Aerial imagery paddy seedlings inspection using deep learning
In recent years complex food security issues caused by climatic changes, limitations in human labour, and increasing production costs require a strategic approach in addressing problems. The emergence of artificial intelligence due to the capability of recent advances in computing architectures coul...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Published: |
Multidisciplinary Digital Publishing Institute
2022
|
| _version_ | 1811137552007036928 |
|---|---|
| author | Anuar, Mohamed Marzhar Abdul Halin, Alfian Perumal, Thinagaran Kalantar, Bahareh |
| author_facet | Anuar, Mohamed Marzhar Abdul Halin, Alfian Perumal, Thinagaran Kalantar, Bahareh |
| author_sort | Anuar, Mohamed Marzhar |
| collection | UPM |
| description | In recent years complex food security issues caused by climatic changes, limitations in human labour, and increasing production costs require a strategic approach in addressing problems. The emergence of artificial intelligence due to the capability of recent advances in computing architectures could become a new alternative to existing solutions. Deep learning algorithms in computer vision for image classification and object detection can facilitate the agriculture industry, especially in paddy cultivation, to alleviate human efforts in laborious, burdensome, and repetitive tasks. Optimal planting density is a crucial factor for paddy cultivation as it will influence the quality and quantity of production. There have been several studies involving planting density using computer vision and remote sensing approaches. While most of the studies have shown promising results, they have disadvantages and show room for improvement. One of the disadvantages is that the studies aim to detect and count all the paddy seedlings to determine planting density. The defective paddy seedlings’ locations are not pointed out to help farmers during the sowing process. In this work we aimed to explore several deep convolutional neural networks (DCNN) models to determine which one performs the best for defective paddy seedling detection using aerial imagery. Thus, we evaluated the accuracy, robustness, and inference latency of one- and two-stage pretrained object detectors combined with state-of-the-art feature extractors such as EfficientNet, ResNet50, and MobilenetV2 as a backbone. We also investigated the effect of transfer learning with fine-tuning on the performance of the aforementioned pretrained models. Experimental results showed that our proposed methods were capable of detecting the defective paddy rice seedlings with the highest precision and an F1-Score of 0.83 and 0.77, respectively, using a one-stage pretrained object detector called EfficientDet-D1 EficientNet. |
| first_indexed | 2024-09-25T03:36:06Z |
| format | Article |
| id | upm.eprints-100142 |
| institution | Universiti Putra Malaysia |
| last_indexed | 2024-09-25T03:36:06Z |
| publishDate | 2022 |
| publisher | Multidisciplinary Digital Publishing Institute |
| record_format | dspace |
| spelling | upm.eprints-1001422024-07-17T02:58:56Z http://psasir.upm.edu.my/id/eprint/100142/ Aerial imagery paddy seedlings inspection using deep learning Anuar, Mohamed Marzhar Abdul Halin, Alfian Perumal, Thinagaran Kalantar, Bahareh In recent years complex food security issues caused by climatic changes, limitations in human labour, and increasing production costs require a strategic approach in addressing problems. The emergence of artificial intelligence due to the capability of recent advances in computing architectures could become a new alternative to existing solutions. Deep learning algorithms in computer vision for image classification and object detection can facilitate the agriculture industry, especially in paddy cultivation, to alleviate human efforts in laborious, burdensome, and repetitive tasks. Optimal planting density is a crucial factor for paddy cultivation as it will influence the quality and quantity of production. There have been several studies involving planting density using computer vision and remote sensing approaches. While most of the studies have shown promising results, they have disadvantages and show room for improvement. One of the disadvantages is that the studies aim to detect and count all the paddy seedlings to determine planting density. The defective paddy seedlings’ locations are not pointed out to help farmers during the sowing process. In this work we aimed to explore several deep convolutional neural networks (DCNN) models to determine which one performs the best for defective paddy seedling detection using aerial imagery. Thus, we evaluated the accuracy, robustness, and inference latency of one- and two-stage pretrained object detectors combined with state-of-the-art feature extractors such as EfficientNet, ResNet50, and MobilenetV2 as a backbone. We also investigated the effect of transfer learning with fine-tuning on the performance of the aforementioned pretrained models. Experimental results showed that our proposed methods were capable of detecting the defective paddy rice seedlings with the highest precision and an F1-Score of 0.83 and 0.77, respectively, using a one-stage pretrained object detector called EfficientDet-D1 EficientNet. Multidisciplinary Digital Publishing Institute 2022-01-07 Article PeerReviewed Anuar, Mohamed Marzhar and Abdul Halin, Alfian and Perumal, Thinagaran and Kalantar, Bahareh (2022) Aerial imagery paddy seedlings inspection using deep learning. Remote Sens, 14 (2). art. no. 274. pp. 1-17. ISSN 2072-4292 https://www.mdpi.com/2072-4292/14/2/274 10.3390/rs14020274 |
| spellingShingle | Anuar, Mohamed Marzhar Abdul Halin, Alfian Perumal, Thinagaran Kalantar, Bahareh Aerial imagery paddy seedlings inspection using deep learning |
| title | Aerial imagery paddy seedlings inspection using deep learning |
| title_full | Aerial imagery paddy seedlings inspection using deep learning |
| title_fullStr | Aerial imagery paddy seedlings inspection using deep learning |
| title_full_unstemmed | Aerial imagery paddy seedlings inspection using deep learning |
| title_short | Aerial imagery paddy seedlings inspection using deep learning |
| title_sort | aerial imagery paddy seedlings inspection using deep learning |
| work_keys_str_mv | AT anuarmohamedmarzhar aerialimagerypaddyseedlingsinspectionusingdeeplearning AT abdulhalinalfian aerialimagerypaddyseedlingsinspectionusingdeeplearning AT perumalthinagaran aerialimagerypaddyseedlingsinspectionusingdeeplearning AT kalantarbahareh aerialimagerypaddyseedlingsinspectionusingdeeplearning |