Connected Component Labeling (CCL): “is used in computer vision to detect connected regions in binary digital images”, and sometimes referred to as blob coloring. Motivation: To keep AccelerEyes’ ever expanding GPU library growing, over a few weeks of this summer I took on the project of writing a CUDA version of connected component labeling to be used in … Read more
Usually, when I’m using GIMP to edit pictures, there are a couple of simple enahcnements I routinely apply to each image. So, I’m slowly learning GIMP scripting and creating some simple GIMP scripts to help automate some steps in my digital darkroom workflow. Here are two scripts that I’ve come up with so far, that … Read more
April 2011 Abstract As a final project for my Computational Photography class at Georgia Tech, I created an application that uses a single video camera to create tonemapped HDR images in real time. This project’s inspiration comes from Soviet Montage Production’s DSLR HDR video. The app runs on Linux PCs (using USB or Firewire … Read more
March 2011 With the help of Motodev Studio for Android, I’ve extracted the android-opencv JNI camera example and spawned a fork of my original computer vision app, Viewer, to an OpenCV version: ViewerCV. Both are available on Git Hub as open source software example of doing Computer Vision on Android with OpenCV. Viewer Features: *FAST Features (default android-opencv example) *Square detection *Sobel … Read more
January 2010 Over the holiday break, I finally created an Android app that allows image processing on the camera’s raw data, and displays it back on the screen. It only uses Java on the CPU for now, but in my free time I’ll be porting the code to OpenGL ES to run on the GPU, and … Read more
March 2010 I recently started playing with the Nvidia CUDA SDK Samples involving image processing. I extracted the SobelFilter kernel and made it run off my USB webcam using OpenCV – the two live modes are single-channel-gray and three-channel-rgb. I wrote two different basic kernels on my own that did binary thresholding and found the most dominant RGB value. Now on Google Code! cam-cuda-sobel
July 2009 I competed in the 2009 Intelligent Ground Vehicle Competition, on the Georgia Tech RoboJackets Team. Our robot: Candi. I developed the computer vision algorithms to navigate an autonomous vehicle using only a vision camera. Our team ranked 6th place nationwide. Competition photos here. I wrote all of the vision and mapping code! The robot navigated using a single camera only. … Read more
September 2008 A project at GTRI FPTD I worked on involving combining a color vision system with a 2D laser projector. Case Study about the project here: Using Lasers to Identify Substandard Food. With Python and OpenCV, I got the system to find contours with the camera, and tell the laser to draw them in real-time. The goal was to … Read more
After installing the new plug-in registry for GIMP, I stumbled upon the amazing National Geographic Script. It is incredible! This script simulates high quality, vivid photos – like the ones from the National Geographic magazine. It uses a configurable mixture of shadow recovery, sharpening, local contrast, and various color overlay layers. The script is buried … Read more