Poster

Automated Traffic Volume Classification and Analysis System (ATVCAS): A Comparison of Methodologies

Authors:
To read the file of this research, you can request a copy directly from the authors.

Abstract

Automatic detection and classification of vehicles allow for speedy, continuous, economical, and real-time traffic data collection. The poster presents methods for detection and classification of vehicles and compares the two methodologies adopted for Automated Traffic Volume Classification and Analysis System (i.e. “background subtraction” and “simultaneous object detection and classification” techniques. The paper analyzes two methodologies of automatic vehicle detection, counting, and classification of the vehicles. Algorithms of two techniques background subtraction and simultaneous object detection and classification have been coded in Python 3x and implemented for counting and classifying vehicles belonging to different classes in the heterogeneous traffic environment. The developed program automatically generates concise reports in a Microsoft Excel readable workbook. The generated worksheets contain the raw data as well as auto-generated charts that are in a ready for analysis form. Due to vehicle overlapping, foreground mask noise and the time-consuming nature, the background subtraction method was found to be comparatively inefficient. Simultaneous object detection and classification technique was, however, found more efficient as the noise generated due to vibrations do not affect detection. Also, it was observed that the latter approach is less time-consuming but requires more computational power which at present is normally not an issue.

No file available

Request Full-text Paper PDF

To read the file of this research,
you can request a copy directly from the authors.

ResearchGate has not been able to resolve any citations for this publication.
ResearchGate has not been able to resolve any references for this publication.