Registered
APPARATUS AND METHOD FOR DETECTING KEYPOINT BASED ON DEEP LEARNIING USING INFORMATION CHANGE ACROSS RECEPTIVE FIELDS
- Inventors
-
Cho Yong Ju, Jeongil Seo, 우사마 사디크, 무하마드 파이살, 모흐센 알리, 리한 하피즈, 타바샤 아리프
- Application No.
-
17565901 (2021.12.30)
- Publication No.
-
20230035307 (2023.02.02)
- Registration No.
- 11989927 (2024.05.21)
- Country
- UNITED STATES
- Project Code
-
20ZH1200, The research of the fundamental media·contents technologies for hyper-realistic media space,
Lee Tae Jin
- Abstract
- 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 Keywords
- Change detection, Keypoint Detection, Learning neural network, Receptive field, Using information, deep learning(DL), different scales, feature extractor, neural network, scale estimation
- Family
-