Objective

The project implemented a face-detection application on the Altera SoCKit development board. The board combines an ARM processor subsystem with FPGA fabric. The work covered the hardware configuration and software needed to capture a USB camera image and process it with OpenCV.

Implementation

QSys and Quartus were used for board configuration. A Linux build prepared with the Linaro toolchain included USB Video Class support for the webcam. OpenCV and the face-detection application completed the processing path. The repository contains thesis documents, development material, and demonstrations of board startup and camera operation.

Results

The integrated application was compared with an Intel Core i7-2670QM system using a standard Lena image. The thesis reports the SoC implementation as approximately 43% slower for that setup and workload. The implementation established a software baseline; FPGA acceleration was proposed as subsequent work.

Publication

The research was carried out in 2013–2014. The related paper, “Integration of OpenCV and Cyclone V Hybrid ARM and FPGA SoC for Face Detection Application,” was published in the ISCIT 2023 proceedings. I am its first author.

Demonstrations

Sources

  1. SoCKit computer-vision research archive
    bangonkali · GitHubSource preview
  2. SoCKit thesis · abstract
    Gil Michael RegaladoSource preview
  3. SoCKit thesis · conclusions and recommendations
    Gil Michael RegaladoSource preview
  4. Microelectronics Laboratory · research publications
    MSU-IIT Microelectronics LaboratorySource preview