The face recognition demo shows person facial feature training via a single photo and subsequent face matching on the live video stream, using VisionLabs’ library integrated onto the H22 System on a Module (SoM).

This demo showcases real-time Human Pose Estimation, based on the Open Pose library, ported onto the camera platform, and designed by Rhonda’s Activity Recognition neural network for human behavior recognition. The two Deep Learning Neural Networks (DNN), along with the video pipeline, run on the Rhonda Software CV22 System on a Module (CV22 SoM).

Introduction

Rhonda software specializes in developing video analytic algorithms, including hardware development for FPGA. Lattice HDR-60 Evaluation board was selected as a development platform. A typical development cycle consists of implementing all required modules in VHDL or Verilog programming language and then debugging them in a simulator. When debugging of individual components is complete, they are integrated and tested on actual FPGA hardware. If something is not working as it should, debugging the hardware video analytics algorithms on the actual hardware can be a challenge, especially if no soft-core CPU is instantiated. HDR-60 board has a camera sensor (input) and an HDMI output. So, many video analytic algorithms take input video signal from the camera, process it and send resulted output video stream to HDMI. If something is not working and the results you see are not what you expected, you have very limited means of debugging.

Recently, Rhonda Software took yet another step towards more power, area and cost effective solutions targeting broad range of embedded devices. In an effort to make one of our leading solutions myAudience-Count embedded-friendly, different possibilities were considered. Here is where FPGA technology came at hand.

myAudience promo video

Rhonda Software will participate in Customer Engagement Technology World (CET World) in San Francisco, April 27-28, 2011. We are pleased to invite you to visit our booth #235.

We’ll be glad to have this chance to introduce you our innovative system myAudience – tool for automated audience measurement for digital signage, kiosks, showcases and many others. You can click this special link to register.

Your special PRIORITY CODE will automatically appear with your registration, giving you a FREE exhibits only pass. For up-to-date information about Customer Engagement Technololgy World, please visit www.CETworld.com.

Performance is essential for video analytic applications since algorithms are usually computationally heavy and such systems are supposed to work almost in real time. From one side it can be increased by improving & changing algorithms. This is a major way since it allows to increase performance dramatically. From another side performance can be increased little bit more by relatively simple way – using of good compiler and by tuning of compile options. Let see how it can be done in real programs.

A modern video analytic system depending on business/customer requirements should work in different situations/conditions. Complex, noisy background with many different objects/textures, changing lighting conditions, shadows, lack of light, weather conditions (for outdoor system installations) like rain, snow, fog and others, motion blur, camera movements, cameral sensor quality, camera resolution, camera focus issues, camera internal optimizations, color temperature, end many other factors make development of the good object recognition software a challenging, almost impossible task. In addition, the usual requirement is that the system should work in real time, which makes this task even more difficult.

2D face recognition is an extensively studied, but still evolving subject of research. Various strategies including statistical approaches, hidden Markov models, neural networks, template based and feature based matching have been proposed. Here we briefly present our implementation which is based on past research and achieves state-of-the-art recognition performance on considerably low resolution input facial images.
Our approach can be divided into three independent phases: Facial landmarks library construction (offline), Building of facial descriptor (once per novel image) and Facial descriptors matching.

Currency recognition seems to be one of the popular topic in “applied” computer vision. There are a lot of articles, blog entries describing different approaches to currency recognition. In this post I’ll share my experience of using so-called HMAX model.

Build platform: Ubuntu 9.10
Target platform: Android

Download and prepare OpenCV library source code.

1. Download the latest version of OpenCV (http://sourceforge.net/project/showfiles.php?group_id=22870).

2. As build platform is Linux, select linux version (for example OpenCV2.1.0.tat.bz).