点云
人工智能
兰萨克
深度学习
计算机科学
特征(语言学)
卷积神经网络
刚性变换
激光扫描
模式识别(心理学)
计算机视觉
算法
激光器
图像(数学)
光学
物理
哲学
语言学
作者
Zhenxin Zhang,Lan Sun,Rugang Zhong,Dong Chen,Zhihua Xu,Cheng Wang,Cheng‐Zhi Qin,Hao Sun,Roujing Li
出处
期刊:IEEE Geoscience and Remote Sensing Letters
[Institute of Electrical and Electronics Engineers]
日期:2019-12-01
卷期号:16 (12): 1904-1908
被引量:29
标识
DOI:10.1109/lgrs.2019.2910546
摘要
Due to errors in sensors and positioning, there exist mismatches between different phases of mobile laser scanning point clouds, which impede the application of point cloud, such as changing detection and deformation monitoring. To rectify such mismatches, we designed a 3-D deep feature construction method for point cloud registration. The proposed method combines two 3-D convolutional neural networks into a uniform deep learning model to extract 3-D deep features. First, the corresponding points and noncorresponding points are set to train the deep learning model to minimize the distance between corresponding points’ features and maximize the distance between features of noncorresponding points. Second, in the test phase, the 3-D deep feature for each keypoint was extracted by the trained deep learning model. This could be used to determine the corresponding points by the $k$ -dimensional tree and random sample consensus (RANSAC) algorithm. Finally, a transformation matrix was calculated based on the corresponding points and was then applied to point cloud registration. The experimental results illustrated that the proposed method of using 3-D deep features is more efficient at a corresponding point search than representatives of three existing methods. It also improved registration accuracy.
科研通智能强力驱动
Strongly Powered by AbleSci AI