Scholarlink

<p>The paper explores the challenges of visual simultaneous localization and mapping (VSLAM) in highly dynamic environments, a capability crucial for applications such as autonomous driving and service robots. We propose <b>s</b>emantic-integrated <b>m</b>ulti-<b>m</b>odel <b>f</b>itting (SMMF)-SLAMMOT, a tightly coupled VSLAM and moving object tracking (MOT) method, capable of simultaneously estimating the full <i>SE</i>(3) motions of a stereo camera and the surrounding moving rigid objects, without relying on geometric priors. The SMMF-SLAMMOT framework begins with a two-level dynamic data association technique, which leverages object embedding descriptors from a detector to enhance matching robustness in crowded scenes. Subsequently, a semantic-integrated multi-model fitting method is proposed to achieve more accurate and robust multiple motion segmentation and estimation. Furthermore, we devise a spatial–temporal reprojection factor to enhance the accuracy and efficiency of the 4D mapping. Evaluations on the OMD and KITTI Tracking datasets, along with a self-collected dataset from the CARLA simulator, demonstrate the superiority of SMMF-SLAMMOT in terms of accuracy of self-localization and moving object tracking, as well as real-time performance. Specifically, on the KITTI Tracking dataset, compared to state-of-the-art systems, our method achieves a median 14% improvement in camera pose estimation accuracy and a median 43% enhancement in sparse feature-based object motion estimation accuracy, while achieving a twofold faster tracking frequency at 24 frames per second. The source code and the datasets are available at <a href="https://github.com/zhangtiantians/SMMF_SLAMMOT">https://github.com/zhangtiantians/SMMF_SLAMMOT</a>. This work not only advances the VSLAM field but also provides practical solutions for real-world applications in dynamic scenes.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Semantic-integrated multi-model fitting for real-time VSLAM in highly dynamic environments

  • 期刊论文

  • 发表日期：

    2025年12月13日

查看全文
  • Tiantian Zhang,
  • Ni Li,
  • Guanghong Gong,
  • Xin Lin

摘要

The paper explores the challenges of visual simultaneous localization and mapping (VSLAM) in highly dynamic environments, a capability crucial for applications such as autonomous driving and service robots. We propose semantic-integrated multi-model fitting (SMMF)-SLAMMOT, a tightly coupled VSLAM and moving object tracking (MOT) method, capable of simultaneously estimating the full SE(3) motions of a stereo camera and the surrounding moving rigid objects, without relying on geometric priors. The SMMF-SLAMMOT framework begins with a two-level dynamic data association technique, which leverages object embedding descriptors from a detector to enhance matching robustness in crowded scenes. Subsequently, a semantic-integrated multi-model fitting method is proposed to achieve more accurate and robust multiple motion segmentation and estimation. Furthermore, we devise a spatial–temporal reprojection factor to enhance the accuracy and efficiency of the 4D mapping. Evaluations on the OMD and KITTI Tracking datasets, along with a self-collected dataset from the CARLA simulator, demonstrate the superiority of SMMF-SLAMMOT in terms of accuracy of self-localization and moving object tracking, as well as real-time performance. Specifically, on the KITTI Tracking dataset, compared to state-of-the-art systems, our method achieves a median 14% improvement in camera pose estimation accuracy and a median 43% enhancement in sparse feature-based object motion estimation accuracy, while achieving a twofold faster tracking frequency at 24 frames per second. The source code and the datasets are available at https://github.com/zhangtiantians/SMMF_SLAMMOT. This work not only advances the VSLAM field but also provides practical solutions for real-world applications in dynamic scenes.