柑橘果实采摘机器人目标识别算法研究进展  

Research progress on target recognition algorithms for citrus fruit picking robots

作　　者：赵玉清 贾奥莹[1,3] 王白娟 邓航宇[1,3] 向铠铭 张悦 ZHAO Yuqing;JIA Aoying;WANG Baijuan;DENG Hangyu;XIANG Kaiming;ZHANG Yue(Faculty of Mechanical and Electrical Engineering,Yunnan Agricultural University,Kunming 650201,China;Faculty of Transportation Engineering,Kunming University of Science and Technology,Kunming 650093,China;The Key Laboratory for Crop Production and Smart Agriculture of Yunnan Province,Kunming 650201,China;College of Tea Science,Yunnan Agricultural University,Kunming 650201,China;College of Big Data,Yunnan Agricultural University,Kunming 650201,China)

机构地区：[1]云南农业大学机电工程学院,云南昆明650201 [2]昆明理工大学交通工程学院,云南昆明650093 [3]云南省作物生产与智慧农业重点实验室,云南昆明650201 [4]云南农业大学茶学院,云南昆明650201 [5]云南农业大学大数据学院,云南昆明650201

出　　处：《江苏农业学报》2024年第8期1552-1560,共9页Jiangsu Journal of Agricultural Sciences

基　　金：云南省科技厅重大科技专项(202302AE0900200105);云南省科技厅科技计划农业联合专项(202301BD070001-105)。

摘　　要：水果采摘机器人作业是提高水果采摘效率,解决劳动力短缺的重要途经。准确高效的柑橘果实采摘机器人已成为农业机器人研究的热点之一。目标识别是柑橘果实采摘机器人精准高效完成采摘作业的首要任务与关键技术。本文综述了近年来应用于柑橘果实采摘机器人中的传统目标识别算法、机器学习算法和深度学习算法,阐述了不同目标识别算法的特征及应用情况,最后指出当前柑橘果实目标识别算法存在的问题,并对柑橘果实目标识别算法发展趋势进行展望。Fruit picking robot operation is an important way to improve fruit picking efficiency and solve labor shortage.Accurate and efficient citrus fruit picking robot has become one of the hotspots in agricultural robot research.Target recognition is the primary task and key technology for citrus fruit picking robots to complete picking operations accurately and efficiently.The traditional target recognition algorithms,machine learning algorithms and deep learning algorithms applied to citrus fruit picking robots in recent years were reviewed in this paper,and the characteristics and applications of different target recognition algorithms were discussed.Finally,the problems existing in the current citrus fruit target recognition algorithms were pointed out,and the future development trend of citrus fruit target recognition algorithms was prospected.

关 键 词：柑橘 采摘机器人 目标识别 研究进展 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]