Study on Target Detection Model and Spatial Location of Greenhouse Muskmelon Automatic Picking System
【Objective】The study was conducted to improve the detection accuracy of muskmelon picking robot in greenhouse under complex light changes and branch and leaf occlusion, and realize the spatial coordinate positioning of detection targets.【Method】Based on YOLOv3, the study explored the impacts of opti...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Guangdong Academy of Agricultural Sciences
2022-03-01
|
Series: | Guangdong nongye kexue |
Subjects: | |
Online Access: | http://gdnykx.cnjournals.org/gdnykx/ch/reader/view_abstract.aspx?file_no=202203017 |
_version_ | 1797802622825005056 |
---|---|
author | Huamin ZHAO Olarewaju LAWAL Defang XU |
author_facet | Huamin ZHAO Olarewaju LAWAL Defang XU |
author_sort | Huamin ZHAO |
collection | DOAJ |
description | 【Objective】The study was conducted to improve the detection accuracy of muskmelon picking robot in greenhouse under complex light changes and branch and leaf occlusion, and realize the spatial coordinate positioning of detection targets.【Method】Based on YOLOv3, the study explored the impacts of optimizing the combination of different backbone networks, head and neck network structures and bounding box loss function on the model detection performance, established a target detection network model YOLOResNet70 under severe muskmelon occlusion, and then fused the model with Intel RealSense D435i depth visual sensor for target space positioning.【Result】With ResNet70 as the backbone network, YOLOResNet70 had the best performance with the combination of SPP (Spatial pyramid pooling), CIoU (Complete Intersection over Union), FPN (Feature Pyramid Network) and NMS (Greedy non-maximum suppression). The average accuracy (AP) of the model reached 89.4%, which was better than 83.3% of YOLOv3 and 82% of YOLOv5, and the detection speed (61.8 frames/s) was 14% faster than that of YOLOv4 (54.1 frames/s).【Conclusion】Through the detection and test of occluded muskmelon images under different lighting conditions, it shows that the YOLOResNet70 model has good robustness, and the model is fused with Intel RealSense D435i depth visual sensor to achieve the spatial positioning coordinates of muskmelon, which is consistent with the manual measurement result. It provides theoretical and model support for target detection and spatial positioning of muskmelon picking robot. |
first_indexed | 2024-03-13T05:08:28Z |
format | Article |
id | doaj.art-f535686a73a04772879824c4fa6f3fe1 |
institution | Directory Open Access Journal |
issn | 1004-874X |
language | English |
last_indexed | 2024-03-13T05:08:28Z |
publishDate | 2022-03-01 |
publisher | Guangdong Academy of Agricultural Sciences |
record_format | Article |
series | Guangdong nongye kexue |
spelling | doaj.art-f535686a73a04772879824c4fa6f3fe12023-06-16T06:42:06ZengGuangdong Academy of Agricultural SciencesGuangdong nongye kexue1004-874X2022-03-0149315116210.16768/j.issn.1004-874X.2022.03.017202203017Study on Target Detection Model and Spatial Location of Greenhouse Muskmelon Automatic Picking SystemHuamin ZHAO0Olarewaju LAWAL1Defang XU2College of Agricultural Engineering, Shanxi Agricultural University, Taigu 030801, ChinaCollege of Agricultural Engineering, Shanxi Agricultural University, Taigu 030801, ChinaDepartment of Economic Management, Lyuliang University, Lyuliang 033001, China【Objective】The study was conducted to improve the detection accuracy of muskmelon picking robot in greenhouse under complex light changes and branch and leaf occlusion, and realize the spatial coordinate positioning of detection targets.【Method】Based on YOLOv3, the study explored the impacts of optimizing the combination of different backbone networks, head and neck network structures and bounding box loss function on the model detection performance, established a target detection network model YOLOResNet70 under severe muskmelon occlusion, and then fused the model with Intel RealSense D435i depth visual sensor for target space positioning.【Result】With ResNet70 as the backbone network, YOLOResNet70 had the best performance with the combination of SPP (Spatial pyramid pooling), CIoU (Complete Intersection over Union), FPN (Feature Pyramid Network) and NMS (Greedy non-maximum suppression). The average accuracy (AP) of the model reached 89.4%, which was better than 83.3% of YOLOv3 and 82% of YOLOv5, and the detection speed (61.8 frames/s) was 14% faster than that of YOLOv4 (54.1 frames/s).【Conclusion】Through the detection and test of occluded muskmelon images under different lighting conditions, it shows that the YOLOResNet70 model has good robustness, and the model is fused with Intel RealSense D435i depth visual sensor to achieve the spatial positioning coordinates of muskmelon, which is consistent with the manual measurement result. It provides theoretical and model support for target detection and spatial positioning of muskmelon picking robot.http://gdnykx.cnjournals.org/gdnykx/ch/reader/view_abstract.aspx?file_no=202203017muskmelonobject detectionyoloresnet70target spatial positioningautomatic picking |
spellingShingle | Huamin ZHAO Olarewaju LAWAL Defang XU Study on Target Detection Model and Spatial Location of Greenhouse Muskmelon Automatic Picking System Guangdong nongye kexue muskmelon object detection yoloresnet70 target spatial positioning automatic picking |
title | Study on Target Detection Model and Spatial Location of Greenhouse Muskmelon Automatic Picking System |
title_full | Study on Target Detection Model and Spatial Location of Greenhouse Muskmelon Automatic Picking System |
title_fullStr | Study on Target Detection Model and Spatial Location of Greenhouse Muskmelon Automatic Picking System |
title_full_unstemmed | Study on Target Detection Model and Spatial Location of Greenhouse Muskmelon Automatic Picking System |
title_short | Study on Target Detection Model and Spatial Location of Greenhouse Muskmelon Automatic Picking System |
title_sort | study on target detection model and spatial location of greenhouse muskmelon automatic picking system |
topic | muskmelon object detection yoloresnet70 target spatial positioning automatic picking |
url | http://gdnykx.cnjournals.org/gdnykx/ch/reader/view_abstract.aspx?file_no=202203017 |
work_keys_str_mv | AT huaminzhao studyontargetdetectionmodelandspatiallocationofgreenhousemuskmelonautomaticpickingsystem AT olarewajulawal studyontargetdetectionmodelandspatiallocationofgreenhousemuskmelonautomaticpickingsystem AT defangxu studyontargetdetectionmodelandspatiallocationofgreenhousemuskmelonautomaticpickingsystem |