草地图像边缘检测算法研究

Research on Edge Detection Algorithm of Grass Image

本文针对草地图像边缘检测进行研究,传统的草地图像边缘检测算法,如canny算法,不仅边缘不够清晰,而且运算时间较长,不能达到智能机器人对实时性的要求。本文运用k-means算法对色彩进行分类进而选定绿色为目标色进行提取,再利用膨胀和腐蚀运算,选取合适的结构元素对图像进行填充和细化,通过实验对比其他传统边缘分割方法,探讨了数学形态学在割草机器人工作区域划分中的重要应用。实验证明,本文选用的边缘检测策略不仅能够清晰准确的识别出草地边缘,而且相比传统的边缘检测算子,运算更快,实用性更强。

This paper aims at a study of lawn image edge detection. Traditional grass image edge detection algorithm such as the canny, its results are not clear enough and the operation time is longer, which can not meet the real-time requirements of intelligent robots. In this paper, the k-means algorithm is used to classify the colors and select the green as the target color. Then, the appro-priate structural elements are selected by expansion and corrosion calculations. Finally, the image is filled and refined using this structural element. This paper discusses the important application of mathematical morphology in the division of working area of mowing robot by comparing other traditional edge segmentation methods. In conclusion, the algorithm presented in this article not only can identify the edge of the grass accurately, but also faster operation and more practical than traditional algorithms.