Traffic State Recognition of Intersection Based on Image Model and PCA Hashing

Algorithm 1

PCA hashing algorithm.

	Input: training samples , control parameter , number of dimensionality reduction , random initialization and .
	Output: hash coding matrix , and .
	Process:
	Start.
	Using to obtain .
	Using (12) to calculate .
	Using (13) to calculate and until convergence.
	Using (15) to obtain hash function.
	The binarization threshold vector is obtained by calculating the mean vector of all samples by .
	Obtain a final hash coding matrix through ;
	Over.