公开(公告)号：US10025096B2

公开(公告)日：2018-07-17

申请号：US15413932

申请日：2017-01-24

Applicant: Electronics and Telecommunications Research Institute

Inventor： Chang Rak Yoon ,  Jungyu Kang ,  Kyong Ho Kim ,  Byoung Jun Park ,  Jeong Woo Lee ,  Yoon Sook Hwang

IPC: G09G5/00 ,  G02B27/01 ,  G06T19/00 ,  G06K9/00 ,  G06K9/46 ,  G06T7/73

Abstract: Provided are an apparatus and method for transforming augmented reality information of a head-up display (HUD) for a vehicle. The apparatus for transforming augmented reality information of a head-up display for a vehicle includes a first projection transforming formula generation unit configured to extract a conjugate point by performing feature point matching on a first feature point of a forward recognition image of the vehicle input from a forward recognition camera and a second feature point of a first driver-based viewpoint image input from a driver-based viewpoint camera whose installation position is different from that of the forward recognition camera, and generate a first projection transforming formula; a second projection transforming formula generation unit configured to generate a second projection transforming formula using a straight-line intersection of a second driver-based viewpoint image, which is extracted from a second driver-based viewpoint image input from the driver-based viewpoint camera, and HUD coordinates pre-defined on the HUD; and an augmented reality information transformation unit configured to sequentially apply the generated first and second projection transforming formulas to recognition coordinates of a forward object, which is recognized from the first forward recognition image, to calculate primary and secondary transformation coordinates, and render the secondary transformation coordinates on the HUD.

公开(公告)号：US11507783B2

公开(公告)日：2022-11-22

申请号：US17380663

申请日：2021-07-20

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Dong-Jin Lee ,  Do-Wook Kang ,  Jungyu Kang ,  Joo-Young Kim ,  Kyoung-Wook Min ,  Jae-Hyuck Park ,  Kyung-Bok Sung ,  Yoo-Seung Song ,  Taeg-Hyun An ,  Yong-Woo Jo ,  Doo-Seop Choi ,  Jeong-Dan Choi ,  Seung-Jun Han

IPC: G06K9/62 ,  G06T7/80 ,  G06V10/24 ,  G06V20/56 ,  G06V20/58 ,  G06V20/64

Abstract: Disclosed herein are an object recognition apparatus of an automated driving system using error removal based on object classification and a method using the same. The object recognition method is configured to train a multi-object classification model based on deep learning using training data including a data set corresponding to a noise class, into which a false-positive object is classified, among classes classified by the types of objects, to acquire a point cloud and image data respectively using a LiDAR sensor and a camera provided in an autonomous vehicle, to extract a crop image, corresponding to at least one object recognized based on the point cloud, from the image data and input the same to the multi-object classification model, and to remove a false-positive object classified into the noise class, among the at least one object, by the multi-object classification model.