Moving surveillance techniques to sousveillance: Towards equiveillance using wearable computing
Corey Mason Manders · 2013
Summary form only given. To date, a large amount of research has been conducted using surveillance systems. In fact many conferences, journals, and research programmes are devoted entirely to this subject. However, Sousveillance [3], “watching from below” (or capturing image data from the perspective of a live observer), being a newer area of investigation currently has much less associated work. Since both research topics involve image pro-cessing, many similarities exist. Thus, much of the work which is done in surveillance may be “ported” to souveillance. One such example is that of colour constancy[1]. In particular, a problem that occurs when using multiple cameras for surveillance and associated tracking, is that colours can vary widely across cameras. An object and it's associated data that appears in one view and one system, may present completely difference data in another camera and system. New techniques have been developed to attempt to unify colours between cameras and systems. The same problem exists in the area of sousveillance. For example, an object observed by one cyborg may appear differently to another cyborg. Given that in the situation of souvellance, the camera control as well as the environment are largely in control of the wearcam operator/cyborg[2], colour constancy techniques which are used surveillance can actually be done more accurately in the case of souveillance. This discussion will present one method of mapping an existing method of colour constancy for multiple surveillance cameras to colour constancy for a group of cyborgs.