A Lightweight YOLO Model for Rice Panicle Detection in Fields Based on UAV Aerial Images
Accurate counting of the number of rice panicles per unit area is essential for rice yield estimation. However, intensive planting, complex growth environments, and the overlapping of rice panicles and leaves in paddy fields pose significant challenges for precise panicle detection. In this study, w...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Drones |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-446X/9/1/1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588645526142976 |
|---|---|
| author | Zixuan Song Songtao Ban Dong Hu Mengyuan Xu Tao Yuan Xiuguo Zheng Huifeng Sun Sheng Zhou Minglu Tian Linyi Li |
| author_facet | Zixuan Song Songtao Ban Dong Hu Mengyuan Xu Tao Yuan Xiuguo Zheng Huifeng Sun Sheng Zhou Minglu Tian Linyi Li |
| author_sort | Zixuan Song |
| collection | DOAJ |
| description | Accurate counting of the number of rice panicles per unit area is essential for rice yield estimation. However, intensive planting, complex growth environments, and the overlapping of rice panicles and leaves in paddy fields pose significant challenges for precise panicle detection. In this study, we propose YOLO-Rice, a rice panicle detection model based on the You Only Look Once version 8 nano (YOLOv8n). The model employs FasterNet, a lightweight backbone network, and incorporates a two-layer detection head to improve rice panicle detection performance while reducing the overall model size. Additionally, we integrate a Normalization-based Attention Module (NAM) and introduce a Minimum Point Distance-based IoU (MPDIoU) loss function to further improve the detection capability. The results demonstrate that the YOLO-Rice model achieved an object detection accuracy of 93.5% and a mean Average Precision (mAP) of 95.9%, with model parameters reduced to 32.6% of the original YOLOv8n model. When deployed on a Raspberry Pi 5, YOLO-Rice achieved 2.233 frames per second (FPS) on full-sized images, reducing the average detection time per image by 81.7% compared to YOLOv8n. By decreasing the input image size, the FPS increased to 11.36. Overall, the YOLO-Rice model demonstrates enhanced robustness and real-time detection capabilities, achieving higher accuracy and making it well-suited for deployment on low-cost portable devices. This model offers effective support for rice yield estimation, as well as for cultivation and breeding applications. |
| format | Article |
| id | doaj-art-ae646cc0c3c64770b68d35e778014251 |
| institution | Kabale University |
| issn | 2504-446X |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Drones |
| spelling | doaj-art-ae646cc0c3c64770b68d35e7780142512025-01-24T13:29:35ZengMDPI AGDrones2504-446X2024-12-0191110.3390/drones9010001A Lightweight YOLO Model for Rice Panicle Detection in Fields Based on UAV Aerial ImagesZixuan Song0Songtao Ban1Dong Hu2Mengyuan Xu3Tao Yuan4Xiuguo Zheng5Huifeng Sun6Sheng Zhou7Minglu Tian8Linyi Li9College of Information Technology, Shanghai Ocean University, Shanghai 201306, ChinaInstitute of Agricultural Science and Technology Information, Shanghai Academy of Agricultural Sciences, Shanghai 201403, ChinaInstitute of Agricultural Science and Technology Information, Shanghai Academy of Agricultural Sciences, Shanghai 201403, ChinaInstitute of Agricultural Science and Technology Information, Shanghai Academy of Agricultural Sciences, Shanghai 201403, ChinaInstitute of Agricultural Science and Technology Information, Shanghai Academy of Agricultural Sciences, Shanghai 201403, ChinaInstitute of Agricultural Science and Technology Information, Shanghai Academy of Agricultural Sciences, Shanghai 201403, ChinaEco-Environmental Protection Research Institute, Shanghai Academy of Agricultural Science, Shanghai 201403, ChinaEco-Environmental Protection Research Institute, Shanghai Academy of Agricultural Science, Shanghai 201403, ChinaInstitute of Agricultural Science and Technology Information, Shanghai Academy of Agricultural Sciences, Shanghai 201403, ChinaInstitute of Agricultural Science and Technology Information, Shanghai Academy of Agricultural Sciences, Shanghai 201403, ChinaAccurate counting of the number of rice panicles per unit area is essential for rice yield estimation. However, intensive planting, complex