The Cooperative Vehicle Infrastructure System Based on Machine Vision

Abstract

The information acquisition is a key procedure of cooperative vehicle-infrastructure system (CVIS). With the advancement of computer image processing technology, more and more researchers use image recognition as the source of information acquisition. On this background, the authors develop a CVIS based on machine vision, including vehicular subsystem, the roadside subsystem and the parking lot subsystem. The system uses improved Canny algorithm to detect road channelization, HOG+SVM method to detect pedestrian and Haar+Adaboost method to detect vehicle. The experiment result shows that the detection accuracy and real-time of system is relatively high. In addition, the test also prove that the system is significant in driving assistance.