Two stages for visual object tracking

• URL: http://arxiv.org/abs/2104.13648v1
• Date: Wed, 28 Apr 2021 09:11:33 GMT
• Title: Two stages for visual object tracking
• Authors: Fei Chen and Xiaodong Wang
• Abstract summary: Siamese-based trackers have achived promising performance on visual object tracking tasks. In this paper, we propose a novel tracker with two-stages: detection and segmentation. Our approach achieves state-of-the-art results, with the EAO of 52.6$%$ on VOT2016, 51.3$%$ on VOT2018, and 39.0$%$ on VOT 2019 datasets.
• Score: 13.851408246039515
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Siamese-based trackers have achived promising performance on visual object tracking tasks. Most existing Siamese-based trackers contain two separate branches for tracking, including classification branch and bounding box regression branch. In addition, image segmentation provides an alternative way to obetain the more accurate target region. In this paper, we propose a novel tracker with two-stages: detection and segmentation. The detection stage is capable of locating the target by Siamese networks. Then more accurate tracking results are obtained by segmentation module given the coarse state estimation in the first stage. We conduct experiments on four benchmarks. Our approach achieves state-of-the-art results, with the EAO of 52.6$\%$ on VOT2016, 51.3$\%$ on VOT2018, and 39.0$\%$ on VOT2019 datasets, respectively.

Related papers

• OmniTracker: Unifying Object Tracking by Tracking-with-Detection [119.51012668709502]
  OmniTracker is presented to resolve all the tracking tasks with a fully shared network architecture, model weights, and inference pipeline. Experiments on 7 tracking datasets, including LaSOT, TrackingNet, DAVIS16-17, MOT17, MOTS20, and YTVIS19, demonstrate that OmniTracker achieves on-par or even better results than both task-specific and unified tracking models.
  arXiv  Detail & Related papers  (2023-03-21T17:59:57Z)
• Minkowski Tracker: A Sparse Spatio-Temporal R-CNN for Joint Object Detection and Tracking [53.64390261936975]
  We present Minkowski Tracker, a sparse-temporal R-CNN that jointly solves object detection and tracking problems. Inspired by region-based CNN (R-CNN), we propose to track motion as a second stage of the object detector R-CNN. We show in large-scale experiments that the overall performance gain of our method is due to four factors.
  arXiv  Detail & Related papers  (2022-08-22T04:47:40Z)
• A Discriminative Single-Shot Segmentation Network for Visual Object Tracking [13.375369415113534]
  We propose a discriminative single-shot segmentation tracker -- D3S2. A single-shot network applies two target models with complementary geometric properties. D3S2 outperforms the leading segmentation tracker SiamMask on video object segmentation benchmarks.
  arXiv  Detail & Related papers  (2021-12-22T12:48:51Z)
• Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook [97.27199633649991]
  Discriminative Correlation Filters (DCFs) and deep Siamese Networks (SNs) have emerged as dominating tracking paradigms. This survey presents a systematic and thorough review of more than 90 DCFs and Siamese trackers, based on results in nine tracking benchmarks.
  arXiv  Detail & Related papers  (2021-12-06T07:57:10Z)
• Track to Detect and Segment: An Online Multi-Object Tracker [81.15608245513208]
  TraDeS is an online joint detection and tracking model, exploiting tracking clues to assist detection end-to-end. TraDeS infers object tracking offset by a cost volume, which is used to propagate previous object features.
  arXiv  Detail & Related papers  (2021-03-16T02:34:06Z)
• Multiple Convolutional Features in Siamese Networks for Object Tracking [13.850110645060116]
  Multiple Features-Siamese Tracker (MFST) is a novel tracking algorithm exploiting several hierarchical feature maps for robust tracking. MFST achieves high tracking accuracy, while outperforming the standard siamese tracker on object tracking benchmarks.
  arXiv  Detail & Related papers  (2021-03-01T08:02:27Z)
• Graph Attention Tracking [76.19829750144564]
  We propose a simple target-aware Siamese graph attention network for general object tracking. Experiments on challenging benchmarks including GOT-10k, UAV123, OTB-100 and LaSOT demonstrate that the proposed SiamGAT outperforms many state-of-the-art trackers.
  arXiv  Detail & Related papers  (2020-11-23T04:26:45Z)
• 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)
• Multi-Object Tracking with Siamese Track-RCNN [23.753970697176946]
  Siamese Track-RCNN is a two stage detect-and-track framework which consists of three functional branches. Siamese Track-RCNN achieves significantly higher results than the state-of-the-art, while also being much more efficient, thanks to its unified design.
  arXiv  Detail & Related papers  (2020-04-16T17:28:52Z)

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.