Abstract
In the semantic segmentation of a point cloud, if the spatial structure correlation between the input features and coordinates are not fully considered, a semantic segmentation error can occur. We propose a method of spatial convolution that makes full use of the characteristics of a multiscale spatial structure by combining local and global features. We call this method MLFNet. We also propose a multiscale feature framework. First, the point cloud is simplified by obtaining the weighted farthest point (by down-sampling combined with farthest-point sampling and the weighted average). The near-near domain of each sampling point is then obtained by a KK octant search (an octant search optimized by the k-nearest neighbor and a custom threshold), and feature information is obtained. The feature information is added to the subsequent multilayer perceptron, and fusion of local context information is achieved. Finally, the fusion features in multiple directions are maximally pooled. Our method was tested on self-made datasets and other standard basic datasets (ModelNet40, ShapeNet, and Stanford large-scale 3D indoor spaces (S3DIS) data). The accuracy of segmentation was 0.937 in our dataset; two percentage points higher than the latest deep learning method. Also, our method obtained a mean intersection over a union of 0.867 in ShapeNet, which was 0.3 percentage points higher than the latest PointGrid. The accuracy on S3DIS was 0.8153, which was three percentage points higher than the latest spatial aggregation net. The results of semantic segmentation verified the superiority of the proposed method.
Highlights
Segmenting a point cloud is a popular way to use it, and the main research direction of point cloud segmentation is currently semantic segmentation
The local domain k of a point is searched by a KK octant search, the octant search [5] is first done by a KK octant search, and the result is further selected by K-NN by setting a threshold (K)
The results show that excellent neighbors are obtained by the KK octant search
Summary
Segmenting a point cloud is a popular way to use it, and the main research direction of point cloud segmentation is currently semantic segmentation. Semantic segmentation is used on workpieces to classify, measure, and recognize them, and for automatic driving, classification of remote sensing images, scene navigation, and other artificial intelligence uses. A 3D point cloud is characterized by disorder and nonuniformity [1], and the order of data in a point cloud cannot be changed casually. A large number of markers are needed to memorize the training data, so the processing takes. The segmentation of 3D point clouds faces great challenges. The types of data have been explored, and the point cloud has been converted into a 2D image data type for the convenience of deep learning. Some necessary features are lost in the process of data transformation, causing over-fitting and unclear features in the training process
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.