A Small Target Strawberry Recognition Method Based on Improved YOLOv8n Model
As technology continues to advance, the automation of strawberry production and picking is an inevitable trend. To address the pressing issues of insufficient detection of smaller strawberries and misdetection resulting from the intricate background of strawberry images, an improved strawberry recog...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2024-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10410837/ |
_version_ | 1797335491003023360 |
---|---|
author | Qiang Luo Chenbo Wu Guangjie Wu Weiyi Li |
author_facet | Qiang Luo Chenbo Wu Guangjie Wu Weiyi Li |
author_sort | Qiang Luo |
collection | DOAJ |
description | As technology continues to advance, the automation of strawberry production and picking is an inevitable trend. To address the pressing issues of insufficient detection of smaller strawberries and misdetection resulting from the intricate background of strawberry images, an improved strawberry recognition method based on the YOLOv8n model was proposed. The improvements are as follows: 1) The deletion of the <inline-formula> <tex-math notation="LaTeX">$20\times20$ </tex-math></inline-formula> pixel detection layer with a focus on small target strawberries and the addition of a <inline-formula> <tex-math notation="LaTeX">$160\times160$ </tex-math></inline-formula> pixel small target detection layer were implemented to reduce the model volume and enhance the network reconstruction. 2) In the neck portion, a global attention mechanism was incorporated. 3) The SPD-Conv method was applied to improve the detection capability of small taget strawberries. 4) To address the limitations of the CIOU loss function, the EIOU loss function was utilized. The results of the experiment conducted on the self-made strawberry dataset demonstrated that the volume of the improved algorithm model was reduced by 59.7%, its precision was improved by 1.3%, and its recall rate increased by 2.1%. Additionally, the mAP was enhanced by 1.6%. The detection time for a single strawberry fruit image on a GPU was 17. 2 ms, which rendered the improved model suitable for practical applications. The model was verified in terms of small targets, and it achieved better detection performance than yolov5n, yolov6n, and yolov8s. The proposed algorithm demonstrated improved detection capabilities, reduced model size, and better target detection of strawberries. |
first_indexed | 2024-03-08T08:38:53Z |
format | Article |
id | doaj.art-05f196bd44c346edaffb3a1464a78ccd |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-03-08T08:38:53Z |
publishDate | 2024-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-05f196bd44c346edaffb3a1464a78ccd2024-02-02T00:03:53ZengIEEEIEEE Access2169-35362024-01-0112149871499510.1109/ACCESS.2024.335686910410837A Small Target Strawberry Recognition Method Based on Improved YOLOv8n ModelQiang Luo0https://orcid.org/0000-0002-8074-5496Chenbo Wu1https://orcid.org/0009-0000-4926-3176Guangjie Wu2https://orcid.org/0009-0003-9252-4281Weiyi Li3https://orcid.org/0009-0009-9429-1198Department of Mechanical Engineering, Chongqing Three Gorges University, Chongqing, ChinaDepartment of Mechanical Engineering, Chongqing Three Gorges University, Chongqing, ChinaDepartment of Mechanical Engineering, Chongqing Three Gorges University, Chongqing, ChinaDepartment of Mechanical Engineering, Chongqing Three Gorges University, Chongqing, ChinaAs technology continues to advance, the automation of strawberry production and picking is an inevitable trend. To address the pressing issues of insufficient detection of smaller strawberries and misdetection resulting from the intricate background of strawberry images, an improved strawberry recognition method based on the YOLOv8n model was proposed. The improvements are as follows: 1) The deletion of the <inline-formula> <tex-math notation="LaTeX">$20\times20$ </tex-math></inline-formula> pixel detection layer with a focus on small target strawberries and the addition of a <inline-formula> <tex-math notation="LaTeX">$160\times160$ </tex-math></inline-formula> pixel small target detection layer were implemented to reduce the model volume and enhance the network reconstruction. 2) In the neck portion, a global attention mechanism was incorporated. 3) The SPD-Conv method was applied to improve the detection capability of small taget strawberries. 4) To address the limitations of the CIOU loss function, the EIOU loss function was utilized. The results of the experiment conducted on the self-made strawberry dataset demonstrated that the volume of the improved algorithm model was reduced by 59.7%, its precision was improved by 1.3%, and its recall rate increased by 2.1%. Additionally, the mAP was enhanced by 1.6%. The detection time for a single strawberry fruit image on a GPU was 17. 2 ms, which rendered the improved model suitable for practical applications. The model was verified in terms of small targets, and it achieved better detection performance than yolov5n, yolov6n, and yolov8s. The proposed algorithm demonstrated improved detection capabilities, reduced model size, and better target detection of strawberries.https://ieeexplore.ieee.org/document/10410837/EIOUglobal attention mechanismmodel reconstructionSPD-Convstrawberry recognitionYOLOv8 |
spellingShingle | Qiang Luo Chenbo Wu Guangjie Wu Weiyi Li A Small Target Strawberry Recognition Method Based on Improved YOLOv8n Model IEEE Access EIOU global attention mechanism model reconstruction SPD-Conv strawberry recognition YOLOv8 |
title | A Small Target Strawberry Recognition Method Based on Improved YOLOv8n Model |
title_full | A Small Target Strawberry Recognition Method Based on Improved YOLOv8n Model |
title_fullStr | A Small Target Strawberry Recognition Method Based on Improved YOLOv8n Model |
title_full_unstemmed | A Small Target Strawberry Recognition Method Based on Improved YOLOv8n Model |
title_short | A Small Target Strawberry Recognition Method Based on Improved YOLOv8n Model |
title_sort | small target strawberry recognition method based on improved yolov8n model |
topic | EIOU global attention mechanism model reconstruction SPD-Conv strawberry recognition YOLOv8 |
url | https://ieeexplore.ieee.org/document/10410837/ |
work_keys_str_mv | AT qiangluo asmalltargetstrawberryrecognitionmethodbasedonimprovedyolov8nmodel AT chenbowu asmalltargetstrawberryrecognitionmethodbasedonimprovedyolov8nmodel AT guangjiewu asmalltargetstrawberryrecognitionmethodbasedonimprovedyolov8nmodel AT weiyili asmalltargetstrawberryrecognitionmethodbasedonimprovedyolov8nmodel AT qiangluo smalltargetstrawberryrecognitionmethodbasedonimprovedyolov8nmodel AT chenbowu smalltargetstrawberryrecognitionmethodbasedonimprovedyolov8nmodel AT guangjiewu smalltargetstrawberryrecognitionmethodbasedonimprovedyolov8nmodel AT weiyili smalltargetstrawberryrecognitionmethodbasedonimprovedyolov8nmodel |