detection in Video with Spatiotemporal Sampling Networks2018
- Fully Motion-Aware Network for Video Object Detection2018
- Towards High Performance Video Object Detection2018
- Detect to Track and Track to Detect2017
- Flow-Guided Feature Aggregation for Video Object Detection2017
- Fully-Convolutional Siamese Networks for Object Tracking2016
- Deep Residual Learning for Image Recognition2016
- Object Detection from Video Tubelets with Convolutional Neural Networks2016
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015