Eye-RIS? system is a multipurpose platform designed to cover the main low-level machine vision primitives with a competitive price in relation with the offered solutions in the market. The present commercial smart cameras provide a reduced collection of machine vision primitives in relation with the Eye-RIS system. On the other hand, we can reuse the same architecture to develop other sort of application much faster that an ad-hoc FPGA solution. Other advantages obtained making use of the focal plane are the GOPS (Giga Operations per Second) and power consumption, where the focal plane [17] (250 GOPS) consume 4mW per GOPS while in a DSP [18] (4.3 GOPS) the obtained consumption is 231 mW per GOPS.

Eye-RIS? system employs an innovative and proven architecture in which image-processing is accomplished following a hierarchical approach with two main levels:Early-processing: This level comes right after signal acquisition. The basic tasks at this level are meant to extract useful information from the input image stream. Outputs of this level are reduced sets of data comprising image features such as object locations, shapes, edges, etc.Post-processing: Here, the amount of data is significantly smaller. Inputs are abstract entities in many cases, and tasks are meant to output complex decisions and to support action-taking. These tasks may involve complex algorithms within long computational flows and may require Carfilzomib greater accuracy than early processing.

One unique characteristic of the Eye-RIS? vision systems compared to other commercial solutions is that image acquisition and early-processing take place at the sensor, which is actually a Smart Image Sensor (SIS).

In this device, image acquisition and pre-processing is performed simultaneously in all pixels of the SIS. Consequently, images do not need to be downloaded from the sensor for the initial stages of the processing. This concept of concurrent sensing-processing extends the Image Sensor concept to the Smart Image Sensor one. The Smart Camera integrates a SIS called Q-Eye, which is a quarter CIF (aka QCIF, 176 �� 144) resolution fully-programmable SIS. It consists of an array of 176 �� 144 cells plus a surrounding global circuitry.

Each cell comprises multi-mode optical sensors, pixel memories, and linear and non-linear analog processors and binary processors. Each cell is interconnected in several ways with its 8 neighboring cells, allowing for highly flexible, programmable, Entinostat efficient, real-time image acquisition and spatial processing operations. In Smart Image Sensors, each local processor is merged with an optical sensor.