Quasi-Dense Similarity Learning for Multiple Object Tracking

• URL: http://arxiv.org/abs/2006.06664v4
• Date: Wed, 8 Sep 2021 02:56:35 GMT
• Title: Quasi-Dense Similarity Learning for Multiple Object Tracking
• Authors: Jiangmiao Pang, Linlu Qiu, Xia Li, Haofeng Chen, Qi Li, Trevor Darrell, Fisher Yu
• Abstract summary: 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)
• Score: 82.93471035675299
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Similarity learning has been recognized as a crucial step for object tracking. However, existing multiple object tracking methods only use sparse ground truth matching as the training objective, while ignoring the majority of the informative regions on the images. In this paper, 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) without turning to displacement regression or motion priors. We also find that the resulting distinctive feature space admits a simple nearest neighbor search at the inference time. Despite its simplicity, QDTrack outperforms all existing methods on MOT, BDD100K, Waymo, and TAO tracking benchmarks. It achieves 68.7 MOTA at 20.3 FPS on MOT17 without using external training data. Compared to methods with similar detectors, it boosts almost 10 points of MOTA and significantly decreases the number of ID switches on BDD100K and Waymo datasets. Our code and trained models are available at http://vis.xyz/pub/qdtrack.

Related papers

• ConsistencyTrack: A Robust Multi-Object Tracker with a Generation Strategy of Consistency Model [20.259334882471574]
  Multi-object tracking (MOT) is a critical technology in computer vision, designed to detect multiple targets in video sequences and assign each target a unique ID per frame. Existed MOT methods excel at accurately tracking multiple objects in real-time across various scenarios. We propose a novel ConsistencyTrack, joint detection and tracking(JDT) framework that formulates detection and association as a denoising diffusion process on bounding boxes.
  arXiv  Detail & Related papers  (2024-08-28T05:53:30Z)
• Temporal Correlation Meets Embedding: Towards a 2nd Generation of JDE-based Real-Time Multi-Object Tracking [52.04679257903805]
  Joint Detection and Embedding (JDE) trackers have demonstrated excellent performance in Multi-Object Tracking (MOT) tasks. Our tracker, named TCBTrack, achieves state-of-the-art performance on multiple public benchmarks.
  arXiv  Detail & Related papers  (2024-07-19T07:48:45Z)
• 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)
• 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)
• EnsembleMOT: A Step towards Ensemble Learning of Multiple Object Tracking [18.741196817925534]
  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.
  arXiv  Detail & Related papers  (2022-10-11T09:18:01Z)
• ByteTrack: Multi-Object Tracking by Associating Every Detection Box [51.93588012109943]
  Multi-object tracking (MOT) aims at estimating bounding boxes and identities of objects in videos. Most methods obtain identities by associating detection boxes whose scores are higher than a threshold. We present a simple, effective and generic association method, called BYTE, tracking BY associaTing every detection box instead of only the high score ones.
  arXiv  Detail & Related papers  (2021-10-13T17:01:26Z)
• Exploring Simple 3D Multi-Object Tracking for Autonomous Driving [10.921208239968827]
  3D multi-object tracking in LiDAR point clouds is a key ingredient for self-driving vehicles. Existing methods are predominantly based on the tracking-by-detection pipeline and inevitably require a matching step for the detection association. We present SimTrack to simplify the hand-crafted tracking paradigm by proposing an end-to-end trainable model for joint detection and tracking from raw point clouds.
  arXiv  Detail & Related papers  (2021-08-23T17:59:22Z)
• Score refinement for confidence-based 3D multi-object tracking [14.853897011640022]
  We show that manipulating the scores depending on time consistency while terminating the tracklets depending on the tracklet score improves tracking results. Compared to count-based methods, our method consistently produces better AMOTA and MOTA scores. It achieved an AMOTA score of 67.6 on nuScenes test evaluation, which is comparable to other state-of-the-art trackers.
  arXiv  Detail & Related papers  (2021-07-09T09:40:07Z)
• Tracking Objects as Points [83.9217787335878]
  We present a simultaneous detection and tracking algorithm that is simpler, faster, and more accurate than the state of the art. Our tracker, CenterTrack, applies a detection model to a pair of images and detections from the prior frame. CenterTrack is simple, online (no peeking into the future), and real-time.
  arXiv  Detail & Related papers  (2020-04-02T17:58:40Z)

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.