一种改善高斯拉普拉斯算子零交叉方法的车辆边缘检测

本文介绍了一种视频交通车辆边缘检测的方法。边缘像素是二阶梯度图像产生零交叉时的位置对应像素,但对于斜坡边缘这一类灰度变化非常缓慢的情形,单纯的零交叉方法并不能检测到有效的边缘,往往还会参杂许多背景物体的轮廓。为解决这个问题,本文在高斯拉普拉斯边缘检测算子的基础上,结合了自适应阈值二值化、边界跟踪和细化技术,从而得到了具有较高定位精度的单像素宽的边缘图像。

An Improved Gauss-Laplace Zero-crossing Traffic Edge Detection Approach

The paper introduces a kind of traffic imagine edge detection .edge pixels should be location where there exists zero- cross- ing in second- order grad image. But under the situation of sloping edge, gray level changes very slowly, one can not get effective edge by the zero- crossing method. For solving this issue, the paper combines the techniques of grad image binaryzation, contour trac- ing and edge thinning on the basis of Gauss- Laplace edge operator, and obtaines one- pixel- edge image with high location precision.