公开(公告)号：US20210304439A1

公开(公告)日：2021-09-30

申请号：US17265271

申请日：2019-08-13

Applicant: LG INNOTEK CO., LTD.

Inventor： Jung Ah PARK ,  Jong Hyun MA ,  Seung Won LEE

IPC: G06T7/80 ,  G06K9/34 ,  G06T7/521 ,  G06K9/46

Abstract: Disclosed are a sensing method and apparatus, according to one embodiment, which process distance information about a feature point by capturing a pattern image. Specifically, disclosed are a sensing method and apparatus capable of improving the quantity and/or accuracy of information to be sensed, by appropriately realizing repeating shapes of a pattern image.

公开(公告)号：US20190087977A1

公开(公告)日：2019-03-21

申请号：US16095583

申请日：2017-04-19

Applicant: LG INNOTEK CO., LTD.

Inventor： Joo Hyung KIM ,  Seung Won LEE

IPC: G06T7/80 ,  H04N5/247 ,  G06T5/00

Abstract: The present embodiment relates to image acquisition and, in particular, to an image acquisition apparatus for acquiring images by a camera installed in a vehicle, and a method therefor. The image acquisition apparatus according to the present embodiment comprises: a projector for illuminating a reference pattern to the ground; a first camera unit for capturing an image of the reference pattern illuminated by the projector; a second camera unit for capturing an image; and a control unit for analyzing a pattern captured by the first camera unit and processing the image captured by the second camera unit.

公开(公告)号：US20210327091A1

公开(公告)日：2021-10-21

申请号：US17268898

申请日：2019-08-26

Applicant: LG INNOTEK CO., LTD.

Inventor： Jung Ah PARK ,  Seung Won LEE ,  Dong Gyun KIM

IPC: G06T7/80 ,  G06T7/33 ,  G06T7/593 ,  G06K9/46 ,  H04N17/00 ,  H04N9/09 ,  H04N13/239

Abstract: An image processing method of an image processing apparatus according to an embodiment of the present invention comprises the steps of: obtaining an RGB image from an RGB camera; obtaining a ToF image from a ToF camera; extracting a first RGB feature point from the RGB image; extracting a first ToF feature point from the ToF image; matching the first RGB feature point and the first ToF feature point and extracting a second RGB feature point and a second ToF feature point such that a correlation between the first RGB feature point and the first ToF feature point is equal to or greater than a predetermined value; calculating an error value between the second RGB feature point and the second ToF feature point; updating pre-stored calibration data when the error value is greater than a threshold value, and calibrating the RGB image and the ToF image by using the updated calibration data; and synthesizing the calibrated RGB and ToF images.

公开(公告)号：US20200267351A1

公开(公告)日：2020-08-20

申请号：US16649941

申请日：2018-09-21

Applicant: LG INNOTEK CO., LTD.

Inventor： Seung Won LEE

IPC: H04N7/18 ,  H04N5/247 ,  H04N13/243 ,  H04N5/232 ,  H04N5/262 ,  B60R1/00

Abstract: An around-view image processing method comprises: generating a first around-view image signal obtained by image synthesis using image information acquired from a plurality of cameras; generating a second around-view image signal obtained by image correction using image information acquired from the plurality of cameras over a predetermined period of time; and outputting the second around-view image signal or outputting the first around-view and second around-view image signals. When the first around-view and second around-view image signals are output, the around-view image processing method may further comprise selecting one image signal from the first around-view and second around-view image signals, and outputting the image signal selected from the first around-view and second around-view image signals.

公开(公告)号：US20190279374A1

公开(公告)日：2019-09-12

申请号：US16463315

申请日：2017-11-23

Applicant: LG INNOTEK CO., LTD.

Inventor： Dong Gyun KIM ,  Seung Won LEE

IPC: G06T7/246 ,  G06T7/00 ,  G06T7/80 ,  B60W40/105

Abstract: The present invention relates to an image analysis method, device, system, and program, which use vehicle driving information, and a recording medium, and according to one embodiment of the present invention, an image analysis method of a device linked with a camera and a controller through an in-vehicle communication network can comprise the steps of: receiving vehicle driving information from at least one controller for controlling vehicle driving; receiving image information captured by the camera; generating a first optical flow pattern estimated on the basis of the vehicle driving information; generating a second optical flow pattern calculated on the basis of the image information; and identifying a foreground movement pattern on the basis of the first optical flow pattern and the second optical flow pattern. Therefore, the present invention can more accurately analyze, by using vehicle driving information, an image captured by a camera.