Automated abnormal potato plant detection system using deep learning models and portable video cameras
Potatoes are the world’s most important root and tuber crop. A diseased seed potato can produce approximately 10 potato tubers, and the disease can propagate through the seed potato production cycle. To promote stable potato production, quality seed potatoes that are healthy and disease-free should...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-12-01
|
| Series: | International Journal of Applied Earth Observations and Geoinformation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0303243421002166 |
| _version_ | 1828337945015222272 |
|---|---|
| author | Yu Oishi Harshana Habaragamuwa Yu Zhang Ryo Sugiura Kenji Asano Kotaro Akai Hiroyuki Shibata Taketo Fujimoto |
| author_facet | Yu Oishi Harshana Habaragamuwa Yu Zhang Ryo Sugiura Kenji Asano Kotaro Akai Hiroyuki Shibata Taketo Fujimoto |
| author_sort | Yu Oishi |
| collection | DOAJ |
| description | Potatoes are the world’s most important root and tuber crop. A diseased seed potato can produce approximately 10 potato tubers, and the disease can propagate through the seed potato production cycle. To promote stable potato production, quality seed potatoes that are healthy and disease-free should be supplied. The Japanese government established a propagation system for the production and distribution of seed potatoes. Experienced laborers are required in the fields for visual inspection and removal of abnormal plants during seed potato production. To aid visual detection, reduce labor effort, and improve assessment time, we developed an automated abnormal potato plant detection system that utilizes a portable video camera and deep learning models. The proposed system detects abnormal plants or leaves considering the stage of growth. It detects three cases: (i) abnormal potato plants in the early growth stage, (ii) abnormal potato plants in comparison to the surrounding plants, and (iii) abnormal potato leaves. For the abnormal and healthy potato plant classification, the accuracy was ~90%, and the average precision (AP) for detection was 78.2%. Furthermore, the classification accuracy of the abnormal and healthy potato leaf classification was 96.7%, and the AP for detection was 90.5%. Therefore, the proposed system can be used to detect abnormal potato plants. |
| first_indexed | 2024-04-13T22:20:42Z |
| format | Article |
| id | doaj.art-08822b9c204d4ec695bc59d6dd123a01 |
| institution | Directory Open Access Journal |
| issn | 1569-8432 |
| language | English |
| last_indexed | 2024-04-13T22:20:42Z |
| publishDate | 2021-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Applied Earth Observations and Geoinformation |
| spelling | doaj.art-08822b9c204d4ec695bc59d6dd123a012022-12-22T02:27:14ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322021-12-01104102509Automated abnormal potato plant detection system using deep learning models and portable video camerasYu Oishi0Harshana Habaragamuwa1Yu Zhang2Ryo Sugiura3Kenji Asano4Kotaro Akai5Hiroyuki Shibata6Taketo Fujimoto7Core Technology Research Headquarters, National Agriculture and Food Research Organization, 1-31-1 Kannondai, Tsukuba, Ibaraki 305-0856, Japan; Corresponding author.Core Technology Research Headquarters, National Agriculture and Food Research Organization, 1-31-1 Kannondai, Tsukuba, Ibaraki 305-0856, JapanCore Technology Research Headquarters, National Agriculture and Food Research Organization, 1-31-1 Kannondai, Tsukuba, Ibaraki 305-0856, JapanCore Technology Research Headquarters, National Agriculture and Food Research Organization, 1-31-1 Kannondai, Tsukuba, Ibaraki 305-0856, JapanHokkaido Agricultural Research Center, National Agriculture and Food Research Organization, 9-4 Shinseiminami, Memuro, Kasai, Hokkaido 082-0081, JapanHokkaido Agricultural Research Center, National Agriculture and Food Research Organization, 9-4 Shinseiminami, Memuro, Kasai, Hokkaido 082-0081, JapanTokachi Federation of Agricultural Cooperatives, Nokyoren Bldg. Nishi 3, Minami 7, 14, Obihiro, Hokaido 080-0013, JapanInstitute for Plant Protection, National Agriculture and Food Research Organization, 2-1-18 Kannondai, Tsukuba, Ibaraki 305-8666, JapanPotatoes are the world’s most important root and tuber crop. A diseased seed potato can produce approximately 10 potato tubers, and the disease can propagate through the seed potato production cycle. To promote stable potato production, quality seed potatoes that are healthy and disease-free should be supplied. The Japanese government established a propagation system for the production and distribution of seed potatoes. Experienced laborers are required in the fields for visual inspection and removal of abnormal plants during seed potato production. To aid visual detection, reduce labor effort, and improve assessment time, we developed an automated abnormal potato plant detection system that utilizes a portable video camera and deep learning models. The proposed system detects abnormal plants or leaves considering the stage of growth. It detects three cases: (i) abnormal potato plants in the early growth stage, (ii) abnormal potato plants in comparison to the surrounding plants, and (iii) abnormal potato leaves. For the abnormal and healthy potato plant classification, the accuracy was ~90%, and the average precision (AP) for detection was 78.2%. Furthermore, the classification accuracy of the abnormal and healthy potato leaf classification was 96.7%, and the AP for detection was 90.5%. Therefore, the proposed system can be used to detect abnormal potato plants.http://www.sciencedirect.com/science/article/pii/S0303243421002166Disease diagnosisPortable cameraDeep learningImage classificationObject detection |
| spellingShingle | Yu Oishi Harshana Habaragamuwa Yu Zhang Ryo Sugiura Kenji Asano Kotaro Akai Hiroyuki Shibata Taketo Fujimoto Automated abnormal potato plant detection system using deep learning models and portable video cameras International Journal of Applied Earth Observations and Geoinformation Disease diagnosis Portable camera Deep learning Image classification Object detection |
| title | Automated abnormal potato plant detection system using deep learning models and portable video cameras |
| title_full | Automated abnormal potato plant detection system using deep learning models and portable video cameras |
| title_fullStr | Automated abnormal potato plant detection system using deep learning models and portable video cameras |
| title_full_unstemmed | Automated abnormal potato plant detection system using deep learning models and portable video cameras |
| title_short | Automated abnormal potato plant detection system using deep learning models and portable video cameras |
| title_sort | automated abnormal potato plant detection system using deep learning models and portable video cameras |
| topic | Disease diagnosis Portable camera Deep learning Image classification Object detection |
| url | http://www.sciencedirect.com/science/article/pii/S0303243421002166 |
| work_keys_str_mv | AT yuoishi automatedabnormalpotatoplantdetectionsystemusingdeeplearningmodelsandportablevideocameras AT harshanahabaragamuwa automatedabnormalpotatoplantdetectionsystemusingdeeplearningmodelsandportablevideocameras AT yuzhang automatedabnormalpotatoplantdetectionsystemusingdeeplearningmodelsandportablevideocameras AT ryosugiura automatedabnormalpotatoplantdetectionsystemusingdeeplearningmodelsandportablevideocameras AT kenjiasano automatedabnormalpotatoplantdetectionsystemusingdeeplearningmodelsandportablevideocameras AT kotaroakai automatedabnormalpotatoplantdetectionsystemusingdeeplearningmodelsandportablevideocameras AT hiroyukishibata automatedabnormalpotatoplantdetectionsystemusingdeeplearningmodelsandportablevideocameras AT taketofujimoto automatedabnormalpotatoplantdetectionsystemusingdeeplearningmodelsandportablevideocameras |