Detection and Monitoring of Woody Vegetation Landscape Features Using Periodic Aerial Photography
Woody vegetation landscape features, such as hedges, tree patches, and riparian vegetation, are important elements of landscape and biotic diversity. For the reason that biodiversity loss is one of the major ecological problems in the EU, it is necessary to establish efficient workflows for the regi...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/11/2766 |
| _version_ | 1797596830514544640 |
|---|---|
| author | Damjan Strnad Štefan Horvat Domen Mongus Danijel Ivajnšič Štefan Kohek |
| author_facet | Damjan Strnad Štefan Horvat Domen Mongus Danijel Ivajnšič Štefan Kohek |
| author_sort | Damjan Strnad |
| collection | DOAJ |
| description | Woody vegetation landscape features, such as hedges, tree patches, and riparian vegetation, are important elements of landscape and biotic diversity. For the reason that biodiversity loss is one of the major ecological problems in the EU, it is necessary to establish efficient workflows for the registration and monitoring of woody vegetation landscape features. In the paper, we propose and evaluate a methodology for automated detection of changes in woody vegetation landscape features from a digital orthophoto (DOP). We demonstrate its ability to capture most of the actual changes in the field and thereby provide valuable support for more efficient maintenance of landscape feature layers, which is important for the shaping of future environmental policies. While the most reliable source for vegetation cover mapping is a combination of LiDAR and high-resolution imagery, it can be prohibitively expensive for continuous updates. The DOP from cyclic aerial photography presents an alternative source of up-to-date information for tracking woody vegetation landscape features in-between LiDAR recordings. The proposed methodology uses a segmentation neural network, which is trained with the latest DOP against the last known ground truth as the target. The output is a layer of detected changes, which are validated by the user before being used to update the woody vegetation landscape feature layer. The methodology was tested using the data of a typical traditional Central European cultural landscape, Goričko, in north-eastern Slovenia. The achieved <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>F</mi><mn>1</mn></msub></semantics></math></inline-formula> of per-pixel segmentation was 83.5% and 77.1% for two- and five-year differences between the LiDAR-based reference and the DOP, respectively. The validation of the proposed changes at a minimum area threshold of 100 m<sup>2</sup> and a minimum area percentage threshold of 20% showed that the model achieved recall close to 90%. |
| first_indexed | 2024-03-11T02:58:32Z |
| format | Article |
| id | doaj.art-640e7dacf76b4a7db16ca7fe4d7b9d9b |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T02:58:32Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-640e7dacf76b4a7db16ca7fe4d7b9d9b2023-11-18T08:28:24ZengMDPI AGRemote Sensing2072-42922023-05-011511276610.3390/rs15112766Detection and Monitoring of Woody Vegetation Landscape Features Using Periodic Aerial PhotographyDamjan Strnad0Štefan Horvat1Domen Mongus2Danijel Ivajnšič3Štefan Kohek4Faculty of Electrical Engineering and Computer Science, University of Maribor, 2000 Maribor, SloveniaFaculty of Electrical Engineering and Computer Science, University of Maribor, 2000 Maribor, SloveniaFaculty of Electrical Engineering and Computer Science, University of Maribor, 2000 Maribor, SloveniaFaculty of Natural Sciences and Mathematics, University of Maribor, 2000 Maribor, SloveniaFaculty of Electrical Engineering and Computer Science, University of Maribor, 2000 Maribor, SloveniaWoody vegetation landscape features, such as hedges, tree patches, and riparian vegetation, are important elements of landscape and biotic diversity. For the reason that biodiversity loss is one of the major ecological problems in the EU, it is necessary to establish efficient workflows for the registration and monitoring of woody vegetation landscape features. In the paper, we propose and evaluate a methodology for automated detection of changes in woody vegetation landscape features from a digital orthophoto (DOP). We demonstrate its ability to capture most of the actual changes in the field and thereby provide valuable support for more efficient maintenance of landscape feature layers, which is important for the shaping of future environmental policies. While the most reliable source for vegetation cover mapping is a combination of LiDAR and high-resolution imagery, it can be prohibitively expensive for continuous updates. The DOP from cyclic aerial photography presents an alternative source of up-to-date information for tracking woody vegetation landscape features in-between LiDAR recordings. The proposed methodology uses a segmentation neural network, which is trained with the latest DOP against the last known ground truth as the target. The output is a layer of detected changes, which are validated by the user before being used to update the woody vegetation landscape feature layer. The methodology was tested using the data of a typical traditional Central European cultural landscape, Goričko, in north-eastern Slovenia. The achieved <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>F</mi><mn>1</mn></msub></semantics></math></inline-formula> of per-pixel segmentation was 83.5% and 77.1% for two- and five-year differences between the LiDAR-based reference and the DOP, respectively. The validation of the proposed changes at a minimum area threshold of 100 m<sup>2</sup> and a minimum area percentage threshold of 20% showed that the model achieved recall close to 90%.https://www.mdpi.com/2072-4292/15/11/2766woody vegetation landscape featureschange detectionsegmentation neural networkcyclic aerial photographydigital orthophoto |
| spellingShingle | Damjan Strnad Štefan Horvat Domen Mongus Danijel Ivajnšič Štefan Kohek Detection and Monitoring of Woody Vegetation Landscape Features Using Periodic Aerial Photography Remote Sensing woody vegetation landscape features change detection segmentation neural network cyclic aerial photography digital orthophoto |
| title | Detection and Monitoring of Woody Vegetation Landscape Features Using Periodic Aerial Photography |
| title_full | Detection and Monitoring of Woody Vegetation Landscape Features Using Periodic Aerial Photography |
| title_fullStr | Detection and Monitoring of Woody Vegetation Landscape Features Using Periodic Aerial Photography |
| title_full_unstemmed | Detection and Monitoring of Woody Vegetation Landscape Features Using Periodic Aerial Photography |
| title_short | Detection and Monitoring of Woody Vegetation Landscape Features Using Periodic Aerial Photography |
| title_sort | detection and monitoring of woody vegetation landscape features using periodic aerial photography |
| topic | woody vegetation landscape features change detection segmentation neural network cyclic aerial photography digital orthophoto |
| url | https://www.mdpi.com/2072-4292/15/11/2766 |
| work_keys_str_mv | AT damjanstrnad detectionandmonitoringofwoodyvegetationlandscapefeaturesusingperiodicaerialphotography AT stefanhorvat detectionandmonitoringofwoodyvegetationlandscapefeaturesusingperiodicaerialphotography AT domenmongus detectionandmonitoringofwoodyvegetationlandscapefeaturesusingperiodicaerialphotography AT danijelivajnsic detectionandmonitoringofwoodyvegetationlandscapefeaturesusingperiodicaerialphotography AT stefankohek detectionandmonitoringofwoodyvegetationlandscapefeaturesusingperiodicaerialphotography |