Crop Identification and Growth Stage Determination for Autonomous Navigation of Agricultural Robots
This study introduces two methods for crop identification and growth stage determination, focused primarily on enabling mobile robot navigation. These methods include a two-phase approach involving separate models for crop and growth stage identification and a one-phase method employing a single mod...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Agronomy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4395/13/12/2873 |
| _version_ | 1797382412862226432 |
|---|---|
| author | Eloisa Cortinas Luis Emmi Pablo Gonzalez-de-Santos |
| author_facet | Eloisa Cortinas Luis Emmi Pablo Gonzalez-de-Santos |
| author_sort | Eloisa Cortinas |
| collection | DOAJ |
| description | This study introduces two methods for crop identification and growth stage determination, focused primarily on enabling mobile robot navigation. These methods include a two-phase approach involving separate models for crop and growth stage identification and a one-phase method employing a single model capable of handling all crops and growth stages. The methods were validated with maize and sugar beet field images, demonstrating the effectiveness of both approaches. The one-phase approach proved to be advantageous for scenarios with a limited variety of crops, allowing, with a single model, to recognize both the type and growth state of the crop and showed an overall Mean Average Precision (mAP) of about 67.50%. Moreover, the two-phase method recognized the crop type first, achieving an overall mAP of about 74.2%, with maize detection performing exceptionally well at 77.6%. However, when it came to identifying the specific maize growth state, the mAP was only able to reach 61.3% due to some difficulties arising when accurately categorizing maize growth stages with six and eight leaves. On the other hand, the two-phase approach has been proven to be more flexible and scalable, making it a better choice for systems accommodating a wide range of crops. |
| first_indexed | 2024-03-08T21:05:03Z |
| format | Article |
| id | doaj.art-f0314f965fca458dbc7c70f52f38e9e5 |
| institution | Directory Open Access Journal |
| issn | 2073-4395 |
| language | English |
| last_indexed | 2024-03-08T21:05:03Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj.art-f0314f965fca458dbc7c70f52f38e9e52023-12-22T13:46:06ZengMDPI AGAgronomy2073-43952023-11-011312287310.3390/agronomy13122873Crop Identification and Growth Stage Determination for Autonomous Navigation of Agricultural RobotsEloisa Cortinas0Luis Emmi1Pablo Gonzalez-de-Santos2Centre for Automation and Robotics (UPM-CSIC), Arganda del Rey, 28500 Madrid, SpainCentre for Automation and Robotics (UPM-CSIC), Arganda del Rey, 28500 Madrid, SpainCentre for Automation and Robotics (UPM-CSIC), Arganda del Rey, 28500 Madrid, SpainThis study introduces two methods for crop identification and growth stage determination, focused primarily on enabling mobile robot navigation. These methods include a two-phase approach involving separate models for crop and growth stage identification and a one-phase method employing a single model capable of handling all crops and growth stages. The methods were validated with maize and sugar beet field images, demonstrating the effectiveness of both approaches. The one-phase approach proved to be advantageous for scenarios with a limited variety of crops, allowing, with a single model, to recognize both the type and growth state of the crop and showed an overall Mean Average Precision (mAP) of about 67.50%. Moreover, the two-phase method recognized the crop type first, achieving an overall mAP of about 74.2%, with maize detection performing exceptionally well at 77.6%. However, when it came to identifying the specific maize growth state, the mAP was only able to reach 61.3% due to some difficulties arising when accurately categorizing maize growth stages with six and eight leaves. On the other hand, the two-phase approach has been proven to be more flexible and scalable, making it a better choice for systems accommodating a wide range of crops.https://www.mdpi.com/2073-4395/13/12/2873object detectionprecision agricultureagricultural robotscrop identification |
| spellingShingle | Eloisa Cortinas Luis Emmi Pablo Gonzalez-de-Santos Crop Identification and Growth Stage Determination for Autonomous Navigation of Agricultural Robots Agronomy object detection precision agriculture agricultural robots crop identification |
| title | Crop Identification and Growth Stage Determination for Autonomous Navigation of Agricultural Robots |
| title_full | Crop Identification and Growth Stage Determination for Autonomous Navigation of Agricultural Robots |
| title_fullStr | Crop Identification and Growth Stage Determination for Autonomous Navigation of Agricultural Robots |
| title_full_unstemmed | Crop Identification and Growth Stage Determination for Autonomous Navigation of Agricultural Robots |
| title_short | Crop Identification and Growth Stage Determination for Autonomous Navigation of Agricultural Robots |
| title_sort | crop identification and growth stage determination for autonomous navigation of agricultural robots |
| topic | object detection precision agriculture agricultural robots crop identification |
| url | https://www.mdpi.com/2073-4395/13/12/2873 |
| work_keys_str_mv | AT eloisacortinas cropidentificationandgrowthstagedeterminationforautonomousnavigationofagriculturalrobots AT luisemmi cropidentificationandgrowthstagedeterminationforautonomousnavigationofagriculturalrobots AT pablogonzalezdesantos cropidentificationandgrowthstagedeterminationforautonomousnavigationofagriculturalrobots |