Development of an automated accident detection system at intersections
Conference Paper
Overview
Additional Document Info
View All
Overview
abstract
This paper presents the development of an automated intersection accident detection system via digital audio signal processing. Audio signals at busy intersections are the inputs to the system. The system is composed of three main signal processing stages: feature extraction, feature reduction, and classification. The results of the study show that the wavelet-based feature extraction in combination with the maximum likelihood classifier is the optimum design. The system is computationally inexpensive, and consistently results in accident detection accuracies of 95% to 100% with a very low false alarm rate in multiple stages of testing in the lab and also in a real-time real-world environment.
