Detection and Localization of Overlapped Fruits Application in an Apple Harvesting Robot
For yield measurement of an apple orchard or the mechanical harvesting of apples, there needs to be accurate identification of the target apple fruit. However, in a natural scene, affected by the apple’s growth posture and camera position, there are many kinds of apple images, such as overlapped app...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-06-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/9/6/1023 |
| _version_ | 1797564498788220928 |
|---|---|
| author | Yuhua Jiao Rong Luo Qianwen Li Xiaobo Deng Xiang Yin Chengzhi Ruan Weikuan Jia |
| author_facet | Yuhua Jiao Rong Luo Qianwen Li Xiaobo Deng Xiang Yin Chengzhi Ruan Weikuan Jia |
| author_sort | Yuhua Jiao |
| collection | DOAJ |
| description | For yield measurement of an apple orchard or the mechanical harvesting of apples, there needs to be accurate identification of the target apple fruit. However, in a natural scene, affected by the apple’s growth posture and camera position, there are many kinds of apple images, such as overlapped apples; mutual shadows or leaves; stems; etc. It is a challenge to accurately locate overlapped apples. They will influence the positioning time and recognition efficiency and then affect the harvesting efficiency of apple-harvesting robots or the accuracy of orchard yield measurement. In response to this problem, an overlapped circle positioning method based on local maxima is proposed. First, the apple image is transformed into the Lab color space and segmented by the <i>K</i>-means algorithm. Second, some morphological processes, like erosion and dilation, are implemented to abstract the outline of the apples. Then image points are divided into central points; edge points; or outer points. Third, a fast algorithm is used to calculate every internal point’s minimum distance from the edge. Then, the centers of the apples are obtained by finding the maxima among these distances. Last, the radii are acquired by figuring out the minimum distance between the center and the edge. Thus, positioning is achieved. Experimental results showed that this method can locate overlapped apples accurately and quickly when the apple contour was complete; and this has certain practicability. |
| first_indexed | 2024-03-10T18:59:02Z |
| format | Article |
| id | doaj.art-2c5e9428ac4a4231badcdf63ae409b31 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T18:59:02Z |
| publishDate | 2020-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-2c5e9428ac4a4231badcdf63ae409b312023-11-20T04:31:05ZengMDPI AGElectronics2079-92922020-06-0196102310.3390/electronics9061023Detection and Localization of Overlapped Fruits Application in an Apple Harvesting RobotYuhua Jiao0Rong Luo1Qianwen Li2Xiaobo Deng3Xiang Yin4Chengzhi Ruan5Weikuan Jia6School of Information Science and Engineering, Shandong Normal University, Jinan 250358, ChinaSchool of Light Industry Science and Engineering, Qilu University of Technology, Shandong Academy of Sciences, Jinan 250351, ChinaSchool of Information Science and Engineering, Shandong Normal University, Jinan 250358, ChinaShandong Key Laboratory for Testing Technology of Material, Chemical Safety, Jinan 250102, ChinaSchool of Agricultural Engineering and Food Science, Shandong University of Technology, Zibo 255000, ChinaCollege of Mechanical and Electrical Engineering, Wuyi University, Wuyishan 354300, ChinaSchool of Information Science and Engineering, Shandong Normal University, Jinan 250358, ChinaFor yield measurement of an apple orchard or the mechanical harvesting of apples, there needs to be accurate identification of the target apple fruit. However, in a natural scene, affected by the apple’s growth posture and camera position, there are many kinds of apple images, such as overlapped apples; mutual shadows or leaves; stems; etc. It is a challenge to accurately locate overlapped apples. They will influence the positioning time and recognition efficiency and then affect the harvesting efficiency of apple-harvesting robots or the accuracy of orchard yield measurement. In response to this problem, an overlapped circle positioning method based on local maxima is proposed. First, the apple image is transformed into the Lab color space and segmented by the <i>K</i>-means algorithm. Second, some morphological processes, like erosion and dilation, are implemented to abstract the outline of the apples. Then image points are divided into central points; edge points; or outer points. Third, a fast algorithm is used to calculate every internal point’s minimum distance from the edge. Then, the centers of the apples are obtained by finding the maxima among these distances. Last, the radii are acquired by figuring out the minimum distance between the center and the edge. Thus, positioning is achieved. Experimental results showed that this method can locate overlapped apples accurately and quickly when the apple contour was complete; and this has certain practicability.https://www.mdpi.com/2079-9292/9/6/1023K-means segmentationoverlapped applesmaximamorphological processing |
| spellingShingle | Yuhua Jiao Rong Luo Qianwen Li Xiaobo Deng Xiang Yin Chengzhi Ruan Weikuan Jia Detection and Localization of Overlapped Fruits Application in an Apple Harvesting Robot Electronics K-means segmentation overlapped apples maxima morphological processing |
| title | Detection and Localization of Overlapped Fruits Application in an Apple Harvesting Robot |
| title_full | Detection and Localization of Overlapped Fruits Application in an Apple Harvesting Robot |
| title_fullStr | Detection and Localization of Overlapped Fruits Application in an Apple Harvesting Robot |
| title_full_unstemmed | Detection and Localization of Overlapped Fruits Application in an Apple Harvesting Robot |
| title_short | Detection and Localization of Overlapped Fruits Application in an Apple Harvesting Robot |
| title_sort | detection and localization of overlapped fruits application in an apple harvesting robot |
| topic | K-means segmentation overlapped apples maxima morphological processing |
| url | https://www.mdpi.com/2079-9292/9/6/1023 |
| work_keys_str_mv | AT yuhuajiao detectionandlocalizationofoverlappedfruitsapplicationinanappleharvestingrobot AT rongluo detectionandlocalizationofoverlappedfruitsapplicationinanappleharvestingrobot AT qianwenli detectionandlocalizationofoverlappedfruitsapplicationinanappleharvestingrobot AT xiaobodeng detectionandlocalizationofoverlappedfruitsapplicationinanappleharvestingrobot AT xiangyin detectionandlocalizationofoverlappedfruitsapplicationinanappleharvestingrobot AT chengzhiruan detectionandlocalizationofoverlappedfruitsapplicationinanappleharvestingrobot AT weikuanjia detectionandlocalizationofoverlappedfruitsapplicationinanappleharvestingrobot |