Beyond Greedy Search: Tracking by Multi-Agent Reinforcement Learning-based Beam Search

Abstract

To track the target in a video, current visual trackers usually adopt greedy search for target object localization in each frame, that is, the candidate region with the maximum response score will be selected as the tracking result of each frame. However, we found that this may be not an optimal choice, especially when encountering challenging tracking scenarios such as heavy occlusion and fast motion. To address this issue, we propose to maintain multiple tracking trajectories and apply beam search strategy for visual tracking, so that the trajectory with fewer accumulated errors can be identified. Accordingly, this paper introduces a novel multi-agent reinforcement learning based beam search tracking strategy, termed BeamTracking. It is mainly inspired by the image captioning task, which takes an image as input and generates diverse descriptions using beam search algorithm. Accordingly, we formulate the tracking as a sample selection problem fulfilled by multiple parallel decision-making processes, each of which aims at picking out one sample as their tracking result in each frame. Each maintained trajectory is associated with an agent to perform the decision-making and determine what actions should be taken to update related information. When all the frames are processed, we select the trajectory with the maximum accumulated score as the tracking result. Extensive experiments on seven popular tracking benchmark datasets validated the effectiveness of the proposed algorithm.

arXiv commentAccepted by IEEE TIP 2022

References in corpus (10)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild
• Learning Spatially Regularized Correlation Filters for Visual Tracking
• Deep Learning for Visual Tracking: A Comprehensive Survey
• Quadruplet Network with One-Shot Learning for Fast Visual Object Tracking
• Distilled Siamese Networks for Visual Tracking
• Deep Reinforcement Learning for Visual Object Tracking in Videos
• An Experimental Survey on Correlation Filter-based Tracking
• Learning regression and verification networks for long-term visual tracking
• VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows