التفاصيل البيبلوغرافية
| العنوان: |
Gradient Enhancement Techniques and Motion Consistency Constraints for Moving Object Segmentation in 3D LiDAR Point Clouds |
| المؤلفون: |
Fangzhou Tang, Bocheng Zhu, Junren Sun |
| المصدر: |
Remote Sensing, Vol 17, Iss 2, p 195 (2025) |
| بيانات النشر: |
MDPI AG, 2025. |
| سنة النشر: |
2025 |
| المجموعة: |
LCC:Science |
| مصطلحات موضوعية: |
LiDAR point cloud, moving object segmentation, range image, gradient enhancement, motion consistency, Science |
| الوصف: |
The ability to segment moving objects from three-dimensional (3D) LiDAR scans is critical to advancing autonomous driving technology, facilitating core tasks like localization, collision avoidance, and path planning. In this paper, we introduce a novel deep neural network designed to enhance the performance of 3D LiDAR point cloud moving object segmentation (MOS) through the integration of image gradient information and the principle of motion consistency. Our method processes sequential range images, employing depth pixel difference convolution (DPDC) to improve the efficacy of dilated convolutions, thus boosting spatial information extraction from range images. Additionally, we incorporate Bayesian filtering to impose posterior constraints on predictions, enhancing the accuracy of motion segmentation. To handle the issue of uneven object scales in range images, we develop a novel edge-aware loss function and use a progressive training strategy to further boost performance. Our method is validated on the SemanticKITTI-based LiDAR MOS benchmark, where it significantly outperforms current state-of-the-art (SOTA) methods, all while working directly on two-dimensional (2D) range images without requiring mapping. |
| نوع الوثيقة: |
article |
| وصف الملف: |
electronic resource |
| اللغة: |
English |
| تدمد: |
2072-4292 |
| Relation: |
https://www.mdpi.com/2072-4292/17/2/195; https://doaj.org/toc/2072-4292 |
| DOI: |
10.3390/rs17020195 |
| URL الوصول: |
https://doaj.org/article/cf6310f1fa3e4cde87046cae307f5543 |
| رقم الانضمام: |
edsdoj.f6310f1fa3e4cde87046cae307f5543 |
| قاعدة البيانات: |
Directory of Open Access Journals |
Full Text Finder