Unsupervised Methodology for Large-Scale Tree Seedling Mapping in Diverse Forestry Settings Using UAV-Based RGB Imagery
Mapping and monitoring tree seedlings is essential for reforestation and restoration efforts. However, achieving this on a large scale, especially during the initial stages of growth, when seedlings are small and lack distinct morphological features, can be challenging. An accurate, reliable, and ef...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/22/5276 |
| _version_ | 1797457932448694272 |
|---|---|
| author | Sadeepa Jayathunga Grant D. Pearse Michael S. Watt |
| author_facet | Sadeepa Jayathunga Grant D. Pearse Michael S. Watt |
| author_sort | Sadeepa Jayathunga |
| collection | DOAJ |
| description | Mapping and monitoring tree seedlings is essential for reforestation and restoration efforts. However, achieving this on a large scale, especially during the initial stages of growth, when seedlings are small and lack distinct morphological features, can be challenging. An accurate, reliable, and efficient method that detects seedlings using unmanned aerial vehicles (UAVs) could significantly reduce survey costs. In this study, we used an unsupervised approach to map young conifer seedlings utilising spatial, spectral, and structural information from UAV digital aerial photogrammetric (UAV-DAP) point clouds. We tested our method across eight trial stands of radiata pine with a wide height range (0.4–6 m) that comprised a total of ca. 100 ha and spanned diverse site conditions. Using this method, seedling detection was excellent, with an overall precision, sensitivity, and <i>F</i>1 score of 95.2%, 98.0%, and 96.6%, respectively. Our findings demonstrated the importance of combining spatial, spectral, and structural metrics for seedling detection. While spectral and structural metrics efficiently filtered out non-vegetation objects and weeds, they struggled to differentiate planted seedlings from regenerating ones due to their similar characteristics, resulting in a large number of false positives. The inclusion of a row segment detection algorithm overcame this limitation and successfully identified most regenerating seedlings, leading to a significant reduction in false positives and an improvement in overall detection accuracy. Our method generated vector files containing seedling positions and key structural characteristics (seedling height, crown dimensions), offering valuable outputs for precision management. This automated pipeline requires fewer resources and user inputs compared to manual annotations or supervised techniques, making it a rapid, cost-effective, and scalable solution which is applicable without extensive training data. While serving as primarily a standalone tool for assessing forestry projects, the proposed method can also complement supervised seedling detection methods like machine learning, i.e., by supplementing training datasets. |
| first_indexed | 2024-03-09T16:29:52Z |
| format | Article |
| id | doaj.art-e7fe0f70e1fe4c8b81a1c303c045f016 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T16:29:52Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-e7fe0f70e1fe4c8b81a1c303c045f0162023-11-24T15:04:09ZengMDPI AGRemote Sensing2072-42922023-11-011522527610.3390/rs15225276Unsupervised Methodology for Large-Scale Tree Seedling Mapping in Diverse Forestry Settings Using UAV-Based RGB ImagerySadeepa Jayathunga0Grant D. Pearse1Michael S. Watt2Scion, Titokorangi Drive, Private Bag 3020, Rotorua 3046, New ZealandScion, Titokorangi Drive, Private Bag 3020, Rotorua 3046, New ZealandScion, 10 Kyle St, Riccarton, Christchurch 8440, New ZealandMapping and monitoring tree seedlings is essential for reforestation and restoration efforts. However, achieving this on a large scale, especially during the initial stages of growth, when seedlings are small and lack distinct morphological features, can be challenging. An accurate, reliable, and efficient method that detects seedlings using unmanned aerial vehicles (UAVs) could significantly reduce survey costs. In this study, we used an unsupervised approach to map young conifer seedlings utilising spatial, spectral, and structural information from UAV digital aerial photogrammetric (UAV-DAP) point clouds. We tested our method across eight trial stands of radiata pine with a wide height range (0.4–6 m) that comprised a total of ca. 100 ha and spanned diverse site conditions. Using this method, seedling detection was excellent, with an overall precision, sensitivity, and <i>F</i>1 score of 95.2%, 98.0%, and 96.6%, respectively. Our findings demonstrated the importance of combining spatial, spectral, and structural metrics for seedling detection. While spectral and structural metrics efficiently filtered out non-vegetation objects and weeds, they struggled to differentiate planted seedlings from regenerating ones due to their similar characteristics, resulting in a large number of false positives. The inclusion of a row segment detection algorithm overcame this limitation and successfully identified most regenerating seedlings, leading to a significant reduction in false positives and an improvement in overall detection accuracy. Our method generated vector files containing seedling positions and key structural characteristics (seedling height, crown dimensions), offering valuable outputs for precision management. This automated pipeline requires fewer resources and user inputs compared to manual annotations or supervised techniques, making it a rapid, cost-effective, and scalable solution which is applicable without extensive training data. While serving as primarily a standalone tool for assessing forestry projects, the proposed method can also complement supervised seedling detection methods like machine learning, i.e., by supplementing training datasets.https://www.mdpi.com/2072-4292/15/22/5276unsupervisedseedling detectionSfMDAPimage segmentation<i>Pinus radiata</i> D. Don |
| spellingShingle | Sadeepa Jayathunga Grant D. Pearse Michael S. Watt Unsupervised Methodology for Large-Scale Tree Seedling Mapping in Diverse Forestry Settings Using UAV-Based RGB Imagery Remote Sensing unsupervised seedling detection SfM DAP image segmentation <i>Pinus radiata</i> D. Don |
| title | Unsupervised Methodology for Large-Scale Tree Seedling Mapping in Diverse Forestry Settings Using UAV-Based RGB Imagery |
| title_full | Unsupervised Methodology for Large-Scale Tree Seedling Mapping in Diverse Forestry Settings Using UAV-Based RGB Imagery |
| title_fullStr | Unsupervised Methodology for Large-Scale Tree Seedling Mapping in Diverse Forestry Settings Using UAV-Based RGB Imagery |
| title_full_unstemmed | Unsupervised Methodology for Large-Scale Tree Seedling Mapping in Diverse Forestry Settings Using UAV-Based RGB Imagery |
| title_short | Unsupervised Methodology for Large-Scale Tree Seedling Mapping in Diverse Forestry Settings Using UAV-Based RGB Imagery |
| title_sort | unsupervised methodology for large scale tree seedling mapping in diverse forestry settings using uav based rgb imagery |
| topic | unsupervised seedling detection SfM DAP image segmentation <i>Pinus radiata</i> D. Don |
| url | https://www.mdpi.com/2072-4292/15/22/5276 |
| work_keys_str_mv | AT sadeepajayathunga unsupervisedmethodologyforlargescaletreeseedlingmappingindiverseforestrysettingsusinguavbasedrgbimagery AT grantdpearse unsupervisedmethodologyforlargescaletreeseedlingmappingindiverseforestrysettingsusinguavbasedrgbimagery AT michaelswatt unsupervisedmethodologyforlargescaletreeseedlingmappingindiverseforestrysettingsusinguavbasedrgbimagery |