Download presentation
Presentation is loading. Please wait.
Published byHeather Waters Modified over 8 years ago
1
1 2012 IEEE International Conference on Multimedia and Expo
2
2
3
Limitations a) object tracking is limited to the image plane, not in the physical world [4]. b) it assumes static background [1]. c) it incurs high computational complexity.[6] [1] R. Rosales and S. Sclaroff, “3D Traject Recovery for Tracking Multiple Objects and Trajectory Guided Recognition of Actions,” [4] S. Weng, C. Kuo and S. Tu, “Video object tracking using adaptive Kalman filter,” [6] M. Roh, T. Kim, J. Park and S. Lee, “Accurate object contour tracking based on boundary edge selection” 3
4
Light-weight computing due to the limited computation power of smartphones, complex algorithms requiring high time complexity and space complexity will not fit. Reasonable accuracy to estimate a remote target position based on video, an accurate tracking with the object boundary appropriately identified is very important. Interactive user interface Input from user’s interaction is a unique feature on smartphones and is very useful for video tracking. 4
5
[13] D. F. Dementhon and L. S. Davis, “Model-based object pose in 25 lines of code,” 5
6
6
7
7
8
8
9
9
10
Optical Flow Tracking [18]Patch Classification [18] B. D. Lucas and T. Kanade, “An interactive image registration technique with an application to stereo vision”. 10
11
shows the moving object’s optical flow features. 11 Variance (noise)
12
12
13
13
14
14
15
L ’s gray scale intensity value at frame t motion compensated prediction residual errors 15
16
threshold value 16
17
17
18
18 threshold value
19
19
20
20
21
21
22
22
23
Kalman gain Correct State prediction Covariance prediction Prediction Correction 23 noise measurement error Observation model Observation matrix
24
24
25
25
26
26
27
27
28
28
29
29
30
30
31
31
Similar presentations
© 2024 SlidePlayer.com Inc.
All rights reserved.