Unsupervised Green Object Tracker (GOT) without Offline Pre-training

• URL: http://arxiv.org/abs/2309.09078v1
• Date: Sat, 16 Sep 2023 19:00:56 GMT
• Title: Unsupervised Green Object Tracker (GOT) without Offline Pre-training
• Authors: Zhiruo Zhou, Suya You, C.-C. Jay Kuo
• Abstract summary: We propose a new single object tracking method, called the green object tracker (GOT) GOT offers competitive tracking accuracy with state-of-the-art unsupervised trackers, which demand heavy offline pre-training, at a lower cost. GOT has a tiny model size (3k parameters) and low inference complexity (around 58M FLOPs per frame)
• Score: 35.60210259607753
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Supervised trackers trained on labeled data dominate the single object tracking field for superior tracking accuracy. The labeling cost and the huge computational complexity hinder their applications on edge devices. Unsupervised learning methods have also been investigated to reduce the labeling cost but their complexity remains high. Aiming at lightweight high-performance tracking, feasibility without offline pre-training, and algorithmic transparency, we propose a new single object tracking method, called the green object tracker (GOT), in this work. GOT conducts an ensemble of three prediction branches for robust box tracking: 1) a global object-based correlator to predict the object location roughly, 2) a local patch-based correlator to build temporal correlations of small spatial units, and 3) a superpixel-based segmentator to exploit the spatial information of the target frame. GOT offers competitive tracking accuracy with state-of-the-art unsupervised trackers, which demand heavy offline pre-training, at a lower computation cost. GOT has a tiny model size (<3k parameters) and low inference complexity (around 58M FLOPs per frame). Since its inference complexity is between 0.1%-10% of DL trackers, it can be easily deployed on mobile and edge devices.

Related papers

• RTrack: Accelerating Convergence for Visual Object Tracking via Pseudo-Boxes Exploration [3.29854706649876]
  Single object tracking (SOT) heavily relies on the representation of the target object as a bounding box. This paper proposes RTrack, a novel object representation baseline tracker. RTrack automatically arranges points to define the spatial extents and highlight local areas.
  arXiv  Detail & Related papers  (2023-09-23T04:41:59Z)
• TrajectoryFormer: 3D Object Tracking Transformer with Predictive Trajectory Hypotheses [51.60422927416087]
  3D multi-object tracking (MOT) is vital for many applications including autonomous driving vehicles and service robots. We present TrajectoryFormer, a novel point-cloud-based 3D MOT framework.
  arXiv  Detail & Related papers  (2023-06-09T13:31:50Z)
• 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)
• ByteTrackV2: 2D and 3D Multi-Object Tracking by Associating Every Detection Box [81.45219802386444]
  Multi-object tracking (MOT) aims at estimating bounding boxes and identities of objects across video frames. We propose a hierarchical data association strategy to mine the true objects in low-score detection boxes. In 3D scenarios, it is much easier for the tracker to predict object velocities in the world coordinate.
  arXiv  Detail & Related papers  (2023-03-27T15:35:21Z)
• Target-Aware Tracking with Long-term Context Attention [8.20858704675519]
  Long-term context attention (LCA) module can perform extensive information fusion on the target and its context from long-term frames. LCA uses the target state from the previous frame to exclude the interference of similar objects and complex backgrounds. Our tracker achieves state-of-the-art performance on multiple benchmarks, with 71.1% AUC, 89.3% NP, and 73.0% AO on LaSOT, TrackingNet, and GOT-10k.
  arXiv  Detail & Related papers  (2023-02-27T14:40:58Z)
• GUSOT: Green and Unsupervised Single Object Tracking for Long Video Sequences [31.600045405499472]
  A green unsupervised single-object tracker, called GUSOT, aims at object tracking for long videos under a resource-constrained environment. GUSOT contains two additional new modules: 1) lost object recovery, and 2) color-saliency-based shape proposal. We conduct experiments on the large-scale dataset LaSOT with long video sequences, and show that GUSOT offers a lightweight high-performance tracking solution.
  arXiv  Detail & Related papers  (2022-07-15T17:42:49Z)
• 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)
• A Lightweight and Detector-free 3D Single Object Tracker on Point Clouds [50.54083964183614]
  It is non-trivial to perform accurate target-specific detection since the point cloud of objects in raw LiDAR scans is usually sparse and incomplete. We propose DMT, a Detector-free Motion prediction based 3D Tracking network that totally removes the usage of complicated 3D detectors.
  arXiv  Detail & Related papers  (2022-03-08T17:49:07Z)
• Learning to Track Objects from Unlabeled Videos [63.149201681380305]
  In this paper, we propose to learn an Unsupervised Single Object Tracker (USOT) from scratch. To narrow the gap between unsupervised trackers and supervised counterparts, we propose an effective unsupervised learning approach composed of three stages. Experiments show that the proposed USOT learned from unlabeled videos performs well over the state-of-the-art unsupervised trackers by large margins.
  arXiv  Detail & Related papers  (2021-08-28T22:10:06Z)
• Track without Appearance: Learn Box and Tracklet Embedding with Local and Global Motion Patterns for Vehicle Tracking [45.524183249765244]
  Vehicle tracking is an essential task in the multi-object tracking (MOT) field. In this paper, we try to explore the significance of motion patterns for vehicle tracking without appearance information. We propose a novel approach that tackles the association issue for long-term tracking with the exclusive fully-exploited motion information.
  arXiv  Detail & Related papers  (2021-08-13T02:27:09Z)

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.