Hi,
For the task of "constructing 3D cloud from a set of 2D images", you can refer to following workflow & resources:
1.Determine the intrinsic camera parameters (such as focal length, principal point, and distortion coefficients) and extrinsic camera parameters (position and orientation in 3D space) by a process called camera calibration.
For camera calibration, you can refer to
- https://www.mathworks.com/help/vision/ug/using-the-single-camera-calibrator-app.html
- https://www.mathworks.com/help/vision/ref/cameracalibrator-app.html
2.After you have calibrated the camera, please refer to this example of structure from motion from multiple views:
- https://www.mathworks.com/help/vision/ug/structure-from-motion-from-multiple-views.html .It mentions detailed steps as to how to reconstruct a 3-D scene from a sequence of 2-D views
Hope this helps you in your task.
