01151037

Component

https://doi.org/10.3141/2198-10

http://scholar.google.com....+Li&publication_year=2010

Data on pedestrian and bicycle volumes are necessary for transportation planning, infrastructure design, and traffic management. Nevertheless, such data cannot be collected directly by the commonly used detectors (e.g., inductive loops, sonar, and microwaves). In this study, a pedestrian and bicycle tracking and classification system was developed to detect pedestrians and bicycles with a video camera. This system contained six modules: a video flow capture module, a movement detection module, a shadow removal module, a feature extraction module, a tracking module, and a classification module. The Gaussian mixture model was used to extract moving objects from an image sequence. In the tracking module, the most challenging part of this system, the trajectories were obtained by use of a Kalman filter. To identify pedestrians and bicycles, a backpropagation neural network was used in the classification module. Two other simple but effective algorithms were used to alleviate the negative impacts of shadows and occlusions. The system was tested at three sites under different traffic and environmental conditions. It has been confirmed that the accuracy for pedestrian detection was approximately 85% and the count error rate was less than 13% for bicycles at all test sites. The proposed system is a feasible alternative for the collection of data for nonmotorized travel modes.

01331205

10-2276

English

pp 83-92

2010

Transportation Research Record: Journal of the Transportation Research Board

9780309160742

Print

Figures; Photos; References (26) ; Tables (1)

Accuracy; Algorithms; Automatic data collection systems; Bicycles; Detection and identification systems; Field tests; Image processing; Kalman filtering; Neural networks; Nonmotorized transportation; Pedestrians; Trajectory; Video cameras

Beijing (China)

Data and Information Technology; Pedestrians and Bicyclists; I70: Traffic and Transport

TRIS, TRB, ATRI

Jan 25 2010 11:03AM

• Assessing Use of Pedestrian Crash Data to Identify Unsafe Transit Service Segments for Safety Improvements
• Association Between Roadway Intersection Characteristics and Pedestrian Crash Risk in Alameda County, California
• Automated Analysis of Pedestrian–Vehicle Conflicts: Context for Before-and-After Studies
• Development and Implementation of a Vehicle–Pedestrian Conflict Analysis Method: Adaptation of a Vehicle–Vehicle Technique
• Driver and Pedestrian Behavior at Uncontrolled Crosswalks in Tahoe Basin Recreation Area of California
• Effect of Pedestrian Safety Retraining for Elementary and Middle School Students
• Effect of Street Network Design on Walking and Biking
• Empirical Bayesian Evaluation of Safety Effects of High-Visibility School (Yellow) Crosswalks in San Francisco, California
• Incorporating Bicycle and Pedestrian Topics in University Transportation Courses: A National Scan
• Modeling the Evacuation of Large-Scale Crowded Pedestrian Facilities
• Multimodal Driveway Design
• Pedestrian Safety Prediction Methodology for Urban Signalized Intersections
• Quantifying Bicyclists’ Perceptions of Shared-Use Paths Adjacent to the Roadway
• Relationships and Characteristics of Pedestrian Traffic Flow in Confined Passageways
• Safety Effectiveness of Leading Pedestrian Intervals Evaluated by a Before–After Study with Comparison Groups
• Signal Timing Optimization Models for Two-Stage Midblock Pedestrian Crossing