Font Size: a A A

Research On The Key Technology Of Vehicle Tracking For Autonomous Flight Of Highway Patrol

Posted on:2019-11-04Degree:MasterType:Thesis
Country:ChinaCandidate:D Y LuFull Text:PDF
GTID:2382330548469833Subject:Control engineering
Abstract/Summary:PDF Full Text Request
With the deepening of reform and opening up and the rapid development of economy,the total mileage of highway in China has reached 4 million 690 thousand kilometers,but at present,the detection means of highway diseases in China are very backward.The detection methods are mainly manual inspection and patrol vehicles carrying automatic detection equipment,but these two inspection methods have great limitations,such as lack of real-time and poor coverage.Because of its high efficiency and wide coverage,UAV has been applied to the field of highway inspection.At present,UAV mainly relies on flying hand to control UAV when carrying out road inspection,which puts forward higher requirements for flying hands.In order to change this situation and improve the degree of automation,a method of combining machine vision with GPS is proposed to control the unmanned aerial vehicle(UAV)to complete the autonomous flight along the road,and some of the key problems are solved.The main contents of this paper are as follows:This paper first introduces the research status of road recognition technology,road tracking algorithm and obstacle avoidance technology,which are the key problems to be solved for the autonomous flight of unmanned aerial vehicles.Secondly,various methods of image preprocessing,such as image grayage,filtering algorithm,image segmentation and edge detection,are studied,and these methods are simulated and verified.The camera calibration algorithm and the road extraction algorithm are studied.The improved Hough transform method is used to extract and identify the road.A tracking autonomous flight scheme is proposed.The road image is collected by the camera,the road boundary information is extracted,and then the processed road information is sent to the unmanned aerial vehicle control system.Work with GPS to complete the action of autonomous flight.The test proves that the scheme is feasible and has a driving effect on the UAV road patrol.At last,the problem of obstacle avoidance in UAV road inspection is studied,a set of obstacle avoidance scheme is put forward,and the corresponding UAV platform is set up,and the main components are selected.Two different obstacle avoidance control methods are proposed according to the different flight conditions of UAV inspection.The actual flight proves the reliability,practicability and security of the obstacle avoidance function,and achieves the expected goal.
Keywords/Search Tags:Trajectory autonomous flight, Machine vision, Road recognition, Improved Hough transform, Obstacle avoidance
PDF Full Text Request
Related items