A 0.8-μm CMOS two-dimensional programmable mixed-signal focal-plane array processor with on-chip binary imaging and instructions storage

Abstract

This paper presents a CMOS chip for the parallel acquisition and concurrent analog processing of two-dimensional (2-D) binary images. Its processing function is determined by a reduced set of 19 analog coefficients whose values are programmable with 7-b accuracy. The internal programming signals are analog, but the external control interface is fully digital. Onchip nonlinear digital-to-analog converters (DAC's) map digitally coded weight values into analog control signals, using feedback to predistort their transfer characteristics in accordance to the response of the analog programming circuitry. This strategy cancels out the nonlinear dependence of the analog circuitry with the programming signal and reduces the influence of interchip technological parameters random fluctuations. The chip includes a small digital RAM memory to store eight sets of processing parameters in the periphery of the cell array and four 2-D binary images spatially distributed over the processing array. It also includes the necessary control circuitry to realize the stored instructions in any order and also to realize programmable logic operations among images. The chip architecture is based on the cellular neural/nonlinear network universal machine (CNN-UM). It has been fabricated in a 0.8-m single-poly double-metal technology and features 2-s operation speed (time required to process an image) and around 7-b accuracy in the analog processing operations. Index Terms-Analog array processors, cellular neural networks, focal plane processors, vision chips. I. INTRODUCTION C ONVENTIONAL image-processing systems use a charge-coupled device (CCD) camera for parallel acquisition of the input image and serial transmission of the digitalized image to a separate processing element. It results in huge data rates which conventional computers are not capable of analyzing in real-time. For instance, a color 512 512 pixel camera delivers about 20 MB/s, for Manuscript

A CMOS Image Processing Sensor for the Detection of Image Features

“…The CNN concept has been further extended to CNN universal machine (CNN-UM) architecture to include programming capabilities [12]. Domínguez-Castro has built a sensor based on this principle and demonstrated its functionality for image processing applications [13]. However, the operation is not very fast, usually in the order of microsecond, due to the settling behavior of the analog interaction between pixels.…”

ACE16k: The Third Generation of Mixed-Signal SIMD-CNN ACE Chips Toward VSoCs

“…Hence, the equivalent state equation obtained for each PU is (4) whose steady state is , as corresponds to the desired convolution output.…”

“…Typically, for implementation purposes, communications between PEs are restricted to the nearest neighbors. However, despite such an architectural limitation, ACE chips are able to implement most early-vision processing tasks [4]- [6], [13]. Adding the capability of sensing the visual information in a one-by-one pixel-to-PE correspondence makes these systems very well suited to implement the front-end stage of VSoCs.…”

“…It highlights a continuous improvement across time. ACE400, the first member of this family, was designed in 1996 using a standard 0.8-m technology [4]. It was conceived to operate only on B/W image flows, and included reduced programming capability.…”

Distributed Sensor Networks: A Cellular Nonlinear Network Perspective

“…Clearly, the incoming data carried by the modulated reflected laser beams has to preprocessed and/or compressed early, most beneficially directly at the CCD sensor. Such a task is certainly tailored to CNNs with optical inputs 66,67,68,69 , since the CNN processing capability permits an efficient detection of relevant patterns in the motes' response.…”