Detecting Individual-Tree Crown Regions from Terrestrial Laser Scans with an Anchor-Free Deep Learning Model
Detecting individual-tree crowns provides a fundamental analysis unit bridging macro ecological patterns and micro physiological functions. This study adapted an anchor-free deep learning model, CenterNet, to detect individual crown locations and regions from dense 3 D terrestrial laser scans. A tot...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2021-03-01
|
| Series: | Canadian Journal of Remote Sensing |
| Online Access: | http://dx.doi.org/10.1080/07038992.2020.1861541 |
| _version_ | 1797661095286013952 |
|---|---|
| author | Zhouxin Xi Chris Hopkinson |
| author_facet | Zhouxin Xi Chris Hopkinson |
| author_sort | Zhouxin Xi |
| collection | DOAJ |
| description | Detecting individual-tree crowns provides a fundamental analysis unit bridging macro ecological patterns and micro physiological functions. This study adapted an anchor-free deep learning model, CenterNet, to detect individual crown locations and regions from dense 3 D terrestrial laser scans. A total of 1181 crowns from twelve plots were manually delineated as reference, among which eight plots were used for training the CenterNet, and another four independent plots for testing model accuracies characterized as the F1-score of location detection and Intersection over Union (IoU) of bounding box area. The maximum training F1-score and IoU were 0.881 and 0.670 over 40k training iterations, respectively. The result testing F1-score and IoU were 0.754 and 0.583, respectively. Five morphological factors were quantified to investigate the causes of accuracy variation among different plots and species, including crown area, tree height, full-width-at-half-maximum, nearest neighbor crown distance, and overlapping ratio of neighboring crowns. Results show that tree height was most important trait for crown detection. A taller, larger, smoother, less crowded, and less overlapped tree was found easier to detect. Among six species, red pine, Scots pine, and silver birch were successfully detected, and Norway spruce, lodgepole pine, and trembling aspen were more difficult to detect. |
| first_indexed | 2024-03-11T18:40:23Z |
| format | Article |
| id | doaj.art-08b1877de7174c9eae19332f0c497bce |
| institution | Directory Open Access Journal |
| issn | 1712-7971 |
| language | English |
| last_indexed | 2024-03-11T18:40:23Z |
| publishDate | 2021-03-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Canadian Journal of Remote Sensing |
| spelling | doaj.art-08b1877de7174c9eae19332f0c497bce2023-10-12T13:36:23ZengTaylor & Francis GroupCanadian Journal of Remote Sensing1712-79712021-03-0147222824210.1080/07038992.2020.18615411861541Detecting Individual-Tree Crown Regions from Terrestrial Laser Scans with an Anchor-Free Deep Learning ModelZhouxin Xi0Chris Hopkinson1Department of Geography and Environment, University of LethbridgeDepartment of Geography and Environment, University of LethbridgeDetecting individual-tree crowns provides a fundamental analysis unit bridging macro ecological patterns and micro physiological functions. This study adapted an anchor-free deep learning model, CenterNet, to detect individual crown locations and regions from dense 3 D terrestrial laser scans. A total of 1181 crowns from twelve plots were manually delineated as reference, among which eight plots were used for training the CenterNet, and another four independent plots for testing model accuracies characterized as the F1-score of location detection and Intersection over Union (IoU) of bounding box area. The maximum training F1-score and IoU were 0.881 and 0.670 over 40k training iterations, respectively. The result testing F1-score and IoU were 0.754 and 0.583, respectively. Five morphological factors were quantified to investigate the causes of accuracy variation among different plots and species, including crown area, tree height, full-width-at-half-maximum, nearest neighbor crown distance, and overlapping ratio of neighboring crowns. Results show that tree height was most important trait for crown detection. A taller, larger, smoother, less crowded, and less overlapped tree was found easier to detect. Among six species, red pine, Scots pine, and silver birch were successfully detected, and Norway spruce, lodgepole pine, and trembling aspen were more difficult to detect.http://dx.doi.org/10.1080/07038992.2020.1861541 |
| spellingShingle | Zhouxin Xi Chris Hopkinson Detecting Individual-Tree Crown Regions from Terrestrial Laser Scans with an Anchor-Free Deep Learning Model Canadian Journal of Remote Sensing |
| title | Detecting Individual-Tree Crown Regions from Terrestrial Laser Scans with an Anchor-Free Deep Learning Model |
| title_full | Detecting Individual-Tree Crown Regions from Terrestrial Laser Scans with an Anchor-Free Deep Learning Model |
| title_fullStr | Detecting Individual-Tree Crown Regions from Terrestrial Laser Scans with an Anchor-Free Deep Learning Model |
| title_full_unstemmed | Detecting Individual-Tree Crown Regions from Terrestrial Laser Scans with an Anchor-Free Deep Learning Model |
| title_short | Detecting Individual-Tree Crown Regions from Terrestrial Laser Scans with an Anchor-Free Deep Learning Model |
| title_sort | detecting individual tree crown regions from terrestrial laser scans with an anchor free deep learning model |
| url | http://dx.doi.org/10.1080/07038992.2020.1861541 |
| work_keys_str_mv | AT zhouxinxi detectingindividualtreecrownregionsfromterrestriallaserscanswithananchorfreedeeplearningmodel AT chrishopkinson detectingindividualtreecrownregionsfromterrestriallaserscanswithananchorfreedeeplearningmodel |