3D Single-object Tracking in Point Clouds with High Temporal Variation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Qiao, Sun, Kun, An, Pei, Salzmann, Mathieu, Zhang, Yanning, Yang, Jiaqi
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909307247788032
author Wu, Qiao
Sun, Kun
An, Pei
Salzmann, Mathieu
Zhang, Yanning
Yang, Jiaqi
author_facet Wu, Qiao
Sun, Kun
An, Pei
Salzmann, Mathieu
Zhang, Yanning
Yang, Jiaqi
contents The high temporal variation of the point clouds is the key challenge of 3D single-object tracking (3D SOT). Existing approaches rely on the assumption that the shape variation of the point clouds and the motion of the objects across neighboring frames are smooth, failing to cope with high temporal variation data. In this paper, we present a novel framework for 3D SOT in point clouds with high temporal variation, called HVTrack. HVTrack proposes three novel components to tackle the challenges in the high temporal variation scenario: 1) A Relative-Pose-Aware Memory module to handle temporal point cloud shape variations; 2) a Base-Expansion Feature Cross-Attention module to deal with similar object distractions in expanded search areas; 3) a Contextual Point Guided Self-Attention module for suppressing heavy background noise. We construct a dataset with high temporal variation (KITTI-HV) by setting different frame intervals for sampling in the KITTI dataset. On the KITTI-HV with 5 frame intervals, our HVTrack surpasses the state-of-the-art tracker CXTracker by 11.3%/15.7% in Success/Precision.
format Preprint
id arxiv_https___arxiv_org_abs_2408_02049
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle 3D Single-object Tracking in Point Clouds with High Temporal Variation
Wu, Qiao
Sun, Kun
An, Pei
Salzmann, Mathieu
Zhang, Yanning
Yang, Jiaqi
Computer Vision and Pattern Recognition
Artificial Intelligence
The high temporal variation of the point clouds is the key challenge of 3D single-object tracking (3D SOT). Existing approaches rely on the assumption that the shape variation of the point clouds and the motion of the objects across neighboring frames are smooth, failing to cope with high temporal variation data. In this paper, we present a novel framework for 3D SOT in point clouds with high temporal variation, called HVTrack. HVTrack proposes three novel components to tackle the challenges in the high temporal variation scenario: 1) A Relative-Pose-Aware Memory module to handle temporal point cloud shape variations; 2) a Base-Expansion Feature Cross-Attention module to deal with similar object distractions in expanded search areas; 3) a Contextual Point Guided Self-Attention module for suppressing heavy background noise. We construct a dataset with high temporal variation (KITTI-HV) by setting different frame intervals for sampling in the KITTI dataset. On the KITTI-HV with 5 frame intervals, our HVTrack surpasses the state-of-the-art tracker CXTracker by 11.3%/15.7% in Success/Precision.
title 3D Single-object Tracking in Point Clouds with High Temporal Variation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2408.02049