CXTrack: Improving 3D Point Cloud Tracking with Contextual Information
- URL: http://arxiv.org/abs/2211.08542v1
- Date: Sat, 12 Nov 2022 11:29:01 GMT
- Title: CXTrack: Improving 3D Point Cloud Tracking with Contextual Information
- Authors: Tian-Xing Xu, Yuan-Chen Guo, Yu-Kun Lai, Song-Hai Zhang
- Abstract summary: 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.
- Score: 59.55870742072618
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 3D single object tracking plays an essential role in many applications, such
as autonomous driving. It remains a challenging problem due to the large
appearance variation and the sparsity of points caused by occlusion and limited
sensor capabilities. Therefore, contextual information across two consecutive
frames is crucial for effective object tracking. However, points containing
such useful information are often overlooked and cropped out in existing
methods, leading to insufficient use of important contextual knowledge. To
address this issue, we propose CXTrack, a novel transformer-based network for
3D object tracking, which exploits ConteXtual information to improve the
tracking results. Specifically, we design a target-centric transformer network
that directly takes point features from two consecutive frames and the previous
bounding box as input to explore contextual information and implicitly
propagate target cues. To achieve accurate localization for objects of all
sizes, we propose a transformer-based localization head with a novel center
embedding module to distinguish the target from distractors. Extensive
experiments on three large-scale datasets, KITTI, nuScenes and Waymo Open
Dataset, show that CXTrack achieves state-of-the-art tracking performance while
running at 29 FPS.
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) - STTracker: Spatio-Temporal Tracker for 3D Single Object Tracking [11.901758708579642]
3D single object tracking with point clouds is a critical task in 3D computer vision.
Previous methods usually input the last two frames and use the template point cloud in previous frame and the search area point cloud in the current frame respectively.
arXiv Detail & Related papers (2023-06-30T07:25:11Z) - Exploiting More Information in Sparse Point Cloud for 3D Single Object
Tracking [9.693724357115762]
3D single object tracking is a key task in 3D computer vision.
The sparsity of point clouds makes it difficult to compute the similarity and locate the object.
We propose a sparse-to-dense and transformer-based framework for 3D single object tracking.
arXiv Detail & Related papers (2022-10-02T13:38:30Z) - 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) - Learnable Online Graph Representations for 3D Multi-Object Tracking [156.58876381318402]
We propose a unified and learning based approach to the 3D MOT problem.
We employ a Neural Message Passing network for data association that is fully trainable.
We show the merit of the proposed approach on the publicly available nuScenes dataset by achieving state-of-the-art performance of 65.6% AMOTA and 58% fewer ID-switches.
arXiv Detail & Related papers (2021-04-23T17:59:28Z) - 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) - Monocular Quasi-Dense 3D Object Tracking [99.51683944057191]
A reliable and accurate 3D tracking framework is essential for predicting future locations of surrounding objects and planning the observer's actions in numerous applications such as autonomous driving.
We propose a framework that can effectively associate moving objects over time and estimate their full 3D bounding box information from a sequence of 2D images captured on a moving platform.
arXiv Detail & Related papers (2021-03-12T15:30:02Z) - Probabilistic 3D Multi-Modal, Multi-Object Tracking for Autonomous
Driving [22.693895321632507]
We propose a probabilistic, multi-modal, multi-object tracking system consisting of different trainable modules.
We show that our method outperforms current state-of-the-art on the NuScenes Tracking dataset.
arXiv Detail & Related papers (2020-12-26T15:00:54Z) - TAO: A Large-Scale Benchmark for Tracking Any Object [95.87310116010185]
Tracking Any Object dataset consists of 2,907 high resolution videos, captured in diverse environments, which are half a minute long on average.
We ask annotators to label objects that move at any point in the video, and give names to them post factum.
Our vocabulary is both significantly larger and qualitatively different from existing tracking datasets.
arXiv Detail & Related papers (2020-05-20T21:07:28Z)
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.