ProTracker: Probabilistic Integration for Robust and Accurate Point Tracking

• URL: http://arxiv.org/abs/2501.03220v1
• Date: Mon, 06 Jan 2025 18:55:52 GMT
• Title: ProTracker: Probabilistic Integration for Robust and Accurate Point Tracking
• Authors: Tingyang Zhang, Chen Wang, Zhiyang Dou, Qingzhe Gao, Jiahui Lei, Baoquan Chen, Lingjie Liu,
• Abstract summary: ProTracker is a novel framework for robust and accurate long-term dense tracking of arbitrary points in videos. Our code and model will be publicly available upon publication.
• Score: 41.889032460337226
• License:
• Abstract: In this paper, we propose ProTracker, a novel framework for robust and accurate long-term dense tracking of arbitrary points in videos. The key idea of our method is incorporating probabilistic integration to refine multiple predictions from both optical flow and semantic features for robust short-term and long-term tracking. Specifically, we integrate optical flow estimations in a probabilistic manner, producing smooth and accurate trajectories by maximizing the likelihood of each prediction. To effectively re-localize challenging points that disappear and reappear due to occlusion, we further incorporate long-term feature correspondence into our flow predictions for continuous trajectory generation. Extensive experiments show that ProTracker achieves the state-of-the-art performance among unsupervised and self-supervised approaches, and even outperforms supervised methods on several benchmarks. Our code and model will be publicly available upon publication.

Related papers

• Post-Hoc MOTS: Exploring the Capabilities of Time-Symmetric Multi-Object Tracking [0.37240490024629924]
  A time-symmetric tracking methodology has been introduced for the detection, segmentation, and tracking of budding yeast cells in pre-recorded samples. We aim to reveal the broader capabilities, advantages, and potential challenges of this architecture across various specifically designed scenarios. We present an attention analysis of the tracking architecture for both pretrained and non-pretrained models.
  arXiv  Detail & Related papers  (2024-12-11T11:50:06Z)
• 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)
• Certified Human Trajectory Prediction [66.1736456453465]
  Tray prediction plays an essential role in autonomous vehicles. We propose a certification approach tailored for the task of trajectory prediction. We address the inherent challenges associated with trajectory prediction, including unbounded outputs, and mutli-modality.
  arXiv  Detail & Related papers  (2024-03-20T17:41:35Z)
• TrackFlow: Multi-Object Tracking with Normalizing Flows [36.86830078167583]
  We aim at extending tracking-by-detection to multi-modal settings. A rough estimate of 3D information is also available and must be merged with other traditional metrics. Our approach consistently enhances the performance of several tracking-by-detection algorithms.
  arXiv  Detail & Related papers  (2023-08-22T15:40:03Z)
• Provable Guarantees for Generative Behavior Cloning: Bridging Low-Level Stability and High-Level Behavior [51.60683890503293]
  We propose a theoretical framework for studying behavior cloning of complex expert demonstrations using generative modeling. We show that pure supervised cloning can generate trajectories matching the per-time step distribution of arbitrary expert trajectories.
  arXiv  Detail & Related papers  (2023-07-27T04:27:26Z)
• MotionTrack: Learning Robust Short-term and Long-term Motions for Multi-Object Tracking [56.92165669843006]
  We propose MotionTrack, which learns robust short-term and long-term motions in a unified framework to associate trajectories from a short to long range. For dense crowds, we design a novel Interaction Module to learn interaction-aware motions from short-term trajectories, which can estimate the complex movement of each target. For extreme occlusions, we build a novel Refind Module to learn reliable long-term motions from the target's history trajectory, which can link the interrupted trajectory with its corresponding detection.
  arXiv  Detail & Related papers  (2023-03-18T12:38:33Z)
• 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)
• MONCE Tracking Metrics: a comprehensive quantitative performance evaluation methodology for object tracking [0.0]
  We propose a suite of MONCE (Multi-Object Non-Contiguous Entities) image tracking metrics that provide both objective tracking model performance benchmarks as well as diagnostic insight for driving tracking model development.
  arXiv  Detail & Related papers  (2022-04-11T17:32:03Z)
• PnPNet: End-to-End Perception and Prediction with Tracking in the Loop [82.97006521937101]
  We tackle the problem of joint perception and motion forecasting in the context of self-driving vehicles. We propose Net, an end-to-end model that takes as input sensor data, and outputs at each time step object tracks and their future level.
  arXiv  Detail & Related papers  (2020-05-29T17:57:25Z)
• Confidence Trigger Detection: Accelerating Real-time Tracking-by-detection Systems [1.6037469030022993]
  Confidence-Triggered Detection (CTD) is an innovative approach that strategically bypasses object detection for frames closely resembling intermediate states. CTD not only enhances tracking speed but also preserves accuracy, surpassing existing tracking algorithms. Our experiments underscore the robustness and versatility of the CTD framework, demonstrating its potential to enable real-time tracking in resource-constrained environments.
  arXiv  Detail & Related papers  (2019-02-02T01:52:53Z)

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.