Font Size: a A A

Research On Binocular Stereoscopic Vision Localization Of EOD Robot

Posted on:2018-04-05Degree:MasterType:Thesis
Country:ChinaCandidate:L X HuFull Text:PDF
GTID:2348330536485010Subject:Mechanical and electrical engineering
Abstract/Summary:
The EOD robot can effectively reduce the risk of the operator.The realization of the EOD function depends on the precise positioning.The binocular stereoscopic vision is the most important distance perception technology in the computer vision ranging method.Therefore,the study of precise positioning technology of EOD robot based on binocular stereoscopic vision has important practical significance.In this paper,firstly,analyzed the working conditions and measurement requirements of the EOD robot,and the research ideas of the static and dynamic scene of the EOD robot are established respectively.According to the principle of binocular stereo vision measurement and measurement model,the three-dimensional coordinate formula of spatial point is deduced,and the calibration work of binocular camera is completed.Second,the image gray scale and smoothing,remove the image of redundant information and interference noise,for the follow-up work to prepare.In the process of static image measurement,the ORB detection algorithm and the Flann matching algorithm are used to match the stereo matching.The PROSAC algorithm is used to remove the mismatch points,and the three-dimensional coordinates and distance are calculated.In the process of dynamic image measurement,CamShift tracking algorithm is used to solve the real-time problem with Kamlan predictor,and the limit constraint of binocular stereo vision is introduced to obtain the exact matching point for 3D reconstruction Coordinates and distance values.Finally,the experiment of static and dynamic scene of binocular stereo camera is carried out respectively,which meets the expected measurement requirements of EOD robot location and distance measurement.
Keywords/Search Tags:Binocular stereoscopic vision, EOD robot, ORB, CamShift, Kalman
Related items