Без темы
<<  SATURN – GAS TURBINES POWER GENERATING AND GAS COMPRESSOR SETS Science and Technology Destination  >>
Scene-Consistent Detection of Feature Points in Video Sequences
Scene-Consistent Detection of Feature Points in Video Sequences
Outline:
Outline:
Task Definition:
Task Definition:
Operator for Feature Detection
Operator for Feature Detection
Operator for Extracting Certain Gradient Orientations
Operator for Extracting Certain Gradient Orientations
Response of Yarg to the Intensity Surface
Response of Yarg to the Intensity Surface
Response of Yarg to the Intensity Surface (cont
Response of Yarg to the Intensity Surface (cont
Response to Local 3D Scene Structure
Response to Local 3D Scene Structure
Tracking Algorithm
Tracking Algorithm
toys
toys
parking
parking
traffic
traffic
Evaluating the Performance of the Algorithm
Evaluating the Performance of the Algorithm
Measures for Evaluation of Scene-Consistency
Measures for Evaluation of Scene-Consistency
Measures for Evaluation of Scene-Consistency (cont
Measures for Evaluation of Scene-Consistency (cont
Tracking Comparison
Tracking Comparison
Completeness:
Completeness:
Experimental Results
Experimental Results
Summary
Summary
Summary (cont
Summary (cont

Презентация на тему: «Scene-Consistent Detection of Feature Points in Video Sequences». Автор: arielt. Файл: «Scene-Consistent Detection of Feature Points in Video Sequences.ppt». Размер zip-архива: 907 КБ.

Scene-Consistent Detection of Feature Points in Video Sequences

содержание презентации «Scene-Consistent Detection of Feature Points in Video Sequences.ppt»
СлайдТекст
1 Scene-Consistent Detection of Feature Points in Video Sequences

Scene-Consistent Detection of Feature Points in Video Sequences

Ariel Tankus & Yehezkel Yeshurun

CVPR - Dec. 2001

Tel-Aviv

University

2 Outline:

Outline:

Relating convexity-based detection of feature points to scene geometry. Feature points tracking algorithm. Comparison with two other methods. Measures for evaluation of tracking algorithms w.r.t 3D scene-consistency.

3 Task Definition:

Task Definition:

Robust detection of scene-consistent features in video sequences.

Object recognition. Correspondence points for recovering 3D characteristics of the scene.

Convexity.

Goals:

Intrinsic Property:

4 Operator for Feature Detection

Operator for Feature Detection

?

Detect convex or concave image domains.

Detect local “circles” where the gradient of the intensity function points outward along the whole circle.

The gradient points in all orientations along the “circles”.

(motivation)

Equivalently:

5 Operator for Extracting Certain Gradient Orientations

Operator for Extracting Certain Gradient Orientations

At the discontinuity ray of the arctan: Yarg??.

Darg - An isotropic variant of Yarg.

6 Response of Yarg to the Intensity Surface

Response of Yarg to the Intensity Surface

Examine Yarg in well behaving image domains. Intensity is twice continuously differentiable.

We examine all possible intensity configurations. Four of them lead to infinite Yarg response.

The basic observation:

7 Response of Yarg to the Intensity Surface (cont

Response of Yarg to the Intensity Surface (cont

?

The cases include: Some configurations where is a local extrema of , and some configurations where one side of is flat, but the other is convex or concave.

Only specific differential geometry structures of the intensity function causes Yarg??.

8 Response to Local 3D Scene Structure

Response to Local 3D Scene Structure

?

?

Yarg responds to certain geometric features of the 3D scene object.

Yarg?? for certain elliptic, hyperbolic or parabolic points on a Lambertian 3D surface illuminated by a point light source at infinity.

9 Tracking Algorithm

Tracking Algorithm

Stable points: points where . These points are the only input to the point tracker.

10 toys

toys

#28

#8

#16

#36

#24

#44

11 parking

parking

#200

#50

#100

#225

#150

#250

12 traffic

traffic

#5

#55

#65

#10

#70

#15

13 Evaluating the Performance of the Algorithm

Evaluating the Performance of the Algorithm

Two measures for evaluating performance of scene-consistent point tracking algorithms. Each measure aimed at a different task: Maximal tracking time. Correspondence of points in successive frames. Their common goal: to quantify the consistency of tracks with 3D scene.

14 Measures for Evaluation of Scene-Consistency

Measures for Evaluation of Scene-Consistency

Completeness: A track is complete if the same 3D scene point is being tracked, up to a certain level of noise, in every frame where it appears.

Correct 3D point of track T = 3D point tracked for the longest time under track T

15 Measures for Evaluation of Scene-Consistency (cont

Measures for Evaluation of Scene-Consistency (cont

Stability:

16 Tracking Comparison

Tracking Comparison

We compare the Darg-based algorithm with two other algorithms: Junction detection (Lindeberg). with automatic scale selection. Tracking by Kalman filter. KLT (Kanade-Lucas-Tomasi). Tracker based on affine image change model. Features maximize tracking quality.

17 Completeness:

Completeness:

Stability:

18 Experimental Results

Experimental Results

Darg is more stable the Junction detection, and sometimes more than KLT. Sometimes Darg equates with KLT. Darg completeness is at least comparable to that of Junction detection or KLT, and sometimes even better. Darg has significantly lower no-tracking time (Darg: 4, KLT: 81, J.D.: 121 frames).

19 Summary

Summary

Convexity-based method for scene-consistent feature points detection in video sequences. Detection relates to specific features of the intensity surface. These intensity features relate to geometric features of the 3D object.

20 Summary (cont

Summary (cont

A stable point tracking algorithm is described (2D Kalman filter). Two measures serve in a comparison with two other tracking methods. Completeness: Maximizes tracking time of a 3D scene point. Stability: Consistent tracking of 3D points between successive frames.

«Scene-Consistent Detection of Feature Points in Video Sequences»
http://900igr.net/prezentacija/anglijskij-jazyk/scene-consistent-detection-of-feature-points-in-video-sequences-79192.html
cсылка на страницу

Без темы

661 презентация
Урок

Английский язык

29 тем
Слайды
900igr.net > Презентации по английскому языку > Без темы > Scene-Consistent Detection of Feature Points in Video Sequences