自然场景下苹果采摘机器人视觉系统研究  

Research on Visual System of Apple Picking Robot in Nature Scene

作　　者：李娜[1] 陈宁[1] LI Na;CHEN Ning(Xi'an Polytechnic University,Xi'an 710048,China)

机构地区：[1]西安工程大学,陕西西安710048

出　　处：《计算机技术与发展》2018年第12期137-141,146,共6页Computer Technology and Development

基　　金：国家"十二五"科技支撑计划项目(2014BAF07B01);中国纺织工业联合会指导项目(2010076)

摘　　要：随着现代农业智能化技术的飞速开展,智慧农业系统的应用越来越多。农业采摘机器人作为智慧农业的一个新兴领域,成为近年来研究的热点。农业机器人的一个重要组成部分—视觉系统,它的性能好坏将直接影响果实识别和目标定位的准确性,从而影响其采摘效率。面对自然环境中的果实目标,采摘机器人的视觉系统仍然面临着巨大的挑战。首先对智慧农业的研究现状进行分析概括,然后对目前自然场景中的苹果果实采摘现状进行分析,进一步对自然场景中的苹果果实受光照影响、果实重叠、果实相互遮挡、树枝遮挡等现状的识别以及所采用的研究方法进行了分析总结,指出各方面需要改进的问题,最后就自然场景中苹果果实目标的识别及其定位技术进行了展望。With the rapid development of modern agricultural intelligent technology,the application of intelligent agricultural system ismore and more.As a new field of intelligent agriculture,agricultural picking robot has become a hot topic in recent years.As an important part of agricultural robot,the performance of vision system will directly affect the accuracy of fruit recognition and target positioning,thus affecting the efficiency of picking.Facing the fruit target in the natural environment,the visual system of picking robot still facesgreat challenges.We firstly summarize the wisdom agriculture research status.Then we analyze the present situation of apple fruit picking in the natural scene,further summarizing the identification of apple fruit under the influence of light,fruit overlapping,fruit mutual occlusion and tree occlusion in the natural scene and the research methods adopted,pointing out the problem to be improved.Finally,weprospect the identification of fruit target in natural scene and its positioning technology.

关 键 词：智慧农业 机器人 视觉系统 果实识别 目标定位 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]