摘要
针对阴天、强光等复杂天气情况下车道线检测准确率低问题,提出一种基于改进麻雀搜索算法的车道线检测与识别方法。首先对拍摄的车道图像进行畸变校正,然后对图像进行预处理,依次进行灰度化、高斯模糊化处理,再基于上一帧的车道线检测情况选取感兴趣区域,最后基于改进麻雀搜索算法进行边缘检测,并利用Hough变换提取车道线。实验结果表明,该方法可以有效提高车道线检测与识别准确率。
Aiming at the problem of low accuracy of lane line detection under complex weather conditions such as cloudy and strong light,a lane line detection and recognition method based on improved sparrow search algorithm is proposed.First,perform distortion correction on the captured lane image,then preprocess the image,sequentially perform grayscale and Gaussian blurring,and then select the region of interest based on the lane line detection of the previous frame,and finally perform based on the improved sparrow search algorithm Edge detection,and use Hough transform to extract lane lines.Experimental results show that this method can effectively improve the accuracy of lane line detection and recognition.
作者
沈业辉
杨振
温秀平
金承珂
SHEN Ye-hui;YANG Zhen;WEN Xiu-ping;JIN Cheng-ke(School of Automation,Nanjing Institute of Technology,Nanjing 211167 China;Industrial center/School of innovation and entrepreneurship,Nanjing Institute of Technology,Nanjing 211167 China)
出处
《自动化技术与应用》
2022年第5期150-155,共6页
Techniques of Automation and Applications
关键词
畸变矫正模型
麻雀搜索算法
HOUGH变换
边缘检测识别
图像处理
distortion correction model
Sparrow search algorithm
Hough transform
edge detection and identification
image process