Extremely low power consumption optical target detection method and device based on neural network

Abstract

The invention relates to the field of target detection, in particular to an extremely low power consumption optical target detection method based on a neural network, which comprises the following steps: constructing a convolutional neural network, and extracting target image features; normalizing the extracted target image features to obtain a target sample; searching a convolution kernel weightvalue and selecting a convolutional neural network framework with the highest average recognition precision through training; constructing a learnable optical prism device and applying the learnable optical prism device to a standard target detection database, learning to obtain a weight of each convolution kernel, searching a threshold value of an excitation layer of a convolutional neural network framework, and selecting to form an excitation function with the highest target position precision through training test; determining the dispersion coefficient of the optical prism and the threshold value of the filter film, customizing a scattering mirror, forming a target light spot through the scattering mirror, and finally imaging through a camera. A plurality of layers of optical prisms ofa convolutional neural network are adopted to calibrate a target frame, so that the method has efficient real-time performance and accuracy, and does not consume any battery energy consumption.

Description

technical field [0001] The invention relates to the technical field of target detection, in particular to a neural network-based ultra-low power consumption optical target detection method and device. Background technique [0002] Target detection is a relatively popular technology. This method obtains specified image information in a specific way, and marks the position of the positioned target on the picture. The target detection system takes the target recognition technology as the core, which is a high-tech technology in the field of international science and technology. The great breakthrough made by the neural network in the field of image recognition has promoted the rapid development of target detection as an image application, provided higher stability for target detection, and thus promoted the wide application of target detection in entertainment, security, etc. more fields. At the same time, it also puts forward higher requirements for target extraction. Target...

AI Technical Summary

Problems solved by technology

[0003] The present invention provides a neural network-based ultra-low-power optical target detection method and device, aiming to solve the lack of a comprehensive, automatic, accurate, and extremely low-power-consumption extraction of target image features and recognition in the prior art. method problem

Images