• Journal of Korea Multimedia Society
• /
• v.23 no.10
• /
• pp.1236-1249
• /
• 2020

In a most recent object tracking research work, applying Convolutional Neural Network and Recurrent Neural Network-based strategies become relevant for resolving the noticeable challenges in it, like, occlusion, motion, object, and camera viewpoint variations, changing several targets, lighting variations. In this paper, the LSTM Network-based Tracking association method has proposed where the technique capable of real-time multi-object tracking by creating one of the useful LSTM networks that associated with tracking, which supports the long term tracking along with solving challenges. The LSTM network is a different neural network defined in Keras as a sequence of layers, where the Sequential classes would be a container for these layers. This purposing network structure builds with the integration of tracking association on Keras neural-network library. The tracking process has been associated with the LSTM Network feature learning output and obtained outstanding real-time detection and tracking performance. In this work, the main focus was learning trackable objects locations, appearance, and motion details, then predicting the feature location of objects on boxes according to their initial position. The performance of the joint object tracking system has shown that the LSTM network is more powerful and capable of working on a real-time multi-object tracking process.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.10
• /
• pp.4117-4135
• /
• 2020

Due to the angle of view, illumination and scene diversity, real-time dynamic face detection and recognition is no small difficulty in those unrestricted environments. In this study, we used the intrinsic correlation between detection and calibration, using a multi-task cascaded convolutional neural network(MTCNN) to improve the efficiency of face recognition, and the output of each core network is mapped in parallel to a compact Euclidean space, where distance represents the similarity of facial features, so that the target face can be identified as quickly as possible, without waiting for all network iteration calculations to complete the recognition results. And after the angle of the target face and the illumination change, the correlation between the recognition results can be well obtained. In the actual application scenario, we use a multi-camera real-time monitoring system to perform face matching and recognition using successive frames acquired from different angles. The effectiveness of the method was verified by several real-time monitoring experiments, and good results were obtained.

• Journal of the Korean Society of Combustion
• /
• v.20 no.4
• /
• pp.26-33
• /
• 2015

American NREL (National Renewable Energy Laboratory) reported that BD20 could reduce PM, CO, SOx and cancerogenic matters by 13.6%, 9.3%, 17.6% and 13% respectively, compared to diesel fuel. BD20 has been being tested on garbage trucks and official vehicles at Seoul City, which is positive on air environment, but negative on combustion by higher viscosity in winter season. This study investigated the combustion characteristics by employing multi cavity piston for improving the deterioration of combustibility caused by the higher viscosity of the biodiesel fuel such as BD20 with the combustion flames taken by a high speed camera and the cylinder pressure diagram. A 4-cycle single cylinder diesel engine was remodeled to a visible 2-cycle engine for taking the flame photographs, which has a common-rail injection system. The test was done at laboratory temperature of about $4{\sim}5^{\circ}C$.

• ETRI Journal
• /
• v.35 no.6
• /
• pp.969-979
• /
• 2013

Various simulation applications for hair, clothing, and makeup of a 3D avatar can provide more useful information to users before they select a hairstyle, clothes, or cosmetics. To enhance their reality, the shapes, textures, and colors of the avatars should be similar to those found in the real world. For a more realistic 3D avatar color reproduction, this paper proposes a spectrum-based color reproduction algorithm and color management process with respect to the implementation of the algorithm. First, a makeup color reproduction model is estimated by analyzing the measured spectral reflectance of the skin samples before and after applying the makeup. To implement the model for a makeup simulation system, the color management process controls all color information of the 3D facial avatar during the 3D scanning, modeling, and rendering stages. During 3D scanning with a multi-camera system, spectrum-based camera calibration and characterization are performed to estimate the spectrum data. During the virtual makeup process, the spectrum data of the 3D facial avatar is modified based on the makeup color reproduction model. Finally, during 3D rendering, the estimated spectrum is converted into RGB data through gamut mapping and display characterization.

