Urban Greenness Extracted from Pedestrian Video and Its Relationship with Surrounding Air Temperatures
Bibliographic record
Abstract
Background: Urban greenness has been associated with a wide range of health benefits, partially attributable to local cooling and visually-stimulated stress reduction. Several approaches have been used to assess greenness exposure at individual and population scales, but there is discrepancy between methods. Image processing of pedestrian video data, collected as part of a study on microscale urban air temperature, provide a novel source of street-level information on vegetation.Methods: Python was used to extract green, yellow, and shaded pixels from ~10 million frames of video footage collected during 40 sampling runs of 20 urban routes measuring 8-10 km. Resulting greenness values (combined total of green, yellow, and shaded pixels as a percentage of all pixels) were compared with concurrent air temperatures using correlations, time series plots, and maps. Shaded pixels were included because vegetation can generate large shaded areas on hot summer days.Results: The mean air temperature measured across the 40 runs ranged from 19.8 to 31.9 °C, with standard deviations ranging from 0.26 to 1.21 °C. In comparison, the mean greenness ranged from 52% to 65%, with standard deviations ranging from 6% to 13%. Correlations ranged from -0.61 to 0.34 and were in the expected direction for 31 of 40 runs, with plots and maps showing clear inverse relationships in many cases. Flat and weakly positive relationships occurred when background temperatures were low, conditions were overcast, or routes were closer to large waterways.Conclusions: Secondary data are limited for such evaluations, but with further refinement, our methods could provide unprecedented spatial and temporal resolution for greenness exposure assessment in individual-level studies. They could also be used to evaluate and compare models used to assess exposure at the population scale as long as the video footage is temporally matched with other methods, such as satellite overpasses or Google Street View imaging.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| 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".