In this post, I will be talking about my dissertation project, which is based on Computer Vision. Lets start from the beginning, I’m working on Ball detection and distance measurement for RoboCup, specifically on NAO Robots. I’m developing this project in Java and using Java Media Framework (JMF) for visual input from webcam and grabbing frames for extracting information from them. As I mentioned earlier in this post, this program will be implemented on NAO Robots for RoboCup. It has to be really quick as ball can move around very quickly in matches. Also, it should use very low amount of resources because NAO Robot has limited resources and there will be a lot of other processing as well.
I posted ‘Real-time Shape Detection’ demonstration video long back, which is also developed in Java and follows almost same logic. However in this project, shape detection isn’t required for multiple and ‘same looking’ objects. Main target will be detecting ball only but one major problem is noise removal and high variance on lightness and surrounding colours which has high impact on the balls colour.
This is where Image Processing will be used, Noise removal and image enhancement algorithms can be applied. But Is it efficient to apply Image processing here? considering the frame processing rate as those algorithms will surely make it slow. Even with enhancement algorithms, you can’t do much about high variance on lightness. So far, all this post and development plan is focused on RGB model and even shape detection demonstration is based on RGB model as well.
The problem with RGB model is, RGB focuses on implementation details. RGB is how computer or machine treats and uses colours not how human eyes perceive colours. On the other hand, HSV focuses on actual colour components and HSV is how human eyes perceive colours. HSV can be used to find the dominating or highly influenced colour as well as its intensity.
Ironically HSV is used more than RGB for Computer Vision techniques. So right now, I’m reading and working on HSV colour model, applying it for shape detection and hoping to get better results. If all goes well, then I will be using HSV colour model for my dissertation project.
That’s it for now and I will update soon on this experiment!
Been off from blogging for almost a year. Last year was one of the busiest year of my life so far (Still my friends think I’m really free and jobless guy, duh!). One big decision and change was moving to Elance as freelancing and project management site. After the acquisition and merger of Scriptlance by Freelancer and I wasn’t really impressed by their new terms, So I decided to moved to Elance (Here’s my profile). Frankly speaking, I’m really happy with my decision and progress as an individual freelancer developer.
Officially over with second year of my degree and unofficially over with fifth semester as grades are not yet out (I just hope, I pass out in all lol). The level of exposure and experience I earned as a student here is extraordinary. Right now, I’m working on my dissertation these days which is based on Ball detection and distance measurement for Nao Robot and progressing steadily towards the end.
With development of great interest in Computer Vision and Image Processing, I have been playing around with algorithms and computer visions techniques. I have developed few applications on it and shared some of them on my Facebook page and posted videos on my Youtube channel. And yes! Finally I posted video tutorial for Sphinx 4 on Ubuntu (Here’s the link).
As freelancer, I have done about couple of dozen projects on Elance. One of the major project was StudentCore which is developed on Codeigniter framework having custom Student Forums and Book Store as key features. Surprisingly, I even did Image Analysis project on C# (Not a hater of .NET, although not even a lover lol). It was more like Quality assurance through Image analysis. Also cracked on many projects from different categories like Server tuning, jQuery and Ajax plugins, WordPress, MySQL DB Optimisation (hated that one) and more.
Very confused about my future afterwards my graduation (MSc Computing or Research?, PhD?, Job?,!@#$?). I still got a month or two in hand to make final decision on it. As long as it is related to Computer Vision and Image Processing, I’m happy with it. And this reminded me of “Augmented Reality”, (which is really awesome thing) I’m trying to crack on this in my free time. I got to know about it few days back only. However, I kind of discussed about same approach on Android based game with my friend (Didn’t knew the exact term on that time). So yea, I got hold on the basic application with 3D Box in it and now trying on some complex ones.
That is pretty much done for now, I will try my best to post on regular basis (which I will have to do anyway for my dissertation).
This category will be all about my dissertation project, which is based on Computer Vision techniques for Nao Robots in use for RoboCup. Stay tuned for further updates.