Real-time face detection and tracking using software and hardware design
Loading...
Date
2018-06
Authors
Chen, Kok Keat
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
This project presents the design and the implementation of face detection
algorithm for video processing applications on FPGAs. Face detection and tracking has
been an active research topic because it offers many important applications, especially in
video surveillance, biometrics, video coding and so on. The goal of this project was to
implement a real-time system on an FPGA to detect and track human faces. The face
detection algorithm involved colour-based skin segmentation and image filtering. The
face location was determined by calculating the centroid of the detected region. A
software version of the algorithm was independently implemented and tested in
MATLAB Simulink. Although the transition from software version to HDL (Verilog)
was not exactly the same between both approaches, experimental results proved the
functionality, accuracy and effectiveness of the real-time system, even under varying
conditions of lights, facial poses and skin colours. For FPGA implementation the entire
face detection algorithm was implemented on Cyclone IV FPGA device using Altera
DE2-115. The input video or image came from a Terasic Capacitive Multi-Touch LCD
with Camera Module (MTLC) and the outputs were displayed on a VGA monitor. All
calculations of the hardware implementation were done in real time with minimal
computational effort, thus suitable for power-limited applications.