Real-time component labelling and feature extraction on FPGA

We present in this work an image component labeller-and feature extraction module that can operate in real-time. This labeller is suitable for smart cameras and Field Programmable Gate Arrays (FPGA). We show in our work how complex gray value features of image components can be calculated in parallel with label assignment without first resolving complex chains of merged labels. The labeller and a simple counter of number of image components are implemented on a Xilinx Virtex II Pro. We report device usage, maximum frequency and power dissipation.

[1]  Donald G. Bailey,et al.  FPGA implementation of a Single Pass Connected Components Algorithm , 2008, 4th IEEE International Symposium on Electronic Design, Test and Applications (delta 2008).

[2]  Jae Wook Jeon,et al.  Real-time component labeling and boundary tracing system based on FPGA , 2007, 2007 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[3]  Donald G. Bailey,et al.  Connected components analysis of streamed images , 2008, 2008 International Conference on Field Programmable Logic and Applications.

[4]  Wayne H. Wolf,et al.  Smart Cameras as Embedded Systems , 2002, Computer.

[5]  Peter Pirsch,et al.  A parallel hardware architecture for connected component labeling based on fast label merging , 2008, 2008 International Conference on Application-Specific Systems, Architectures and Processors.

[6]  Li Shang,et al.  Dynamic power consumption in Virtex™-II FPGA family , 2002, FPGA '02.