Saturday, 21 July 2012

AndroidWifi is live!

Following my post few months back about how to set up a simple script to share your connection with Android devices in particular, I found that there was no application which provided full capabilities as my batch scripts did. I started work on a very simple application to convert these scripts into an easy to use application. Today I am releasing first version of this application.




Why AndroidWifi?
While reading this post, some of you might be wondering, why use AndroidWifi? why go through all these steps?

The answer is simple. This is the only free software available to date which enables you to share all types of internet connections over wifi.

These include:
  • 3G dongle internet
  • Wired internet
  • Wifi internet from another router
  • internet accessed through USB adapters

Update 13/08/2013: I am seeing people copying this blogpost as it is on their blogs. For this reason I have put a password on the file.

The software can be downloaded at: AndroidWifi_0.9  AndroidWifi_0.91 AndroidWifi_0.95
Download password: seevisionc.blogspot.co.uk

Friday, 20 July 2012

Congestion? Not a problem!

This post is about another course project which I did for my Master's degree in Computer Vision Engineering. It's as simple and innovative as it could get. The idea is to estimate the flow of traffic in real-time using the CCTV video. Four categories of congestion/flow are first categorized, which are Low, Medium, Medium-High and High Congestion.

Here is a short demo video for this project:



While implementing this, the most difficult part was to distinguish between Medium-High and High Congestion, as both types of congestion have data which overlaps and is difficult to model with a machine learning algorithm such as K-means Clustering.

Wednesday, 4 July 2012

Compiling OpenCV with OpenNI for Microsoft Kinect Sensor

I have implemented code for using OpenCV 2.4.x with latest OpenNI 2.x SDK. Detailed tutorial and code on this newer method can be found here

After installing OpenNI, as I am more familiar with OpenCV, therefore I wanted to work with the data from Kinect sensor using OpenCV. I searched online and a lot of people had been able to compile and run OpenCV with OpenNI. However I could not find any guide on how to do this. I managed to compile OpenCV successfully with OpenNI after some research, and now I am writing this tutorial for those of you who are in the same situation as me.

If you already know how to compile OpenCV with Visual C++ then this tutorial will be straight forward for you. However for completeness sake I will write everything in detail, so even if you are new to OpenCV you wont have any problems compiling from the source code.

If you want to use OpenCV with Microsoft Kinect using OpenNI SDK then, obviously, the first pre requisite is that you should have already installed and set up Kinect sensor using OpenNI and NITE libaries. If you have not already done that then please head over to OpenNI installation Tutorial and first install everything needed to set up. If you have successfully set up everything correctly then precompiled samples inside OpenNI and NITE folders should be working with your Kinect Sensor., which means you are good to go with this tutorial.