Electronic Letters on Computer Vision and Image Analysis 13(2):65-66, 2014 Monocular Depth Cues in Computer Vision Applications

Depth perception is a key aspect of human vision. It is a routine and essential visual task that the human do effortlessly in many daily activities. This has often been associated with stereo vision, but humans have an amazing ability to perceive depth relations even from a single image by using several monocular cues. In the computer vision field, if image depth information were available, many tasks could be posed from a different perspective for the sake of higher performance and robustness. Nevertheless, given a single image, this possibility is usually discarded, since obtaining depth information has frequently been performed by three-dimensional reconstruction techniques, requiring two or more images of the same scene taken from different viewpoints. Recently, the problem of estimating depths from a single image has received a growing interest. Current approaches are mainly focused on the design of sophisticated features and levels of reasoning for accurate depth estimation. Their final goal is inferring the 3D structure of the scene as good as possible. However, with the aim of solving a given computer vision problem, the computation of 3D information could be just the starting step to subsequently analyze an image more reliably instead of being a goal in itself. Furthermore, even just a rough depth description could help to achieve better performances