Gr-IoU: Ground-Intersection over Union for Robust Multi-Object Tracking with 3D Geometric Constraints

• URL: http://arxiv.org/abs/2409.03252v1
• Date: Thu, 5 Sep 2024 05:09:03 GMT
• Title: Gr-IoU: Ground-Intersection over Union for Robust Multi-Object Tracking with 3D Geometric Constraints
• Authors: Keisuke Toida, Naoki Kato, Osamu Segawa, Takeshi Nakamura, Kazuhiro Hotta,
• Abstract summary: Gr-IoU transforms traditional bounding boxes from the image space to the ground plane using the vanishing point geometry. The IoU calculated with these transformed bounding boxes is more sensitive to the front-to-back relationships of objects. We evaluated our Gr-IoU method on the MOT17 and MOT20 datasets, which contain diverse tracking scenarios.
• Score: 3.2855317710497625
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose a Ground IoU (Gr-IoU) to address the data association problem in multi-object tracking. When tracking objects detected by a camera, it often occurs that the same object is assigned different IDs in consecutive frames, especially when objects are close to each other or overlapping. To address this issue, we introduce Gr-IoU, which takes into account the 3D structure of the scene. Gr-IoU transforms traditional bounding boxes from the image space to the ground plane using the vanishing point geometry. The IoU calculated with these transformed bounding boxes is more sensitive to the front-to-back relationships of objects, thereby improving data association accuracy and reducing ID switches. We evaluated our Gr-IoU method on the MOT17 and MOT20 datasets, which contain diverse tracking scenarios including crowded scenes and sequences with frequent occlusions. Experimental results demonstrated that Gr-IoU outperforms conventional real-time methods without appearance features.

Related papers

• 3D-Aware Instance Segmentation and Tracking in Egocentric Videos [107.10661490652822]
  Egocentric videos present unique challenges for 3D scene understanding. This paper introduces a novel approach to instance segmentation and tracking in first-person video. By incorporating spatial and temporal cues, we achieve superior performance compared to state-of-the-art 2D approaches.
  arXiv  Detail & Related papers  (2024-08-19T10:08:25Z)
• Multi-Scene Generalized Trajectory Global Graph Solver with Composite Nodes for Multiple Object Tracking [61.69892497726235]
  Composite Node Message Passing Network (CoNo-Link) is a framework for modeling ultra-long frames information for association. In addition to the previous method of treating objects as nodes, the network innovatively treats object trajectories as nodes for information interaction. Our model can learn better predictions on longer-time scales by adding composite nodes.
  arXiv  Detail & Related papers  (2023-12-14T14:00:30Z)
• Uni3DETR: Unified 3D Detection Transformer [75.35012428550135]
  We propose a unified 3D detector that addresses indoor and outdoor detection within the same framework. Specifically, we employ the detection transformer with point-voxel interaction for object prediction. We then propose the mixture of query points, which sufficiently exploits global information for dense small-range indoor scenes and local information for large-range sparse outdoor ones.
  arXiv  Detail & Related papers  (2023-10-09T13:20:20Z)
• Multi-Ship Tracking by Robust Similarity metric [10.882525351991875]
  Multi-ship tracking (MST) as a core technology has been proven to be applied to situational awareness at sea and the development of a navigational system for autonomous ships. Despite impressive tracking outcomes achieved by multi-object tracking (MOT) algorithms for pedestrian and vehicle datasets, these models and techniques exhibit poor performance when applied to ship datasets. In this paper, we address the weaknesses of IoU by incorporating the smallest convex shapes that enclose both the predicted and detected bounding boxes.
  arXiv  Detail & Related papers  (2023-10-08T14:05:10Z)
• UnsMOT: Unified Framework for Unsupervised Multi-Object Tracking with Geometric Topology Guidance [6.577227592760559]
  UnsMOT is a novel framework that combines appearance and motion features of objects with geometric information to provide more accurate tracking. Experimental results show remarkable performance in terms of HOTA, IDF1, and MOTA metrics in comparison with state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-09-03T04:58:12Z)
• Spatial-Temporal Graph Enhanced DETR Towards Multi-Frame 3D Object Detection [54.041049052843604]
  We present STEMD, a novel end-to-end framework that enhances the DETR-like paradigm for multi-frame 3D object detection. First, to model the inter-object spatial interaction and complex temporal dependencies, we introduce the spatial-temporal graph attention network. Finally, it poses a challenge for the network to distinguish between the positive query and other highly similar queries that are not the best match.
  arXiv  Detail & Related papers  (2023-07-01T13:53:14Z)
• 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)
• 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)
• Seeing Behind Objects for 3D Multi-Object Tracking in RGB-D Sequences [46.65702220573459]
  We infer the complete geometry of objects as well as track them, for rigidly moving objects over time. From a sequence of RGB-D frames, we detect objects in each frame and learn to predict their complete object geometry. Experiments on both synthetic and real-world RGB-D data demonstrate that we achieve state-of-the-art performance on dynamic object tracking.
  arXiv  Detail & Related papers  (2020-12-15T10:33:21Z)
• Relation3DMOT: Exploiting Deep Affinity for 3D Multi-Object Tracking from View Aggregation [8.854112907350624]
  3D multi-object tracking plays a vital role in autonomous navigation. Many approaches detect objects in 2D RGB sequences for tracking, which is lack of reliability when localizing objects in 3D space. We propose a novel convolutional operation, named RelationConv, to better exploit the correlation between each pair of objects in the adjacent frames.
  arXiv  Detail & Related papers  (2020-11-25T16:14:40Z)
• How to track your dragon: A Multi-Attentional Framework for real-time RGB-D 6-DOF Object Pose Tracking [35.21561169636035]
  We present a novel multi-attentional convolutional architecture to tackle the problem of real-time RGB-D 6D object pose tracking. We consider the special geometrical properties of both the object's 3D model and the pose space, and we use a more sophisticated approach for data augmentation during training.
  arXiv  Detail & Related papers  (2020-04-21T23:00:06Z)

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.