← 返回 JSSC 论文列表JSSC 2022第1期Memory65nm
A 513-TOPSW 1344-GOPS In-Memory Binary Image Filtering in 65-nm CMOS Sumon Kumar
65nm CMOS工艺下基于6T-SRAM存内计算的图像去噪方案，能效比达51.3 TOPS/W。
65nm CMOS, 峰值吞吐量134.4 GOPS, 峰值能效51.3 TOPS/W
神经形态视觉传感器存内计算6T-SRAM图像去噪中值滤波
▸提出非重叠中值滤波器(NOMF)用于事件驱动二进制图像去噪
▸利用6T-SRAM固有读干扰现象实现存内计算架构
▸相比全数字方案实现70倍能效提升和3倍处理速度提升
Abstract
Neuromorphic vision sensors (NVSs) can enable
energy savings due to their event-driven that exploits the tem-
poral redundancy in video streams from a stationary camera.
However, noise-driven events lead to the false triggering of the
object recognition processor. Image denoise operations require
memory-intensive processing leading to a bottleneck in energy
and latency. In this article, we present in-memory filtering
(IMF), a 6T-SRAM in-memory c omputing (IMC)-based image
denoising for event-base