Target Tracking a Non-Linear Target Path Using Kalman Predictive Algorithm

1
Target Tracking a Non-Linear Target Path Using
Kalman Predictive Algorithm

• byJames Dennis Musick

2
Agenda

• Introduction
• Problem Definition
• Centroid Algorithm
• 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
• Centroid calculation
• Prediction
• Discrimination

5
Problem Definition cont.

• Trials used
• Walking Trial
• Jumping Trial
• Waving Wand Trial
• Increasing complexity

6
Centroid Algorithm

• Introduction
• Scanning scheme

7
Centroid Algorithm cont.

• 640 x 480
• 307200 pixels
• 8-bit Gray-scale
• Block diagram

8
Centroid Algorithm cont.

• Threshold

9
Centroid Algorithm cont.

• x/y addressing

10
Centroid Algorithm cont.

• Target Pixel Discrimination Buffer
• x_sum, y_sum, LS_target, RS_target, Bot_target,
  target_pixel_num

11
Centroid Algorithm cont.

• Logic Control and Centroid Calculation

12
Centroid Algorithm cont.

• Centroid Memory Buffer
• Once a target is completed (defined as no pixels
  within the search criteria at the row just below
  the target), then the centroid data is stored in
  a memory array until the data is read out at the
  end of the number of pictures that are being
  analyzed.
• The array would be structured in the following
  manner if there were three targets in each of 5
  pictures
• Target_Centroid_Array (xy,Target , Picture )
  gt (12, 13, 15).

13
Centroid Algorithm cont.

• Examples

14
Centroid Algorithm cont.

• Performance and Limitations
• Three targets simultaneous
• Total number

15
Centroid Algorithm cont.

• 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)

16
Kalman Filter

• Introduction
• State Space representation

17
Kalman Filter cont.
18
Kalman Filter cont
19
Kalman Filter cont
20
Kalman Filter cont

• Target Models
• Noisy Acceleration model

21
Kalman Filter cont

• Target Models
• Noisy Jerk model

22
Kalman Filter cont

• Selection of update time
• T 1

23
Kalman Filter cont

• b

24
Kalman Filter cont

• Operation of the Kalman Filter

25
Kalman Filter cont

• Operation of the Kalman Filter

26
Kalman Filter cont

• Operation of the Kalman Filter

27
Kalman Filter cont

• Operation of the Kalman Filter

28
Kalman Filter cont

• Operation of the Kalman Filter

29
Kalman Filter cont

• Operation of the Kalman Filter

30
Target Discrimination

• Introduction
• Goal

31
Target Discrimination

• Example

32
Target Discrimination

• Example cont

33
Target Discrimination

• Operation of algorithm

34
Target Discrimination

• Operation of algorithm cont

35
Target Discrimination

• Operation of algorithm cont

Jumping Trial
36
Target Discrimination

• Operation of algorithm cont

37
Target Discrimination

• Occluded targets

38
Conclusion

• Centroid algorithm
• Kalman filter
• Model
• Discrimination

39
Future Work

• Hardware implementation
• 3D application
• Other biomechanical target discrimination
  (segmentation, etc.)
• Other tracking application (space, robotics,
  etc.)