Registered
SYSTEM FOR LOCAL OPTIMIZATION OF OBJECT DETECTOR BASED ON DEEP NEURAL NETWORK AND METHOD OF CREATING LOCAL DATABASE THEREFOR
- Inventors
-
Joon-Goo Lee, Han Byung Gil, Baek Jang Woon, Choi Yun Won, Lim Kil Taek
- Application No.
-
17497771 (2021.10.08)
- Publication No.
-
20220147773 (2022.05.12)
- Registration No.
- 12026231 (2024.07.02)
- Country
- UNITED STATES
- Project Code
-
20ZD1100, 대경권 지역산업 기반 ICT 융합기술 고도화 지원사업,
Moon Ki Young
- Abstract
- Provided is a method of creating a local database for local optimization of an object detector based on a deep neural network. The method includes performing preprocessing on an image extracted from real-time collected or pre-collected images from an edge device, modeling a static background image based on the image received through the pre-processing unit and calculating a difference image between a current input image and a background model to model a dynamic foreground image, detecting an object image from the image based on a training model, and creating a local database based on the background image, the foreground image synthesized with the background image, and the object image synthesized with the background image.
- KSP Keywords
- Background image, Background model, Deep neural network(DNN), Difference image, Edge devices, Local database, Local optimization, Object image, Pre-processing, Processing unit, Real-Time, neural network, object detector, training model
- Family
-