公开(公告)号：US20210118123A1

公开(公告)日：2021-04-22

申请号：US17036475

申请日：2020-09-29

Applicant: TSINGHUA UNIVERSITY

Inventor： Lu Fang ,  Mengqi Ji ,  Shi Mao ,  Qionghai Dai

IPC: G06T7/00 ,  G06T5/00 ,  G01N21/39 ,  G02B27/48 ,  G06K9/62

Abstract: The present disclosure provides a material identification method and a device based on laser speckle and modal fusion, an electronic device and a non-transitory computer readable storage medium. The method includes: performing data acquisition on an object by using a structured light camera to obtain a color modal image, a depth modal image and an infrared modal image; preprocessing the color modal image, the depth modal image and the infrared modal image; and inputting the color modal image, the depth modal image and the infrared modal image preprocessed into a preset depth neural network for training, to learn a material characteristic from a speckle structure and a coupling relation between color modal and depth modal, to generate a material classification model for classifying materials, and to generate a material prediction result in testing by the material classification model of the object.

公开(公告)号：US11782285B2

公开(公告)日：2023-10-10

申请号：US17036475

申请日：2020-09-29

Applicant: TSINGHUA UNIVERSITY

Inventor： Lu Fang ,  Mengqi Ji ,  Shi Mao ,  Qionghai Dai

IPC: G06T7/00 ,  G02B27/48 ,  G01N21/39 ,  G06T5/00 ,  G06F18/214 ,  G06F18/25 ,  G06V10/56 ,  G06V10/764 ,  G06V10/774 ,  G06V10/80 ,  G06V10/82 ,  G06V10/60 ,  G06V10/143

CPC classification number: G02B27/48 ,  G01N21/39 ,  G06F18/214 ,  G06F18/251 ,  G06T5/009 ,  G06T7/0004 ,  G06V10/143 ,  G06V10/56 ,  G06V10/60 ,  G06V10/764 ,  G06V10/774 ,  G06V10/803 ,  G06V10/82 ,  G06T2207/10024 ,  G06T2207/10028 ,  G06T2207/10048 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: The present disclosure provides a material identification method and a device based on laser speckle and modal fusion, an electronic device and a non-transitory computer readable storage medium. The method includes: performing data acquisition on an object by using a structured light camera to obtain a color modal image, a depth modal image and an infrared modal image; preprocessing the color modal image, the depth modal image and the infrared modal image; and inputting the color modal image, the depth modal image and the infrared modal image preprocessed into a preset depth neural network for training, to learn a material characteristic from a speckle structure and a coupling relation between color modal and depth modal, to generate a material classification model for classifying materials, and to generate a material prediction result in testing by the material classification model of the object.