Department of Semiconductor Science, Dongguk University-Seoul, Seoul 04620, Korea.
Department of Industrial and Systems Engineering, Dongguk University-Seoul, Seoul 04620, Korea.
Sensors (Basel). 2020 May 30;20(11):3101. doi: 10.3390/s20113101.
This paper presents an always-on Complementary Metal Oxide Semiconductor (CMOS) image sensor (CIS) using an analog convolutional neural network for image classification in mobile applications. To reduce the power consumption as well as the overall processing time, we propose analog convolution circuits for computing convolution, max-pooling, and correlated double sampling operations without operational transconductance amplifiers. In addition, we used the voltage-mode MAX circuit for max pooling in the analog domain. After the analog convolution processing, the image data were reduced by 99.58% and were converted to digital with a 4-bit single-slope analog-to-digital converter. After the conversion, images were classified by the fully connected processor, which is traditionally performed in the digital domain. The measurement results show that we achieved an 89.33% image classification accuracy. The prototype CIS was fabricated in a 0.11 μm 1-poly 4-metal CIS process with a standard 4T-active pixel sensor. The image resolution was 160 × 120, and the total power consumption of the proposed CIS was 1.12 mW with a 3.3 V supply voltage and a maximum frame rate of 120.
本文提出了一种基于模拟卷积神经网络的用于移动应用图像分类的始终开启互补金属氧化物半导体（CMOS）图像传感器（CIS）。为了降低功耗和总处理时间，我们提出了用于计算卷积、最大池化和相关双采样操作的模拟卷积电路，而无需运算跨导放大器。此外，我们在模拟域中使用电压模式 MAX 电路进行最大池化。模拟卷积处理后，图像数据减少了 99.58%，并使用 4 位单斜率模数转换器转换为数字。转换后，图像由全连接处理器进行分类，这通常在数字域中完成。测量结果表明，我们实现了 89.33%的图像分类准确率。该原型 CIS 是在具有标准 4T 有源像素传感器的 0.11μm1-poly4-metal CIS 工艺中制造的。图像分辨率为 160×120，在 3.3V 电源电压下，所提出的 CIS 的总功耗为 1.12mW，最大帧率为 120。
