Large-scale point cloud semantic segmentation method based on lightweight neural network

A semantic segmentation and neural network technology, applied in biological neural network models, neural learning methods, neural architectures, etc., can solve the problem of high computational complexity of semantic segmentation methods, achieve simplified point cloud semantic segmentation networks, reduce time complexity, The effect of reducing training time

CN113627440APending Publication Date: 2021-11-09张冉
0 Cites 2 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2021-11-09

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a large-scale point cloud semantic segmentation method based on a lightweight neural network. The main body of the method is a semantic segmentation neural network model which comprises a feature extraction network and a feature propagation network. The feature extraction network is used for extracting global features and local features of the three-dimensional point cloud, the feature propagation network propagates the features to original points, and an output feature map corresponds to the probability that each point belongs to each semantic category. According to the method, a non-local module is designed in local and non-local modules, feature learning of the local module is enhanced, network weight parameters are updated by using a focus loss function, the weight of a simple sample is automatically reduced in the training process, and the model is quickly concentrated on a difficult sample. In terms of performance, the training time and the memory space are greatly reduced, and meanwhile, the method has very high point cloud semantic segmentation precision.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the field of three-dimensional point cloud and pattern recognition, and the field of deep learning technology, and more specifically relates to a large-scale point cloud semantic segmentation method based on a lightweight neural network. Background technique

[0002] Semantic segmentation is one of the most important research techniques in the field of computer vision, which aims to divide each pixel or point in the scene into several regions with specific semantic categories. Semantic segmentation is the basis of 3D scene understanding. It has achieved very good results in the fields of map geographic information, navigation and positioning, computer vision, pattern recognition, etc. It has important research significance and broad application prospects. The 3D point cloud semantic segmentation methods based on deep learning are mainly divided into indirect segmentation methods and direct segmentation methods. The indirect me...

Examples

Embodiment Construction

[0027] The specific implementation manners of the present invention are described below, so that those skilled in the art can implement with reference to the description.

[0028] Such as figure 1 , 2 , the present invention provides a 3D point cloud semantic segmentation method based on a lightweight neural network, comprising:

[0029] S1. Use the 3D point cloud training set to train the semantic segmentation neural network model, and the training samples are 3D lidar point clouds {P i |i=1,2,...,n}, where each point P i is a vector (x, y, z, int, ret, num) representing the original (x, y, z) coordinates, intensity, number of returns, and number of returns of the lidar data, respectively, and corresponds to a label y i , representing the real semantic category.

[0030] Perform rasterization, sampling, and normalization preprocessing on the point cloud dataset to establish a training set.

[0031] The data set used in the present invention is a remote sensing three-dime...