Cassava stalk detection for a cassava harvesting robot based on YOLO v4 and Mask R-CNN
The quality of fresh cassava roots can be increased through the use of precision equipment. As a first step towards developing an automatic cassava root cutting system, this study demonstrates the use of a computer vision system with deep learning for cassava stalk detection. An RGB image of a cass...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PAGEPress Publications
2023-08-01
|
| Series: | Journal of Agricultural Engineering |
| Subjects: | |
| Online Access: | https://agroengineering.org/index.php/jae/article/view/1301 |
| _version_ | 1797767003608449024 |
|---|---|
| author | Thanaporn Singhpoo Khwantri Saengprachatanarug Seree Wongpichet Jetsada Posom Kanda Runapongsa Saikaew |
| author_facet | Thanaporn Singhpoo Khwantri Saengprachatanarug Seree Wongpichet Jetsada Posom Kanda Runapongsa Saikaew |
| author_sort | Thanaporn Singhpoo |
| collection | DOAJ |
| description |
The quality of fresh cassava roots can be increased through the use of precision equipment. As a first step towards developing an automatic cassava root cutting system, this study demonstrates the use of a computer vision system with deep learning for cassava stalk detection. An RGB image of a cassava tree mounted on a cassava-pulling machine was captured, and the YOLO v4 model and two Mask R-CNN models with ResNet 101 and ResNet 50 base architectures were employed to train the weights to predict the position of the cassava stalk. One hundred test images of stalks of various shapes and sizes were used to determine the grasping point and inclination, and the results from manual annotation were compared with the predicted results. Regarding localisation, Mask R-CNN with ResNet 101 gave a significantly higher performance than the other models, with an F1 score and a mean IoU of 0.81 and 0.70, respectively. YOLO v4 showed the highest correlation for the x- and y-coordinates for the prediction of the grasping point, with values for R2 of 0.89 and 0.53, respectively. For inclination prediction, Mask R-CNN with ResNet 101 and Mask R-CNN with ResNet 50 gave the same level of correlation, with values for R2 of 0.50 and 0.61, respectively. These results were acceptable for use as design criteria for developing a cassava rootcutting robot.
|
| first_indexed | 2024-03-12T20:32:27Z |
| format | Article |
| id | doaj.art-9727524864fe4e4d8001e64cacc41f44 |
| institution | Directory Open Access Journal |
| issn | 1974-7071 2239-6268 |
| language | English |
| last_indexed | 2024-03-12T20:32:27Z |
| publishDate | 2023-08-01 |
| publisher | PAGEPress Publications |
| record_format | Article |
| series | Journal of Agricultural Engineering |
| spelling | doaj.art-9727524864fe4e4d8001e64cacc41f442023-08-01T19:29:56ZengPAGEPress PublicationsJournal of Agricultural Engineering1974-70712239-62682023-08-0154210.4081/jae.2023.1301Cassava stalk detection for a cassava harvesting robot based on YOLO v4 and Mask R-CNNThanaporn Singhpoo0Khwantri Saengprachatanarug1Seree Wongpichet2Jetsada Posom3Kanda Runapongsa Saikaew4Department of Agricultural Engineering, Faculty of Engineering, Khon Kaen UniversityDepartment of Agricultural Engineering, Faculty of Engineering, Khon Kaen University; The Northeast Thailand Cane and Sugar Research Center (NECS), Khon Kaen UniversityThe Northeast Thailand Cane and Sugar Research Center (NECS), Khon Kaen UniversityDepartment of Agricultural Engineering, Faculty of Engineering, Khon Kaen University; The Northeast Thailand Cane and Sugar Research Center (NECS), Khon Kaen UniversityDepartment of Computer Engineering, Faculty of Engineering, Khon Kaen University The quality of fresh cassava roots can be increased through the use of precision equipment. As a first step towards developing an automatic cassava root cutting system, this study demonstrates the use of a computer vision system with deep learning for cassava stalk detection. An RGB image of a cassava tree mounted on a cassava-pulling machine was captured, and the YOLO v4 model and two Mask R-CNN models with ResNet 101 and ResNet 50 base architectures were employed to train the weights to predict the position of the cassava stalk. One hundred test images of stalks of various shapes and sizes were used to determine the grasping point and inclination, and the results from manual annotation were compared with the predicted results. Regarding localisation, Mask R-CNN with ResNet 101 gave a significantly higher performance than the other models, with an F1 score and a mean IoU of 0.81 and 0.70, respectively. YOLO v4 showed the highest correlation for the x- and y-coordinates for the prediction of the grasping point, with values for R2 of 0.89 and 0.53, respectively. For inclination prediction, Mask R-CNN with ResNet 101 and Mask R-CNN with ResNet 50 gave the same level of correlation, with values for R2 of 0.50 and 0.61, respectively. These results were acceptable for use as design criteria for developing a cassava rootcutting robot. https://agroengineering.org/index.php/jae/article/view/1301Automatic harvestercassava rootcomputer visioncrop detectionstalk detection |
| spellingShingle | Thanaporn Singhpoo Khwantri Saengprachatanarug Seree Wongpichet Jetsada Posom Kanda Runapongsa Saikaew Cassava stalk detection for a cassava harvesting robot based on YOLO v4 and Mask R-CNN Journal of Agricultural Engineering Automatic harvester cassava root computer vision crop detection stalk detection |
| title | Cassava stalk detection for a cassava harvesting robot based on YOLO v4 and Mask R-CNN |
| title_full | Cassava stalk detection for a cassava harvesting robot based on YOLO v4 and Mask R-CNN |
| title_fullStr | Cassava stalk detection for a cassava harvesting robot based on YOLO v4 and Mask R-CNN |
| title_full_unstemmed | Cassava stalk detection for a cassava harvesting robot based on YOLO v4 and Mask R-CNN |
| title_short | Cassava stalk detection for a cassava harvesting robot based on YOLO v4 and Mask R-CNN |
| title_sort | cassava stalk detection for a cassava harvesting robot based on yolo v4 and mask r cnn |
| topic | Automatic harvester cassava root computer vision crop detection stalk detection |
| url | https://agroengineering.org/index.php/jae/article/view/1301 |
| work_keys_str_mv | AT thanapornsinghpoo cassavastalkdetectionforacassavaharvestingrobotbasedonyolov4andmaskrcnn AT khwantrisaengprachatanarug cassavastalkdetectionforacassavaharvestingrobotbasedonyolov4andmaskrcnn AT sereewongpichet cassavastalkdetectionforacassavaharvestingrobotbasedonyolov4andmaskrcnn AT jetsadaposom cassavastalkdetectionforacassavaharvestingrobotbasedonyolov4andmaskrcnn AT kandarunapongsasaikaew cassavastalkdetectionforacassavaharvestingrobotbasedonyolov4andmaskrcnn |