Non-vision-field target detection method and device and storage medium

Abstract

The invention discloses a non-vision-field target detection method and device, which are used for reducing the detection cost and improving the target detection precision, are suitable for machine vision application scenes of high-precision industrial detection such as the semiconductor manufacturing industry and the electronic manufacturing industry, and are also used for detection in the fields of automatic driving, security monitoring and the like. The method comprises the following steps: transmitting coherent light pulses to an intermediate surface corresponding to a non-vision field target; receiving a diffuse reflection mixed light pulse returned by the non-vision target, wherein the diffuse reflection mixed light pulse comprises the shape information of the non-vision target; preprocessing the diffuse reflection mixed light pulse according to an application scene to obtain a standard diffuse reflection mixed light pulse meeting a required scale; converting each light pulse of the standard diffuse reflection mixed light pulses into a discrete digital sequence; combining the discrete digital sequences corresponding to each optical pulse conversion to obtain a digital matrix; and inputting the digital matrix into a deep learning network for feature extraction to obtain feature information of the non-vision target.

Description

technical field [0001] The present invention relates to the technical fields of artificial intelligence and target detection, in particular to a non-visual target detection method, device and computer storage medium. Background technique [0002] The target detection technology based on traditional optical imaging has been relatively popular. It uses CCD, CMOS and other detectors to directly acquire target images, and performs target detection based on image features. However, traditional optical imaging can only image objects that can be seen, and cannot image areas that cannot be directly reached by light, and cannot detect occluded objects. [0003] At present, there are also non-line-of-sight imaging technologies such as laser range gating, time-of-flight transient imaging, and photon counting detection. However, the above-mentioned non-line-of-sight imaging technology solutions have high equipment requirements and are difficult to apply to actual non-line-of-sight targe...

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a target detection method based on a deep learning network, specifically, a non-line-of-sight target detection method based on a deep learning network, which is used to solve the poor detection effect of non-line-of-sight target features in the prior art , high cost and other technical issues

Images