Road Vehicle Monitoring System Based on Intelligent Visual Internet of Things

Table 9

Comparison of vehicle type recognition accuracies using different methods.

	Method	Accuracy
Original local features	SIFT	75.49%
	SURF	72.85%
	SIFT and SURF	78.68%
BoW-based features	SIFT	83.53%
	SURF	81.28%
	SIFT and SURF (our method)	93.56%