• Journal of the Institute of Convergence Signal Processing
• /
• v.22 no.1
• /
• pp.30-37
• /
• 2021

Accurate 3D object tracking with camera images is a key enabling technology for augmented reality applications. Motivated by the impressive success of convolutional neural networks (CNNs) in computer vision tasks such as image classification, object detection, image segmentation, recent studies for 3D object tracking have focused on leveraging deep learning. In this paper, we review deep learning approaches for 3D object tracking. We describe key methods in this field and discuss potential future research directions.

• Annual Conference of KIPS
• /
• 2020.11a
• /
• pp.814-817
• /
• 2020

The number of single-person households is increasing every year, and there are also high concerns about the crime and safety of single-person households. In particular, crimes targeting women are increasing. Although home surveillance camera applications, which are mostly used by single-person households, only provide intrusion detection functions, this service utilizes AI image recognition technologies such as face recognition and object detection to provide theft, violence, stranger and intrusion detection. Users can receive security-related notifications, relieve their anxiety, and prevent crimes through this service.

• Journal of the Korean Society for Precision Engineering
• /
• v.10 no.3
• /
• pp.168-174
• /
• 1993

A new digital image processing method for measuring of the flank wear of cutting tool is presented. The method is based on computer vision technology in which the tool is illuminated by two halogen lamps and the wear zone is visualized using a CCD camera. The image is converted into digital pixel and processed to detect the wearland width. As a conclusion, it has been proved that the average wearland area and mzximum peak values of the flank wear width can monitored effectively to a measuring resolution of 0.01mm.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.248-249
• /
• 2022

In this paper, we propose a method for classifying and tracking objects based on information of multiple users obtained using RGB-D cameras. The 3D information and color information acquired through the RGB-D camera are acquired and information about each user is stored. We propose a user classification and location tracking algorithm in the entire image by calculating the similarity between users in the current frame and the previous frame through the information on the location and appearance of each user obtained from the entire image.

• Journal of Advanced Navigation Technology
• /
• v.27 no.5
• /
• pp.685-689
• /
• 2023

The proposed system in the study aims to detect forest fires in real-time stream data received from the drone-camera. Recently, the number of wildfires has been increasing, and also the large scaled wildfires are frequent more and more. In order to prevent forest fire damage, many experiments using the drone camera and vision analysis are actively conducted, however there were many challenges, such as network speed, pre-processing, and model performance, to detect forest fires from real-time streaming data of the flying drone. Therefore, this study applied image data processing works to capture five good image frames for vision analysis from whole streaming data and then developed the object detection model based on YOLO_v2. As the result, the classification model performance of forest fire images reached upto 93% of accuracy, and the field test for the model verification detected the forest fire with about 70% accuracy.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.7
• /
• pp.93-99
• /
• 2015

In this paper, we propose a gaze correction method for realistic video teleconferencing. Typically, cameras used in teleconferencing are installed at the side of the display monitor, but not in the center of the monitor. This system makes it too difficult for users to contact each eyes. Therefore, eys contact is the most important in the immersive videoconferencing. In the proposed method, we use the stereo camera and the depth camera to correct the eye contact. The depth camera is the kinect camera, which is the relatively cheap price, and estimate the depth information efficiently. However, the kinect camera has some inherent disadvantages. Therefore, we fuse the kinect camera with stereo camera to compensate the disadvantages of the kinect camera. Consecutively, for the gaze-corrected image, view synthesis is performed by 3D warping according to the depth information. Experimental results verify that the proposed system is effective in generating natural gaze-corrected images.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.6
• /
• pp.793-799
• /
• 2018

The CCD camera is easily deteriorated by radiation, and an integrated camera using an image pickup tube is used in a high radiation area. We implemented a radiation camera system which is divided into a camera head using radiation-resistant electronic components and a remote control using weak radiation-resistant electronic components such as TR, IC, etc. According to the experimental results, the first damage of the electronic parts was IC for horizontal and vertical sync generation, and it was confirmed that if the radiation of $2{\times}10^5{\sim}10^6rad$ is accumulated, the normal function is lost. In addition, the signal transmission cable for remoteization has added an input/output buffer circuit and reduced the closed loop area of the shield and the cable to eliminate signal loss correction and noise. Therefore, it is expected that the maintenance cost will be greatly reduced and practical because only the camera head part can be used instead of replacing the entire system.

• The Journal of the Acoustical Society of Korea
• /
• v.37 no.2
• /
• pp.99-109
• /
• 2018

The precision of the vibration-sensors, contact or non-contact types, is usually satisfactory for the practical measurement applications, but a sensor is confined to the measurement of a point or a direction. Although the precision and frequency span of the low-cost camera are inferior to these sensors, it has the merits in the cost and in the capability of simultaneous measurement of a large vibrating area. Furthermore, a camera can measure multi-degrees-of-freedom of a vibrating object simultaneously. In this study, the calibration method and the dynamic characteristics of the low-cost machine vision camera as a sensor are studied with a demonstrating example of the two-dimensional vibration of a cantilever beam. The planar image of the camera shot reveals two rectilinear and one rotational motion. The rectilinear vibration motion of a single point is first measured using a camera and the camera is experimentally calibrated by calculating error referencing the LDV (Laser Doppler Vibrometer) measurement. Then, by measuring the motion of multiple points at once, the rotational vibration motion and the whole vibration motion of the cantilever beam are measured. The whole vibration motion of the cantilever beam is analyzed both in time and frequency domain.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2004.04a
• /
• pp.251-257
• /
• 2004

The Electro-Optical Camera(EOC) image of the first Korea Multi-Purpose Satellitel(KOMPSAT-1) has both high resolution and convenient acquisition of research data, but on the other hand it has a defect of one band image. Fortunately, the multispectral Moderate Resolution Imaging Spectroradiometer (MODIS) image data are receiving every day at the Korea Aerospace Research Institute (KARI). Therefore, this paper performed an effective merging for survey of reclaimed land using the high-resolution (6.6m) KOMPSAT-1 EOC image and the multispectral MODIS image data. According this paper prepared map of reclaimed lands in Western Coast of North Korea as quantitative(position and form) survey of reclaimed lands of North Korea using merged image. The use of KOPSAT-1 EOC image and MODIS images was found to be economical such using of large scale areas as reclaimed land or according easy to collect information and such north korea as inaccessible areas like as receiving every day.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2010.10a
• /
• pp.527-532
• /
• 2010

This paper is concerned with the measurement of static and dynamic displacement by image processing(IP) and study for prediction method of velocity and acceleration. To measure the displacement visually, the measurement system consists of a telephoto zoom camera, ccd image device and a computer. The specific target on the white board is used to calculate the displacement of the structure. The captured image is then converted into a pixel-based data and then analyzed numerically. The limitation of the system depends on the image capturing speed and the pixel-size of image. In this paper, we developed for the displacement measurement using the image processing method. The proposed method enables us to measure the vibration measurement, velocity and acceleration directly without any contact. The current resolution of the displacement measurement is limited to 1/100 millimeter scale.