Hee Seok Lee

Learn More
Existing approaches to template-based visual tracking, in which the objective is to continuously estimate the spatial transformation parameters of an object template over video frames, have primarily been based on deterministic optimization, which as is well-known can result in convergence to local optima. To overcome this limitation of the deterministic(More)
BACKGROUND The impact of procedure sequence and primary procedure has not been studied in the combined application of endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) and endoscopic ultrasound-guided fine needle aspiration (EUS-FNA) in lung cancer staging. METHODS In a randomised controlled trial, 160 patients with(More)
We investigated whether direct tissue matrix-assisted laser desorption/ionization (MALDI) mass spectrometry (MS) analysis on lipid may assist with the histopathologic diagnosis of non-small cell lung cancers (NSCLCs). Twenty-one pairs of frozen, resected NSCLCs and adjacent normal tissue samples were initially analyzed using histology-directed, MALDI MS.(More)
OBJECTIVE We performed this study to evaluate the role of transesophageal endoscopic ultrasound with bronchoscope-guided fine-needle aspiration (EUS-B-FNA) following endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) in the mediastinal staging of lung cancer. METHODS In this prospective study, we applied transbronchial and(More)
OBJECTIVE The goal of this study was to determine the optimal number of aspirations per lymph node (LN) station during endobronchial ultrasound (EBUS)-guided transbronchial needle aspiration (TBNA) for maximum diagnostic yield in mediastinal staging of non-small cell lung cancer (NSCLC) in the absence of rapid on-site cytopathologic examination. METHODS(More)
BACKGROUND The fact that only 10% of people infected with Mycobacterium tuberculosis develop clinical tuberculosis (TB) suggests the presence of genetic factors in the pathogenesis of TB. To date, a number of single nucleotide polymorphisms (SNPs) in several candidate genes have been proposed as genetic risk factors of TB; however, reports are conflicting.(More)
Motion blur frequently occurs in dense 3D reconstruction using a single moving camera, and it degrades the quality of the 3D reconstruction. To handle motion blur caused by rapid camera shakes, we propose a blur-aware depth reconstruction method, which utilizes a pixel correspondence that is obtained by considering the effect of motion blur. Motion blur is(More)
Many state-of-the-art optical flow estimation algorithms optimize the data and regularization terms to solve ill-posed problems. In this paper, in contrast to the conventional optical flow framework that uses a single or fixed data model, we study a novel framework that employs locally varying data term that adaptively combines different multiple types of(More)
Handling motion blur is one of important issues in visual SLAM. For a fast-moving camera, motion blur is an unavoidable effect and it can degrade the results of localization and reconstruction severely. In this paper, we present a unified algorithm to handle motion blur for visual SLAM, including the blur-robust data association method and the fast(More)
In this paper we present a new vision-based SLAM approach for multi-robot formulation. For a cooperative map reconstruction, the robots have to know each other's relative poses, but estimating these at the start of operation puts a limit on real applications. In our study, the robots start the single SLAM with their own global coordinate, and merge their(More)