Tuesday, July 19th, 2016, 1 year ago
Write before the post
There have been over tens of thousands of devices that are equipped with bluetooth and are capable of connecting to other devices such as mobile phones. Also, there are numerous tutorials and instructions around the internet telling people how to setup all kinds of bluetooth devices and configure the connection. However, an interesting thing is, if searching bluetooth connection in google, there are far more questions and errors than solutions and successful project. So I am motivated to write down my experience of setting up bluetooth connection between a raspberry pi 3 model B and a Marshmallow Android mobile phone.
1. A brief background
The project background was to setup bluetooth connection to send sensor data to mobile phone, so the phone can visualise and responds to the sensing results. The sensor was connected to RPi through I2C interface, RPi 3 had necessary pins of SDA, SCL, 3V3, and GPIOs. Because this is not the key part of the bluetooth connection, I just make a quick explanation here.
By the time of writing the post, there are three general bluetooth versions that are available for remote connection, including the conventional bluetooth 2, bluetooth low energy (BLE) and bluetooth smart. In the following project, the conventional bluetooth and the BLE were explored, but only the former was successfully implemented.
Tuesday, July 7th, 2015, 2 years ago
After long ages of not updating the blog, this is a new start with a new interactive device.
Saturday, January 11th, 2014, 4 years ago
This book is quite interesting in guiding starters from knowing-nothing to basic image processing. Also it is a good learning material for emgu cv based image processing.
In chapter 1, an introduction to emgu cv is given, along with the comparisons between the native openCV and other computer vision libraries. However, this part seems somehow over emphasised as the comparisons between the libraries cannot bring too much value to readers who want to learn emgu CV and how to use it in programmes. So, the advantages of emgu CV that are presented in forms of practical examples may give more benefits to readers.
Monday, July 1st, 2013, 4 years ago
Extending openCV from pure 2D world to 3D environments seems challengeable – the first one is to find out the a 3D engine to support 3D rendering, based on the data gained from openCV. Irrlicht engine is seemed as a good option, as it provides good supports to 3D rendering with open source codes. However, compiling the engine for ubuntu & eclipse use is not an easy job. When I tried to run the first helloworld example, the problem popped up –
Undefined reference to 'createDevice()'.
Friday, June 28th, 2013, 4 years ago
OpenCV 2.4.5 has released and it is exciting to take a bite.
So openCV is downloaded and compiled, but when it is to play video files, an error popped up:
libopencv_highgui.so.2.4: cannot open shared object file
Wednesday, March 20th, 2013, 4 years ago
The video vibration is annoying, because as we know it, this causes big barriers to programmers from recognising objects/people accurately. However, the thing is, when the vibrations are amplified, i mean hugely amplified with a set of algorithms, there are amazing results happenning, as demonsted in this picture.
Thursday, November 8th, 2012, 5 years ago
The release of HAAR training classifier for hand gesture detection
This is the last post of the GSoC hand gesture detection series, and the trained HAAT classifier is finally released here.
This is only a short announcement, but the classifier in .xml file can be reached here in https://github.com/yandol/GstHanddetect.
The release contains two .xml classifier files, respectively they are for CLOSED PALM and FIST detection.
Hope this is useful.
Thursday, November 8th, 2012, 5 years ago
A previous article has described a method to detect and recognise hand gestures using OpenCV, actually the c# wrapper of OpenCV called emgu CV. Details of this method can be found here a method of detecting and recognising hand gestures using Opencv. But Tongo’s project wrapped in emgu CV may not be easy to configure, so this article gives a new example transfering thet project to plain c++ OpenCV environment.
Saturday, September 29th, 2012, 5 years ago
The first try of HAAR training was based on the tutorial mentioned in the previous post (see Collection of own hand gesture samples – the call for pictures, training method, tool and results). The aim was to go through all steps of HAAR training and see:
1) How positive and negative samples should be captured and setup for training?