Target%20Tracking%20a%20Non-Linear%20Target%20Path%20Using%20Kalman%20Predictive%20Algorithm%20and%20Maximum%20Likelihood%20Estimation - PowerPoint PPT Presentation

About This Presentation
Title:

Target%20Tracking%20a%20Non-Linear%20Target%20Path%20Using%20Kalman%20Predictive%20Algorithm%20and%20Maximum%20Likelihood%20Estimation

Description:

In the field of biomechanical research there is a subcategory that studies human ... Waving Wand Trial. Increasing complexity. Video Target Identification. Threshold ... – PowerPoint PPT presentation

Number of Views:32
Avg rating:3.0/5.0
Slides: 32
Provided by: csU75
Learn more at: http://cs.uccs.edu
Category:

less

Transcript and Presenter's Notes

Title: Target%20Tracking%20a%20Non-Linear%20Target%20Path%20Using%20Kalman%20Predictive%20Algorithm%20and%20Maximum%20Likelihood%20Estimation


1
Target Tracking a Non-Linear Target Path Using
Kalman Predictive Algorithm and Maximum
Likelihood Estimation
  • byJames Dennis Musick

2
Agenda
  • Introduction
  • Problem Definition
  • Kalman Filter
  • Target Discrimination
  • Conclusion
  • Future Work

3
Introduction
  • In the field of biomechanical research there is a
    subcategory that studies human movement or
    activity by video-based analysis
  • Markers used
  • Optical
  • RF
  • Passive reflective
  • Etc
  • Video based motion analysis
  • 2D Analysis
  • 3D analysis
  • Golf swing example

4
Problem Definition
  • In order to track the following have to be
    accomplished
  • Path Prediction
  • Discrimination

5
Problem Definition cont.
  • Trials used
  • Walking Trial
  • Jumping Trial
  • Waving Wand Trial
  • Increasing complexity

6
Video Target Identification
  • Threshold

7
Target Algorithm Uncertainty
  • Measurement Uncertainty
  • Correct (3.5,4) Correct (3.5,3)
  • Blue missing (3.5,4) Red missing (3.8,3.17)
  • Red missing (3.64, 4.21)

8
Kalman Filter
  • Introduction
  • State Space representation

9
Kalman Filter cont.
10
Kalman Filter cont
11
Kalman Filter cont
12
Kalman Filter cont
  • Target Models
  • Noisy Acceleration model

13
Kalman Filter cont
  • Target Models
  • Noisy Jerk model

14
Kalman Filter cont
  • Selection of update time
  • T 1

15
Kalman Filter cont
  • b

16
Kalman Filter Noisy Acceleration
  • Operation of the Kalman Filter

17
Kalman Filter Noisy Acceleration
  • Operation of the Kalman Filter

18
Kalman Filter Noisy Acceleration
  • Operation of the Kalman Filter

19
Kalman Filter Noisy Jerk
  • Operation of the Kalman Filter

20
Kalman Filter Noisy Jerk
  • Operation of the Kalman Filter

21
Kalman Filter Noisy Jerk
  • Operation of the Kalman Filter

22
Kalman Filter
  • Occluded targets

23
Target Discrimination
  • Introduction
  • Goal

24
Target Discrimination
  • Example

25
Target Discrimination
  • Example cont

26
Target Discrimination
  • Operation of algorithm

27
Target Discrimination
  • Operation of algorithm cont

28
Target Discrimination
  • Operation of algorithm cont

Jumping Trial
29
Target Discrimination
  • Operation of algorithm cont

30
Conclusion
  • Kalman filter
  • Model
  • Discrimination

31
Future Work
  • Hardware implementation
  • 3D application
  • Other biomechanical target discrimination
    (segmentation, etc.)
  • Other tracking application (space, robotics,
    etc.)
Write a Comment
User Comments (0)
About PowerShow.com