An Efficient Group Convolution and Feature Fusion Method for Weed Detection
Weed detection is a crucial step in achieving intelligent weeding for vegetables. Currently, research on vegetable weed detection technology is relatively limited, and existing detection methods still face challenges due to complex natural conditions, resulting in low detection accuracy and efficien...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Agriculture |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0472/15/1/37 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841549481437298688 |
|---|---|
| author | Chaowen Chen Ying Zang Jinkang Jiao Daoqing Yan Zhuorong Fan Zijian Cui Minghua Zhang |
| author_facet | Chaowen Chen Ying Zang Jinkang Jiao Daoqing Yan Zhuorong Fan Zijian Cui Minghua Zhang |
| author_sort | Chaowen Chen |
| collection | DOAJ |
| description | Weed detection is a crucial step in achieving intelligent weeding for vegetables. Currently, research on vegetable weed detection technology is relatively limited, and existing detection methods still face challenges due to complex natural conditions, resulting in low detection accuracy and efficiency. This paper proposes the YOLOv8-EGC-Fusion (YEF) model, an enhancement based on the YOLOv8 model, to address these challenges. This model introduces plug-and-play modules: (1) The Efficient Group Convolution (EGC) module leverages convolution kernels of various sizes combined with group convolution techniques to significantly reduce computational cost. Integrating this EGC module with the C2f module creates the C2f-EGC module, strengthening the model’s capacity to grasp local contextual information. (2) The Group Context Anchor Attention (GCAA) module strengthens the model’s capacity to capture long-range contextual information, contributing to improved feature comprehension. (3) The GCAA-Fusion module effectively merges multi-scale features, addressing shallow feature loss and preserving critical information. Leveraging GCAA-Fusion and PAFPN, we developed an Adaptive Feature Fusion (AFF) feature pyramid structure that amplifies the model’s feature extraction capabilities. To ensure effective evaluation, we collected a diverse dataset of weed images from various vegetable fields. A series of comparative experiments was conducted to verify the detection effectiveness of the YEF model. The results show that the YEF model outperforms the original YOLOv8 model, Faster R-CNN, RetinaNet, TOOD, RTMDet, and YOLOv5 in detection performance. The detection metrics achieved by the YEF model are as follows: precision of 0.904, recall of 0.88, F1 score of 0.891, and mAP0.5 of 0.929. In conclusion, the YEF model demonstrates high detection accuracy for vegetable and weed identification, meeting the requirements for precise detection. |
| format | Article |
| id | doaj-art-14a01a4c5f494767bfda9ed43612d084 |
| institution | Kabale University |
| issn | 2077-0472 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agriculture |
| spelling | doaj-art-14a01a4c5f494767bfda9ed43612d0842025-01-10T13:13:29ZengMDPI AGAgriculture2077-04722024-12-011513710.3390/agriculture15010037An Efficient Group Convolution and Feature Fusion Method for Weed DetectionChaowen Chen0Ying Zang1Jinkang Jiao2Daoqing Yan3Zhuorong Fan4Zijian Cui5Minghua Zhang6College of Engineering, South China Agricultural University, Guangzhou 510642, ChinaCollege of Engineering, South China Agricultural University, Guangzhou 510642, ChinaCollege of Engineering, South China Agricultural University, Guangzhou 510642, ChinaCollege of Engineering, South China Agricultural University, Guangzhou 510642, ChinaCollege of Engineering, South China Agricultural University, Guangzhou 510642, ChinaCollege of Engineering, South China Agricultural University, Guangzhou 510642, ChinaCollege of Engineering, South China Agricultural University, Guangzhou 510642, ChinaWeed detection is a crucial step in achieving intelligent weeding for vegetables. Currently, research on vegetable weed detection technology is relatively limited, and existing detection methods still face challenges due to complex natural conditions, resulting in low detection accuracy and efficiency. This paper proposes the YOLOv8-EGC-Fusion (YEF) model, an enhancement based on the YOLOv8 model, to address these challenges. This model introduces plug-and-play modules: (1) The Efficient Group Convolution (EGC) module leverages convolution kernels of various sizes combined with group convolution techniques to significantly reduce computational cost. Integrating this EGC module with the C2f module creates the C2f-EGC module, strengthening the model’s capacity to grasp local contextual information. (2) The Group Context Anchor Attention (GCAA) module strengthens the model’s capacity to capture long-range contextual information, contributing to improved feature comprehension. (3) The GCAA-Fusion module effectively merges multi-scale features, addressing shallow feature loss and preserving critical information. Leveraging GCAA-Fusion and PAFPN, we developed an Adaptive Feature Fusion (AFF) feature pyramid structure that amplifies the model’s feature extraction capabilities. To ensure effective evaluation, we collected a diverse dataset of weed images from various vegetable fields. A series of comparative experiments was conducted to verify the detection effectiveness of the YEF model. The results show that the YEF model outperforms the original YOLOv8 model, Faster R-CNN, RetinaNet, TOOD, RTMDet, and YOLOv5 in detection performance. The detection metrics achieved by the YEF model are as follows: precision of 0.904, recall of 0.88, F1 score of 0.891, and mAP0.5 of 0.929. In conclusion, the YEF model demonstrates high detection accuracy for vegetable and weed identification, meeting the requirements for precise detection.https://www.mdpi.com/2077-0472/15/1/37weed detectionYOLOv8feature extractionmulti-scale features |
| spellingShingle | Chaowen Chen Ying Zang Jinkang Jiao Daoqing Yan Zhuorong Fan Zijian Cui Minghua Zhang An Efficient Group Convolution and Feature Fusion Method for Weed Detection Agriculture weed detection YOLOv8 feature extraction multi-scale features |
| title | An Efficient Group Convolution and Feature Fusion Method for Weed Detection |
| title_full | An Efficient Group Convolution and Feature Fusion Method for Weed Detection |
| title_fullStr | An Efficient Group Convolution and Feature Fusion Method for Weed Detection |
| title_full_unstemmed | An Efficient Group Convolution and Feature Fusion Method for Weed Detection |
| title_short | An Efficient Group Convolution and Feature Fusion Method for Weed Detection |
| title_sort | efficient group convolution and feature fusion method for weed detection |
| topic | weed detection YOLOv8 feature extraction multi-scale features |
| url | https://www.mdpi.com/2077-0472/15/1/37 |
| work_keys_str_mv | AT chaowenchen anefficientgroupconvolutionandfeaturefusionmethodforweeddetection AT yingzang anefficientgroupconvolutionandfeaturefusionmethodforweeddetection AT jinkangjiao anefficientgroupconvolutionandfeaturefusionmethodforweeddetection AT daoqingyan anefficientgroupconvolutionandfeaturefusionmethodforweeddetection AT zhuorongfan anefficientgroupconvolutionandfeaturefusionmethodforweeddetection AT zijiancui anefficientgroupconvolutionandfeaturefusionmethodforweeddetection AT minghuazhang anefficientgroupconvolutionandfeaturefusionmethodforweeddetection AT chaowenchen efficientgroupconvolutionandfeaturefusionmethodforweeddetection AT yingzang efficientgroupconvolutionandfeaturefusionmethodforweeddetection AT jinkangjiao efficientgroupconvolutionandfeaturefusionmethodforweeddetection AT daoqingyan efficientgroupconvolutionandfeaturefusionmethodforweeddetection AT zhuorongfan efficientgroupconvolutionandfeaturefusionmethodforweeddetection AT zijiancui efficientgroupconvolutionandfeaturefusionmethodforweeddetection AT minghuazhang efficientgroupconvolutionandfeaturefusionmethodforweeddetection |