Daniel Bardsley

A curious mix of personal shenanigans and computer vision research

Lizzard Fight

Comments Off on Lizzard Fight

Ahh, the sun is back out in Orlando despite google telling me there was going to be storms. Here are todays photos.

I’m off out for a big fat US steak. Sure I’ll post again tomorrow…

Sunshine State?

Comments Off on Sunshine State?

Rain in OrlandoBah, rained all day yesterday so we went shopping. The pictures from the trip are in the gallery.

Something random I noticed in the mall was that they bleep God out of songs over here: “This ain’t an a scene it’s a *bleep* damn arms race…” WTF?

The sun is shining today. No time to type – we’re off out.

You can view todays photos here.

Orlando Photos

Comments Off on Orlando Photos

Orlando HotelI’ve added the first set of photos from Orlando. Check out the photo gallery using the link on the right. More updates coming as I take more photos!

Orlando

Comments Off on Orlando

I’m in Orlando for the next two weeks for the Defence and Security Symposium. I’ve got internet access in my room so pictures and updates will be coming soon!

Synthesis of video realistic facial animations

Comments Off on Synthesis of video realistic facial animations

One of my colleagues (Leif Oppermann) recently visited the 2007 game developers conference and told me about some quite amazing work by Silicon Studio. Their Motion Portrait software uses model based reconstruction to create a 3D head model from a single frontal image of a subject. The model is then fully animated and capable of a wide range of human expression.

This is exactly what I’m trying to achieve at this stage of my research. Shame this blows anything I’m likely to be able to construct out of the water!

Check out the video below for a demonstration from the show.
Read the rest of this entry »

Full Body Animation

Comments Off on Full Body Animation

Full body trackThe new scientist is running an article on full body capture techniques. From the article: A 3D animation technique that could take the hard work out of acting has been developed by German researchers. It allows a high-resolution 3D scan of one person to be pasted on to another person’s movements.

Team members from the Max Planck Institute for Computer Science in Saarbrücken, Germany, say their technique is faster than traditional animation methods. Usually animators must design a skeleton to go inside a character and ensure its movements translate into realistic deformations of the outer surface.
Read the rest of this entry »

Homemade Contraption

Comments Off on Homemade Contraption

This is an excellent example of a Rube Goldberg Machine. A Rube Goldberg machine or device is any exceedingly complex apparatus that performs a very simple task in a very indirect and convoluted way.

I first saw this on the TV program homemade but the original video is at: www.baynhamtyers.com (in the videos section). There are another couple of contraptions too, so it’s well worth checking out.

My favorite is shown below:
Read the rest of this entry »

Surveillance Cameras Get Smarter

Comments Off on Surveillance Cameras Get Smarter

Flow control exampleThe International Business Times is running a report on the future of surveillance cameras. The latest generation of surveillance cameras are aiming to provide a greater degree of video analysis in order to ease the burden of conventional human based video monitoring. Using algorithms to monitor crowd movement or suspicious behaviour, human operators can be alerted faster to potential problems.
Read the rest of this entry »

Automatic Facial Animation Analysis

Comments Off on Automatic Facial Animation Analysis

A number of recent research projects have been focusing their attentions to the open-ended problem of generating realistic facial animations from 3D head models. Initially we discuss the motivation for researching automated facial animation methods. Secondly we investigate a variety of traditional and cutting edge approaches to the problem.

Download: Automatic Facial Animation Analysis (pdf)

3D Reconstruction and Recognition

Comments Off on 3D Reconstruction and Recognition

Accepted for publication in: Biometric Technology for Human Identification IV 2007

Download: 3D Reconstruction and Recognition (pdf)

In this paper we propose a novel 3D face recognition system. Furthermore we propose and discuss the development of a 3D reconstruction system designed specifically for the purpose of face recognition. The reconstruction subsystem utilises a capture rig comprising of six cameras to obtain two independent stereo pairs of the subject face during a structured light projection with the remaining two cameras obtaining texture data under normal lighting conditions. Whilst the most common approaches to 3D reconstruction use least square comparison of image intensity values, our system achieves dense point matching using Gabor Wavelets as the primary correspondence measure.
Read the rest of this entry »