Know Your Surroundings: Exploiting Scene Information for Object Tracking

• URL: http://arxiv.org/abs/2003.11014v2
• Date: Fri, 1 May 2020 16:15:51 GMT
• Title: Know Your Surroundings: Exploiting Scene Information for Object Tracking
• Authors: Goutam Bhat, Martin Danelljan, Luc Van Gool, Radu Timofte
• Abstract summary: Current state-of-the-art trackers only rely on a target appearance model in order to localize the object in each frame. We propose a novel tracking architecture which can utilize scene information for tracking.
• Score: 181.1750279330811
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Current state-of-the-art trackers only rely on a target appearance model in order to localize the object in each frame. Such approaches are however prone to fail in case of e.g. fast appearance changes or presence of distractor objects, where a target appearance model alone is insufficient for robust tracking. Having the knowledge about the presence and locations of other objects in the surrounding scene can be highly beneficial in such cases. This scene information can be propagated through the sequence and used to, for instance, explicitly avoid distractor objects and eliminate target candidate regions. In this work, we propose a novel tracking architecture which can utilize scene information for tracking. Our tracker represents such information as dense localized state vectors, which can encode, for example, if the local region is target, background, or distractor. These state vectors are propagated through the sequence and combined with the appearance model output to localize the target. Our network is learned to effectively utilize the scene information by directly maximizing tracking performance on video segments. The proposed approach sets a new state-of-the-art on 3 tracking benchmarks, achieving an AO score of 63.6% on the recent GOT-10k dataset.

Related papers

• DenseTrack: Drone-based Crowd Tracking via Density-aware Motion-appearance Synergy [33.57923199717605]
  Drone-based crowd tracking faces difficulties in accurately identifying and monitoring objects from an aerial perspective. To address these challenges, we present the Density-aware Tracking (DenseTrack) framework. DenseTrack capitalizes on crowd counting to precisely determine object locations, blending visual and motion cues to improve the tracking of small-scale objects.
  arXiv  Detail & Related papers  (2024-07-24T13:39:07Z)
• CXTrack: Improving 3D Point Cloud Tracking with Contextual Information [59.55870742072618]
  3D single object tracking plays an essential role in many applications, such as autonomous driving. We propose CXTrack, a novel transformer-based network for 3D object tracking. We show that CXTrack achieves state-of-the-art tracking performance while running at 29 FPS.
  arXiv  Detail & Related papers  (2022-11-12T11:29:01Z)
• SpOT: Spatiotemporal Modeling for 3D Object Tracking [68.12017780034044]
  3D multi-object tracking aims to consistently identify all mobile time. Current 3D tracking methods rely on abstracted information and limited history. We develop a holistic representation of scenes that leverage both spatial and temporal information.
  arXiv  Detail & Related papers  (2022-07-12T21:45:49Z)
• Tracking by Joint Local and Global Search: A Target-aware Attention based Approach [63.50045332644818]
  We propose a novel target-aware attention mechanism (termed TANet) to conduct joint local and global search for robust tracking. Specifically, we extract the features of target object patch and continuous video frames, then we track and feed them into a decoder network to generate target-aware global attention maps. In the tracking procedure, we integrate the target-aware attention with multiple trackers by exploring candidate search regions for robust tracking.
  arXiv  Detail & Related papers  (2021-06-09T06:54:15Z)
• Learning to Track with Object Permanence [61.36492084090744]
  We introduce an end-to-end trainable approach for joint object detection and tracking. Our model, trained jointly on synthetic and real data, outperforms the state of the art on KITTI, and MOT17 datasets.
  arXiv  Detail & Related papers  (2021-03-26T04:43:04Z)
• e-TLD: Event-based Framework for Dynamic Object Tracking [23.026432675020683]
  This paper presents a long-term object tracking framework with a moving event camera under general tracking conditions. The framework uses a discriminative representation for the object with online learning, and detects and re-tracks the object when it comes back into the field-of-view.
  arXiv  Detail & Related papers  (2020-09-02T07:08:56Z)
• An Exploration of Target-Conditioned Segmentation Methods for Visual Object Trackers [24.210580784051277]
  We show how to transform a bounding-box tracker into a segmentation tracker. Our analysis shows that such methods allow trackers to compete with recently proposed segmentation trackers.
  arXiv  Detail & Related papers  (2020-08-03T16:21:18Z)
• Visual Tracking by TridentAlign and Context Embedding [71.60159881028432]
  We propose novel TridentAlign and context embedding modules for Siamese network-based visual tracking methods. The performance of the proposed tracker is comparable to that of state-of-the-art trackers, while the proposed tracker runs at real-time speed.
  arXiv  Detail & Related papers  (2020-07-14T08:00:26Z)
• Applying r-spatiogram in object tracking for occlusion handling [16.36552899280708]
  The aim of video tracking is to accurately locate a moving target in a video sequence and discriminate target from non-targets in the feature space of the sequence. In this paper, we use the basic idea of many trackers which consists of three main components of the reference model, i.e. object modeling, object detection and localization, and model updating.
  arXiv  Detail & Related papers  (2020-03-18T02:42:51Z)

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.