融合多特征的禁停区域车辆检测方法

摘要

An algorithm for vehicle detection in illegal parking area was proposed. Firstly, region of interesting was selected. Secondly, Gaussian Mixture Model was used for background, and moving objects were detected by background subtraction. Then fuse of ellipse fitting, compact features detection and tire circularity detection for vehicle detection. Exercises show that, this algorithm could realize monitoring exactly, and keep illegal parking area smooth.%本文提出一种用于禁停区域车辆违章停放的检测算法。首先确定感兴趣区域，然后利用混合高斯模型建立监控区域背景，采用背景差分法检测出运动对象；再经过Hough椭圆拟合、紧凑性特征提取，以及车轮圆形度等多个特征检测，将驶入禁停区域的车辆检测出来。实验表明，该算法对禁停区域可以达到良好的监测效果，从而有效地保障消防通道等禁停区域的通畅。