A convolution operation circuit in a cmos image sensor

Abstract

The invention discloses a convolution operation framework in a CMOS image sensor. It has an intra-pixel circuit as the basic unit for realizing light-sensing and multiplication-add operations, and a pixel array circuit composed of basic units for realizing array convolution operations; one basic unit controls one pixel of the image, and a group of elements of the basic unit represents image pixels One channel, using the weight value of the convolution kernel, one pixel and one channel to control the conduction time of a PMOS transistor in a basic unit; through the switching of the PMOS transistor in the component, the charge and discharge of the capacitor are controlled, and then the capacitor voltage of each group of components is controlled. , to achieve single-pixel operation control. The invention can complete the first-layer calculation of the convolutional neural network while sensing light, and convert the first-layer calculation result into a digital signal for output, reducing the energy consumption of subsequent calculations, and has high dynamic range, high frame rate, low power consumption, Support variable convolution operation parameters and other features.

Description

technical field [0001] The invention discloses a convolution operation architecture of a CMOS image sensor, and in particular relates to a convolution operation architecture of a CMOS image sensor capable of completing the convolution operation of the first layer of a convolutional neural network. Background technique [0002] In the image field, with the continuous development of machine learning technologies such as convolutional neural networks (CNN), applications such as object detection and face recognition have gradually matured, and various machine vision perception systems have been proposed. In most application scenarios, machine vision systems need to continuously shoot and work for a long time, and have strict requirements on power consumption, especially for battery-powered devices, such as field monitoring equipment and wearable devices. However, the power consumption of these systems has not been well resolved. On the one hand, deep learning algorithms often h...

AI Technical Summary

Problems solved by technology

However, these studies still have not fully utilized the characteristics of the image sensor itself. As an interface for photoelectric conversion, the pixel array itself has the function of analog storage and has the conditions to complete simple calculations.

Images