본 출원은 세그멘테이션 이미지 생성 방법에 관한 것으로, 제1 종류의 타겟 객체가 반영된 타겟 이미지를 획득하는 단계, 타겟 이미지 및 세그멘테이션 모델을 이용하여 타겟 이미지에서 타겟 객체가 반영된 적어도 하나의 픽셀에 대응하는 타겟 픽셀에 타겟 객체에 대한 객체 정보가 할당된 타겟 세그멘테이션 이미지를 생성하는 단계, 타겟 세그멘테이션 이미지의 타겟 픽셀에 할당된 객체 정보에 기초하여 타겟 객체의 근접 레벨을 판단하는 단계 및 타겟 객체의 근접 레벨이 제1 근접 레벨인 경우, 타겟 객체를 제1 종류의 다른 객체와 서로 구분하기 위한 식별자를 타겟 세그멘테이션 이미지의 타겟 픽셀에 더 할당하는 단계를 포함한다.
The present invention relates to a distance measuring method which is to monitor a periphery of a vessel and a port by sensing surrounding environment using an artificial neural network. According to an aspect of the present invention, the distance measuring method includes: a step of preparing an artificial neural network learned by a learning set; a step of obtaining a target image; a step of calculating object information related to a target image from the target image by using the artificial neural network; a step of detecting a moving object in the target image based on the calculated object information; and a step of determining proximity of the moving object in the target image based on a relative proximity level reflected in the calculated object information. The learning set includes a plurality of images and object information labeled in a pixel of the images. At least a part of the images includes at least a part of a standard object positioned in the lower part, the moving object, and a sailable area. The object information reflects an object kind and the relative proximity level from the standard object. The pixel corresponding to the moving object is labeled with the object information indicating a section corresponding to a section in which the moving object is positioned among a plurality of sections where the object kind indicates the moving object and the relative proximity level divides the sailable area. The plurality of sections are arranged in order from a boundary line between the sailable section and the standard object to an upper limit of the sailable area. The pixel corresponding to the sailable area is labeled with the object information where the object kind indicates the sailable area and the relative proximity level indicates undefined proximity.
DISTANCE MEASUREMENT METHOD AND DISTANCE MEASUREMENT DEVICE USING THE SAME
거리 측정 방법 및 이를 이용하는 거리 측정 장치
05.06.2024
Patent
Elektronische Ressource
Koreanisch
IPC: | G06V / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G06T Bilddatenverarbeitung oder Bilddatenerzeugung allgemein , IMAGE DATA PROCESSING OR GENERATION, IN GENERAL / B63B Schiffe oder sonstige Wasserfahrzeuge , SHIPS OR OTHER WATERBORNE VESSELS |
DISTANCE MEASUREMENT METHOD AND DISTANCE MEASUREMENT DEVICE USING SAME
Europäisches Patentamt | 2022
|DISTANCE MEASUREMENT METHOD AND DISTANCE MEASUREMENT DEVICE USING THE SAME
Europäisches Patentamt | 2024
DISTANCE MEASUREMENT METHOD AND DISTANCE MEASUREMENT DEVICE USING THE SAME
Europäisches Patentamt | 2023
DISTANCE MEASUREMENT METHOD AND DISTANCE MEASUREMENT DEVICE USING THE SAME
Europäisches Patentamt | 2022
|DISTANCE MEASUREMENT METHOD AND DISTANCE MEASUREMENT DEVICE USING THE SAME
Europäisches Patentamt | 2023
|