Channel Attention GAN-Based Synthetic Weed Generation for Precise Weed Identification
Weed is a major biological factor causing declines in crop yield. However, widespread herbicide application and indiscriminate weeding with soil disturbance are of great concern because of their environmental impacts. Site-specific weed management (SSWM) refers to a weed management strategy for digi...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
American Association for the Advancement of Science (AAAS)
2024-01-01
|
| Series: | Plant Phenomics |
| Online Access: | https://spj.science.org/doi/10.34133/plantphenomics.0122 |
| _version_ | 1797233134294532096 |
|---|---|
| author | Tang Li Motoaki Asai Yoichiro Kato Yuya Fukano Wei Guo |
| author_facet | Tang Li Motoaki Asai Yoichiro Kato Yuya Fukano Wei Guo |
| author_sort | Tang Li |
| collection | DOAJ |
| description | Weed is a major biological factor causing declines in crop yield. However, widespread herbicide application and indiscriminate weeding with soil disturbance are of great concern because of their environmental impacts. Site-specific weed management (SSWM) refers to a weed management strategy for digital agriculture that results in low energy loss. Deep learning is crucial for developing SSWM, as it distinguishes crops from weeds and identifies weed species. However, this technique requires substantial annotated data, which necessitates expertise in weed science and agronomy. In this study, we present a channel attention mechanism-driven generative adversarial network (CA-GAN) that can generate realistic synthetic weed data. The performance of the model was evaluated using two datasets: the public segmented Plant Seedling Dataset (sPSD), featuring nine common broadleaf weeds from arable land, and the Institute for Sustainable Agro-ecosystem Services (ISAS) dataset, which includes five common summer weeds in Japan. Consequently, the synthetic dataset generated by the proposed CA-GAN obtained an 82.63% recognition accuracy on the sPSD and 93.46% on the ISAS dataset. The Fréchet inception distance (FID) score test measures the similarity between a synthetic and real dataset, and it has been shown to correlate well with human judgments of the quality of synthetic samples. The synthetic dataset achieved a low FID score (20.95 on the sPSD and 24.31 on the ISAS dataset). Overall, the experimental results demonstrated that the proposed method outperformed previous state-of-the-art GAN models in terms of image quality, diversity, and discriminability, making it a promising approach for synthetic agricultural data generation. |
| first_indexed | 2024-04-24T16:11:20Z |
| format | Article |
| id | doaj.art-b01b321f0ce84a4892200b90329fef76 |
| institution | Directory Open Access Journal |
| issn | 2643-6515 |
| language | English |
| last_indexed | 2024-04-24T16:11:20Z |
| publishDate | 2024-01-01 |
| publisher | American Association for the Advancement of Science (AAAS) |
| record_format | Article |
| series | Plant Phenomics |
| spelling | doaj.art-b01b321f0ce84a4892200b90329fef762024-03-31T18:18:39ZengAmerican Association for the Advancement of Science (AAAS)Plant Phenomics2643-65152024-01-01610.34133/plantphenomics.0122Channel Attention GAN-Based Synthetic Weed Generation for Precise Weed IdentificationTang Li0Motoaki Asai1Yoichiro Kato2Yuya Fukano3Wei Guo4Graduate School of Agricultural and Life Sciences, The University of Tokyo, Tokyo 188-0002, Japan.Institute for Plant Protection, National Agriculture and Food Research Organization, Fukushima 960-2156, Japan.Graduate School of Agricultural and Life Sciences, The University of Tokyo, Tokyo 188-0002, Japan.Graduate School of Horticulture, Chiba University, Chiba 271-0092, Japan.Graduate School of Agricultural and Life Sciences, The University of Tokyo, Tokyo 188-0002, Japan.Weed is a major biological factor causing declines in crop yield. However, widespread herbicide application and indiscriminate weeding with soil disturbance are of great concern because of their environmental impacts. Site-specific weed management (SSWM) refers to a weed management strategy for digital agriculture that results in low energy loss. Deep learning is crucial for developing SSWM, as it distinguishes crops from weeds and identifies weed species. However, this technique requires substantial annotated data, which necessitates expertise in weed science and agronomy. In this study, we present a channel attention mechanism-driven generative adversarial network (CA-GAN) that can generate realistic synthetic weed data. The performance of the model was evaluated using two datasets: the public segmented Plant Seedling Dataset (sPSD), featuring nine common broadleaf weeds from arable land, and the Institute for Sustainable Agro-ecosystem Services (ISAS) dataset, which includes five common summer weeds in Japan. Consequently, the synthetic dataset generated by the proposed CA-GAN obtained an 82.63% recognition accuracy on the sPSD and 93.46% on the ISAS dataset. The Fréchet inception distance (FID) score test measures the similarity between a synthetic and real dataset, and it has been shown to correlate well with human judgments of the quality of synthetic samples. The synthetic dataset achieved a low FID score (20.95 on the sPSD and 24.31 on the ISAS dataset). Overall, the experimental results demonstrated that the proposed method outperformed previous state-of-the-art GAN models in terms of image quality, diversity, and discriminability, making it a promising approach for synthetic agricultural data generation.https://spj.science.org/doi/10.34133/plantphenomics.0122 |
| spellingShingle | Tang Li Motoaki Asai Yoichiro Kato Yuya Fukano Wei Guo Channel Attention GAN-Based Synthetic Weed Generation for Precise Weed Identification Plant Phenomics |
| title | Channel Attention GAN-Based Synthetic Weed Generation for Precise Weed Identification |
| title_full | Channel Attention GAN-Based Synthetic Weed Generation for Precise Weed Identification |
| title_fullStr | Channel Attention GAN-Based Synthetic Weed Generation for Precise Weed Identification |
| title_full_unstemmed | Channel Attention GAN-Based Synthetic Weed Generation for Precise Weed Identification |
| title_short | Channel Attention GAN-Based Synthetic Weed Generation for Precise Weed Identification |
| title_sort | channel attention gan based synthetic weed generation for precise weed identification |
| url | https://spj.science.org/doi/10.34133/plantphenomics.0122 |
| work_keys_str_mv | AT tangli channelattentionganbasedsyntheticweedgenerationforpreciseweedidentification AT motoakiasai channelattentionganbasedsyntheticweedgenerationforpreciseweedidentification AT yoichirokato channelattentionganbasedsyntheticweedgenerationforpreciseweedidentification AT yuyafukano channelattentionganbasedsyntheticweedgenerationforpreciseweedidentification AT weiguo channelattentionganbasedsyntheticweedgenerationforpreciseweedidentification |