Computer vision is a branch of artificial intelligence that maps pictures to descriptions. Without computer vision a picture of a parking lot is just a grid of color values. With computer vision, the parking lot picture maps to an intelligent description including the position and speed of the cars and people in the image. The goals of computer vision are achieved by means of pattern recognition, statistical learning, projective geometry, image processing, graph theory and other related fields

Goals of Computer Vision:

• The detection, segmentation, location, and recognition of certain objects in images
• The evaluation of results (e.g. segmentation, classification, registration)
• Registration of different views of the same scene or object
• Tracking an object through an image sequence
• Mapping a scene to a three-dimensional model of the scene; such a model might be used by a robot to navigate the imaged scene
• Estimation of the three-dimensional poses of humans and their limbs
• Searching for digital images by their contents (content-based image retrieval)

Potential Commercial Applications for Computer Vision

Though not a new science, – research in computer vision dates back over 25 years – the technology has had limited commercial success due primarily to the insufficient processing capacity of computers. However, recent advances in the computational power of PCs, as well as computer vision technology, have allowed the science to move from the theoretical world into reliable commercial automated video surveillance software. Moreover, because the applications of computer vision vary greatly and computational capacity will continue to advance at the pace of Moore’s Law, new market applications and the commercialization of the technology will continue to expand in the foreseeable future.

With the heightened global demand for improved physical security, the most immediate commercial opportunity for computer vision technology lies in improving video surveillance through the introduction of IVS software.