Urban Roadside Tree Inventory Using a Mobile Laser Scanning System
Bibliographic record
Abstract
the road environment. Thus, effective methods are needed for the MLS data processing. \nThe main goal of this thesis is to establish a feasible workflow by testing a series of methods to extract geometrical information of roadside trees from the MLS-acquired point clouds. The workflow developed in this study consists of three parts. The first part deals with ground point removal. As such, only off-ground points are used to extract trees. The second part handles tree detection by comparing four segmentation and clustering methods: the Euclidian distance clustering algorithm, the region growing segmentation method, the normalized cut (Ncut) method, and the supervoxel-based tree detection method. The third part focuses on automated extraction of tree geometric parameters such as tree height, DBH, crown spread, and horizontal slices features. Finally, classification of tree species was conducted using the k-Nearest Neighbour (k-NN) and the random forests (RF) algorithm. A total of four MLS datasets (three in Xiamen, China and one in Kingston, Ontario) acquired in \niv \n2013 and 2015, respectively, were used to test the developed method. The ground truthing data of DBH estimation were obtained through manual measurement of selected roadside trees after the two MLS missions in Xiamen in the fall 2015. The field surveyed DBH values of the 163 roadside trees were used to estimate the accuracy of the proposed tree extraction method. The 200 manually labeled trees with 8 different species were selected to examine accuracy of the proposed classification method. The results show that over 90% of the roadside trees were correctly detected, with an average error of about 5% in DBH estimation when compared to the field survey, and an overall accuracy of 78% for the classification of tree species.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".