Understanding Depth

For us human beings, it is easy to understand pictures. We are able to estimate depth easily by using the information given by motion or the disparity between the two images seen with our two eyes. In contrast to this, - even with the incredible growth of computational capacity and power in the last years - computers are not able to understand images in every context. An image provided by a common camera depicts the intensity distribution of the scene without any 3D data. One of the main problems in the research field of image understanding is the lack of three-dimensional (3D) data. The interest in range images for high-end research projects and applications has increased dramatically in the last decade. One way to capture 3D information is the ability to directly acquire range images with laser range sensors. These sensors deliver a discrete representation of the surface in the scene, which offers a greater chance for computers to increase the level in image understanding.