arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.04833cs.CVcs.AI
收藏

面向域不变点云识别的3D自适应结构卷积网络

3D Adaptive Structural Convolution Network for Domain-Invariant Point Cloud Recognition

University of Central Florida(中佛罗里达大学);Ajou University(亚洲大学)

Younggun Kim, Beomsik Cho, Seonghoon Ryoo, Soomok Lee

AI总结:

本文提出3D自适应结构卷积网络(3D-ASCN),通过结合3D卷积核、结构树和自适应邻域采样提取域不变几何特征,在无需参数调整的情况下提升自动驾驶点云识别在不同传感器配置下的鲁棒性与效率。

摘要:

由于数据集和传感器技术的差异性,在自动驾驶车辆中适配用于点云数据识别的深度学习网络面临挑战,这强调了需要自适应技术以在不同条件下保持准确性。在本文中,我们提出了3D自适应结构卷积网络(3D-ASCN),这是一个用于3D点云识别的前沿框架。它结合了3D卷积核、结构树结构和自适应邻域采样,以实现有效的几何特征提取。该方法获得域不变特征,并在各种点云数据集上展示了鲁棒、自适应的性能,确保在不同传感器配置下无需参数调整即可兼容。这凸显了其显著提升自动驾驶车辆技术可靠性和效率的潜力。

英文摘要:

Adapting deep learning networks for point cloud data recognition in self-driving vehicles faces challenges due to the variability in datasets and sensor technologies, emphasizing the need for adaptive techniques to maintain accuracy across different conditions. In this paper, we introduce the 3D Adaptive Structural Convolution Network (3D-ASCN), a cutting-edge framework for 3D point cloud recognition. It combines 3D convolution kernels, a structural tree structure, and adaptive neighborhood sampling for effective geometric feature extraction. This method obtains domain-invariant features and demonstrates robust, adaptable performance on a variety of point cloud datasets, ensuring compatibility across diverse sensor configurations without the need for parameter adjustments. This highlights its potential to significantly enhance the reliability and efficiency of self-driving vehicle technology.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