Presentation is loading. Please wait.

Presentation is loading. Please wait.

Acquiring 3D models of objects via a robotic stereo head David Virasinghe Department of Computer Science University of Adelaide Supervisors: Mike Brooks.

Similar presentations


Presentation on theme: "Acquiring 3D models of objects via a robotic stereo head David Virasinghe Department of Computer Science University of Adelaide Supervisors: Mike Brooks."— Presentation transcript:

1 Acquiring 3D models of objects via a robotic stereo head David Virasinghe Department of Computer Science University of Adelaide Supervisors: Mike Brooks and Anton van den Hengel

2 Stereo Vision Stereo is an important concept of human vision. Yorick 8-11R cameras are mounted to a movable platform, which mimics degrees of freedom of a human head. Each camera can be moved along four axes.

3 The 3D reconstruction process Comprises of three main stages: Camera calibration Image matching Reconstruction

4 Camera Calibration Camera calibration involves computation of internal and external properties of the camera. It requires an image of an object with some known 3D measurements. We use a calibration grid.

5 Extracting Image Coordinates To extract 2D image coordinates of the corners of the squares in the calibration grid we use the following process: 1. Apply edge detection to the image. 2. Perform line fitting. 3. Find where lines intersect.

6 Edge detection

7 Line fitting

8 Junction detection

9 Tsai Camera Calibration The model has 11 parameters. Five internal parameters: f – focal length of the camera,  – radial distortion coefficient, C X, C Y – the principle point, S – scale factor. and six external parameters: R X, R Y, R Z – rotational angles, T X, T Y, T Z – translation components.

10 The Projection Matrix Encapsulates the orientation and properties for the camera. A projection matrix can be decomposed as A is a matrix describing the camera’s internal properties.

11 Image Matching Involves finding corresponding points in left and right images that depict same points in the scene. A program called Image-Matching was used to perform matching. Implements a robust technique for image matching by exploiting the only available geometric constraint, the epipolar constraint.

12 Image Matching The algorithm consists of three steps: 1. Establish initial correspondences 2. Estimate robustly the epipolar geometry 3. Stereo matching

13 Image Matching 1. Establish initial correspondences A corner detector is first applied to each image to extract high curvature points. Then a classical correlation technique is then used to establish matching candidates between the two images. Matching ambiguities are then resolved using a relaxation technique.

14 After Corner Detection

15 After Correlation

16 After Relaxation

17 Image Matching 2. Estimate robustly the epipolar geometry The fundamental matrix is recovered. 3. Stereo matching Establish a new set of correspondences using a correlation based approach that takes into account the recovered epipolar geometry.

18 After stereo matching

19 Image-Matching is unpredictable

20 Reconstruction Determine depth of points by using triangulation. Triangulation results in 3D cloud of points being determined; however to visualize the structure of the 3D object easily points need to be connected. We use Delaunay triangulation.

21 Point Clouds

22 Delaunay Triangulation

23 YorickIn3D In this project a GUI has been created that enables a user to perform the 3D reconstruction process.

24 Conclusion We have successfully created an easy-to-use program that allows the 3D reconstruction process to be performed and creates accurate reconstructions. We have discovered a process that accurately extracts image coordinates used in calibration.


Download ppt "Acquiring 3D models of objects via a robotic stereo head David Virasinghe Department of Computer Science University of Adelaide Supervisors: Mike Brooks."

Similar presentations


Ads by Google