EnsembleMOT: A Step towards Ensemble Learning of Multiple Object Tracking

• URL: http://arxiv.org/abs/2210.05278v1
• Date: Tue, 11 Oct 2022 09:18:01 GMT
• Title: EnsembleMOT: A Step towards Ensemble Learning of Multiple Object Tracking
• Authors: Yunhao Du, Zihang Liu and Fei Su
• Abstract summary: Multiple Object Tracking (MOT) has rapidly progressed in recent years. We propose a simple but effective ensemble method for MOT, called EnsembleMOT. Our method is model-independent and doesn't need the learning procedure.
• Score: 18.741196817925534
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multiple Object Tracking (MOT) has rapidly progressed in recent years. Existing works tend to design a single tracking algorithm to perform both detection and association. Though ensemble learning has been exploited in many tasks, i.e, classification and object detection, it hasn't been studied in the MOT task, which is mainly caused by its complexity and evaluation metrics. In this paper, we propose a simple but effective ensemble method for MOT, called EnsembleMOT, which merges multiple tracking results from various trackers with spatio-temporal constraints. Meanwhile, several post-processing procedures are applied to filter out abnormal results. Our method is model-independent and doesn't need the learning procedure. What's more, it can easily work in conjunction with other algorithms, e.g., tracklets interpolation. Experiments on the MOT17 dataset demonstrate the effectiveness of the proposed method. Codes are available at https://github.com/dyhBUPT/EnsembleMOT.

Related papers

• Associate Everything Detected: Facilitating Tracking-by-Detection to the Unknown [22.819492352604428]
  We present a unified framework, Associate Everything Detected (AED), that tackles CV-MOT and OV-MOT by integrating with any off-the-shelf detector. AED gets rid of prior knowledge (e.g. motion cues) and relies solely on highly robust feature learning to handle complex trajectories. Compared with existing powerful OV-MOT and CV-MOT methods, AED achieves superior performance on TAO, SportsMOT, and DanceTrack without any prior knowledge.
  arXiv  Detail & Related papers  (2024-09-14T03:52:49Z)
• Multiple Object Tracking as ID Prediction [14.890192237433771]
  In Multiple Object Tracking (MOT), tracking-by-detection methods have stood the test for a long time. They leverage single-frame detectors and treat object association as a post-processing step through hand-crafted algorithms and surrogate tasks. However, the nature of techniques prevents end-to-end exploitation of training data, leading to increasingly cumbersome and challenging manual modification.
  arXiv  Detail & Related papers  (2024-03-25T15:09:54Z)
• SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depth [84.64121608109087]
  We propose a pseudo-depth estimation method for obtaining the relative depth of targets from 2D images. Secondly, we design a depth cascading matching (DCM) algorithm, which can use the obtained depth information to convert a dense target set into multiple sparse target subsets. By integrating the pseudo-depth method and the DCM strategy into the data association process, we propose a new tracker, called SparseTrack.
  arXiv  Detail & Related papers  (2023-06-08T14:36:10Z)
• Bridging the Gap Between End-to-end and Non-End-to-end Multi-Object Tracking [27.74953961900086]
  Existing end-to-end Multi-Object Tracking (e2e-MOT) methods have not surpassed non-end-to-end tracking-by-detection methods. We present Co-MOT, a simple and effective method to facilitate e2e-MOT by a novel coopetition label assignment with a shadow concept.
  arXiv  Detail & Related papers  (2023-05-22T05:18:34Z)
• QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Tracking [73.52284039530261]
  We present Quasi-Dense Similarity Learning, which densely samples hundreds of object regions on a pair of images for contrastive learning. We find that the resulting distinctive feature space admits a simple nearest neighbor search at inference time for object association. We show that our similarity learning scheme is not limited to video data, but can learn effective instance similarity even from static input.
  arXiv  Detail & Related papers  (2022-10-12T15:47:36Z)
• Transformer-based assignment decision network for multiple object tracking [0.0]
  We introduce Transformer-based Assignment Decision Network (TADN) that tackles data association without the need of explicit optimization during inference. Our proposed approach outperforms the state-of-the-art in most evaluation metrics despite its simple nature as a tracker.
  arXiv  Detail & Related papers  (2022-08-06T19:47:32Z)
• Tracking Every Thing in the Wild [61.917043381836656]
  We introduce a new metric, Track Every Thing Accuracy (TETA), breaking tracking measurement into three sub-factors: localization, association, and classification. Our experiments show that TETA evaluates trackers more comprehensively, and TETer achieves significant improvements on the challenging large-scale datasets BDD100K and TAO.
  arXiv  Detail & Related papers  (2022-07-26T15:37:19Z)
• Unified Transformer Tracker for Object Tracking [58.65901124158068]
  We present the Unified Transformer Tracker (UTT) to address tracking problems in different scenarios with one paradigm. A track transformer is developed in our UTT to track the target in both Single Object Tracking (SOT) and Multiple Object Tracking (MOT)
  arXiv  Detail & Related papers  (2022-03-29T01:38:49Z)
• Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking [102.31092931373232]
  We propose a simple online model named Chained-Tracker (CTracker), which naturally integrates all the three subtasks into an end-to-end solution. The two major novelties: chained structure and paired attentive regression, make CTracker simple, fast and effective.
  arXiv  Detail & Related papers  (2020-07-29T02:38:49Z)
• Quasi-Dense Similarity Learning for Multiple Object Tracking [82.93471035675299]
  We present Quasi-Dense Similarity Learning, which densely samples hundreds of region proposals on a pair of images for contrastive learning. We can directly combine this similarity learning with existing detection methods to build Quasi-Dense Tracking (QDTrack)
  arXiv  Detail & Related papers  (2020-06-11T17:57:12Z)

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.