基于机器视觉的水稻秧苗图像分割

浙江农业学报

基于机器视觉的水稻秧苗图像分割

（1.安徽农业大学工学院，安徽合肥 230036； 2.安徽省粮食作物协同创新中心，安徽合肥 230036； 3.中国科学院合肥智能机械研究所，安徽合肥230031； 4.安徽农业大学农学院，安徽合肥 230036）

出版日期:2016-06-25 发布日期:2016-06-12

Machine vision based segmentation algorithm for rice seedling

（1. School of Engineering， Anhui Agricultural University， Hefei 230036， China; 2. Center of Collaborative Innovation of Anhui Grain Crops， Hefei 230036， China; 3. Institute of Intelligent Machines， Chinese Academy of Sciences， Hefei 230031， China; 4. School of Agriculture， Anhui Agricultural University， Hefei 230036， China）

Online:2016-06-25 Published:2016-06-12

摘要/Abstract

摘要： 水稻秧苗的识别是水稻插秧机自主导航系统的关键内容之一。针对插秧机机器视觉导航中稻田图像秧苗与背景分割问题，建立了基于RGB（红绿蓝）颜色空间的秧苗表面颜色模型。通过颜色特征对秧苗图像进行处理，使用Photoshop软件获取秧苗部分和背景R，G，B分量值；通过对GR值与GB值的分析统计，发现两者之间存在分界关系：各自的权重与各分量的乘积之和为某个定值；为方便分析，选取权值a，b为05，即ExG因子，采用Otsu法获取定值最佳值，最大程度分割出目标和背景。与适合于大多数绿色作物的传统RGB法进行比较，并采用分割质量因子和算法运算时间作为评判标准，分析各算法的综合性能。试验发现，ExG因子结合Otsu分割法分割效果相对理想、稳定性更高，而且耗时更短。

关键词: 水稻秧苗, ExG因子, Otsu法, 图像分割, 质量因子

Abstract: The recognition of rice seedling is one of the significant parts of autonomous guidance for rice transplanting. Considering the segmentation of seedlings and remainder based on machine vision system， a simple dichromatic reflection model was established in RGB color space， which represented that the seedling could be recognized by using its color feature. The values of R， G， B components of seedlings and remainder were obtained in Photoshop software respectively and analyzed statistically in order to get the relation between them. In order to simplify the computing process， the weight values of a and b were set as 05， ExG index and Otsu method （ExG+Otsu method） which could obtain the optimal threshold were combined to distinguish the seedlings and remainder well. The RGB method and previous ExG+Otsu method were carried out to compare their performance intuitively. Their comprehensive performance was evaluated with segmentation quality factor and time consuming. The results have proved that the latter for segmenting was more efficient， highly stable and timesaving.

Key words: rice seedling, ExG index, Otsu method, image segmentation, quality factor

袁加红1，朱德泉1，2，*，孙丙宇3，孙磊1，武立权2，4，宋宇1，蒋锐1. 基于机器视觉的水稻秧苗图像分割[J]. 浙江农业学报.

YUAN Jiahong1， ZHU Dequan1，2，*， SUN Bingyu3， SUN Lei1， WU Liquan2，4， SONG Yu1， JIANG Rui1. Machine vision based segmentation algorithm for rice seedling[J]. .

[1]	覃磊1，2，孙开琼1，3，李诗高1，刘春苔1，阮松1. 基于RGB颜色相似度的成熟草莓图像分割[J]. 浙江农业学报, 2016, 28(2): 330-.
[2]	田海韬, 赵军, 蒲富鹏. 马铃薯芽眼图像的分割与定位方法[J]. 浙江农业学报, 2016, 28(11): 1947-1953.
[3]	胡孟晗，董庆利，刘宝林. 基于多阈值算法的包装箱内香蕉区域的图像分割方法[J]. 浙江农业学报, 2015, 27(10): 1828-.
[4]	张芳1，王璐2，付立思1，*，田有文1. 复杂背景下黄瓜病害叶片的分割方法研究 [J]. 浙江农业学报, 2014, 26(5): 1346-.