UnDER: Unsupervised Dense Point Cloud Extraction Routine for UAV Imagery Using Deep Learning
Extraction of dense 3D geographic information from ultra-high-resolution unmanned aerial vehicle (UAV) imagery unlocks a great number of mapping and monitoring applications. This is facilitated by a step called dense image matching, which tries to find pixels corresponding to the same object within...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/1/24 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841548993806467072 |
|---|---|
| author | John Ray Bergado Francesco Nex |
| author_facet | John Ray Bergado Francesco Nex |
| author_sort | John Ray Bergado |
| collection | DOAJ |
| description | Extraction of dense 3D geographic information from ultra-high-resolution unmanned aerial vehicle (UAV) imagery unlocks a great number of mapping and monitoring applications. This is facilitated by a step called dense image matching, which tries to find pixels corresponding to the same object within overlapping images captured by the UAV from different locations. Recent developments in deep learning utilize deep convolutional networks to perform this dense pixel correspondence task. A common theme in these developments is to train the network in a supervised setting using available dense 3D reference datasets. However, in this work we propose a novel unsupervised dense point cloud extraction routine for UAV imagery, called UnDER. We propose a novel disparity-shifting procedure to enable the use of a stereo matching network pretrained on an entirely different typology of image data in the disparity-estimation step of UnDER. Unlike previously proposed disparity-shifting techniques for forming cost volumes, the goal of our procedure was to address the domain shift between the images that the network was pretrained on and the UAV images, by using prior information from the UAV image acquisition. We also developed a procedure for occlusion masking based on disparity consistency checking that uses the disparity image space rather than the object space proposed in a standard 3D reconstruction routine for UAV data. Our benchmarking results demonstrated significant improvements in quantitative performance, reducing the mean cloud-to-cloud distance by approximately 1.8 times the ground sampling distance (GSD) compared to other methods. |
| format | Article |
| id | doaj-art-653a3b19a2a34286a40957faba26a9f3 |
| institution | Kabale University |
| issn | 2072-4292 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-653a3b19a2a34286a40957faba26a9f32025-01-10T13:19:59ZengMDPI AGRemote Sensing2072-42922024-12-011712410.3390/rs17010024UnDER: Unsupervised Dense Point Cloud Extraction Routine for UAV Imagery Using Deep LearningJohn Ray Bergado0Francesco Nex1Department of Earth Observation Science, Faculty of Geo-Information Science and Earth Observation (ITC), University of Twente, 7522NH Enschede, The NetherlandsDepartment of Earth Observation Science, Faculty of Geo-Information Science and Earth Observation (ITC), University of Twente, 7522NH Enschede, The NetherlandsExtraction of dense 3D geographic information from ultra-high-resolution unmanned aerial vehicle (UAV) imagery unlocks a great number of mapping and monitoring applications. This is facilitated by a step called dense image matching, which tries to find pixels corresponding to the same object within overlapping images captured by the UAV from different locations. Recent developments in deep learning utilize deep convolutional networks to perform this dense pixel correspondence task. A common theme in these developments is to train the network in a supervised setting using available dense 3D reference datasets. However, in this work we propose a novel unsupervised dense point cloud extraction routine for UAV imagery, called UnDER. We propose a novel disparity-shifting procedure to enable the use of a stereo matching network pretrained on an entirely different typology of image data in the disparity-estimation step of UnDER. Unlike previously proposed disparity-shifting techniques for forming cost volumes, the goal of our procedure was to address the domain shift between the images that the network was pretrained on and the UAV images, by using prior information from the UAV image acquisition. We also developed a procedure for occlusion masking based on disparity consistency checking that uses the disparity image space rather than the object space proposed in a standard 3D reconstruction routine for UAV data. Our benchmarking results demonstrated significant improvements in quantitative performance, reducing the mean cloud-to-cloud distance by approximately 1.8 times the ground sampling distance (GSD) compared to other methods.https://www.mdpi.com/2072-4292/17/1/24UAVpoint clouddeep learningunsupervised learningdense image matchingocclusion masking |
| spellingShingle | John Ray Bergado Francesco Nex UnDER: Unsupervised Dense Point Cloud Extraction Routine for UAV Imagery Using Deep Learning Remote Sensing UAV point cloud deep learning unsupervised learning dense image matching occlusion masking |
| title | UnDER: Unsupervised Dense Point Cloud Extraction Routine for UAV Imagery Using Deep Learning |
| title_full | UnDER: Unsupervised Dense Point Cloud Extraction Routine for UAV Imagery Using Deep Learning |
| title_fullStr | UnDER: Unsupervised Dense Point Cloud Extraction Routine for UAV Imagery Using Deep Learning |
| title_full_unstemmed | UnDER: Unsupervised Dense Point Cloud Extraction Routine for UAV Imagery Using Deep Learning |
| title_short | UnDER: Unsupervised Dense Point Cloud Extraction Routine for UAV Imagery Using Deep Learning |
| title_sort | under unsupervised dense point cloud extraction routine for uav imagery using deep learning |
| topic | UAV point cloud deep learning unsupervised learning dense image matching occlusion masking |
| url | https://www.mdpi.com/2072-4292/17/1/24 |
| work_keys_str_mv | AT johnraybergado underunsuperviseddensepointcloudextractionroutineforuavimageryusingdeeplearning AT francesconex underunsuperviseddensepointcloudextractionroutineforuavimageryusingdeeplearning |