基于Harris算法的图像拼接技术在无人机路径规划方面的应用  

Application of Image Stitching Technology Based on Harris Algorithm in UAV Path Planning

作　　者：杜雨桐 秦工[1] 江督 万彤 章萧鹏 付俊泽 DU Yutong;QIN Gong;JIANG Du;WAN Tong;ZHANG Xiaopeng;FU Junze(School of Artifi cial Intelligence,Jianghan University,Wuhan Hubei 430000;School of Intelligent Manufacturing,Jianghan University,Wuhan Hubei 430000)

机构地区：[1]江汉大学人工智能学院,湖北武汉430000 [2]江汉大学智能制造学院,湖北武汉430000

出　　处：《软件》2022年第4期69-72,共4页Software

基　　金：国家级大学生创新创业计划项目(202111072001)“无人机物流配送控制系统的研究与应用”支持。

摘　　要：无人机在飞行过程中,需要对地面进行路径规划。配备在无人机上的摄像头往往无法在特定高度获取到无畸变的全景图,因此利用图像拼接技术来解决这一问题。本文深入研究了基于Harris算法的图像拼接技术,首先是利用Harris算法查找关键点,然后利用NMS算法去除重复的关键点,最后利用RANSAC算法消除错配点并得到投影变换关系,从而完成图像拼接。During the flight of the UAV, it is necessary to plan the path on the ground. The camera equipped on the drone often cannot obtain an undistorted panorama at a specific height, so image stitching technology is used to solve this problem. This paper has studied the image stitching technology based on Harris algorithm in depth. Firstly, use Harris algorithm to find key points, then use NMS algorithm to remove duplicate key points, and finally use RANSAC algorithm to eliminate mismatching points and get the relationship of the projection transform, thereby completing image stitching.

关 键 词：无人机路径规划 HARRIS 图像拼接 NMS RANSAC 

分 类 号：TP317.4[自动化与计算机技术—计算机软件与理论]