Automated Health Estimation of <i>Capsicum annuum</i> L. Crops by Means of Deep Learning and RGB Aerial Images
Recently, the use of small UAVs for monitoring agricultural land areas has been increasingly used by agricultural producers in order to improve crop yields. However, correctly interpreting the collected imagery data is still a challenging task. In this study, an automated pipeline for monitoring <...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/19/4943 |
| _version_ | 1827653162721345536 |
|---|---|
| author | Jesús A. Sosa-Herrera Nohemi Alvarez-Jarquin Nestor M. Cid-Garcia Daniela J. López-Araujo Moisés R. Vallejo-Pérez |
| author_facet | Jesús A. Sosa-Herrera Nohemi Alvarez-Jarquin Nestor M. Cid-Garcia Daniela J. López-Araujo Moisés R. Vallejo-Pérez |
| author_sort | Jesús A. Sosa-Herrera |
| collection | DOAJ |
| description | Recently, the use of small UAVs for monitoring agricultural land areas has been increasingly used by agricultural producers in order to improve crop yields. However, correctly interpreting the collected imagery data is still a challenging task. In this study, an automated pipeline for monitoring <i>C. Annuum</i> crops based on a deep learning model is implemented. The system is capable of performing inferences on the health status of individual plants, and to determine their locations and shapes in a georeferenced orthomosaic. Accuracy achieved on the classification task was 94.5. AP values among classes were in the range of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>[</mo><mn>63</mn><mo>,</mo><mn>100</mn><mo>]</mo></mrow></semantics></math></inline-formula> for plant location boxes, and in <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>[</mo><mn>40</mn><mo>,</mo><mn>80</mn><mo>]</mo></mrow></semantics></math></inline-formula> for foliar area predictions. The methodology requires only RGB images, and so, it can be replicated for the monitoring of other types of crops by only employing consumer-grade UAVs. A comparison with random forest and large-scale mean shift segmentation methods which use predetermined features is presented. NDVI results obtained with multispectral equipment are also included. |
| first_indexed | 2024-03-09T21:13:08Z |
| format | Article |
| id | doaj.art-8f745b0ba6c14b18bbd00f913e34c5a8 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T21:13:08Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-8f745b0ba6c14b18bbd00f913e34c5a82023-11-23T21:41:18ZengMDPI AGRemote Sensing2072-42922022-10-011419494310.3390/rs14194943Automated Health Estimation of <i>Capsicum annuum</i> L. Crops by Means of Deep Learning and RGB Aerial ImagesJesús A. Sosa-Herrera0Nohemi Alvarez-Jarquin1Nestor M. Cid-Garcia2Daniela J. López-Araujo3Moisés R. Vallejo-Pérez4Laboratorio Nacional de Geointeligencia, CONACYT-Centro de Investigación En Ciencias de Información Geospacial, Aguascalientes 20313, MexicoLaboratorio Nacional de Geointeligencia, CONACYT-Centro de Investigación En Ciencias de Información Geospacial, Aguascalientes 20313, MexicoLaboratorio Nacional de Geointeligencia, CONACYT-Centro de Investigación En Ciencias de Información Geospacial, Aguascalientes 20313, MexicoLaboratorio Nacional de Geointeligencia, CONACYT-Centro de Investigación En Ciencias de Información Geospacial, Aguascalientes 20313, MexicoCoordinación para la Innovación y Aplicación de la Ciencia y la Tecnología (CIACYT), CONACYT-Universidad Autónoma de San Luis Potosí, San Luis Potosí 78000, MexicoRecently, the use of small UAVs for monitoring agricultural land areas has been increasingly used by agricultural producers in order to improve crop yields. However, correctly interpreting the collected imagery data is still a challenging task. In this study, an automated pipeline for monitoring <i>C. Annuum</i> crops based on a deep learning model is implemented. The system is capable of performing inferences on the health status of individual plants, and to determine their locations and shapes in a georeferenced orthomosaic. Accuracy achieved on the classification task was 94.5. AP values among classes were in the range of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>[</mo><mn>63</mn><mo>,</mo><mn>100</mn><mo>]</mo></mrow></semantics></math></inline-formula> for plant location boxes, and in <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>[</mo><mn>40</mn><mo>,</mo><mn>80</mn><mo>]</mo></mrow></semantics></math></inline-formula> for foliar area predictions. The methodology requires only RGB images, and so, it can be replicated for the monitoring of other types of crops by only employing consumer-grade UAVs. A comparison with random forest and large-scale mean shift segmentation methods which use predetermined features is presented. NDVI results obtained with multispectral equipment are also included.https://www.mdpi.com/2072-4292/14/19/4943deep learningMask RCNNprecision agricultureUAVs |
| spellingShingle | Jesús A. Sosa-Herrera Nohemi Alvarez-Jarquin Nestor M. Cid-Garcia Daniela J. López-Araujo Moisés R. Vallejo-Pérez Automated Health Estimation of <i>Capsicum annuum</i> L. Crops by Means of Deep Learning and RGB Aerial Images Remote Sensing deep learning Mask RCNN precision agriculture UAVs |
| title | Automated Health Estimation of <i>Capsicum annuum</i> L. Crops by Means of Deep Learning and RGB Aerial Images |
| title_full | Automated Health Estimation of <i>Capsicum annuum</i> L. Crops by Means of Deep Learning and RGB Aerial Images |
| title_fullStr | Automated Health Estimation of <i>Capsicum annuum</i> L. Crops by Means of Deep Learning and RGB Aerial Images |
| title_full_unstemmed | Automated Health Estimation of <i>Capsicum annuum</i> L. Crops by Means of Deep Learning and RGB Aerial Images |
| title_short | Automated Health Estimation of <i>Capsicum annuum</i> L. Crops by Means of Deep Learning and RGB Aerial Images |
| title_sort | automated health estimation of i capsicum annuum i l crops by means of deep learning and rgb aerial images |
| topic | deep learning Mask RCNN precision agriculture UAVs |
| url | https://www.mdpi.com/2072-4292/14/19/4943 |
| work_keys_str_mv | AT jesusasosaherrera automatedhealthestimationoficapsicumannuumilcropsbymeansofdeeplearningandrgbaerialimages AT nohemialvarezjarquin automatedhealthestimationoficapsicumannuumilcropsbymeansofdeeplearningandrgbaerialimages AT nestormcidgarcia automatedhealthestimationoficapsicumannuumilcropsbymeansofdeeplearningandrgbaerialimages AT danielajlopezaraujo automatedhealthestimationoficapsicumannuumilcropsbymeansofdeeplearningandrgbaerialimages AT moisesrvallejoperez automatedhealthestimationoficapsicumannuumilcropsbymeansofdeeplearningandrgbaerialimages |