Sparse surface feature classification and labeling method based on visible light and laser radar images

Abstract

The present invention relates to a sparse surface feature classification and labeling method based on visible light and laser radar images. According to the method, the height information of the laser radar image is used to extract corresponding surface feature image areas in the visible light image and coordinate positions, then the surface feature image areas are subjected to classification judgment by using a classifier, and labeling is carried out on the corresponding coordination positions. According to the method, the problems of difficult extraction of a target area and time consumption and low accuracy brought by a sliding window strategy are solved, surface features can be accurately and rapidly classified and labeled, the classification speed and labeling accuracy of the surface features are improved, the accuracy of classification and labeling is ensured, and the classification time is reduced.

Description

technical field [0001] The technical field of the present invention is the field of spatial information technology or pattern recognition, and relates to technologies such as image processing and computer vision, and in particular to a method for classifying and marking sparse ground objects based on visible light and laser radar images. Background technique [0002] Classification of raised sparse objects such as buildings, vehicles or trees in the image can use the traditional detection and classification method based on object modeling, that is, to calibrate a large number of training sample targets, train different classifiers, and then perform multiple scales on the image Sliding window scanning, so as to obtain the circumscribed rectangular window of all objects of interest in the image. However, the sliding window strategy used in the above method consumes a lot of time, especially when the target category is not one but multiple, this strategy is more difficult to re...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a sparse object classification and labeling method based on visible light and lidar images, in order to solve the problem that the target area is not easy to extract, and the sliding window strategy traverses the entire image for object classification. Time-consuming and low accuracy The problem

Images