A Fine-Tuned RetinaNet for Real-Time Lettuce Detection
The agricultural industry plays a vital role in the global demand for food production. Along with population growth, there is an increasing need for efficient farming practices that can maximize crop yields. Conventional methods of harvesting lettuce often rely on manual labor, which can be time-con...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Udayana University, Institute for Research and Community Services
2024-03-01
|
| Series: | Lontar Komputer |
| Online Access: | https://ojs.unud.ac.id/index.php/lontar/article/view/109624 |
| _version_ | 1827300506499809280 |
|---|---|
| author | Eko Wahyu Prasetyo Hidetaka Nambo |
| author_facet | Eko Wahyu Prasetyo Hidetaka Nambo |
| author_sort | Eko Wahyu Prasetyo |
| collection | DOAJ |
| description | The agricultural industry plays a vital role in the global demand for food production. Along with population growth, there is an increasing need for efficient farming practices that can maximize crop yields. Conventional methods of harvesting lettuce often rely on manual labor, which can be time-consuming, labor-intensive, and prone to human error. These challenges lead to research into automation technology, such as robotics, to improve harvest efficiency and reduce reliance on human intervention. Deep learning-based object detection models have shown impressive success in various computer vision tasks, such as object recognition. RetinaNet model can be trained to identify and localize lettuce accurately. However, the pre-trained models must be fine-tuned to adapt to the specific characteristics of lettuce, such as shape, size, and occlusion, to deploy object recognition models in real-world agricultural scenarios. Fine-tuning the models using lettuce-specific datasets can improve their accuracy and robustness for detecting and localizing lettuce. The data acquired for RetinaNet has the highest accuracy of 0.782, recall of 0.844, f1-score of 0.875, and mAP of 0,962. Metrics evaluate that the higher the score, the better the model performs. |
| first_indexed | 2024-04-24T16:06:00Z |
| format | Article |
| id | doaj.art-28d14ce7a9ef44c0b94855cee4c02e19 |
| institution | Directory Open Access Journal |
| issn | 2088-1541 2541-5832 |
| language | English |
| last_indexed | 2024-04-24T16:06:00Z |
| publishDate | 2024-03-01 |
| publisher | Udayana University, Institute for Research and Community Services |
| record_format | Article |
| series | Lontar Komputer |
| spelling | doaj.art-28d14ce7a9ef44c0b94855cee4c02e192024-04-01T02:58:36ZengUdayana University, Institute for Research and Community ServicesLontar Komputer2088-15412541-58322024-03-01151132510.24843/LKJITI.2024.v15.i01.p02109624A Fine-Tuned RetinaNet for Real-Time Lettuce DetectionEko Wahyu Prasetyo0Hidetaka Nambo1Universitas Merdeka MalangKakumamachi, Kanazawa, Ishikawa, JepangThe agricultural industry plays a vital role in the global demand for food production. Along with population growth, there is an increasing need for efficient farming practices that can maximize crop yields. Conventional methods of harvesting lettuce often rely on manual labor, which can be time-consuming, labor-intensive, and prone to human error. These challenges lead to research into automation technology, such as robotics, to improve harvest efficiency and reduce reliance on human intervention. Deep learning-based object detection models have shown impressive success in various computer vision tasks, such as object recognition. RetinaNet model can be trained to identify and localize lettuce accurately. However, the pre-trained models must be fine-tuned to adapt to the specific characteristics of lettuce, such as shape, size, and occlusion, to deploy object recognition models in real-world agricultural scenarios. Fine-tuning the models using lettuce-specific datasets can improve their accuracy and robustness for detecting and localizing lettuce. The data acquired for RetinaNet has the highest accuracy of 0.782, recall of 0.844, f1-score of 0.875, and mAP of 0,962. Metrics evaluate that the higher the score, the better the model performs.https://ojs.unud.ac.id/index.php/lontar/article/view/109624 |
| spellingShingle | Eko Wahyu Prasetyo Hidetaka Nambo A Fine-Tuned RetinaNet for Real-Time Lettuce Detection Lontar Komputer |
| title | A Fine-Tuned RetinaNet for Real-Time Lettuce Detection |
| title_full | A Fine-Tuned RetinaNet for Real-Time Lettuce Detection |
| title_fullStr | A Fine-Tuned RetinaNet for Real-Time Lettuce Detection |
| title_full_unstemmed | A Fine-Tuned RetinaNet for Real-Time Lettuce Detection |
| title_short | A Fine-Tuned RetinaNet for Real-Time Lettuce Detection |
| title_sort | fine tuned retinanet for real time lettuce detection |
| url | https://ojs.unud.ac.id/index.php/lontar/article/view/109624 |
| work_keys_str_mv | AT ekowahyuprasetyo afinetunedretinanetforrealtimelettucedetection AT hidetakanambo afinetunedretinanetforrealtimelettucedetection AT ekowahyuprasetyo finetunedretinanetforrealtimelettucedetection AT hidetakanambo finetunedretinanetforrealtimelettucedetection |