• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.4 no.3
• /
• pp.174-181
• /
• 2011

A new registration method for IR image and EO image is proposed in this paper. IR sensor is applicable to many area because it absorbs thermal radiation energy unlike EO sensor does. However, IR sensor has difficulty to extract and match features due to low contrast compared to EO image. In order to register both images, we used modified SIFT(Scale Invariant Feature Transform) and block processing to increase feature distinctiveness. To remove outlier, we applied RANSAC(RANdom SAample Concensus) for each block. Finally, we unified matching features into single coordinate system and remove outlier again. We used 3~5um range IR image, and our experiment result showed good robustness in registration with IR image.

• Journal of Korea Multimedia Society
• /
• v.22 no.9
• /
• pp.1000-1010
• /
• 2019

Image semantic segmentation and dehazing are key tasks in the computer vision. In recent years, researches in both tasks have achieved substantial improvements in performance with the development of Convolutional Neural Network (CNN). However, most of the previous works for semantic segmentation assume the images are captured in clear weather and show degraded performance under hazy images with low contrast and faded color. Meanwhile, dehazing aims to recover clear image given observed hazy image, which is an ill-posed problem and can be alleviated with additional information about the image. In this work, we propose a deep multi-task network for simultaneous semantic segmentation and dehazing. The proposed network takes single haze image as input and predicts dense semantic segmentation map and clear image. The visual information getting refined during the dehazing process can help the recognition task of semantic segmentation. On the other hand, semantic features obtained during the semantic segmentation process can provide cues for color priors for objects, which can help dehazing process. Experimental results demonstrate the effectiveness of the proposed multi-task approach, showing improved performance compared to the separate networks.

• Journal of Korea Multimedia Society
• /
• v.22 no.10
• /
• pp.1149-1159
• /
• 2019

We present a novel deep learning architecture for obtaining a latent image from a single blurry image, which contains dynamic motion blurs through object/camera movements. The proposed architecture consists of two sub-modules: blur image restoration and optical flow estimation. The tasks are highly related in that object/camera movements make cause blurry artifacts, whereas they are estimated through optical flow. The ablation study demonstrates that training multi-task architecture simultaneously improves both tasks compared to handling them separately. Objective and subjective evaluations show that our method outperforms the state-of-the-arts deep learning based techniques.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.10
• /
• pp.19-26
• /
• 2017

In this paper, we propose an efficient image equipment implementation for the detector characteristics of various detectors by analyzing un-cooled thermal detector that exhibits nonlinear changes due to external temperature effects. First, we explain Thermal Electric Cooler for un-cooled detector temperature control system and Non-image correction methode for IR system. Second, we present the results of a study on an efficient control technique that can minimize the deterioration of image quality by controlling a un-cooled thermal detector without a thermal electric cooler(TEC) inside. Third, we suggest Image Correction Methods for Uncooled IR TECless Detector with Non-linear characteristics due to Temperature Change. So, we analyze and present the results of Image correction methods for various un-cooled thermal detector.

• Korean Journal of Radiology
• /
• v.23 no.11
• /
• pp.1044-1054
• /
• 2022

Objective: This study aimed to investigate whether a deep learning reconstruction (DLR) method improves the image quality, stent evaluation, and visibility of the valve apparatus in coronary computed tomography angiography (CCTA) when compared with filtered back projection (FBP) and hybrid iterative reconstruction (IR) methods. Materials and Methods: CCTA images of 51 patients (mean age ± standard deviation [SD], 63.9 ± 9.8 years, 36 male) who underwent examination at a single institution were reconstructed using DLR, FBP, and hybrid IR methods and reviewed. CT attenuation, image noise, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and stent evaluation, including 10%-90% edge rise slope (ERS) and 10%-90% edge rise distance (ERD), were measured. Quantitative data are summarized as the mean ± SD. The subjective visual scores (1 for worst -5 for best) of the images were obtained for the following: overall image quality, image noise, and appearance of stent, vessel, and aortic and tricuspid valve apparatus (annulus, leaflets, papillary muscles, and chordae tendineae). These parameters were compared between the DLR, FBP, and hybrid IR methods. Results: DLR provided higher Hounsfield unit (HU) values in the aorta and similar attenuation in the fat and muscle compared with FBP and hybrid IR. The image noise in HU was significantly lower in DLR (12.6 ± 2.2) than in hybrid IR (24.2 ± 3.0) and FBP (54.2 ± 9.5) (p < 0.001). The SNR and CNR were significantly higher in the DLR group than in the FBP and hybrid IR groups (p < 0.001). In the coronary stent, the mean value of ERS was significantly higher in DLR (1260.4 ± 242.5 HU/mm) than that of FBP (801.9 ± 170.7 HU/mm) and hybrid IR (641.9 ± 112.0 HU/mm). The mean value of ERD was measured as 0.8 ± 0.1 mm for DLR while it was 1.1 ± 0.2 mm for FBP and 1.1 ± 0.2 mm for hybrid IR. The subjective visual scores were higher in the DLR than in the images reconstructed with FBP and hybrid IR. Conclusion: DLR reconstruction provided better images than FBP and hybrid IR reconstruction.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.16 no.4
• /
• pp.246-253
• /
• 2016

