Guest Editorial: Big Data

Abstract

Computer vision has a split personality. Within the same field, and largely guided by the same set of fundamental algorithms, it combines two problems that are utterly disparate in their aims and philosophy—here we will call them “Vision as Measurement” and “Vision as Understanding”. Measurement problems deal with obtaining objective, quantifiable information about the physical world (e.g. scene depth in meters, visual angle in radians, light-source brightness in candelas-per-meter-squared, etc.). Measurement problems are akin to physics—they are well-posed and the validity of a solution can always be testedwith an experiment. Employing careful physical or geometric modeling and rigorous mathematics, this area has been quite successful in solving a number of important problems, such as stereo and structurefrom-motion. Vision as Understanding, on the other hand, has much more to do with psychology and philosophy than physics and mathematics. The goals are defined not in terms of objective quantities, but as subjective, observer-centric tasks. Implicit in tasks such as “find a table in the image” are much deeper issues involving the notion of what is meant by “table”, which could vary across cultures, contexts, and even individual observers. Because of this, approaches based on concise models and elegant mathematics, that proved so successful at