박진선 교수
Jin-Seon Park
한양대학교 내과 · 컴퓨터과학
연구실 소개
박진선 교수의 연구실은 시각 기반 3D 인식 및 초해상도 복원 기술에 중점을 두고 있으며, 라이트필드 카메라를 활용한 정밀 깊이 추정, 다중 모odal 센서 융합을 통한 환경 적응형 깊이 추정, 그리고 자동차 이동 환경에서의 고해상도 시각 검사 시스템 개발을 핵심 연구 방향으로 삼고 있습니다. 특히, 비디오 기반 초해상도 복원, 손실 최소화 기반 특징 추출, 깊이 맵의 정밀한 보정 기술을 통해 실시간 및 정밀한 3D 환경 인식을 구현하고자 합니다. 연구는 센서 융합, 딥러닝 기반 특징 추출, 실시간 제어 알고리즘 등 다학제적 접근을 통해 이루어지고 있습니다.
연구 현황
연구 성과 추이
표시된 성과는 수집된 데이터 기준으로 산출되며, 일부 차이가 있을 수 있습니다.
주요 논문
15This paper introduces an algorithm that accurately estimates depth maps using a lenslet light field camera. The proposed algorithm estimates the multi-view stereo correspondences with sub-pixel accuracy using the cost volume. The foundation for constructing accurate costs is threefold. First, the sub-aperture images are displaced using the phase shift theorem. Second, the gradient costs are adaptively aggregated using the angular coordinates of the light field. Third, the feature correspondences
In this paper, we propose a novel and efficient reference feature extraction module referred to as the Similarity Search and Extraction Network (SSEN) for reference-based super-resolution (RefSR) tasks. The proposed module extracts aligned relevant features from a reference image to increase the performance over single image super-resolution (SISR) methods. In contrast to conventional algorithms which utilize brute-force searches or optical flow estimations, the proposed algorithm is end-to-end
Pinosylvin is a known functional compound of the Pinus species. Pinosylvin at low concentrations (∼ pmol/L) was reported to promote cell proliferation in endothelial cells. However, this study found that pinosylvin at a high concentration (100 μmol/L) induces cell death in bovine aortic endothelial cells. Therefore, we examined how pinosylvin was associated with apoptosis, autophagy, and necrosis. Pinosylvin at a high concentration appeared to promote caspase-3 activation, nuclear condensation,
In this letter, we propose an adaptive cost volume fusion algorithm for multi-modal depth estimation in changing environments. Our method takes measurements from multi-modal sensors to exploit their complementary characteristics and generates depth cues from each modality in the form of adaptive cost volumes using deep neural networks. The proposed adaptive cost volume considers sensor configurations and computational costs to resolve an imbalanced and redundant depth bases problem of convention
In this paper, we introduce robust and synergetic hand-crafted features and a simple but efficient deep feature from a convolutional neural network (CNN) architecture for defocus estimation. This paper systematically analyzes the effectiveness of different features, and shows how each feature can compensate for the weaknesses of other features when they are concatenated. For a full defocus map estimation, we extract image patches on strong edges sparsely, after which we use them for deep and han
In this paper, we present a multi-camera sensor system along with its control algorithm for automated visual inspection from a moving vehicle. To accomplish this task, we propose a unique hardware configuration consisting of a frontal stereo vision system, six lateral cameras motorized to tilt, and a GPS/IMU sensor mounted on the roof of a car. From the frontal stereo system, we detect electric poles and estimate their corresponding 3D positions. Based on this 3D estimation, the tilt angles of t
Sleep patterns are important predictors of long-term health outcomes. We investigated the associations of sleep duration, sleep regularity, and their combinations with all-cause mortality and cardiovascular events in a large Korean cohort, including sex-specific analyses. This prospective cohort study included 9,641 adults aged 40-69 years from the Ansung-Ansan cohort in Korea. Participants were categorized by self-reported sleep duration (< 7 h, 7-8 h, or > 8 h) and regularity (regular vs. irre
This study investigated the distribution of vascular plants in Mt. Anam located in Haksa-ri in Kimwha-eup, Cheorwon-gun, Gangwon-do. Eight surveys were conducted from March 2015 to May 2018. In this survey, a total of 416 taxa of vascular plants were observed, comprising 354 species, 4 subspecies, 52 varieties, and 6 forms belonging to 260 genera and 86 families. This included five taxa of endemic plants (such as Salix koriyanagi Kimura, Clematis brachyura Maxim., and Berberis koreana Palib.), n
Supraventricular or ventricular tachycardia is one of the most serious late sequelae in patients with a single ventricle who have undergone a Fontan operation. A patient with ventricular tachycardia involving the His-Purkinje system was deemed at high risk of atrioventricular block with ablation. Three-dimensional electroanatomic mapping-guided cryoablation was feasible without the development of atrioventricular block with long-term freedom from recurrence.
본 연구는 임상실습 전 단계 간호대학생의 식습관에 대한 건강행위, 건강관리 자기효능감 및 동기의 영향을 확인함으로써 바람직한 식습관 형성을 위한 중재 마련에 근거자료를 제공하고자 시도되었다. 두 개 대학 간호학과 1, 2학년 총 125명을 편의표집하여 구조화된 설문지를 이용하여 온라인 조사를 시행하였다. 수집된 자료는 SPSS/WIN 26.0 프로그램을 이용하여, 기술통계, Pearson’s correlation coefficient, 위계적 다중회귀분석을 이용하였다. 연구결과 식습관 평균 2.06점, 스트레스관리 평균 3.06점, 비활동적 여가활동 평균 3.55점, 건강관리 자기효능감 평균 3.94점, 자율적 동기 평균 5.79점, 통제적 동기 평균 3.65점이었다. 식습관, 건강관리 자기효능감, 자율적 동기, 스트레스 관리는 정적 상관관계가 있었고 비활동성 여가활동은 식습관과 부적 상관관계가 있었다. 회귀분석 결과 건강관리 자기효능감과 자율적 동기는 식습관에 긍정적 영향을 주었고
We should note that one cannot hold the evidential conception and the consequentialist conception of rationality of beliefs simultaneously, since they can make contradictory requirements on beliefs.The divergence between these two conceptions can easily be seen by an example.? Suppose an agent has some symptoms of a brain disease for which we have no cure available.But the agent knows that if he finds out or comes to believe that he has the disease, he would become very nervous.And it is known t
대표 연구 분야
박진선 교수의 연구를 Nubint에서 더 깊이 살펴보세요
이 연구실의 논문을 앱에서 열어 AI와 함께 읽고, 핵심을 요약하고, 내 글에 인용하세요.