Development of Bicycle and Pedestrian Detection and Classification Algorithm for Active-Infrared Overhead Vehicle Imaging Sensors

Abstract

Existing algorithms used with active-infrared overhead vehicle-imaging sensors consider vehicle size and speed attributes as basic parameters to detect and classify 11 categories of motorized vehicles. These algorithms could not detect and classify bicycles and pedestrians. This research focused on developing and evaluating algorithms for active-infrared overhead vehicle-imaging sensor technology to detect and classify non-motorized users. Development of the theory and algorithm used to automate the simultaneous detection and classification of bicycles and pedestrians along with the field investigations to evaluate its effectiveness are described. The new algorithm used the concept of message sequencing to incorporate existing active-infrared technology theory. Bicycles and pedestrians intersected the infrared scan patterns in different sequences that, along with the infrared images, provided unique detection and classification identification. The algorithm was integrated within the existing active-infrared technology, and a field evaluation was conducted on bicycle and pedestrian trails. The algorithm created an intelligent technology to detect and classify bicycles and pedestrians. Nearly 100% of bicycles and pedestrians were detected, and about 92% of them were successfully classified. Automated data collection technology can be useful in obtaining more comprehensive travel data and in forecasting demand for design and policy making related to nonmotorized transportation.