JSSC 2015第4期Memory65nm

A V ocabulary Forest Object Matching Processor With 207 M-V ectors Throughput an

提出一种基于词汇森林的高效对象匹配处理器，通过集成片上数据库消除外部内存访问，显著提升处理速度和能效。

65nm CMOS, 2.07 M-vector/s throughput, 13.3 nJ/vector per-vector energy, 95.7% matching accuracy

近似最近邻搜索对象识别词汇森林硬件加速能效优化

▸集成片上数据库以消除外部内存访问

▸采用面积高效的复用词汇树架构减少面积

▸提出传播-计算阵列架构提升处理速度

Abstract

Approximate nearest neighbor searching has been studied as the keypoint matching algorithm for object recognition systems, and its hardware realization has reduced the external memory access which is the main bottleneck in object recognition process. However, external memory access reduction alone cannot satisfy the ever-increasing memory bandwidth requirement due to the rapid increase of the image resolution and frame ra te of many recent applications such as advanced driver assistance system.