Automated Collection of Pedestrian Data through Computer Vision Techniques
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
New urban planning concepts are being redefined to emphasize walkability (a measure of how walker-friendly an area is) and to accommodate the pedestrian as a key road user. However, the availability of reliable information on pedestrian traffic remains a major challenge and inhibits a better understanding of many pedestrian issues. Therefore, the importance of developing new techniques for the collection of pedestrian data cannot be overstated. This paper describes the use of computer vision techniques for the automated collection of pedestrian data through several applications, including measurement of pedestrian counts, tracking, and walking speeds. An efficient pedestrian-tracking algorithm, the MMTrack, was used. The algorithm employed a large-margin learning criterion to combine different sources of information effectively. The applications were demonstrated with a real-world data set from Vancouver, British Columbia, Canada. The data set included 1,135 pedestrian tracks. Manual counts and tracking were performed to validate the results of the automated data collection. The results show a 5% average error in counting, which is considered reliable. The results of walking speed validation showed excellent agreement between manual and automated walking speed values (root mean square error = 0.0416 m/s, R 2 = .9269). Further analysis was conducted on the mean walking speed of pedestrians as it related to several factors. Gender, age, and the group size were found to influence the pedestrian mean walking speed significantly. The results demonstrate that computer vision techniques have the potential to collect microscopic data on road users at a degree of automation and accuracy that cannot be feasibly achieved by manual or semiautomated techniques.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.013 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.004 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.003 |
| Open science | 0.003 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it