Infrared (IR) imaging has been researched for various applications such as surveillance. IR radiation has the capability to detect thermal characteristics of objects under low-light conditions. However, automatic segmentation for finding the object of interest would be challenging since the IR detector often provides the low spatial and contrast resolution image without color and texture information. Another hindrance is that the image can be degraded by noise and clutters. This paper proposes multi-level segmentation for extracting regions of interest (ROIs) and objects of interest (OOIs) in the IR scene. Each level of the multi-level segmentation is composed of a k-means clustering algorithm, an expectation-maximization (EM) algorithm, and a decision process. The k-means clustering initializes the parameters of the Gaussian mixture model (GMM), and the EM algorithm estimates those parameters iteratively. During the multi-level segmentation, the area extracted at one level becomes the input to the next level segmentation. Thus, the segmentation is consecutively performed narrowing the area to be processed. The foreground objects are individually extracted from the final ROI windows. In the experiments, the effectiveness of the proposed method is demonstrated using several IR images, in which human subjects are captured at a long distance. The average probability of error is shown to be lower than that obtained from other conventional methods such as Gonzalez, Otsu, k-means, and EM methods.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.12 no.4
• /
• pp.500-507
• /
• 2009

This paper presents a novel method which can detect a target in IR image for active protection system. The target in IR image for the active protection system is small, moreover it moves with enormous speed. The proposed algorithm is comprised of robust clutter rejection methods and target optimized detection algorithms for small target, and an advanced method of selecting a final target position in target area, it can work in some milliseconds. The proposed algorithm provides the active protective system with more correct positions than those of radar, so that helps the active protection system can defense all threats with the utmost precision.

• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.8
• /
• pp.767-773
• /
• 2008

This paper presents a localization system based on the use of electric compass and tracking IR light source. Digital RGB(Red, Green, Blue)signal of digital CMOS Camera is sent to CPLD which converts the color image to binary image at 30 frames per second. CMOS camera has IR filter and UV filter in front of CMOS cell. The filters cut off above 720nm light source. Binary output data of CPLD is sent to DSP that rapidly tracks the IR light source by moving Camera tilt DC motor. At a robot toward north, electric compass signals and IR light source angles which are used for calculating the data of the location system. Because geomagnetic field is linear in local position, this location system is possible. Finally, it is shown that position error is within ${\pm}1.3cm$ in this system.

• Journal of Korea Multimedia Society
• /
• v.15 no.7
• /
• pp.870-878
• /
• 2012

Recently, very rapid development of computer and sensor technologies induces various kinds of user interface (UI) technologies based on user experience (UX). In this study, we investigate and develop a smart touch projector system technology on the basis of IR sensor and image processing. In the proposed system, a user can control computer by understanding the control events based on gesture of IR pen as an input device. In the IR image, we extract the movement (or gesture) of the devised pen and track it for recognizing gesture pattern. Also, to correct the error between the coordinate of input image sensor and display device (projector), we propose a coordinate correction algorithm to improve the accuracy of operation. Through this system technology as the next generation human-computer interaction, we can control the events of the equipped computer on the projected image screen without manipulating the computer directly.

• Proceedings of the IEEK Conference
• /
• 2007.07a
• /
• pp.245-246
• /
• 2007

Recently, the problem of binarization in night surveillance image using IR-LED(InfraRed-LED) is an issue because the same object has different intensity in the image according to the distance between camera and the object. This paper introduces a new local thresholding technique based on the relative intensity of IR-LED that is acquired with the camera and installation informations.