Research on Precise Segmentation and Center Localization of Weeds in Tea Gardens Based on an Improved U-Net Model and Skeleton Refinement Algorithm
The primary objective of this research was to develop an efficient method for accurately identifying and localizing weeds in ecological tea garden environments, aiming to enhance the quality and yield of tea production. Weed competition poses a significant challenge to tea production, particularly d...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-02-01
|
| Series: | Agriculture |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0472/15/5/521 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850030790531874816 |
|---|---|
| author | Zhiyong Cao Shuai Zhang Chen Li Wei Feng Baijuan Wang Hao Wang Ling Luo Hongbo Zhao |
| author_facet | Zhiyong Cao Shuai Zhang Chen Li Wei Feng Baijuan Wang Hao Wang Ling Luo Hongbo Zhao |
| author_sort | Zhiyong Cao |
| collection | DOAJ |
| description | The primary objective of this research was to develop an efficient method for accurately identifying and localizing weeds in ecological tea garden environments, aiming to enhance the quality and yield of tea production. Weed competition poses a significant challenge to tea production, particularly due to the small size of weed plants, their color similarity to tea trees, and the complexity of their growth environment. A dataset comprising 5366 high-definition images of weeds in tea gardens has been compiled to address this challenge. An enhanced U-Net model, incorporating a Double Attention Mechanism and an Atrous Spatial Pyramid Pooling module, is proposed for weed recognition. The results of the ablation experiments show that the model significantly improves the recognition accuracy and the Mean Intersection over Union (MIoU), which are enhanced by 4.08% and 5.22%, respectively. In addition, to meet the demand for precise weed management, a method for determining the center of weed plants by integrating the center of mass and skeleton structure has been developed. The skeleton was extracted through a preprocessing step and a refinement algorithm, and the relative positional relationship between the intersection point of the skeleton and the center of mass was cleverly utilized to achieve up to 82% localization accuracy. These results provide technical support for the research and development of intelligent weeding equipment for tea gardens, which helps to maintain the ecology of tea gardens and improve production efficiency and also provides a reference for weed management in other natural ecological environments. |
| format | Article |
| id | doaj-art-6e094144d02b4a869a6aed2f0c29799e |
| institution | DOAJ |
| issn | 2077-0472 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agriculture |
| spelling | doaj-art-6e094144d02b4a869a6aed2f0c29799e2025-08-20T02:59:07ZengMDPI AGAgriculture2077-04722025-02-0115552110.3390/agriculture15050521Research on Precise Segmentation and Center Localization of Weeds in Tea Gardens Based on an Improved U-Net Model and Skeleton Refinement AlgorithmZhiyong Cao0Shuai Zhang1Chen Li2Wei Feng3Baijuan Wang4Hao Wang5Ling Luo6Hongbo Zhao7College of Big Data, Yunnan Agricultural University, Kunming 650201, ChinaCollege of Big Data, Yunnan Agricultural University, Kunming 650201, ChinaCollege of Big Data, Yunnan Agricultural University, Kunming 650201, ChinaCollege of Big Data, Yunnan Agricultural University, Kunming 650201, ChinaCollege of Big Data, Yunnan Agricultural University, Kunming 650201, ChinaCollege of Big Data, Yunnan Agricultural University, Kunming 650201, ChinaCollege of Big Data, Yunnan Agricultural University, Kunming 650201, ChinaCollege of Big Data, Yunnan Agricultural University, Kunming 650201, ChinaThe primary objective of this research was to develop an efficient method for accurately identifying and localizing weeds in ecological tea garden environments, aiming to enhance the quality and yield of tea production. Weed competition poses a significant challenge to tea production, particularly due to the small size of weed plants, their color similarity to tea trees, and the complexity of their growth environment. A dataset comprising 5366 high-definition images of weeds in tea gardens has been compiled to address this challenge. An enhanced U-Net model, incorporating a Double Attention Mechanism and an Atrous Spatial Pyramid Pooling module, is proposed for weed recognition. The results of the ablation experiments show that the model significantly improves the recognition accuracy and the Mean Intersection over Union (MIoU), which are enhanced by 4.08% and 5.22%, respectively. In addition, to meet the demand for precise weed management, a method for determining the center of weed plants by integrating the center of mass and skeleton structure has been developed. The skeleton was extracted through a preprocessing step and a refinement algorithm, and the relative positional relationship between the intersection point of the skeleton and the center of mass was cleverly utilized to achieve up to 82% localization accuracy. These results provide technical support for the research and development of intelligent weeding equipment for tea gardens, which helps to maintain the ecology of tea gardens and improve production efficiency and also provides a reference for weed management in other natural ecological environments.https://www.mdpi.com/2077-0472/15/5/521tea garden weedscomplex environmentASPPcenter localization |
| spellingShingle | Zhiyong Cao Shuai Zhang Chen Li Wei Feng Baijuan Wang Hao Wang Ling Luo Hongbo Zhao Research on Precise Segmentation and Center Localization of Weeds in Tea Gardens Based on an Improved U-Net Model and Skeleton Refinement Algorithm Agriculture tea garden weeds complex environment ASPP center localization |
| title | Research on Precise Segmentation and Center Localization of Weeds in Tea Gardens Based on an Improved U-Net Model and Skeleton Refinement Algorithm |
| title_full | Research on Precise Segmentation and Center Localization of Weeds in Tea Gardens Based on an Improved U-Net Model and Skeleton Refinement Algorithm |
| title_fullStr | Research on Precise Segmentation and Center Localization of Weeds in Tea Gardens Based on an Improved U-Net Model and Skeleton Refinement Algorithm |
| title_full_unstemmed | Research on Precise Segmentation and Center Localization of Weeds in Tea Gardens Based on an Improved U-Net Model and Skeleton Refinement Algorithm |
| title_short | Research on Precise Segmentation and Center Localization of Weeds in Tea Gardens Based on an Improved U-Net Model and Skeleton Refinement Algorithm |
| title_sort | research on precise segmentation and center localization of weeds in tea gardens based on an improved u net model and skeleton refinement algorithm |
| topic | tea garden weeds complex environment ASPP center localization |
| url | https://www.mdpi.com/2077-0472/15/5/521 |
| work_keys_str_mv | AT zhiyongcao researchonprecisesegmentationandcenterlocalizationofweedsinteagardensbasedonanimprovedunetmodelandskeletonrefinementalgorithm AT shuaizhang researchonprecisesegmentationandcenterlocalizationofweedsinteagardensbasedonanimprovedunetmodelandskeletonrefinementalgorithm AT chenli researchonprecisesegmentationandcenterlocalizationofweedsinteagardensbasedonanimprovedunetmodelandskeletonrefinementalgorithm AT weifeng researchonprecisesegmentationandcenterlocalizationofweedsinteagardensbasedonanimprovedunetmodelandskeletonrefinementalgorithm AT baijuanwang researchonprecisesegmentationandcenterlocalizationofweedsinteagardensbasedonanimprovedunetmodelandskeletonrefinementalgorithm AT haowang researchonprecisesegmentationandcenterlocalizationofweedsinteagardensbasedonanimprovedunetmodelandskeletonrefinementalgorithm AT lingluo researchonprecisesegmentationandcenterlocalizationofweedsinteagardensbasedonanimprovedunetmodelandskeletonrefinementalgorithm AT hongbozhao researchonprecisesegmentationandcenterlocalizationofweedsinteagardensbasedonanimprovedunetmodelandskeletonrefinementalgorithm |