ICP point cloud map fusion method, system and device based on multi-unmanned aerial vehicle cooperation and storage medium

Abstract

The invention provides an ICP point cloud map fusion method, system and device based on multi-unmanned aerial vehicle cooperation and a storage medium. The ICP point cloud map fusion method comprisesthe following steps: an extraction step: extracting key points from two data sets according to the same key point selection standard, the two data sets being two point cloud maps with overlapping regions and being respectively marked as a point cloud P and a point cloud Q, the point cloud P being a target point cloud, and the point cloud Q being a reference point cloud; in the calculation step, calculating feature descriptors of all the selected key points respectively; a processing step: combining the coordinate positions of the feature descriptors in the two data sets, taking the similarityof the features and the positions between the feature descriptors as the basis to estimate the corresponding relationship between the feature descriptors and the data sets, and estimating corresponding point pairs; and a registration step: estimating rigid body transformation by using the corresponding relationship, and performing complete registration. The method has the advantages that the convergence speed of the ICP algorithm can be increased while high precision is achieved, and a very good technical effect is achieved.

Description

technical field [0001] The present invention relates to the technical field of unmanned aerial vehicles, in particular to an ICP point cloud map fusion method, system, device and storage medium based on multi-unmanned aerial vehicle cooperation. Background technique [0002] 1. Multi-UAV collaborative SLAM technology: [0003] In an unknown environment, UAVs can estimate their own position and attitude, which is a key technology to effectively complete tasks. When the UAV is traveling at low altitude and at low speed, the position, speed and other information required for flight can be obtained by using the Global Positioning System (Global Positioning System, GPS) and the Inertial Navigation System (Inertial Navigation System, INS). flight requirements. However, there are limitations in the use of GPS and INS. The error range of GPS is 3-10 meters, and it cannot work normally due to weak signals in indoor environments and harsh environments such as mountains and valleys. ...

AI Technical Summary

Problems solved by technology

[0022] Although the ICP algorithm can meet the requirements of our registration tasks in many cases, there are still some problems

First of all, the biggest impact on the ICP algorithm is that the algorithm relies on a good initial registration result. If the initial registration position is poor, the algorithm will easily fall into local optimum or infinite iteration, which greatly affects the performance of the algorithm. Convergence speed, increasing time complexity

Images