Non-visual target detection method, device and storage medium

Abstract

The invention discloses a method and device for non-visual target detection, which are used to reduce the detection cost and improve the accuracy of target detection. Applicable scenarios include machine vision application scenarios for high-precision industrial detection such as semiconductor manufacturing and electronics manufacturing. In the detection of automatic driving, security monitoring and other fields. The method part includes: transmitting coherent light pulses to the intermediate surface corresponding to the non-line-of-sight target; receiving the diffuse reflection mixed light pulse returned by the non-line-of-sight target, and the diffuse reflection mixed light pulse contains the shape information of the non-line-of-sight target; The reflection mixed light pulse is preprocessed to obtain a standard diffuse reflection mixed light pulse that meets the required scale; each light pulse of the standard diffuse reflection mixed light pulse is converted into a discrete digital sequence; each light pulse is converted into a corresponding discrete digital sequence Combine to obtain a digital matrix; input the digital matrix to the deep learning network for feature extraction to obtain the feature information of the non-visual 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