Fruit localization and environment perception for strawberry harvesting robots
Peer reviewed, Journal article
MetadataShow full item record
Original versionIEEE Access. 2019, 7 147642-147652. 10.1109/ACCESS.2019.2946369
This work presents a machine vision system for the localization of strawberries and environment perception in a strawberry-harvesting robot for use in table-top strawberry production. A deep convolutionalneuralnetworkforsegmentationisutilizedtodetectthestrawberries.Segmentedstrawberries are localized through coordinate transformation, density base point clustering and the proposed location approximation method. To avoid collisions between the gripper and ﬁxed obstacles, the safe manipulation region is limited to the space in front of the table and underneath the strap. Therefore, a safe region classiﬁcation algorithm, based on Hough Transform algorithm, is proposed to segment the strap masks into a belt region in order to identify the pickable strawberries located underneath the strap. Similarly, a safe region classiﬁcation algorithm is proposed for the table, to calculate its points in 3D and ﬁt the points onto a 3D plane based on the 3D point cloud, so that pickable strawberries in front of the table can be identiﬁed. Experimentaltestsshowedthatthealgorithmcouldaccuratelyclassifyripeandunripestrawberriesandcould identify whether the strawberries are within the safe region for harvesting. Furthermore, harvester robot’s optimized localization method could accurately locate the strawberry targets with a picking accuracy rate of 74.1% in modiﬁed situations.