Sistem Pengukur Kecepatan Kendaraan Berbasis Pengolahan Video

Abstract

This system is implemented by digital image processing to detect the objects and measure the speed. This system using background subtraction method with Gaussian Mixture Model (GMM) algorithm. Background subtraction will separate background and detected objects. Coordinates of the objects midpoint used as the the object moving value in pixel. The actual distance also measured in meters where the distance is limited by region of interest (ROI). The ROI is 160 pixel. Having obtained the moving objects time from previous frame to current frame so the value of pixel/s can converted to km/h.

System testing the measurement validation, calculate the speed after being validated, and the influence of light intensity. The speed validation process uses average speed of early three frames speed as the reference for the speed measurement in the next frame. The average speed accuracy of 3 frames early gives a percentage error about 1,92% - 15,75%. When validation is performed on the entire reading frame of video, it produces an error range 1,21% - 21,37%. The system works well in the morning, afternoon, and evening conditions with light intensity about 600-1900 lux. While at night with 0-5 lux light intensity range, the system can’t work properly.