The Research And Implementation Of Traffic Video Detector Based On Davinci

With the rapid growth of number of cars and the increasing pressure of urban traffic,IntelligentTransportation was gradually emerging advantage in many ways to improve transportefficiency.Actually,Intelligent Transportation Systems adjust and control traffic flow reasonablythrough the extraction of traffic information on road.In recent years,the application of imageanalysis and computer vision in the field of intelligent video surveillance also get moremature,People at home and abroad also put more and more attention on investment and research inIntelligent Transportation Systems.In this paper,intelligent video analysis methods was used todetect and analyze traffic video on road,to build an embedded traffic video detector based onDaVinci technology.In this paper, DM6446 chip of TI's DaVinci platform was used as core. Firstly, we build anembedded video detection hardware system, analyzing major modules of hardware system, cuttingand transplanting the embedded operating system, booting the system. Secondly,In respect of targetdetection,it study several commonly used detection algorithm in video detection system.Against thecharacteristics of DaVinci embedded platform,we select continuous three frame difference methodto detect target vehicle.In respect of target tracking,the combination method of color histogram andKalman filter was used to track the target vehicle. Finally, transplant and optimize the algorithm tothe DM6446 platform, completed xDAIS algorithm standard package,established the Codec Engineand Codec Server.And gradually optimized the detection algorithm based on the characteristics ofDSP platform,to meet the requirements of embedded system.The focus of this paper is how to take use of the DaVinci dual-core resources moreeffectively,in order to take full advantage of powerful hardware processing and software resourcesof DaVinci.The experimental results show that this traffic video detector based on DM6446 hasgood detection results,it can be used in some practical detection system.