http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Integrated Deep Learning Framework for Accelerated Optical Coherence Tomography Angiography
김규원,김종범,최우준,김철홍,이승철 대한기계학회 2021 대한기계학회 춘추학술대회 Vol.2021 No.4
Optical coherence tomography angiography (OCTA) has become a premium imaging tool in clinics to obtain structural and functional information of microvasculatures. One primary technical drawback for OCTA is its imaging speed. The current protocols require high sampling density and multiple acquisitions of cross-sectional B-scans to form one image frame, resulting in low acquisition speed. Recently, deep learning (DL)-based methods have gained attention in accelerating the OCTA acquisition process. They achieve faster acquisition using two independent reconstructing approaches: high-quality angiograms from a few repeated B-scans and high-resolution angiograms from undersampled data. While these approaches have shown promising results, they provide limited solutions that only partially account for the OCTA scanning mechanism. Herein, we propose an integrated DL method to tackle both factors in tandem and further enhance the reconstruction performance in speed and quality. We designed two-stage convolutional neural networks (CNNs) to reconstruct fully-sampled, high-quality (8 repeated B-scans) angiograms from their corresponding undersampled, low-quality (2 repeated B-scans) counterparts by successively enhancing the pixel resolution and the image quality. Using an in-vivo mouse brain vasculature dataset, we evaluate our proposed models through quantitative and qualitative assessments and demonstrate that our method can achieve superior reconstruction performance compared to conventional interpolation-based methods.
강결합 기반LIDAR-Visual-Inertial Odometry 기법 개발
김규원,정태기,서성훈,지규인 제어·로봇·시스템학회 2020 제어·로봇·시스템학회 논문지 Vol.26 No.8
. For autonomous flight of drones in a GPS-denied environment such as indoors, a sensor-based navigation system isrequired. Navigation sensors such as LIDAR, camera, and IMU are often used for this purpose. In this paper, we propose a TCLVIO(Tightly-Coupled LIDAR-Visual-Inertial Odometry) integration algorithm. It is based on a sliding window nonlinearoptimization method, and the raw measurements of the sensor are all tightly coupled together in the optimization cost function. Theadvantage of one sensor can be optimally utilized to complement the others weakness. Therefore, more precise and robust positioningis possible. The performance of the proposed TC-LVIO integration method is evaluated and compared with other odometry methodthrough indoor-outdoor flight experiments.