结合分块Hough变换与Kalman预测的车道线检测方法

Combining the Blocked Hough Transform and Kalman Prediction Method for Lane Detection

利用分块Hough变换与Kalman预测相结合的方法来处理车载摄像机采集的道路图像。在极大的降低算法复杂度的同时能够对弯道处的车道线进行有效的检测。这种采用分块变换与预测相结合的方法能有效地降低计算量,提高车道检测的实时性。实验表明,本文方法既可以得到稳定的检测结果又能提高检测的速度,同时继承了Hough变换的容错性和鲁棒性。

It uses the method of combining the blocked Hough transform and Kalman prediction to handle the vehicle-mounted camera capturing images, which will greatly reduce the complexity of the algorithm and effectively detect the bend lane as well. This method can effectively reduce the amount of computation, and improve the real-time detection of lane. Experiments have proved that this method can achieve both stable detection results and higher detection rate. It is the heritage of Hough transform fault tolerance and robustness.