Deploying intelligent visual algorithms in terminal devices for always-on sensing is an attractive trend in the IoT era. in-sensor-processing architecture is proposed to reduce power consumption on A/D conversion and ...
详细信息
ISBN:
(纸本)9781728110851
Deploying intelligent visual algorithms in terminal devices for always-on sensing is an attractive trend in the IoT era. in-sensor-processing architecture is proposed to reduce power consumption on A/D conversion and data transmission, which performs pre-processing and only converting low-throughput features. However, current designs still require high energy consumption on photoelectric conversion and analog data movement. In this paper, two methods are proposed to improve the energy efficiency of in-sensor-processing architecture, including direct photocurrent computation and 2D kernel scheduling. Photocurrents are directly involved in computation to avoid data conversion;thus the indispensable imaging power is also utilized for computing. Since the location of the pixel data is fixed, data scheduling is conducted on digital weights to eliminate analog data storage and movement. We implement a prototype chip with an array of 32 x 32 units to calculate the first layer of binarized LeNet-5. The post-simulation shows that the proposed architecture reaches the energy efficiency of 11.49TOPs/W, about 14.8x higher than previous works.
Deploying intelligent visual algorithms in terminal devices for always-on sensing is an attractive trend in the IoT era. in-sensor-processing architecture is proposed to reduce power consumption on A/D conversion and ...
详细信息
ISBN:
(纸本)9781450367257
Deploying intelligent visual algorithms in terminal devices for always-on sensing is an attractive trend in the IoT era. in-sensor-processing architecture is proposed to reduce power consumption on A/D conversion and data transmission, which performs pre-processing and only converting low-throughput features. However, current designs still require high energy consumption on photoelectric conversion and analog data movement. In this paper, two methods are proposed to improve the energy efficiency of in-sensor-processing architecture, including direct photocurrent computation and 2D kernel scheduling. Photocurrents are directly involved in computation to avoid data conversion; thus the indispensable imaging power is also utilized for computing. Since the location of the pixel data is fixed, data scheduling is conducted on digital weights to eliminate analog data storage and movement. We implement a prototype chip with an array of 32 X 32 units to calculate the first layer of binarized LeNet-5. The post-simulation shows that the proposed architecture reaches the energy efficiency of 11.49TOPs/W, about 14.8x higher than previous works.
in-sensor-processing (ISP) paradigm has been exploited in state-of-the-art vision system designs to pave the way towards power-efficient sensing and processing. The redundant data transmission between sensors and proc...
详细信息
in-sensor-processing (ISP) paradigm has been exploited in state-of-the-art vision system designs to pave the way towards power-efficient sensing and processing. The redundant data transmission between sensors and processors is significantly minimized by local computation within each pixel. However, existing ISP designs suffer from limited frame rates and degraded fill factors. In this brief, we introduce a low-latency in-sensor-intelligence neuromorphic vision system using neuromorphic spiking neurons, namely SpikeSen. SpikeSen directly operates on the photocurrents and executes the computation in the frequency domain, reducing the long exposure time and speeding up the computation. Experiments show that SpikeSen can achieve more than 6.1x computation speedup compared to existing ISP designs with competitive energy consumption per pixel.
暂无评论