Grape-Bunch Identification and Location of Picking Points on Occluded Fruit Axis Based on YOLOv5-GAP
Due to the short fruit axis, many leaves, and complex background of grapes, most grape cluster axes are blocked from view, which increases robot positioning difficulty in harvesting. This study discussed the location method for picking points in the case of partial occlusion and proposed a grape clu...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Horticulturae |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2311-7524/9/4/498 |
| _version_ | 1797605248265617408 |
|---|---|
| author | Tao Zhang Fengyun Wu Mei Wang Zhaoyi Chen Lanyun Li Xiangjun Zou |
| author_facet | Tao Zhang Fengyun Wu Mei Wang Zhaoyi Chen Lanyun Li Xiangjun Zou |
| author_sort | Tao Zhang |
| collection | DOAJ |
| description | Due to the short fruit axis, many leaves, and complex background of grapes, most grape cluster axes are blocked from view, which increases robot positioning difficulty in harvesting. This study discussed the location method for picking points in the case of partial occlusion and proposed a grape cluster-detection algorithm “You Only Look Once v5-GAP” based on “You Only Look Once v5”. First, the Conv layer of the first layer of the YOLOv5 algorithm Backbone was changed to the Focus layer, then a convolution attention operation was performed on the first three C3 structures, the C3 structure layer was changed, and the Transformer in the Bottleneck module of the last layer of the C3 structure was used to reduce the computational amount and execute a better extraction of global feature information. Second, on the basis of bidirectional feature fusion, jump links were added and variable weights were used to strengthen the fusion of feature information for different resolutions. Then, the adaptive activation function was used to learn and decide whether neurons needed to be activated, such that the dynamic control of the network nonlinear degree was realized. Finally, the combination of a digital image processing algorithm and mathematical geometry was used to segment grape bunches identified by YOLOv5-GAP, and picking points were determined after finding centroid coordinates. Experimental results showed that the average precision of YOLOv5-GAP was 95.13%, which was 16.13%, 4.34%, and 2.35% higher than YOLOv4, YOLOv5, and YOLOv7 algorithms, respectively. The average positioning pixel error of the point was 6.3 pixels, which verified that the algorithm effectively detected grapes quickly and accurately. |
| first_indexed | 2024-03-11T04:58:20Z |
| format | Article |
| id | doaj.art-b473cadda8ec42948b8271d40598649c |
| institution | Directory Open Access Journal |
| issn | 2311-7524 |
| language | English |
| last_indexed | 2024-03-11T04:58:20Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Horticulturae |
| spelling | doaj.art-b473cadda8ec42948b8271d40598649c2023-11-17T19:29:36ZengMDPI AGHorticulturae2311-75242023-04-019449810.3390/horticulturae9040498Grape-Bunch Identification and Location of Picking Points on Occluded Fruit Axis Based on YOLOv5-GAPTao Zhang0Fengyun Wu1Mei Wang2Zhaoyi Chen3Lanyun Li4Xiangjun Zou5College of Engineering, South China Agricultural University, Guangzhou 510642, ChinaCollege of Engineering, South China Agricultural University, Guangzhou 510642, ChinaCollege of Economics and Management, South China Agricultural University, Guangzhou 510642, ChinaCollege of Engineering, South China Agricultural University, Guangzhou 510642, ChinaFoshan-Zhongke Innovation Research Institute of Intelligent Agriculture, Foshan 528010, ChinaCollege of Engineering, South China Agricultural University, Guangzhou 510642, ChinaDue to the short fruit axis, many leaves, and complex background of grapes, most grape cluster axes are blocked from view, which increases robot positioning difficulty in harvesting. This study discussed the location method for picking points in the case of partial occlusion and proposed a grape cluster-detection algorithm “You Only Look Once v5-GAP” based on “You Only Look Once v5”. First, the Conv layer of the first layer of the YOLOv5 algorithm Backbone was changed to the Focus layer, then a convolution attention operation was performed on the first three C3 structures, the C3 structure layer was changed, and the Transformer in the Bottleneck module of the last layer of the C3 structure was used to reduce the computational amount and execute a better extraction of global feature information. Second, on the basis of bidirectional feature fusion, jump links were added and variable weights were used to strengthen the fusion of feature information for different resolutions. Then, the adaptive activation function was used to learn and decide whether neurons needed to be activated, such that the dynamic control of the network nonlinear degree was realized. Finally, the combination of a digital image processing algorithm and mathematical geometry was used to segment grape bunches identified by YOLOv5-GAP, and picking points were determined after finding centroid coordinates. Experimental results showed that the average precision of YOLOv5-GAP was 95.13%, which was 16.13%, 4.34%, and 2.35% higher than YOLOv4, YOLOv5, and YOLOv7 algorithms, respectively. The average positioning pixel error of the point was 6.3 pixels, which verified that the algorithm effectively detected grapes quickly and accurately.https://www.mdpi.com/2311-7524/9/4/498deep learningmachine visionimage processinggrape detectionpicking-point positioning |
| spellingShingle | Tao Zhang Fengyun Wu Mei Wang Zhaoyi Chen Lanyun Li Xiangjun Zou Grape-Bunch Identification and Location of Picking Points on Occluded Fruit Axis Based on YOLOv5-GAP Horticulturae deep learning machine vision image processing grape detection picking-point positioning |
| title | Grape-Bunch Identification and Location of Picking Points on Occluded Fruit Axis Based on YOLOv5-GAP |
| title_full | Grape-Bunch Identification and Location of Picking Points on Occluded Fruit Axis Based on YOLOv5-GAP |
| title_fullStr | Grape-Bunch Identification and Location of Picking Points on Occluded Fruit Axis Based on YOLOv5-GAP |
| title_full_unstemmed | Grape-Bunch Identification and Location of Picking Points on Occluded Fruit Axis Based on YOLOv5-GAP |
| title_short | Grape-Bunch Identification and Location of Picking Points on Occluded Fruit Axis Based on YOLOv5-GAP |
| title_sort | grape bunch identification and location of picking points on occluded fruit axis based on yolov5 gap |
| topic | deep learning machine vision image processing grape detection picking-point positioning |
| url | https://www.mdpi.com/2311-7524/9/4/498 |
| work_keys_str_mv | AT taozhang grapebunchidentificationandlocationofpickingpointsonoccludedfruitaxisbasedonyolov5gap AT fengyunwu grapebunchidentificationandlocationofpickingpointsonoccludedfruitaxisbasedonyolov5gap AT meiwang grapebunchidentificationandlocationofpickingpointsonoccludedfruitaxisbasedonyolov5gap AT zhaoyichen grapebunchidentificationandlocationofpickingpointsonoccludedfruitaxisbasedonyolov5gap AT lanyunli grapebunchidentificationandlocationofpickingpointsonoccludedfruitaxisbasedonyolov5gap AT xiangjunzou grapebunchidentificationandlocationofpickingpointsonoccludedfruitaxisbasedonyolov5gap |