Automated Pedestrian Detection, Count and Analysis System
archive: archived pipeline: cataloged verified
Get this paper ↗ (full text — opens at the source; we link to it, we don't host it)
Summary
This document is a quarterly progress report for a research project sponsored by the Nevada Department of Transportation (NDOT), titled "Automated Pedestrian Detection, Count and Analysis System." The study addresses the critical need for automated pedestrian and bicycle count data to support transportation planning, safety countermeasure implementation, and the evaluation of pedestrian Level of Service (LOS) and Safety Performance Functions (SPF). The primary motivation is the lack of comprehensive, automated tools for detecting pedestrian-vehicle conflicts and collecting microscopic flow data, which are currently reliant on manual collection or limited existing technologies. The research aims to develop an automated framework that detects and counts pedestrians and bicycles, generates flow characteristics, and evaluates pedestrian-vehicle conflicts using live video feeds. The project is structured into five tasks: a literature review, development of a pedestrian-bicycle count system, creation of a pedestrian-vehicle conflict detection system, development of a safety database and analysis tool, and final reporting. The system is designed to run on multi-core GPU systems to process video data in real-time, extracting metrics such as direction of motion, walking speed, and vehicle counts by lane. The team includes faculty and graduate/undergraduate students specializing in computer vision and traffic engineering. As of the report date in April 2015, the team has completed the literature review component, which surveyed existing methods for pedestrian, vehicle, and bicycle detection. The review highlights that while general pedestrian and vehicle detection are well-studied, automated detection of pedestrian-vehicle conflicts remains an underexplored area. The report details various detection algorithms, including sliding window approaches, Histogram of Oriented Gradients (HOG), and template-based methods for bicycles. The team is currently in the process of collecting data at specific intersections to evaluate detection and tracking algorithms and is testing safety analysis tools such as PBCAT, LOS+, and HSIS. Future work involves implementing identified methods to extract data from video frames and developing the database for network screening and countermeasure selection. The significance of this work lies in its potential to provide NDOT with a robust, automated tool for comprehensive intersection safety analysis. By integrating crash and conflict data, the system aims to identify critical pedestrian locations and recommend safety countermeasures. The project represents a shift from manual data collection to automated, video-based analysis, offering a more efficient and scalable method for monitoring pedestrian and bicycle safety. The successful completion of this project will support the selection and evaluation of safety improvements, ultimately enhancing multimodal transportation safety in Nevada.
Provenance
The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed. Discovered via bulk_ingest_rosap on 2026-05-23 (85 acquisition events logged).
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | rosap | — | — | 2 | 2026-05-23 |
| archive | success | — | — | — | 1 | 2026-05-23 |
| extract | success | cached | — | — | 6 | 2026-06-15 |
| clean | success | — | — | — | 1 | 2026-06-01 |
| chunk | success | — | — | — | 1 | 2026-06-01 |
| embed | success | — | — | — | 1 | 2026-06-02 |
| enrich | success | — | — | — | 1 | 2026-05-23 |
| promote | success | — | — | — | 1 | 2026-05-23 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 85 | 2026-06-15 |
| tag | success | vector_similarity | — | — | 19 | 2026-06-11 |
| verify | success | — | — | — | 1 | 2026-06-15 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-15; verification: verified.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.