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

• URL: http://arxiv.org/abs/2205.09676v1
• Date: Thu, 19 May 2022 16:35:36 GMT
• Title: Beyond Greedy Search: Tracking by Multi-Agent Reinforcement Learning-based Beam Search
• Authors: Xiao Wang, Zhe Chen, Jin Tang, Bin Luo, Dacheng Tao
• Abstract summary: Existing trackers usually select a location or proposal with the maximum score as tracking result for each frame. We propose a novel multi-agent reinforcement learning based beam search strategy (termed BeamTracking) to address this issue.
• Score: 103.53249725360286
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• RTracker: Recoverable Tracking via PN Tree Structured Memory [71.05904715104411]
  We propose a recoverable tracking framework, RTracker, that uses a tree-structured memory to dynamically associate a tracker and a detector to enable self-recovery. Specifically, we propose a Positive-Negative Tree-structured memory to chronologically store and maintain positive and negative target samples. Our core idea is to use the support samples of positive and negative target categories to establish a relative distance-based criterion for a reliable assessment of target loss.
  arXiv  Detail & Related papers  (2024-03-28T08:54:40Z)
• Exploring Dynamic Transformer for Efficient Object Tracking [58.120191254379854]
  We propose DyTrack, a dynamic transformer framework for efficient tracking. DyTrack automatically learns to configure proper reasoning routes for various inputs, gaining better utilization of the available computational budget. Experiments on multiple benchmarks demonstrate that DyTrack achieves promising speed-precision trade-offs with only a single model.
  arXiv  Detail & Related papers  (2024-03-26T12:31:58Z)
• Single-Shot and Multi-Shot Feature Learning for Multi-Object Tracking [55.13878429987136]
  We propose a simple yet effective two-stage feature learning paradigm to jointly learn single-shot and multi-shot features for different targets. Our method has achieved significant improvements on MOT17 and MOT20 datasets while reaching state-of-the-art performance on DanceTrack dataset.
  arXiv  Detail & Related papers  (2023-11-17T08:17:49Z)
• CoCoLoT: Combining Complementary Trackers in Long-Term Visual Tracking [17.2557973738397]
  We propose a framework, named CoCoLoT, that combines the characteristics of complementary visual trackers to achieve enhanced long-term tracking performance. CoCoLoT perceives whether the trackers are following the target object through an online learned deep verification model, and accordingly activates a decision policy. The proposed methodology is evaluated extensively and the comparison with several other solutions reveals that it competes favourably with the state-of-the-art on the most popular long-term visual tracking benchmarks.
  arXiv  Detail & Related papers  (2022-05-09T13:25:13Z)
• A Bayesian Detect to Track System for Robust Visual Object Tracking and Semi-Supervised Model Learning [1.7268829007643391]
  We ad-dress problems in a Bayesian tracking and detection framework parameterized by neural network outputs. We propose a particle filter-based approximate sampling algorithm for tracking object state estimation. Based on our particle filter inference algorithm, a semi-supervised learn-ing algorithm is utilized for learning tracking network on intermittent labeled frames.
  arXiv  Detail & Related papers  (2022-05-05T00:18:57Z)
• Tracking by Joint Local and Global Search: A Target-aware Attention based Approach [63.50045332644818]
  We propose a novel target-aware attention mechanism (termed TANet) to conduct joint local and global search for robust tracking. Specifically, we extract the features of target object patch and continuous video frames, then we track and feed them into a decoder network to generate target-aware global attention maps. In the tracking procedure, we integrate the target-aware attention with multiple trackers by exploring candidate search regions for robust tracking.
  arXiv  Detail & Related papers  (2021-06-09T06:54:15Z)
• Dynamic Attention guided Multi-Trajectory Analysis for Single Object Tracking [62.13213518417047]
  We propose to introduce more dynamics by devising a dynamic attention-guided multi-trajectory tracking strategy. In particular, we construct dynamic appearance model that contains multiple target templates, each of which provides its own attention for locating the target in the new frame. After spanning the whole sequence, we introduce a multi-trajectory selection network to find the best trajectory that delivers improved tracking performance.
  arXiv  Detail & Related papers  (2021-03-30T05:36:31Z)
• Revisiting the details when evaluating a visual tracker [0.0]
  This report focuses on single object tracking and revisits the details of tracker evaluation based on widely used OTBciteotb benchmark. Experimental results suggest that there may not be an absolute winner among tracking algorithms.
  arXiv  Detail & Related papers  (2021-01-25T13:43:27Z)
• AAA: Adaptive Aggregation of Arbitrary Online Trackers with Theoretical Performance Guarantee [9.410583483182657]
  It is difficult to realize an almighty online tracker due to the huge variations of target appearance depending on an image sequence. This paper proposes an online tracking method that adaptively aggregates arbitrary multiple online trackers.
  arXiv  Detail & Related papers  (2020-09-19T14:16:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.