**Scilab for Kalman Filtering**

**Practical Use of Kalman Filter with Scilab, Arduino and Webcam**

Learn how to design your kalman filter with Scilab, and test the results with hardward such as Arduino Uno and Webcam!

**“A good practrical use for Kalman Filter and its variant, the use of the webcam & the Arduino board..." **

**Course Synopsis**

**We have enhanced the training to include few soft real-time examples to make the course more interesting!**

**Course Methodology**

**Course Objectives**

This course is intended as a practical introduction to the Kalman filter and its variants. As such, there will be a series of hands-on exercises which are generally aimed to help translate the theoretical models to practical applications.

**Who Must Attend**

Scientists, mathematicians, engineers and programmers at all levels who work with or need to learn about Kalman filtering and/or state estimation. No background in either of these topics are, however, assumed. The detailed course material and many source code listings will be invaluable for both learning and reference.

**Prerequisites**

A basic knowledge of probability theory, signal processing and Scilab programming is necessary.

**What you will learn**

Basic theoretical concepts and principles of the Kalman filter and its variants

Scilab implementation of the estimation algorithms

**Course Outline**

**Fundamental of Kalman Filter and its Variants:**

**Introduction**

- The estimation problem
- The state variable model

**Kalman ﬁlter**

- Conditional mean
- State estimate and state predictor
- Minimum mean square error
- Prediction and update steps
- Innovations, Recurrence relations
- Example application
**Arduino Example:****This example will use the Scilab to communicate with Arduino and get the signal from a sensor and apply kalman filter to the signal**

**Extended Kalman ﬁlter**

- Nonlinear state variable model
- Taylor series expansion
- Prediction and update steps
- Recurrence relations
- Example application

**Unscented Kalman ﬁlter**

- The unscented transform
- Sigma points, Prediction and update steps
- Recurrence relations
- Example application
**Mouse cursor tracking example – This example extend the kalman filter to the 2D surface and track the coordinates x and y, of which is the mouse cursor.**

**Ensemble Kalman ﬁlter**

- Ensemble points
- Prediction and update steps
- Recurrence relations
- Example application

**Particle ﬁlter**

- Monte Carlo integration
- Importance sampling
- Sequential importance sampling
- Degeneracy phenomenon
- Resampling
- Example application
**Webcam example – Using the webcam participants will get the webcam connected to Scilab and applying particle filter in real-time to detect the location of an color object.**

**Summary**