High-throughput image-based plant stand count estimation using convolutional neural networks.
The landscape of farming and plant breeding is rapidly transforming due to the complex requirements of our world. The explosion of collectible data has started a revolution in agriculture to the point where innovation must occur. To a commercial organization, the accurate and efficient collection of...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2022-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0268762 |
| _version_ | 1811214702994259968 |
|---|---|
| author | Saeed Khaki Hieu Pham Zahra Khalilzadeh Arezoo Masoud Nima Safaei Ye Han Wade Kent Lizhi Wang |
| author_facet | Saeed Khaki Hieu Pham Zahra Khalilzadeh Arezoo Masoud Nima Safaei Ye Han Wade Kent Lizhi Wang |
| author_sort | Saeed Khaki |
| collection | DOAJ |
| description | The landscape of farming and plant breeding is rapidly transforming due to the complex requirements of our world. The explosion of collectible data has started a revolution in agriculture to the point where innovation must occur. To a commercial organization, the accurate and efficient collection of information is necessary to ensure that optimal decisions are made at key points of the breeding cycle. In particular, recent technology has enabled organizations to capture in-field images of crops to record color, shape, chemical properties, and disease susceptibility. However, this new challenge necessitates the need for advanced algorithms to accurately identify phenotypic traits. This work, advanced the current literature by developing an innovative deep learning algorithm, named DeepStand, for image-based counting of corn stands at early phenological stages. The proposed method adopts a truncated VGG-16 network to act as a feature extractor backbone. We then combine multiple feature maps with different dimensions to ensure the network is robust against size variation. Our extensive computational experiments demonstrate that our DeepStand framework accurately identifies corn stands and out-performs other cutting-edge methods. |
| first_indexed | 2024-04-12T06:09:08Z |
| format | Article |
| id | doaj.art-1f5802f3e6154876aeb97e7cd2e794fa |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-04-12T06:09:08Z |
| publishDate | 2022-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-1f5802f3e6154876aeb97e7cd2e794fa2022-12-22T03:44:46ZengPublic Library of Science (PLoS)PLoS ONE1932-62032022-01-01177e026876210.1371/journal.pone.0268762High-throughput image-based plant stand count estimation using convolutional neural networks.Saeed KhakiHieu PhamZahra KhalilzadehArezoo MasoudNima SafaeiYe HanWade KentLizhi WangThe landscape of farming and plant breeding is rapidly transforming due to the complex requirements of our world. The explosion of collectible data has started a revolution in agriculture to the point where innovation must occur. To a commercial organization, the accurate and efficient collection of information is necessary to ensure that optimal decisions are made at key points of the breeding cycle. In particular, recent technology has enabled organizations to capture in-field images of crops to record color, shape, chemical properties, and disease susceptibility. However, this new challenge necessitates the need for advanced algorithms to accurately identify phenotypic traits. This work, advanced the current literature by developing an innovative deep learning algorithm, named DeepStand, for image-based counting of corn stands at early phenological stages. The proposed method adopts a truncated VGG-16 network to act as a feature extractor backbone. We then combine multiple feature maps with different dimensions to ensure the network is robust against size variation. Our extensive computational experiments demonstrate that our DeepStand framework accurately identifies corn stands and out-performs other cutting-edge methods.https://doi.org/10.1371/journal.pone.0268762 |
| spellingShingle | Saeed Khaki Hieu Pham Zahra Khalilzadeh Arezoo Masoud Nima Safaei Ye Han Wade Kent Lizhi Wang High-throughput image-based plant stand count estimation using convolutional neural networks. PLoS ONE |
| title | High-throughput image-based plant stand count estimation using convolutional neural networks. |
| title_full | High-throughput image-based plant stand count estimation using convolutional neural networks. |
| title_fullStr | High-throughput image-based plant stand count estimation using convolutional neural networks. |
| title_full_unstemmed | High-throughput image-based plant stand count estimation using convolutional neural networks. |
| title_short | High-throughput image-based plant stand count estimation using convolutional neural networks. |
| title_sort | high throughput image based plant stand count estimation using convolutional neural networks |
| url | https://doi.org/10.1371/journal.pone.0268762 |
| work_keys_str_mv | AT saeedkhaki highthroughputimagebasedplantstandcountestimationusingconvolutionalneuralnetworks AT hieupham highthroughputimagebasedplantstandcountestimationusingconvolutionalneuralnetworks AT zahrakhalilzadeh highthroughputimagebasedplantstandcountestimationusingconvolutionalneuralnetworks AT arezoomasoud highthroughputimagebasedplantstandcountestimationusingconvolutionalneuralnetworks AT nimasafaei highthroughputimagebasedplantstandcountestimationusingconvolutionalneuralnetworks AT yehan highthroughputimagebasedplantstandcountestimationusingconvolutionalneuralnetworks AT wadekent highthroughputimagebasedplantstandcountestimationusingconvolutionalneuralnetworks AT lizhiwang highthroughputimagebasedplantstandcountestimationusingconvolutionalneuralnetworks |