MLFNet- Point Cloud Semantic Segmentation Convolution Network Based on Multi-Scale Feature Fusion
Open Access
- 8 February 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 44950-44962
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.Keywords
Funding Information
- Machine visionbased online intelligentsegmentation of foreign objects in liquids (2019GXRC067)
This publication has 38 references indexed in Scilit:
- Multi-View Incremental Segmentation of 3-D Point Clouds for Mobile RobotsIEEE Robotics and Automation Letters, 2019
- SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters2018
- PointGrid: A Deep Network for 3D Shape Understanding2018
- SPLATNet: Sparse Lattice Networks for Point Cloud Processing2018
- Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling2018
- SO-Net: Self-Organizing Network for Point Cloud Analysis2018
- Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models2017
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation2017
- A scalable active framework for region annotation in 3D shape collectionsACM Transactions on Graphics, 2016
- 3D Semantic Parsing of Large-Scale Indoor Spaces2016