自然环境下贴叠葡萄串的识别与图像分割算法

针对自然环境下贴叠葡萄串难以识别与分割的问题,该文首先提取HSV颜色空间中的H分量,获取贴叠葡萄串区域,分析该区域长宽比从而判定葡萄串的贴叠性质;提取葡萄串图像轮廓信息,获取轮廓拐点与类圆心点信息;利用拐点与中心点之间的斜率判定目标葡萄串所在位置。然后,利用Chan-Vese模型进行葡萄串的迭代识别,并结合拐点信息获得重叠边界的轮廓信息。最后,将重叠边界轮廓与图像轮廓进行融合,实现目标葡萄串识别。试验结果表明,该文方法的平均精准度为89.71%,平均假阳率为4.24%,识别成功率为90.91%,与现有方法相比,该文方法可实现完整目标葡萄串的识别与分割,并提高了识别与分割的精准度,为葡萄采摘机器人成功采收贴叠葡萄串提供切实可行的算法。

Algorithm for recognition and image segmentation of overlapping grape cluster in natural environment

In order to solve the problem that it is difficult to identify and segment the overlapping grape clusters in the natural conditions, this paper selected Xiahei grape as the experimental sample to carry out relevant research. Firstly, the RGB color channel was transformed into HSV color channel and YCbCr color channel. Through histogram analysis and comparison of each component of HSV color channel and YCbCr color channel, H component in HSV space was determined as the experimental object of image preprocessing. Then, K-means clustering algorithm was used to extract the H component in HSV color space. To obtain the region of overlapping grape clusters, Sobel operator was used to extract the contour of the overlapping grape clusters. Then the contour analysis method was used to analyze the contour of the overlapping grape clusters, and the contour extreme points and the central point of the overlapping grape clusters were obtained. By analyzing the aspect ratio of grape cluster region, we could judge the overlapping type of grape clusters. If it was a single grape cluster, it would be identified directly. If it was a veritcally overlapping grape cluster, rotated the image 90° anticlockwise, and then used the same processing method as the left and right overlapping grape clusters proposed in this paper. The general target grape cluster area was obtained by contour analysis. After that, we could solve the quasi-central point by the central point between the midpoint and the right extreme point, and the intersection point of the two lines between up and lower extreme points and left and right extreme points in the target grape cluster region. The improved Chan-Vese model limited the iteration times of the Chan-Vese model by using the distance between the center point and the quasi-central point. After that, based on the ChanVese model and the quasi-central point as the origin, the iterative identification of target grape cluster was carried out. The binary image processing was carried out for the grape cluster area obtained by Chan-Vese, and the contour information of the overlapping boundary was obtained. Finally, image fusion was used to fuse the grape cluster contour obtained by Chan-Vese model with the original contour. The test results show that the average recognition accuracy of the target grape cluster on the left of the overlapping grape cluster was 92.19%, and the average false positive rate was 2.82%. The average recognition accuracy of the target grape cluster on the right of the overlapping grape cluster was 87.22%, and the average false positive rate was 6.03%. The average recognition accuracy of all the target grape cluster was 89.71%, and the average false positive rate was 4.24%. Compared with the existing segmentation method which only based on contour analysis, the method proposed in this paper could recognize and segment the whole target grape cluster, and greatly improve the accuracy of recognition and segmentation. This method is more conducive to acquisition the information of the target grape cluster picking point,the study provide an efficient and stable recognition and segmentation algorithm for the grape picking robot to successfully pick overlapping grape clusters.