← 返回 JSSC 论文列表JSSC 2012第11期Digital Circuits0.13μm CMOS
A 92-mW Real-Time Traf fic Sign Recognition System With Robust Illumination Adapt
提出一种低功耗实时交通标志识别系统，具有强光照适应能力
90%识别准确率，92 mW功耗，1.2 V电压
交通标志识别Retinex预处理SVM处理器低功耗光照适应
▸采用Retinex预处理和SVM处理器
▸递归高斯引擎和反射引擎并行处理
▸自适应神经模糊推理系统优化参数
Abstract
A low-power real-time traf fics i gn recognition system
that is robust under various illumination conditions is proposed.
It is composed of a Retinex preprocessor and an SVM processor.
The Retinex preprocessor performs the Mu lti-Scale Retinex
(MSR) algorithm for robust light and dark adaptation under
harsh illumination environments . In the Retinex preprocessor,
the recursive Gaussian engine (RGE) an dr eflectance engine (RE)
exploit parallelism of the MSR t asks with a two-stage pipeline,
and a