김선주 교수

Video super-resolution (VSR) has become even more important recently to provide high resolution (HR) contents for ultra high definition displays. While many deep learning based VSR methods have been proposed, most of them rely heavily on the accuracy of motion estimation and compensation. We introduce a fundamentally different framework for VSR in this paper. We propose a novel end-to-end deep neural network that generates dynamic upsampling filters and a residual image, which are computed depen

We present an efficient method for the semi-supervised video object segmentation. Our method achieves accuracy competitive with state-of-the-art methods while running in a fraction of time compared to others. To this end, we propose a deep Siamese encoder-decoder network that is designed to take advantage of mask propagation and object detection while avoiding the weaknesses of both approaches. Our network, learned through a two-stage training process that exploits both synthetic and real data,

In many computer vision systems, it is assumed that the image brightness of a point directly reflects the scene radiance of the point. However, the assumption does not hold in most cases due to nonlinear camera response function, exposure changes, and vignetting. The effects of these factors are most visible in image mosaics and textures of 3D models where colors look inconsistent and notable boundaries exist. In this paper, we propose a full radiometric calibration algorithm that includes robus

We present a study of in-camera image processing through an extensive analysis of more than 10,000 images from over 30 cameras. The goal of this work is to investigate if image values can be transformed to physically meaningful values, and if so, when and how this can be done. From our analysis, we found a major limitation of the imaging model employed in conventional radiometric calibration methods and propose a new in-camera imaging model that fits well with today's cameras. With the new model

The images of an outdoor scene collected over time are valuable in studying the scene appearance variation which can lead to novel applications and help enhance existing methods that were constrained to controlled environments. However, the images do not reflect the true appearance of the scene in many cases due to the radiometric properties of the camera : the radiometric response function and the changing exposure. We introduce a new algorithm to compute the radiometric response function and t

Color values in an image are related to image irradiance by a nonlinear function called radiometric response function. Since this function depends on the aperture and the shutter speed, image intensity of a same object may vary during the acquisition of an image sequence due to auto exposure feature of the camera. While this is desirable to make optimal use of the limited dynamic range of most cameras, this causes problems for a number of applications in computer vision. In this paper we propose

This paper presents an interactive visualization tool to study and analyze hyperspectral images (HSI) of historical documents. This work is part of a collaborative effort with the Nationaal Archief of the Netherlands (NAN) and Art Innovation, a manufacturer of hyperspectral imaging hardware designed for old and fragile documents. The NAN is actively capturing HSI of historical documents for use in a variety of tasks related to the analysis and management of archival collections, from ink and pap

To capture the full brightness range of natural scenes, cameras automatically adjust the exposure value which causes the brightness of scene points to change from frame to frame. Given such a video sequence, we introduce a new method for tracking features and estimating the radiometric response function of the camera and the exposure difference between frames simultaneously. We model the global and nonlinear process that is responsible for the changes in image brightness rather than adapting to

Purpose: Severe acute respiratory syndrome coronavirus 2, which causes coronavirus disease 2019 (COVID-19), has spreadworldwide. Global health systems, including emergency medical systems, are suffering from a lack of medical resources. Using amethod for classifying patients visiting the emergency department (ED), we aimed to investigate trends in emergency medicalsystem usage during the COVID-19 epidemic in Korea. Materials and Methods: This retrospective observational study included patients w

In this work we propose a dynamic scene model to provide information about the presence of salient motion in the scene, and that could be used for focusing the attention of a pan/tilt/zoom camera, or for background modeling purposes. Rather than proposing a set of saliency detectors, we define what we mean by salient motion, and propose a precise model for it. Detecting salient motion becomes equivalent to detecting a model change. We derive optimal online procedures to solve this problem, which