Vision-based pedestrian behavior analysis at intersections

Shirazi, Mohammad Shokrolah; Morris, Brendan

doi:10.1117/1.jei.25.5.051203

Cited by 15 publications

(2 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2, is 0.049 µg in the morning and 0.026 µg in the afternoon. If we assume that the average waiting time of pedestrians at an intersection varies from 1 to 10 seconds (Huang and Cynecki, 2001;Shirazi and Morris, 2016), then the air pollution inhalation while waiting at the intersection will range from 8.7 × 10 -5 µg to 8.7 × 10 -4 µg in the morning, and 4.7 × 10 -5 µg to 4.7 × 10 -4 µg in the afternoon. Therefore, waiting at intersections will add an extra 0.2% to 1.8% to the overall inhaled mass.…”

Section: Resultsmentioning

confidence: 99%

Reducing pedestrians' inhalation of traffic-related air pollution through route choices: Case study in California suburb

Luo

Boriboonsomsin

Barth

2018

Journal of Transport & Health

View full text Add to dashboard Cite

Pedestrians often face risks of inhaling a high amount of traffic-related air pollution due to their proximity to the emission sources and increased breathing rates during walking. This paper presents an innovative way for pedestrians to mitigate such risks. Specifically, a method for incorporating the estimated inhaled mass of fine particles (PM 2.5) into walking route calculations was developed, and the calculated low air pollution inhalation route was compared against the traditional shortest duration route. For the case study of a suburban road network in Riverside, California, a low inhalation route could be found for 4% of the simulated walking trips in both morning and afternoon periods. In the morning period, the low inhalation routes would reduce a pedestrian's inhalation of traffic-related primary PM 2.5 by 48% while increasing the walking duration by only 2% on average. Similarly, in the afternoon period, the low inhalation routes would reduce the inhalation by 44% while increasing the walking duration by merely 1% on average. These results indicate that if people who choose to walk can accommodate a slight increase in walking duration in some of their walking trips, they can substantially reduce the inhalation of traffic-related primary PM 2.5 on those trips. The presented concept of low air pollution inhalation route can be enhanced by the integration of real-time traffic, weather, and even roadside air quality data to result in navigation applications for pedestrians. This may be particularly important for sensitive population groups such as school-aged children and seniors.

show abstract

Section: Resultsmentioning

confidence: 99%

Reducing pedestrians' inhalation of traffic-related air pollution through route choices: Case study in California suburb

Luo

Boriboonsomsin

Barth

2018

Journal of Transport & Health

View full text Add to dashboard Cite

show abstract

“…Interesting method of pedestrian detection was published in (Shirazi and Morris, 2016). Suggested system of detection and tracking works only with necessary area including typical pedestrian paths in the frame.…”

Section: Related Workmentioning

confidence: 99%

An Algorithm for Pedestrian Detection in Multispectral Image Sequences

Kniaz

Федоренко

2017

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:The growing interest for self-driving cars provides a demand for scene understanding and obstacle detection algorithms. One of the most challenging problems in this field is the problem of pedestrian detection. Main difficulties arise from a diverse appearances of pedestrians. Poor visibility conditions such as fog and low light conditions also significantly decrease the quality of pedestrian detection. This paper presents a new optical flow based algorithm BipedDetet that provides robust pedestrian detection on a single-borad computer. The algorithm is based on the idea of simplified Kalman filtering suitable for realization on modern single-board computers. To detect a pedestrian a synthetic optical flow of the scene without pedestrians is generated using slanted-plane model. The estimate of a real optical flow is generated using a multispectral image sequence. The difference of the synthetic optical flow and the real optical flow provides the optical flow induced by pedestrians. The final detection of pedestrians is done by the segmentation of the difference of optical flows. To evaluate the BipedDetect algorithm a multispectral dataset was collected using a mobile robot.

show abstract