Computer tracking and analysis of field sports using multi- camera angles is nothing new, but how about taking the brain’s own system for picking what it wants to watch and using it to improve live broadcast programming and post-match analysis?

Senior Lecturer in Information Science Dr Jeremiah Deng is working with PhD candidate Munir Shah, Dr Brendon Woodford and Professor Martin Purvis on sports-related computer vision research.

Dr Deng says computers are already able to do a lot of things, including tracking the ball and the players, and knowing which player belongs to which team.

“The idea is not new, but the approach we want to take is. Our model is inspired by the human biological neuron system. When you watch a movie or a rugby game you have numerous neurons working together processing the flow of information. We are adapting that model using smart algorithms implemented on multi-core computers and using multiple digital cameras. It will give us a better chance of understanding the game and detecting interesting events.

“In sports broadcasting you have a lot of cameras trained on a field and someone manually choosing which shot to use. Instead we can have the computer choose which angle gives the best view, instantaneously.”

Dr Deng envisages using the system with multiple overhead ‘spider cams’ that ‘fly’ over a field game, assisting referee decision- making.

“Fouls, faking, offsides, dives, and other infringements would all become much more apparent, reducing human error,” he says.

Mr Shah says the enhanced footage would help coaches and players analyse their performance.

PhD candidate Munir Shah, Dr Brendon Woodford and Dr Jeremiah Deng are part of a team looking to vastly improve the quality of sports video recording by mimicking our brain’s visual processing methods.

“Our model is inspired by the human biological neuron system.”

He says the research is primarily focused on soccer footage, but the technology could be fine-tuned to any field sport, rugby included.

Computer vision research associated this work has been supported by two University of Otago grants, with results published in the top tier journals including Pattern Recognition.

ML has been around for quite sometime now! These are definitely some interesting papers to read on this Springer website.

Random forests, SVM, relational learning ……

What’ the next big thing, you wonder? Time to make your footprint there?

In a way, all those research directions relate somehow to data mining and machine learning.

There are so many cool things we could do, but we need more smart minds to brave out new ideas and more nifty hands to write code and conduct experiments!

The link: http://metaoptimize.com/qa/questions/3163/good-machine-learning-blogs

Cheers!

Andy

• 3rd Asian Conference on Machine Learning ACML 2011, Nov., Taiwan, submission date: 19/7, 2011
• ICONIP 2011, Shanghai, 14/11., deadline: 1/6
• ACPR, 1st Asian Conference on Pattern Recognition, 28/11, deadline: 15/6
• ICDM’11, Vancouver, 11/12, deadline: 17/6
• AI’2011, Perth, 5/12, deadline: 28/6

CVPR’11 has finished paper review and it’s interesting to see the acceptance across subject areas.

Mental illness diagnosis using physiology - it is possible

I have probably mentioned too many applications of machine learning and data mining in the 1st lecture.

To add to the already long list, here is an interesting article about an IEEE Spectrum article that a Harvard Medical Research that enables computers to detect and diagnose mental diseases such as bipolar and depression. Clues? EEG signals, and fMRI brain imaging. Techniques? Machine learning algorithms.

I am pretty sure everybody agrees mining is dirty and risky. So congratulations to everyone for surviving the first semester of our Data Mining paper.
Actually I think we did better than surviving. I’ve seen quality work in the labs, and really enjoyed the presentations – I found a lot of gold there.
To sum up our first semester our lab and assignment work (t.b.p., p for published) will be a good place for you to try things out from Weka and apply them into a small problem solving task.
It is of course more than appropriate for me to post out the comments for our presentations. I go after the presentation order.
Presentation 1. Face Recognition.
This relates to a specific application but Maheshwar managed to present a good background and history line about the face processing: detection, verification and recognition. The Haar-like features were explained. The introduction to the AdaBoost algorithm was concise and clear, but I feel some more details could be helpful. I hope you’ll find this presentation make more sense after Lecture 8.
The class basically rank the presentation as ‘Good’(3)/’Excellent’(1)
, and suggest using more diagrams in explanation, and also giving information about the state of art – how effective can computers do face recognition now?
Presentation 2. GESCONDA.
This presentation gives us a new perspective about building a domain-specific system for intelligent data analysis. Apart from a very smooth introduction about the system, what I really liked about this presentation is Max’s critics especially on the authors (lack of) justification about particular inclusion and treatment of various algorithms for the domain of environmental data analysis. How the agents interact is not clear either.
GESCONDA is an old system that doesn’t seem to be supported anymore apart from being cited favourably. So it is hard for us to get more information or even download it to have a try. However, I would have hoped that Google had helped us to find some other pointers – e.g., this conference article by the same group actually contained more examples. Take a look if you are interested in doing a similar system for a particular domain, say, in the 2nd semester.
The class, feeling more examples would be helpful, enjoyed the presentation and ranked it Good(3)/Excellent(1).
Presentation 3. Distributed Data Mining in P2P networks
This is an interesting topic and gives us a complementary picture of large-scale, distributed data mining problems in real-world scenario. The background about P2P networking was presented and the requirements for distributed data mining were outlined well. It’s good effort for Ethem to drill down into specific algorithms and presented diagrams etc. to show us the ideas behind the algorithms. The approximate k-means was explained well. Anybody who’s interested in implementing such a local/collective algorithm?
The class voted Good(3)/Fair(1) on this presentation, but given the complexity of the algorithms I feel it is a good talk.
Presentation 4. Anomaly Detection
This is a very interesting topic and I think Rui made a wise decision to focus on the big picture and gave very good coverage on the problem and major approaches. I liked the parts on contextual anomalies and the three types of learning. What the class feels lacking is some specific techniques as examples.
The votes are on Good(2)/Excellent(1)/Fair(1).
Presentation 5. LOF
This aligns well with the last presentation but focuses on a specific outlier detection algorithm. Thanks to Shuang’s great effort in understanding and presenting the algorithm in a way we all feel we know what it is about. It’ll be great if we can implement an (improved) version of this popular algorithm and conduct some comparison study. The paper has an experiment of looking for odd records of Bundesliga football players, and there are other interesting applications too , e.g. video shot boundary detection.
If you are interested in implementing a LOF-like algorithm, read this follow-up paper too.
Presentation 6. Soccer video analysis
The title says it all – this is a very interesting and also complicated topic. Every single steps require considerable machine learning techniques, from image segmentation, recognition, and tracking. Thankfully we have someone like Munir who is never afraid of details. The tracking part of the paper seems to be a weakness since without a frame-by-frame tracking approach using e.g. particle filters, the ambiguity of player identities may become a problem when they move near each other or even occlude (unfortunately this happens very often). Still a challenging task but promisingly a lot of fun – any volunteers to work with Munir?

• “Hey dad, can your program tell the twins apart?”
• “Can your algorithm be parameters free?”

Any more?

Let's Face it.

Someone volunteers a 411 talk on this subject?