基于霍夫变换与改进模板匹配算法的水果检测  

Fruit Detection Based on Hough Transform and Improved Template Matching

作　　者：李玉红 刘俊豪 许曈 LI Yuhong;LIU Junhao;XU Tong(School of Information Technology,Jiangsu Open University,Nanjing 210036,China)

机构地区：[1]江苏开放大学信息工程学院,江苏南京210036

出　　处：《软件导刊》2024年第11期166-171,共6页Software Guide

基　　金：国家自然科学基金项目(62403218);江苏省社会教育规划课题(JSS-C-2023035)。

摘　　要：在水果尺寸较小、部分遮挡、光照变化、背景杂乱等情况下,采摘机器人的检测、识别准确率难以提高,导致采摘时出现漏采、错采等问题。针对该问题,通过融合霍夫圆检测算法和改进模板匹配算法,提出一种新型的目标检测方法,以有效地检测与识别复杂情况下的小尺寸、多类水果。首先,对目标水果数据进行自适应阈值二值化等预处理以除噪;其次,采用霍夫圆检测算法检测出水果位置;再次,对模板匹配算法进行改进,设计一种像素、亮度、对比度和结构4个层面的匹配相似度计算方法,识别出水果品种;最后,以草莓、红枣、蓝莓进行实验验证。结果表明,所提算法用时约3.2 ms,平均检测精度均值达95%,优于SSD、YOLOv8、YOLOv9这3种算法。同时,该算法在复杂环境下的识别准确率为92%,能够为小尺寸水果的自动采摘提供有效的理论方法和实践经验。In the context of small fruits,partial occlusion,changing light,cluttered background,etc.,it is difficult for the picking robot to improve the accuracy of detection and recognition,leading to issues such as missed and erroneous picking during the picking process.To solve this problem,a novel object detection method is proposed by integrating the Hough circle detection algorithm and the improved template matching algorithm.It aims to effectively detect and recognize small-sized and multi-class fruits in complicated situations.Firstly,denoising pre-processing,such as adaptive threshold binarization,is performed on the target fruit data.Secondly,this is followed by the application of the Hough circle detection algorithm to detect the position of the fruit.And then the template matching algorithm is enhanced by calculating the matching similarity from four levels of pixel,brightness,contrast and structure to identify the fruit variety.Finally,It is validated experimen⁃tally using the fruits of strawberries,jujubes and blueberries.And the results indicate that the proposed algorithm takes about 3.2ms and exhib⁃its the mean average accuracy of 95%when detecting fruits,which is superior to the three algorithms of SSD,YOLOv8 and YOLOv9.Addition⁃ally,the recognition accuracy of the algorithm in complex environments is 92%.The proposed algorithm offers an effective theoretical method and practical experience for automatic picking of small-sized fruits.

关 键 词：采摘机器人 水果检测 霍夫圆检测 模板匹配 匹配相似度 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]