Structure from motion

From Wikipedia, the free encyclopedia

We, as humans, perceive a great deal of information about the 3 dimensional structure of our environment by moving through it. When we move and or objects around us move, we obtain information from images sensed over time. ^[1] In computer vision, structure from motion refers to the process of finding the 3 dimensional structure by analyzing the motion of an object over time.

Finding structure from motion presents similar problems to that of finding structure from stereo vision. In both instances, the correspondence between images and the reconstruction of 3D object need to found.

To find correspondence between images, features such as corner points (edges with gradients in multiple directions) need to be tracked from one image to the next. The feature trajectories over time are then used to reconstruct their 3D positions and the cameras motion. ^[2]

[edit] Related Topic

Structure from motion is related to the kinetic depth effect in perception whereby subjects viewing the shadow cast by a wire frame or other structure in rotation, perceive the full three-dimensional structure of the object, whereas when viewing the shadow of a static object they perceive only its two-dimensional projection.