DỰ ĐOÁN HƯỚNG DI CHUYỂN VÀ XÁC ĐỊNH TỐC ĐỘ XE QUA CAMERA QUAN SÁT

Lâm Hữu Tuấn, Huỳnh Phụng Toàn, Nguyễn Thị Hồng Nhung, Trần Cao Đệ
2017 FAIR - NGHIÊN CỨU CƠ BẢN VÀ ỨNG DỤNG CÔNG NGHỆ THÔNG TIN - 2016   unpublished
Currently, road traffic system of our country has been improved significantly. Besides building new roads to modern standards, the management, traffic monitoring have also been strengthened. Many camera systems to monitor the traffic situation in combination with security surveillance has been installed. There have been more and more applications of data mining from this monitoring system as traffic density computing, vehicle traffic counts, number plate recognition, vehicle speed measured...
more » ... e determination of the velocity of the vehicle from the image of the CCTV system has been studied before, they often rely on a combination of machine learning methods for identification and use Meanshift algorithm or Camshift algorithm to track objects. Use Kalman filter to predict the movement, the velocity of the vehicle. This paper will present a method of determining the speed of movement of the car from the video image with a "measurement frame" is set on some basic methods of image processing such as background subtraction method to detect objects motion, using the weighted average calculations to predict the direction of movement and velocity of the object. The installation and testing has shown the accuracy and feasibility of this approach is entirely possible put into practical application.
doi:10.15625/vap.2016.00018 fatcat:jwlldy4yebei5aiyyqcnphrrri