Traffic Foreground Detection at Complex Urban Intersections Using a Novel Background Dictionary Learning Model

Table 1

Traffic foreground detection algorithm for intersection scenarios.

---

Input: current frame ; background dictionary ;

Output: foreground detection result ; background update dictionary ; sparse representation ;

Initialization: initial background dictionary; initial foreground dictionary; parameters , and ;

1. Sparse coding: with fixed , the sparse coefficient is updated by equation (24);

2. Foreground detection: is updated by equation (25);

3. Foreground dictionary update: the foreground dictionary is updated according to the foreground detection result ;

4. Background dictionary update: the dictionary is updated according to formula (12) to get a new background dictionary ;

5. Return to the step 1 for the next frame detection.

---