Low cost smartcams design

Abstract

Nowadays, digital image processing is the most common form of image processing. Digital image processing makes it possible to enhance image features of interest while attenuating detail irrelevant to a given application, and then extract useful information about the scene from the enhanced image. For instance, digital cameras usually include dedicated digital image processing chips in order to improve at real-time the quality of images directly on-board. This paper proposes a very low cost vision system that is able to perform image processing tasks with a wide set of digital image processing algorithms, that have been specifically optimized for the proposed architecture. Some of these algorithms can be used to detect and to track a set of previously acquired targets. Finally, the proposed solution has been proved to be an effective solution even when applied to real-world case studies, such as the detection and the tracking of test-tubes in a medical environment.