摘要
为解决传统双目视觉对树木和障碍物测距存在图像采集和处理速度较慢、CPU负载较大和采集图像分辨率较低等问题,设计一种基于双目视觉的林间目标测距系统,实现对树木和障碍物等林间目标距离的快速测量。采用双目摄像头和FPGA(Field Programmable Gate Array)作为系统的图像采集和处理平台,结合千兆以太网将图像传输至PC端。然后使用MATLAB完成系统的双目标定,从而获取双目摄像头的内参和外参。最后基于VS2022平台,通过SGBM(Semi-Global Block Matching)算法和BM(Block Matching)算法进行立体匹配,得到视差图和深度图,进而通过树木和障碍物关键点的三维坐标信息得到当前的树木和障碍物距离。研究结果表明,在1.4 m范围内,SGBM和BM算法树木和障碍物距离测量结果的相对误差均小于2%,2种算法对图像的处理速度分别为130 ms和119 ms。此研究表明该双目视觉测距系统能够实现图像数据的快速处理,并能够较为准确地完成树木和障碍物等林间目标的测距,为计算机视觉技术在森林资源调查中的应用提供参考。
Aiming at the problems of slow image acquisition and processing speed,large CPU load and low image resolution in traditional binocular vision-based distance measurement of trees and obstacles,a forest target ranging system based on binocular vision is designed to realize the rapid measurement of the distance of forest targets such as trees and obstacles.The binocular camera and FPGA(Field Programmable Gate Array)are used as the image acquisition and processing platform of the system,and the gigabit Ethernet is used to transmit the image to the PC.Then,MATLAB is used to complete the binocular calibration of the system,so as to obtain the internal and external parameters of the binocular camera.Finally,based on VS2022 platform,stereo matching is performed through SGBM(Semi-Global Block Matching)algorithm and BM(Block Matching)algorithm to obtain disparity map and depth map,so that the current distance between trees and obstacles can be obtained through the 3D coordinate information of key points of trees and obstacles.The results show that the relative error of tree and obstacle distance measurement results of SGBM and BM algorithms is less than 2%in the range of 1.4 m,and the processing speed of the two algorithms for frame is 130 ms and 119 ms,respectively.The results show that the binocular visual ranging system can realize the rapid processing of image data,and it can complete the ranging of forest targets such as trees and obstacles more accurately,providing a reference for the application of computer vision technology in forest resource investigation.
作者
庄培桎
林文树
ZHUANG Peizhi;LIN Wenshu(College of Mechanical and Electrical Engineering,Northeast Forestry University,Harbin 150040,China)
出处
《森林工程》
北大核心
2023年第5期111-117,127,共8页
Forest Engineering
基金
黑龙江省博士后项目(LBH-Z15007)。
