등록
리셉티브 필드의 차이 정보를 활용한 스케일변화에 강인한 딥러닝기반 특징점 추출 방법 및 장치
- 발명자
-
조용주, 서정일, 리한 하피즈, 우사마 사디크, 타바샤 아리프, 모흐센 알리, 무하마드 파이살
- 출원번호
-
17565901 (2021.12.30)
- 공개번호
-
20230035307 (2023.02.02)
- 등록번호
- 11989927 (2024.05.21)
- 출원국
- 미국
- 협약과제
-
20ZH1200, 초실감 입체공간 미디어·콘텐츠 원천기술연구,
이태진
- 초록
- Disclosed herein are an apparatus and method for detecting a keypoint based on deep learning robust to scale changes based on information change across receptive fields. The apparatus for detecting a keypoint based on deep learning robust to scale changes based on information change across receptive fields includes a feature extractor for extracting a feature from an input image based on a pre-trained deep learning neural network, an information accumulation pyramid module for outputting, from the feature, at least two filter responses corresponding to receptive fields having different scales, an information change detection module for calculating an information change between the at least two filter responses, a keypoint detection module for creating a score map having a keypoint probability of each pixel based on the information change, and a continuous scale estimation module for estimating a scale of a receptive field having a biggest information change for each pixel.
- KSP 제안 키워드
- Change detection, Keypoint Detection, Learning neural network, Receptive field, Using information, deep learning(DL), different scales, feature extractor, neural network, scale estimation
- 패밀리
-