基于TOF成像技术的柑橘实时识别与定位  

Real-time citrus recognition and location based on TOF imaging technology

作　　者：孙力[1] 蔡健荣[1] 李永平[2] 赵杰文[1] 袁雷明[1] 

机构地区：[1]江苏大学食品与生物工程学院,江苏镇江212013 [2]宁波大红鹰学院,浙江宁波315175

出　　处：《江苏大学学报（自然科学版）》2013年第3期293-297,共5页Journal of Jiangsu University：Natural Science Edition

基　　金：国家自然科学基金资助项目(30771243);江苏省普通高校研究生科研创新计划项目(1221360037)

摘　　要：通过分析TOF(time of flight)成像信息,将场景反射光强度与深度信息采用图像表示,应用各向异性扩散与冲击滤波耦合的滤波模型,滤除深度图中的噪声,采用阈值分割、区域生长、区域最小外接圆等算法将柑橘从背景中分割出,并以区域距离极差、距离方差和识别柑橘半径值为约束条件,对识别的柑橘区域进一步筛选,再结合三维数据库信息提取柑橘的基本特征参数,最后实现树上柑橘的实时识别与定位.自然生长状态下柑橘的识别正确率达86.7%,误判率为0,深度误差小于12 mm,实际半径误差小于13 mm,图像实时采集与处理耗时小于100 ms.The intensity and depth information of reflected light were represented with image based on the analysis of TOF（time of flight） imaging technology.A new adaptive filter model coupling with partial differential equations filter and shock filter was established to remove noise and to sharpen edges efficiently.The algorithms of thresholding,region growing and smallest surrounding circle were used to segment mature citrus from the background.Depth range and variance within the selected region and radius of recognized citrus were calculated and used as constraint condition for further selecting of recognized citrus regions.Three-dimensional database was integrated with extracted characteristic parameters of recognized citrus to realize real-time recognition and location.The total classification results show that recognition accuracy of about 86.7% can be obtained without false detection.The error of depth information is less than 12 mm with actual radius of citrus less than 13 mm.It takes less than 100 ms for image recognition and location.

关 键 词：柑橘 视觉系统 强度图 深度图 识别 定位 

分 类 号：N391.41[自然科学总论] S666.2[农业科学—果树学]