Deep Flow Collaborative Network for Online Visual Tracking
This work addresses efficiency issues in online visual tracking for applications like surveillance and robotics, but it is incremental as it builds on existing deep tracking methods.
The paper tackles the slow feature extraction problem in deep learning-based visual trackers by proposing a deep flow collaborative network that executes expensive feature networks only on sparse keyframes and transfers features via optical flow, achieving considerable speedup and high precision on OTB2013 and OTB2015 datasets.
The deep learning-based visual tracking algorithms such as MDNet achieve high performance leveraging to the feature extraction ability of a deep neural network. However, the tracking efficiency of these trackers is not very high due to the slow feature extraction for each frame in a video. In this paper, we propose an effective tracking algorithm to alleviate the time-consuming problem. Specifically, we design a deep flow collaborative network, which executes the expensive feature network only on sparse keyframes and transfers the feature maps to other frames via optical flow. Moreover, we raise an effective adaptive keyframe scheduling mechanism to select the most appropriate keyframe. We evaluate the proposed approach on large-scale datasets: OTB2013 and OTB2015. The experiment results show that our algorithm achieves considerable speedup and high precision as well.