Performance Analysis of Multispectral LiDAR in Land Cover Classification
Bibliographic record
Abstract
The Optech Titan is the world’s first multispectral airborne Light Detection and Ranging (LIDAR) sensor, a revolutionary sensor that includes three active imaging channels of different wavelengths for day or night mapping of complex environments. Multispectral imagery and monochromatic LIDAR have long existed as independent technologies and both systems have developed workflows to perform land cover classification. This project was undertaken to analyze the performance of Optech Titan’s three active imaging channels and LIDAR attributes in land cover classification. By processing selective parameters through the multispectral image land cover classification process, we can determine the accuracy performance of individual channels and attributes in land cover classification. The outcome of this process will measure the effectiveness of combining LIDAR attributes with multispectral imagery for land cover classification. The test site was a 600m x 600m residential neighbourhood in Oshawa, Ontario captured at point-spacing of 0.5 meter. Multispectral imagery had an overall accuracy result of 77%. The most accurate land cover classification result from our testing was 77.5%. This was produced as a special index scenario by using the three intensities along with the nDSM. It is apparent from the results that the intensity-attribute provides the most useful information in land cover classification. The highest monochromatic LIDAR accuracy result of 70% came from Channel 2 (NIR - 1024 mm). Channel 2’s accuracy is only 7% lower than multispectral imagery result. Channel 1 and 3 had less-favorable results at 59.5% and 58% respectively. Individual land cover classification tests on Z-attribute and N-attribute produced unfavorable results of 37% and 47.5% respectively.
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 | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".