• Korean Journal of Remote Sensing
• /
• v.26 no.6
• /
• pp.629-644
• /
• 2010

A real-time image georeferencing system requires all inputs to be determined in real-time. The intrinsic camera parameters can be identified in advance from a camera calibration process while other control information can be derived instantaneously from real-time GPS/INS data. The bottleneck process is tie point acquisition since manual operations will be definitely obstacles for real-time system while the existing extraction methods are not fast enough. In this paper, we present a fast-and-automated image matching technique based on the KLT tracker to obtain a set of tie-points in real-time. The proposed work accelerates the KLT tracker by supplying the initial guessed tie-points computed using the GPS/INS data. Originally, the KLT only works effectively when the displacement between tie-points is small. To drive an automated solution, this paper suggests an appropriate number of depth levels for multi-resolution tracking under large displacement using the knowledge of uncertainties the GPS/INS data measurements. The experimental results show that our suggested depth levels is promising and the proposed work can obtain tie-points faster than the ordinary KLT by 13% with no less accuracy. This promising result suggests that our proposed algorithm can be effectively integrated into the real-time image georeferencing for further developing a real-time surveillance application.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.11
• /
• pp.2179-2184
• /
• 2007

The Intelligent Space(ISpace) provides challenging research fields for surveillance, human-computer interfacing, networked camera conferencing, industrial monitoring or service and training applications. ISpace is the space where many intelligent devices, such as computers and sensors, are distributed. According to the cooperation of many intelligent devices, the environment, it is very important that the system knows the location information to offer the useful services. In order to achieve these goals, we present a method for representing, tracking and human following by fusing distributed multiple vision systems in ISpace, with application to pedestrian tracking in a crowd. This paper described appearance based unknown object tracking with the distributed vision system in intelligent space. First, we discuss how object color information is obtained and how the color appearance based model is constructed from this data. Then, we discuss the global color model based on the local color information. The process of learning within global model and the experimental results are also presented.

• Journal of the Korea Computer Graphics Society
• /
• v.23 no.5
• /
• pp.9-17
• /
• 2017

Filming using multiple cameras is required for the production of the multi-screen content. It can fill the viewer's field of view (FOV) entirely to provide an increased sense of immersion. In such a filming scenario, it is very important to monitor how images captured by multiple cameras are displayed as a single content or how the content will be displayed in an actual theatre. Most recent studies on creating the content of special format have been focused on their own purposes, such as stereoscopic and panoramic images. There is no research on content creation optimized for theatres that use three screens that are spreading recently. In this paper, we propose a novel content production system with a rig that can control three cameras and monitoring software specialized for multi-screen content. The proposed rig can precisely control the angles between the cameras and capture wide angle of view with three cameras. It works with monitoring software via remote communication. The monitoring software automatically aligned the content in real time, and the alignment of the content is updated according to the angle of camera rig. Futher, the producion efficiency is greatly improved by making the alignment information available for post-production.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.1840-1843
• /
• 1997

The task environment of a robot is changing rapidly and task itself becomes complicated due to current industrial trends of multi-product and small lot size production. A convenient user-interfaced off-line programming(OLP) system is being developed in order to overcome the difficulty in teaching a robot task. Using the OLP system, operators can easily teach robot tasks off-line and verify feasibility of the task through simulation of a robot prior to the on-line execution. However, some task errors are inevitable by kinematic differences between the robot model in OLP and the actual robot. Three calibration methods using image information are proposed to compensate the kinematic differences. These methods compose of a relative position vector method, three point compensation method, and base line compensation method. To compensate a kinematic differences the vision system with one monochrome camera is used in the calibration experiment.

• Journal of Korea Multimedia Society
• /
• v.20 no.8
• /
• pp.1224-1235
• /
• 2017

Recently, augmented reality technology has received much attention in many fields. This paper presents an augmented reality system using Rubiks' Cube which can augment various 3D objects depending on patterns of a Rubiks' cube. The system first detects a cube from an image using partitional clustering and strongly connected graph. Thereafter, the system detects the top side of the cube and finds a proper pattern to determine which object should be augmented. An object corresponding to the pattern is finally augmented according to the camera viewpoint. Experimental results show that the proposed system successfully augments various virtual objects in real time.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.5
• /
• pp.870-876
• /
• 2017

In this paper, we proposed the automatic vision inspection system using multi-layer perceptron to detect the defects occurred on rail surface. The proposed system consists of image acquisition part and analysis part. Rail surface image is acquired as equal interval using line scan camera and lighting. Mean filter and dynamic threshold is used to reduce noise and segment defect area. Various features to characterize the defects are extracted. And they are used to train and distinguish defects by MLP-classifier. The system is installed on HEMU-430X and applied to analyze the rail surface images acquired from Honam-line at high speed up to 300 km/h. Recognition rate is calculated through comparison with manual inspection results.