9dof-orientation-estimation - Various kind of 9 Degrees of freedom IMU orientation estimation algori
The aim of this project is to achieve efficient orientation estimation algorithms using a 9 DOF IMU. We used the iNEMO V2 as IMU; It is the inertial module unit released by ST Microelectronics (official site http://www.st.com/internet/evalboard/product/250367.jsp ). This project is done in cooperation with ST Microelectronics: R&D group, AST Advanced System Technologies / Remote Monitoring (email@example.com). We're two software engineering students of "Università degli studi di Bergamo" ( http://www.unibg.it/ ). The project has started as an academic experience related to "Progetto di Microelettronica" course, and over time it has became an hobby. We developed the following algorithms: - Complementary filter: the simplest way to estimate orientation using a 9DOF IMU. Attached in the "Download" section Matlab and C# sources. - Kalman filter: implementation of Kalman filter using quaternion as system state. Attached in the "Download" section Matlab and C# sources. - AHRS estimation algorithm: this implementation is provided by the project imumargalgorithm30042010sohm ( http://code.google.com/p/imumargalgorithm30042010sohm/ ). We inserted the source as a class into our C# project, fitting it to our IMU (downloadable in the "Download" section). There's also a report of our work attached as pdf file (Italian language). Demonstration videos: http://www.youtube.com/watch?v=p8H2-vkUM0I 2011/05/16: UPLOADED latest improvements achieved during last month. Old versions of Kalman filter, Complementary filter and C# application has been marked with the "OLD" label. 2011/12/29: We are sorry for the long time during which this site has not been maintained: in the latest months we have been busy a lot (inter alia, we got the master's degree in computer engineering). Nevertheless we have continued to work on this project in the spare time; here is below a link to a demonstration video showing our rough first prototype of a motion tracking system. As you can see, there are ONLY two BIG and WIRE CONNECTED marg sensors without the CASE. Besides, some TAPE has been used to keep them fixed on the arm, hence the system is not very precise. The software application is a NOT optimized alpha version and uses a very old version of a quaternion based Complementary Filter. http://www.youtube.com/watch?v=mn8vfYt1U1I&context=C3e2c6f5ADOEgsToPDskKHH6ybFsuhwhsC-CkazIrX Soon we'll be able to post some stuff about this work. Meanwhile, you can of course contact us! See ya in 2012...
comments powered by Disqus
HyperGraphDB is a general purpose, open-source data storage mechanism based on a powerful knowledge management formalism known as directed hypergraphs. While a persistent memory model designed mostly for Knowledge management, Artificial Intelligence and Semantic web projects, it can also be used as an embedded object-oriented database for Java projects of all sizes. It could also be used as graph database or as (non-SQL) relational database.
OpenBR is a framework for investigating new modalities, improving existing algorithms, interfacing with commercial systems, measuring recognition performance, and deploying automated biometric systems. Off-the-shelf algorithms are also available for specific modalities including Face Recognition, Age Estimation, and Gender Estimation.
OrientDB has the flexibility of the Document databases and the power of the Graph databases to manage relationships. It can work in schema-less mode, schema-full or a mix of both. It can store up to 150,000 records per second on common hardware. OrientDB has been designed to be very fast. It inherits the best features and concepts from the Object Databases, Graph DBMS and the modern NoSQL engines.
The S-Space Package is a collection of algorithms for building Semantic Spaces as well as a highly-scalable library for designing new distributional semantics algorithms. Distributional algorithms process text corpora and represent the semantic for words as high dimensional feature vectors.
A dynamic, open source programming language with a focus on simplicity and productivity. It has an elegant syntax that is natural to read and easy to write. The syntax inspired by Perl with Smalltalk-like features. It was also influenced by Eiffel and Lisp. It is a scripting language that is more powerful than Perl, and more object-oriented than Python.
Object relational mapper (ORM) for PHP that sits on top of a powerful database abstraction layer (DBAL). One of its key features is the option to write database queries in a proprietary object oriented SQL dialect called Doctrine Query Language (DQL), inspired by Hibernates HQL. This provides developers with a powerful alternative to SQL that maintains flexibility without requiring unnecessary code duplication.
Computer vision and image processing library for Qt.
JUnit is a simple framework to write repeatable tests. It is an instance of the xUnit architecture for unit testing frameworks.