Semantic segmentation and point cloud processing combined plant recognition and model construction method

Abstract

The invention provides a semantic segmentation and point cloud processing combined plant recognition and model construction method. The method comprises the following steps: 1, generating an orthoimage according to a landscape image obtained by oblique photography; 2, training a deep learning network, and performing semantic segmentation on the orthoimage by a neural network to identify a plant region; 3, generating a point cloud corresponding to the image, and realizing coordinate correspondence between point cloud data and the orthoimage through coordinate system conversion; 4, segmenting the point cloud data to obtain a plant area point cloud; 5, in combination with oblique photography images and point cloud data, plant species are further recognized through k-means point cloud clustering, target detection and other methods; 6, establishing a plant model library; 7, processing the point cloud of the plant area, determining parameters including plant types, positions, sizes and the like, and importing a plant model to replace the point cloud; and 8, converting the plant model into a required format. According to the invention, efficient and accurate recognition of plant species and construction of a three-dimensional plant scene with a sense of reality can be realized.

Description

Technical field [0001] The present invention relates to the field of image processing and three-dimensional scenes, and more particularly to a method for binding a semantic segmentation and point cloud processing. Background technique [0002] The type identification of plants containing a wide range of scenarios has always been one of the important research contents of virtual reality. By camera calibration, feature extraction, stereo matching, sparse reconstruction, dense The steps such as reconstruction can restore the three-dimensional dot cloud data of the scene in the two-dimensional image, and apply to subsequent model reconstruction, serve virtual reality, environmental simulation and other fields. To achieve scene identification and scene construction of the plant area, first, you need to identify the plant type included in the scenic image, and then processes the point cloud data to generate a real sense of plant model. [0003] Semantic segmentation refers to a given p...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to overcome the deficiencies of the prior art, and provide a plant recognition and model building method that combines semantic segmentation and point cloud processing to solve the problem that simple semantic segmentation cannot accurately identify plant specie

Images