Deep Flow Collaborative Network for Online Visual Tracking

TL;DR

This paper introduces a deep flow collaborative network for online visual tracking that significantly improves speed by computing features only on keyframes and transferring them via optical flow, maintaining high accuracy.

Contribution

It proposes a novel deep flow collaborative network with an adaptive keyframe scheduling mechanism to enhance tracking efficiency without sacrificing precision.

Findings

Achieves significant speedup in tracking process.

Maintains high tracking accuracy on large-scale datasets.

Effective keyframe selection improves overall performance.

Abstract

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.