Real Time Passenger Flow Calculation Based on Zynq

There are many researches on pedestrian detection. These researches are mainly used in ADAS systems based on the front view of the pedestrian. However in some situation, for example on the bus or in the public access, passenger flow calculation needs to be done based on the top view images. This paper presents an efficient FPGA-based passenger flow calculation on a Xilinx Zynq SoC. The algorithms presented include hair model and head detection. The hardware and software collaborative design realized accurate detection in real-time.

[1]  Ting Wang,et al.  Color image segmentation using pixel wise support vector machine classification , 2011, Pattern Recognit..

[2]  Eam Khwang Teoh,et al.  Human Hair Segmentation and Length Detection for Human Appearance Model , 2014, 2014 22nd International Conference on Pattern Recognition.

[3]  Huang Xin.  Head Detection Based on Randomized Hough Transform , 2012 .

[4]  Nan Wang,et al.  What are good parts for hair shape modeling? , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).