이경재 교수

In this paper, we propose a convolutional neural network for thermal image enhancement by incorporating the brightness domain with a residual-learning technique, which improves the performance of enhancement and speed of convergence. Typically, the training domain uses the same domain as that of the target image; however, we evaluated several domains to determine the most suitable one for the network. In the analyses, we first compared the performance of networks that were trained by the corresp

Weakly-supervised Video Anomaly Detection is the task of detecting frame-level anomalies using video-level labeled training data. It is difficult to explore class representative features using minimal supervision of weak labels with a single backbone branch. Furthermore, in real-world scenarios, the boundary between normal and abnormal is ambiguous and varies depending on the situation. For example, even for the same motion of running person, the abnormality varies depending on whether the surro

A novel dodecanuclear manganese metalladiazamacrocycle was synthesized employing a new pentadentate ligand N-2-pentenoylsalicylhydrazide (H(3)tpeshz) by supramolecular self-assembly. The backbone of this metal-organic assembly is a repeating unit of an M-N-N-M linkage that extends to complete a 36-membered cyclic structure involving 12 manganese(III) centers. Successive manganese centers are in a chemically different ...ABABAB...-type environment while the chirality varies as ...LambdaLambdaDelt

Heterogeneous Face Recognition (HFR) is a task that matches faces across two different domains such as visible light (VIS), near-infrared (NIR), or the sketch domain. Due to the lack of databases, HFR methods usually exploit the pre-trained features on a large-scale visual database that contain general facial information. However, these pre-trained features cause performance degradation due to the texture discrepancy with the visual domain. With this motivation, we propose a graph-structured mod

Instance segmentation has gained attention in various computer vision fields, such as autonomous driving, drone control, and sports analysis. Recently, many successful models have been developed, which can be classified into two categories: accuracy- and speed-focused. Accuracy and inference time are important for real-time applications of this task. However, these models just present inference time measured on different hardware, which makes their comparison difficult. This study is the first t

Depth completion is the task of reconstructing dense depth images from sparse LiDAR data. LiDAR depth completion, for which LiDAR data is the only input, is an ill-posed and challenging problem owing to the underlying properties of LiDAR data: extremely few points, presence of discontinuities, and absence of texture information. Accordingly, most approaches are heavily dependent on guided color images, which leads to unsatisfactory results when the color images are degraded. To alleviate the dep

Studies on depth images containing three-dimensional information have been performed for many practical applications. However, the depth images acquired from depth sensors have inherent problems, such as missing values and noisy boundaries. These problems significantly affect the performance of applications that use a depth image as their input. This paper describes a depth enhancement algorithm based on a combination of color and depth information. To fill depth holes and recover object shapes,

In this study, we propose a multi-scale ensemble learning method for thermal image enhancement in different image scale conditions based on convolutional neural networks. Incorporating the multiple scales of thermal images has been a tricky task so that methods have been individually trained and evaluated for each scale. However, this leads to the limitation that a network properly operates on a specific scale. To address this issue, a novel parallel architecture leveraging the confidence maps o

This study aims to generate visually useful imagery by preventing cropping while maintaining resolution and minimizing the degradation of stability and distortion to enhance the stability of a video for Augmented Reality applications. The focus is placed on conducting research that balances maintaining execution speed with performance improvements. By processing Inertial Measurement Unit (IMU) sensor data using the Versatile Quaternion-based Filter algorithm and optical flow, our research first

Many studies have been conducted on recommender systems in both the academic and industrial fields, as they are currently broadly used in various digital platforms to make personalized suggestions. Despite the improvement in the accuracy of recommenders, the diversity of interest areas recommended to a user tends to be reduced, and the sparsity of explicit feedback from users has been an important issue for making progress in recommender systems. In this paper, we introduce a novel approach, nam

AGV systems are widely used to increase the flexibility and the efficiency of the material handling systems. AGV systems are one of critical factors which determine the overall performance of the manufacturing systems. To this end, the optimal design for AGV systems is essential. Commercial simulation software is often used as an analysis tool during the design of AGV systems, however a series of procedures are desirable to simplify the analysis processes. In this paper, we present and develop t

Many researchers have suggested improving the retention of a user in the digital platform using a recommender system. Recent studies show that there are many potential ways to assist users to find interesting items, other than high-precision rating predictions. In this paper, we study how the diverse types of information suggested to a user can influence their behavior. The types have been divided into visual information, evaluative information, categorial information, and narrational informatio

본 연구는 칸트 미학에서 제시된 상상력 개념을 성질적 측면에서 고찰하여 미술을 교육적 측면에서 탐색해 보는데 목적이 있다. 상상력은 경험하지 못한 일이나 사물을 우리의 경험과 지식으로 연결시킴으로서 새로움을 창조할 수 있는 역량으로 중요성이 커지고 있으며, 상상력을 강조해 온 예술 분야의 특성상 미술교육에서는 상상력을 중요한 요소로 다루고 있다. 우리의 교육에서 상상력에 대한 연구는 취미 판단이나 예술작품의 창조라는 기능적 관점에서 바라보았으며, 상상력을 어떻게 활용할 것인가에 대한 문제 등 예술적 관점에서 다루어져 왔다고 할 수 있다. 그러나 칸트의 상상력 개념에서 취미 판단이 숭고의 판단으로 확대되어 가고, 예술작품의 창작이 미적 이념의 표현으로 확대되어 가는 논의 전개에서 자율성과 확장성이라는 상상력의 성질적 측면을 발견할 수 있었다. 이러한 발견은 상상력을 개인적 기질이 아닌 인간의 역량으로 바라볼 수 있는 시각을 제공하여 상상력의 교육가능성을 확인할 수 있었을 뿐 아니라,

본 연구는 2015 개정 미술과 교육과정에서 중시되고 있는 ‘미술 문화 이해 능력’을 홀리스틱 패러다임의 교육에서 적용을 위한 기초적 배경과 실천적 사례를 탐구한 것이다. 홀리스틱 교육의 배경과 필요성, 미술 교육과의 연관성을 고찰 한 후, 서양 미술사를 중심으로 한 프로젝트 수업의 실천 사례를 통해 교육 방안과 의미를 탐색하였다. 급변하는 사회의 흐름 속에서 교육은 더 이상 단편적인 교과 지식을 가르치는 것이 아니라 기초 소양과 학력을 배경으로 서로 통합하고 융합하여 새로운 지식을 재생산하는 방향으로 변화하였다. 또한, 홀리스틱 교육은 과거 서구의 이성 중심의 세계관에서 벗어나고자 하는 대안에서 시작한 교육운동으로 ‘전체성’이라는 전제에서 유기적 관계 속에서 세상을 이해하고 통합과 협동, 변용의 과정을 거치며 끊임없이 새로움을 추구한다는 점에서 현재의 교육 흐름과 그 맥락을 같이 한다고 할 수 있다. 이 관점에서 출발하여 연구자는 서양 미술사에 기초하여 수업을 설계하고 실천하였다.