The ubiquity and proliferation of digital imaging devices and computational power enable the use of computer vision in a variety of ubiquitous applications that previously would have been impractical. This paper presents a new such application domain called emergent displays (a type of actuator network), and goes on to describe its use of computer vision as a means of simultaneous localisation of large numbers of nodes. The effectiveness of a state of the art computer vision tool is analysed against this application with quantitative and qualitative results, and then put into context against further more general ubiquitous applications.