Testing Photoelectric Sensor System to Classify Vehicles

Abstract

This paper describes the 1990 test of an automatic vehicle classification (AVC) system employing an inductance detector loop and photoelectric sensors emitting infrared‐spectrum light beams, which were reflected off commonly used raised traffic lane markers. The passing of a vehicle activated the sensors. Signals from the activation go through a special microprocessor into a personal computer for interpretations, display, and recording. Vehicle speed and axle patterns are inferred from the pattern of the photoelectric beam interruptions. The system is tested several times at a high‐speed (50–65 mph) Oklahoma turnpike site by comparing the automatic classifications with classifications by a person. The researchers use computer printouts and written field observations to evaluate the number and type of errors. An error is said to occur when the automatic vehicle classification does not agree with the classification by the observer. The evaluation shows that the first‐generation AVC system correctly classifies about 95% of 1,736 observed vehicles. Further analysis of the raw data and the errors found therein suggests that, with modifications, the AVC system can correctly classify about 97–98% of the vehicles. Snow or heavy rain does not occur during the tests, so ability to classify in these conditions is not evaluated.