Laser radar point cloud multi-target ground object identification method based on deep learning

Abstract

The invention discloses a laser radar point cloud multi-target ground object identification method based on deep learning, and relates to the field of point cloud identification methods. The method comprises the following steps: sequentially carrying out region segmentation, feature representation and label marking on a point cloud scene to obtain point cloud data comprising a plurality of three-dimensional spaces; establishing a network model comprising an input layer, N convolution layers, a full connection layer and a Softmax function, inputting a test set in the data set, training the model to obtain an optimal model, and inputting the test set in the data set into the optimal model to obtain an identification result; searching suspected misclassification points according to the depthinformation, the high-level difference, the spatial relationship of the power tower beside the power line and the relationship between the adjacent three-dimensional spaces, and classifying again to obtain a final identification result. According to the method, the problems of large calculation amount, difficult feature extraction and low recognition accuracy of the existing neural network due tomassive, sparse and disordered point clouds are solved.

Description

[0001] This research was supported by the Science and Technology Program of Sichuan Province (No: 2019YFS0487). technical field [0002] The invention relates to the field of point cloud recognition methods, in particular to a deep learning-based laser radar point cloud multi-target feature recognition method. Background technique [0003] The object recognition of 3D point cloud is the process of identifying and extracting artificial and natural objects (roads, houses, trees, power lines, towers, etc.) , with the introduction and development of deep learning methods, it does not need to manually extract features, but automatically extracts object features by simulating the working structure of human brain neurons, overcoming the shortcomings of traditional methods such as complex feature extraction and insufficient representation. , Su and Maji et al. used the projection images of 3D shapes at 12 different angles, each angle was learned by VGG-M convolutional neural network...

AI Technical Summary

Problems solved by technology

[0005] The object of the present invention is: the present invention provides a method for recognizing multi-target objects in laser radar point clouds based on deep learning, which solves the problem of large amount of calculations caused by the massive, sparse and disordered nature of point clouds in existing neural networks. Difficult feature extraction and low recognition accuracy

Images