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

05/19/2022
by   Xiao Wang, et al.
11

Existing trackers usually select a location or proposal with the maximum score as tracking result for each frame. However, such greedy search scheme maybe not the optimal choice, especially when encountering challenging tracking scenarios like heavy occlusions and fast motion. Since the accumulated errors would make response scores not reliable anymore. In this paper, we propose a novel multi-agent reinforcement learning based beam search strategy (termed BeamTracking) to address this issue. Specifically, 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. We take the target feature, proposal feature, and its response score as state, and also consider actions predicted by nearby agent, to train multi-agents to select their actions. 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.

READ FULL TEXT

page 1

page 2

page 9

page 11

research
01/26/2022

Exploiting Semantic Epsilon Greedy Exploration Strategy in Multi-Agent Reinforcement Learning

Multi-agent reinforcement learning (MARL) can model many real world appl...
research
07/29/2020

Compare and Select: Video Summarization with Multi-Agent Reinforcement Learning

Video summarization aims at generating concise video summaries from the ...
research
07/14/2020

Correlation filter tracking with adaptive proposal selection for accurate scale estimation

Recently, some correlation filter based trackers with detection proposal...
research
07/10/2022

SRRT: Search Region Regulation Tracking

Dominant trackers generate a fixed-size rectangular region based on the ...
research
07/17/2017

Tracking as Online Decision-Making: Learning a Policy from Streaming Videos with Reinforcement Learning

We formulate tracking as an online decision-making process, where a trac...
research
07/31/2019

Multi-Agent Reinforcement Learning Based Frame Sampling for Effective Untrimmed Video Recognition

Video Recognition has drawn great research interest and great progress h...
research
09/19/2021

Greedy UnMixing for Q-Learning in Multi-Agent Reinforcement Learning

This paper introduces Greedy UnMix (GUM) for cooperative multi-agent rei...

Please sign up or login with your details

Forgot password? Click here to reset