基于激光扫描三维图像的树上苹果识别算法  

Apple Fruit Recognition Algorithm Based on Laser Scanning 3-D Image

作　　者：冯娟[1,2] 刘刚[1] 司永胜[2] 王圣伟[1] 任雯[1] 周薇[1] 

机构地区：[1]中国农业大学现代精细农业系统集成研究教育部重点实验室,北京100083 [2]河北农业大学信息科学与技术学院,保定071001

出　　处：《农业机械学报》2013年第4期217-222,共6页Transactions of the Chinese Society for Agricultural Machinery

基　　金：国家自然科学基金资助项目(31071333);保定市科学技术研究与发展计划资助项目(12ZG011)

摘　　要：为消除不同光线和复杂背景的影响,提出了一种自动识别树上苹果的算法。使用激光视觉系统获取果树局部的三维图像,参考设定的场景知识对图像背景进行简化;采用基于平滑频率曲线的自动阈值检测方法实现图像的二值化;通过轮廓跟踪技术记录目标边界的走向,据此计算链码和与链码差,并根据两者在果树各部分的变化规律确立相应的准则,以提取苹果的轮廓像素点;利用随机圆环法获得果实的形状特征完成对苹果的识别。实验结果表明,该算法具有较好的实时性,当枝叶遮挡面积小于40%时,果实的正确识别率高于93.75%,且识别效果不受光照条件与果实表面颜色的影响。An algorithm was proposed for recognizing apple fruit on the tree in order to eliminate the effects of different light and complex background. A kind of 3-D image of fruit tree was acquired with laser vision system. Image background was simplified by given scene knowledge. A double threshold detecting method was used for binarize image. Contour to record direction of target＇ s boundary. According to tracking technology based on chain code was used change rules of chain code information, relevant standards were established for extracting contour points of apple. Shape features of fruit were obtained by random circle method. The experimental results under various conditions showed that the algorithm was real-time. Its recognition rate reached to 93.75% while fruit area sheltered was less than 40% , and the whole effect was immune to light conditions and fruit surface color.

关 键 词：苹果 激光扫描 三维图像 识别 

分 类 号：TP242.62[自动化与计算机技术—检测技术与自动化装置]