growth environments, and the overlapping of rice panicles and leaves in paddy fields pose significant challenges for precise panicle detection. In this study, we propose YOLO-Rice, a rice panicle detection model based on the You Only Look Once version 8 nano (YOLOv8n). The model employs FasterNet, a lightweight backbone network, and incorporates a two-layer detection head to improve rice panicle detection performance while reducing the overall model size. Additionally, we integrate a Normalization-based Attention Module (NAM) and introduce a Minimum Point Distance-based IoU (MPDIoU) loss function to further improve the detection capability. The results demonstrate that the YOLO-Rice model achieved an object detection accuracy of 93.5% and a mean Average Precision (mAP) of 95.9%, with model parameters reduced to 32.6% of the original YOLOv8n model. When deployed on a Raspberry Pi 5, YOLO-Rice achieved 2.233 frames per second (FPS) on full-sized images, reducing the average detection time per image by 81.7% compared to YOLOv8n. By decreasing the input image size, the FPS increased to 11.36. Overall, the YOLO-Rice model demonstrates enhanced robustness and real-time detection capabilities, achieving higher accuracy and making it well-suited for deployment on low-cost portable devices. This model offers effective support for rice yield estimation, as well as for cultivation and breeding applications.https://www.mdpi.com/2504-446X/9/1/1rice panicle detectionYOLOv8FasterNetlightweight network |
| spellingShingle | Zixuan Song Songtao Ban Dong Hu Mengyuan Xu Tao Yuan Xiuguo Zheng Huifeng Sun Sheng Zhou Minglu Tian Linyi Li A Lightweight YOLO Model for Rice Panicle Detection in Fields Based on UAV Aerial Images Drones rice panicle detection YOLOv8 FasterNet lightweight network |
| title | A Lightweight YOLO Model for Rice Panicle Detection in Fields Based on UAV Aerial Images |
| title_full | A Lightweight YOLO Model for Rice Panicle Detection in Fields Based on UAV Aerial Images |
| title_fullStr | A Lightweight YOLO Model for Rice Panicle Detection in Fields Based on UAV Aerial Images |
| title_full_unstemmed | A Lightweight YOLO Model for Rice Panicle Detection in Fields Based on UAV Aerial Images |
| title_short | A Lightweight YOLO Model for Rice Panicle Detection in Fields Based on UAV Aerial Images |
| title_sort | lightweight yolo model for rice panicle detection in fields based on uav aerial images |
| topic | rice panicle detection YOLOv8 FasterNet lightweight network |
| url | https://www.mdpi.com/2504-446X/9/1/1 |
| work_keys_str_mv | AT zixuansong alightweightyolomodelforricepanicledetectioninfieldsbasedonuavaerialimages AT songtaoban alightweightyolomodelforricepanicledetectioninfieldsbasedonuavaerialimages AT donghu alightweightyolomodelforricepanicledetectioninfieldsbasedonuavaerialimages AT mengyuanxu alightweightyolomodelforricepanicledetectioninfieldsbasedonuavaerialimages AT taoyuan alightweightyolomodelforricepanicledetectioninfieldsbasedonuavaerialimages AT xiuguozheng alightweightyolomodelforricepanicledetectioninfieldsbasedonuavaerialimages AT huifengsun alightweightyolomodelforricepanicledetectioninfieldsbasedonuavaerialimages AT shengzhou alightweightyolomodelforricepanicledetectioninfieldsbasedonuavaerialimages AT minglutian alightweightyolomodelforricepanicledetectioninfieldsbasedonuavaerialimages AT linyili alightweightyolomodelforricepanicledetectioninfieldsbasedonuavaerialimages AT zixuansong lightweightyolomodelforricepanicledetectioninfieldsbasedonuavaerialimages AT songtaoban lightweightyolomodelforricepanicledetectioninfieldsbasedonuavaerialimages AT donghu lightweightyolomodelforricepanicledetectioninfieldsbasedonuavaerialimages AT mengyuanxu lightweightyolomodelforricepanicledetectioninfieldsbasedonuavaerialimages AT taoyuan lightweightyolomodelforricepanicledetectioninfieldsbasedonuavaerialimages AT xiuguozheng lightweightyolomodelforricepanicledetectioninfieldsbasedonuavaerialimages AT huifengsun lightweightyolomodelforricepanicledetectioninfieldsbasedonuavaerialimages AT shengzhou lightweightyolomodelforricepanicledetectioninfieldsbasedonuavaerialimages AT minglutian lightweightyolomodelforricepanicledetectioninfieldsbasedonuavaerialimages AT linyili lightweightyolomodelforricepanicledetectioninfieldsbasedonuavaerialimages |