Weed Detection from Unmanned Aerial Vehicle Imagery Using Deep Learning—A Comparison between High-End and Low-Cost Multispectral Sensors
In order to meet the increasing demand for crops under challenging climate conditions, efficient and sustainable cultivation strategies are becoming essential in agriculture. Targeted herbicide use reduces environmental pollution and effectively controls weeds as a major cause of yield reduction. Th...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/5/1544 |
| _version_ | 1797263852598984704 |
|---|---|
| author | Anna Teresa Seiche Lucas Wittstruck Thomas Jarmer |
| author_facet | Anna Teresa Seiche Lucas Wittstruck Thomas Jarmer |
| author_sort | Anna Teresa Seiche |
| collection | DOAJ |
| description | In order to meet the increasing demand for crops under challenging climate conditions, efficient and sustainable cultivation strategies are becoming essential in agriculture. Targeted herbicide use reduces environmental pollution and effectively controls weeds as a major cause of yield reduction. The key requirement is a reliable weed detection system that is accessible to a wide range of end users. This research paper introduces a self-built, low-cost, multispectral camera system and evaluates it against the high-end MicaSense Altum system. Pixel-based weed and crop classification was performed on UAV datasets collected with both sensors in maize using a U-Net. The training and testing data were generated via an index-based thresholding approach followed by annotation. As a result, the F1-score for the weed class reached 82% on the Altum system and 76% on the low-cost system, with recall values of 75% and 68%, respectively. Misclassifications occurred on the low-cost system images for small weeds and overlaps, with minor oversegmentation. However, with a precision of 90%, the results show great potential for application in automated weed control. The proposed system thereby enables sustainable precision farming for the general public. In future research, its spectral properties, as well as its use on different crops with real-time on-board processing, should be further investigated. |
| first_indexed | 2024-04-25T00:19:36Z |
| format | Article |
| id | doaj.art-0011786997d7475fb07ad6f9844bc7a1 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-25T00:19:36Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-0011786997d7475fb07ad6f9844bc7a12024-03-12T16:55:10ZengMDPI AGSensors1424-82202024-02-01245154410.3390/s24051544Weed Detection from Unmanned Aerial Vehicle Imagery Using Deep Learning—A Comparison between High-End and Low-Cost Multispectral SensorsAnna Teresa Seiche0Lucas Wittstruck1Thomas Jarmer2Institute of Computer Science, Osnabrück University, 49090 Osnabrück, GermanyInstitute of Computer Science, Osnabrück University, 49090 Osnabrück, GermanyInstitute of Computer Science, Osnabrück University, 49090 Osnabrück, GermanyIn order to meet the increasing demand for crops under challenging climate conditions, efficient and sustainable cultivation strategies are becoming essential in agriculture. Targeted herbicide use reduces environmental pollution and effectively controls weeds as a major cause of yield reduction. The key requirement is a reliable weed detection system that is accessible to a wide range of end users. This research paper introduces a self-built, low-cost, multispectral camera system and evaluates it against the high-end MicaSense Altum system. Pixel-based weed and crop classification was performed on UAV datasets collected with both sensors in maize using a U-Net. The training and testing data were generated via an index-based thresholding approach followed by annotation. As a result, the F1-score for the weed class reached 82% on the Altum system and 76% on the low-cost system, with recall values of 75% and 68%, respectively. Misclassifications occurred on the low-cost system images for small weeds and overlaps, with minor oversegmentation. However, with a precision of 90%, the results show great potential for application in automated weed control. The proposed system thereby enables sustainable precision farming for the general public. In future research, its spectral properties, as well as its use on different crops with real-time on-board processing, should be further investigated.https://www.mdpi.com/1424-8220/24/5/1544weed detectionself-builtdroneprecision farmingRaspberry PiU-Net |
| spellingShingle | Anna Teresa Seiche Lucas Wittstruck Thomas Jarmer Weed Detection from Unmanned Aerial Vehicle Imagery Using Deep Learning—A Comparison between High-End and Low-Cost Multispectral Sensors Sensors weed detection self-built drone precision farming Raspberry Pi U-Net |
| title | Weed Detection from Unmanned Aerial Vehicle Imagery Using Deep Learning—A Comparison between High-End and Low-Cost Multispectral Sensors |
| title_full | Weed Detection from Unmanned Aerial Vehicle Imagery Using Deep Learning—A Comparison between High-End and Low-Cost Multispectral Sensors |
| title_fullStr | Weed Detection from Unmanned Aerial Vehicle Imagery Using Deep Learning—A Comparison between High-End and Low-Cost Multispectral Sensors |
| title_full_unstemmed | Weed Detection from Unmanned Aerial Vehicle Imagery Using Deep Learning—A Comparison between High-End and Low-Cost Multispectral Sensors |
| title_short | Weed Detection from Unmanned Aerial Vehicle Imagery Using Deep Learning—A Comparison between High-End and Low-Cost Multispectral Sensors |
| title_sort | weed detection from unmanned aerial vehicle imagery using deep learning a comparison between high end and low cost multispectral sensors |
| topic | weed detection self-built drone precision farming Raspberry Pi U-Net |
| url | https://www.mdpi.com/1424-8220/24/5/1544 |
| work_keys_str_mv | AT annateresaseiche weeddetectionfromunmannedaerialvehicleimageryusingdeeplearningacomparisonbetweenhighendandlowcostmultispectralsensors AT lucaswittstruck weeddetectionfromunmannedaerialvehicleimageryusingdeeplearningacomparisonbetweenhighendandlowcostmultispectralsensors AT thomasjarmer weeddetectionfromunmannedaerialvehicleimageryusingdeeplearningacomparisonbetweenhighendandlowcostmultispectralsensors |