Presentation is loading. Please wait.

Presentation is loading. Please wait.

EE392J Final Project, March 20, 2002 1 Multiple Camera Object Tracking Helmy Eltoukhy and Khaled Salama.

Similar presentations


Presentation on theme: "EE392J Final Project, March 20, 2002 1 Multiple Camera Object Tracking Helmy Eltoukhy and Khaled Salama."— Presentation transcript:

1 EE392J Final Project, March 20, 2002 1 Multiple Camera Object Tracking Helmy Eltoukhy and Khaled Salama

2 EE392J Final Project, March 20, 2002 2 Outline b Introduction b Point Correspondence between multiple cameras b Robust Object Tracking b Camera Communication and decision making b Results

3 EE392J Final Project, March 20, 2002 3 Object Tracking b The objective is to obtain an accurate estimate of the position (x,y) of the object tracked b Tracking algorithms can be classified into Single object & Single CameraSingle object & Single Camera Multiple object & Single CameraMultiple object & Single Camera Multiple objects & Multiple CamerasMultiple objects & Multiple Cameras Single object & Multiple CamerasSingle object & Multiple Cameras

4 EE392J Final Project, March 20, 2002 4 Single Object & Single Camera b Accurate camera calibration and scene model b Suffers from Occlusions b Not robust and object dependant

5 EE392J Final Project, March 20, 2002 5 Single Object & Multiple Camera b Accurate point correspondence between scenes b Occlusions can be minimized or even avoided b Redundant information for better estimation b Multiple camera Communication problem

6 EE392J Final Project, March 20, 2002 6 System Architecture

7 EE392J Final Project, March 20, 2002 7 Static Point Correspondence b The output of the tracking stage is b A simple scene model is used to get real estimate of coordinates b Both Affine and Perspective models were used for the scene modeling and static corresponding points were used for parameter estimation b Least mean squares was used to improve parameter estimation

8 EE392J Final Project, March 20, 2002 8 Dynamic Point Correspondence

9 EE392J Final Project, March 20, 2002 9 Block-Based Motion Estimation b Typically, in object tracking precise sub-pixel optical flow estimation is not needed. b Furthermore, motion can be on the order of several pixels, thereby precluding use of gradient methods. b We started with a simple sum of squared differences error criterion coupled with full search in a limited region around the tracking window.

10 EE392J Final Project, March 20, 2002 10 Adaptive Window Sizing b Although simple block-based motion estimation may work reasonably well when motion is purely translational, it can lose the object if its relative size changes. If the object’s camera field of view shrinks, the SSD error is strongly influenced by the background.If the object’s camera field of view shrinks, the SSD error is strongly influenced by the background. If the object’s camera field of view grows, the window fails to make use of entire object information and can slip away.If the object’s camera field of view grows, the window fails to make use of entire object information and can slip away.

11 EE392J Final Project, March 20, 2002 11 Four Corner Method b This technique divides the rectangular object window into 4 basic regions - each one quadrant. b Motion vectors are calculated for each subregion and each controls one of four corners. b Translational motion is captured by all four moving equally, while window size is modulated when motion is differential. b Resultant tracking window can be non-rectangular, i.e., any quadrilateral approximated by four rectangles with a shared center corner.

12 EE392J Final Project, March 20, 2002 12 Example: Four Corner Method Synthetically generated test sequences:

13 EE392J Final Project, March 20, 2002 13 Correlative Method b Four corner method is strongly subject to error accumulation which can result in drift of one or more of the tracking window quadrants. b Once drift occurs, sizing of window is highly inaccurate. b Need a method that has some corrective feedback so window can converge to correct size even after some errors. b Correlation of current object features to some template view is one solution.

14 EE392J Final Project, March 20, 2002 14 Correlative Method (con’t) b Basic form of technique involves storing initial view of object as a reference image. b Block matching is performed through a combined interframe and correlative MSE: where sc’(x0,y0,0) is the resized stored template image. b Furthermore, minimum correlative MSE is used to direct resizing of current window.

15 EE392J Final Project, March 20, 2002 15 Example: Correlative Method

16 EE392J Final Project, March 20, 2002 16 Occlusion Detection b In order for multi-camera feature tracking to work, each camera must possess an ability to assess the validity of its tracking (e.g. to detect occlusion). b Comparing the minimum error at each point to some absolute threshold is problematic since error can grow even when tracking is still valid. b Threshold must be adaptive to current conditions. b One solution is to use a threshold of k (constant > 1) times the moving average of the MSE. b Thus, only precipitous changes in error trigger indication of possibly fallacious tracking.

17 EE392J Final Project, March 20, 2002 17 Redetection Procedure (1 Camera) Normal TrackingOcclusion Detected Motion TrackingRemain Stationary I t < d  Noise I t > d  Noise Error <  Err avg Error > k  Err avg b Redetection is difficult at most general level – Object recognition. b Proximity and size constancy constraints can be imposed to simplify redetection.

18 EE392J Final Project, March 20, 2002 18 Example: Occlusion

19 EE392J Final Project, March 20, 2002 19 Camera Communication

20 EE392J Final Project, March 20, 2002 20 Result

21 EE392J Final Project, March 20, 2002 21 Conclusion b Multiple cameras can do more than just 3D imaging b Camera calibration only works if you have an accurate scene and camera model b Tracking is sensitive to the camera characteristics (noise, blur, frame rate,..) b Tracking accuracy can be improved using multiple cameras


Download ppt "EE392J Final Project, March 20, 2002 1 Multiple Camera Object Tracking Helmy Eltoukhy and Khaled Salama."

Similar presentations


Ads by Google