KEYWORDS: Image processing algorithms and systems, Roads, Image segmentation, Image processing, Field programmable gate arrays, Control systems, Prototyping, Color image segmentation, Neurons, RGB color model
Digital architecture for real time processing in vision systems for control of traffic lights is presented. The main idea of
this work is to identify cars on intersections, switching traffic lights in order to reduce traffic jam. The architecture is
based on a color image segmentation algorithm that comprises three stages. Stage one is a color space transformation in
order to measure the color difference properly, image colors are represented in a modified L* u* v* color space. Stage
two consists in a color reduction, where image colors are projected into a small set of prototypes using a self-organizing
map (SOM). Stage three realizes color clustering, where simulated annealing (SA) seeks the optimal clusters from SOM
prototypes. The proposed hardware architecture is implemented in a Virtex II Pro FPGA and tested; having a processing
time inferior to 25ms per 128x128 pixels. The implementation comprises 262,479 equivalent gates.
In this work a thin film gas microsensor based on both a double polysilicon micro-hotplate (MHP) and a polysilicon floating gate MIS transistor (FG-MIS) is described. Sensing section is a squared polysilicon plate which contains a doped Zinc Oxide (ZnO) thin film. The sensing section is heated by an U-shaped polysilicon stripe which is electrically isolated from the top and the bottom using oxide films. The micro-hotplate is both mechanically supported and thermally isolated using a deep cavity micromachined in the silicon substrate. The sensing film is electrically connected to the floating-gate transistor where the conductivity channel is modulated by the charged generated at the sensing film. The sensor structure was characterized for detecting carbon monoxide (CO) at 300 °C. The hot area is thermally isolated using an arrangement of cavities micromachined in the silicon substrate. Finally a complete layout of the sensor system is presented in this paper.