INFO0903 Introduction to Artificial Intelligence and Computer Vision
Table of Contents
1.
An Abstract View of Tracking
2.
Modeling the State
3.
Representing the State and the Observations
4.
Independence Assumptions
5.
Recursive Inference of the State
6.
How to compute these guys?
7.
Modeling State Dynamics
8.
Linear Dynamic Models Under Gaussian Noise
9.
1D Quick-Thinks
10.
2D Quick-Thinks
11.
Constant Velocity
12.
Constant Acceleration
13.
More Complicated Models
14.
The Kalman Filter
15.
A Linear, Recursive Estimator
16.
Example: Kalman for a 1D Drifting Point
17.
The Kalman Filter Equations
18.
Intuitions
19.
Example: Constant Velocity, Noisy Measurements
20.
Example: Constant Acceleration, Less Noisy Measurements
21.
Limitations
22.
Data Association and Gating
23.
How to deal with missing or multiple measurements?
24.
How about spurious measurements?
25.
Conclusion
26.
Conclusion
27.
References