Design And Implementation Of Parking Spaces Analyzing And Guiding System Based On Video

With the improvement of people’s living standards,more and more people choose to buy private cars as a means of transport in recent years.The parking resources become more and more intense,how to make effective management of parking spaces has become a topic for the intelligent transportation system.Compared with the infrared detection and the sensing coil detection,the video analysis method has the advantages of saving hardware cost,easy installation and extending other functions and so on.Based on literature review and in-depth study of the vehicle detection technology,the thesis designed the implementation of video parking space analysis and guidance system.The system used the ICETEK-DM6437-B board as a hardware development platform.System consists of two binary images,feature extraction,connected domain labeling,eliminate the non vehicle regions,occlusion handling,parking occupancy state detection,parking guidance function,and can detect and guide the results displayed in the LED screen.The main achievements can be described as follows.(1)Vehicle detection.The thesis studied the algorithm of analyzing location of parking spaces in video which is based on license plate(license plate detection)and the detecting algorithm based on gray change of the stationary area of parking spaces(gray assay),and then designed an algorithm which combine the above tow algorithms.License plate detection method is used to detect vehicle,and gray assay is used to solve car license plate occlusion detection.Vehicle detection include:feature extraction,region binary,median filtering,connected domain labeling and gray assay.(2)Parking occupancy status and vehicle guidance.In this thesis,the boundary coordinates and central coordinates of the license plate region are detected to determine the occupancy of the parking space.The method of detecting the gray level of the parking area is used to determine the occupancy of the vehicle.By the current occupancy status of all the parking spaces,the thesis is based on the shortest path method to the parking lot of vehicles which is entering the parking space.(3)Making the LED screen.Design schematic,PCB board and software,the production and debug of LED screen is finished.(4)On the ICETEK-DM6437-B hardware,this thesis achieves the function of the system.By using C language,it achieves the video parking state detection and guidance system in CCS.Parking space detection and guidance function is realized,and the results are displayed in the LED screen.The experiment shows that recognition rate of the parking space detection system designed in this thesis is beyond 90%and the system has a certain degree of stability and a strong practicality.It lays a good foundation for the further study of face recognition.