TM2B: Transformer-Based Motion-to-Box Network for 3D Single Object Tracking on Point Clouds

A Xu, J Nie, Z He, X Lv - IEEE Robotics and Automation Letters, 2024 - ieeexplore.ieee.org
3D single object tracking plays a crucial role in numerous applications such as autonomous
driving. Recent trackers based on motion-centric paradigm perform well as they exploit …

Visual Object Tracking across Diverse Data Modalities: A Review

M Wang, T Ma, S **n, X Hou, J **ng, G Dai… - arxiv preprint arxiv …, 2024 - arxiv.org
Visual Object Tracking (VOT) is an attractive and significant research area in computer
vision, which aims to recognize and track specific targets in video sequences where the …

Robust 3D Tracking with Quality-Aware Shape Completion

J Zhang, Z Zhou, G Lu, J Tian, W Pei - Proceedings of the AAAI …, 2024 - ojs.aaai.org
3D single object tracking remains a challenging problem due to the sparsity and
incompleteness of the point clouds. Existing algorithms attempt to address the challenges in …

Three-stage cascade architecture-based siamese sliding window network algorithm for object tracking

Z Yang, K Liu, Q Li, Y Hou, Z Yan - Heliyon, 2025 - cell.com
To enhance the correlation of feature information and enrich the pattern of cross-correlation
metrics, we propose the Siam ST algorithm, which is based on a three-stage cascade (TSC) …

Learning Adaptive Conceptual Prototypes for 3D Single Object Tracking

J **ao, Y Ma, W Yang, T Zhang - IEEE Transactions on Circuits …, 2025 - ieeexplore.ieee.org
3D single object tracking (3D SOT) in LiDAR point clouds plays a crucial role in autonomous
driving. It remains a challenging problem due to the incompleteness and the sparsity of …

Spatio-Temporal Bi-directional Cross-frame Memory for Distractor Filtering Point Cloud Single Object Tracking

S Sun, C Wang, X Liu, C Shi, Y Ding, G ** - arxiv preprint arxiv …, 2024 - arxiv.org
3D single object tracking within LIDAR point clouds is a pivotal task in computer vision, with
profound implications for autonomous driving and robotics. However, existing methods …

[引用][C] 2D LiDAR 기반사용자추적데이터셋구축

오지용, 정유수, 이준구 - 한국통신학회인공지능학술대회논문집, 2024 - dbpia.co.kr
요 약본 연구의 목적은 비용 효율적인 사용자 추종 로봇을 개발하기 위해 2D LiDAR 만으로
동작하는 사용자 추종 로봇을 개발하는것이다. 획득 정보가 단순하지만, 비교적 제작 단가가 …