基于图像处理的水稻成熟期密度检测  

Detection of Rice Density during Maturity Based on Image Processing

作　　者：刘海娟[1] 邵陆寿[1] 朱建辉[1] 钱良存[1] 王川[1] 

机构地区：[1]安徽农业大学工学院,安徽合肥230036

出　　处：《昆明理工大学学报（理工版）》2009年第2期84-88,共5页Journal of Kunming University of Science and Technology(Natural Science Edition)

基　　金：江苏大学"江苏省现代农业装备与技术重点实验室"资助项目(项目编号:NZ200607)

摘　　要：针对目前联合收割机在收获过程中,行走速度,喂入量都是人工调节.调节不当时,便会造成脱不净,夹带,脱粒损失大等情况,其主要因素是喂入量没有根据作物空间密度得到实时调整.本文从研究水稻冠层密度分布出发,提出了一种基于RGB彩色模型的水稻冠层密度分布图像的检测方法,对2R+G颜色特征量图像采用迭代法自动选取阈值将谷、叶从背景中分割出来;建立冠层图像像素与水稻喂入量的定量关系.为联合收割机实时调整喂入量提供一种可行方案,对改进联合收割机的收获质量有很大的参考价值.The walking speed and feeding of crop of the present combine are controlled manually. Improper regulation may lead to partially threshing, entrainment or threshing large losses, as a result of failure in real-time ajustment of feeding of crop according to spatial density of rice. With the study of the rice canopy density distribution, a detecting method based on its RGB color model is proposed in this paper. Threshold images are automatically selected by iterative method to segment cereal and leaves from the background. The quantitative relationship between image pixels and feeding of rice is set up. This research provides the combine some basis for real-time adjustment of feeding and has great referential value to improve the quality of the combine.

关 键 词：收割机 图像处理 喂入量 

分 类 号：TP317.4[自动化与计算机技术—计算机软件与理论]