• Proceedings of the KSME Conference
• /
• 2008.11a
• /
• pp.768-772
• /
• 2008

Various scanning systems have been studied in many industrial areas to acquire a range data or to reconstruct an explicit 3D model. Currently optical technology has been used widely by virtue of noncontactness and high-accuracy. In this paper, we describe a 3D laser scanning system developped to reconstruct the 3D surface of a large-scale object such as a curved-plate of ship-hull. Our scanning system comprises of 4ch-parallel laser vision modules using a triangulation technique. For multi laser vision, calibration method based on least square technique is applied. In global scanning, an effective method without solving difficulty of matching problem among the scanning results of each camera is presented. Also minimal image processing algorithm and robot-based calibration technique are applied. A prototype had been implemented for testing.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.05a
• /
• pp.699-701
• /
• 2010

For the development of surveillance Multi Sensor and IFOG, development of integrated surveillance camera for day and night time of its system Control Unit design and navigation device interlocking system was made. Control Unit analysis of integrated ship system began with selection of control unit related to feasible navigation device list.After sorting navigation equipment list, applications, features, connection methods, communication methods, data type of control unit and data direction between navigation equipments and the data types of each navigation equipment is sorted to observe its performance.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 1996.06c
• /
• pp.621-631
• /
• 1996

It is said that robot can be used for multi-purpose use by changing end effector or/and visual sensor with its software. In this study, it was investigated what multi-purpose robot for fruit-production was using a tomato harvesting robot and a robot to work in vineyard. Tomato harvesting robot consisted of manipulator, end-effector, visual sensor and traveling device. Plant training system of larger size tomato is similar with that of cherry-tomato. Two end-effectors were prepared for larger size tomato and cherry-tomato fruit harvesting operations, while the res components were not changed for the different work objects. A color TV camera could be used for the both work objects, however fruit detecting algorithm and extracted features from image should be changed. As for the grape-robot , several end-effector for harvesting , berry thinning , bagging and spraying were developed and experimented after attaching each end-effector to manipulator end. The manipulator was a polar coordinate type and had five degrees of freedom so that it could have enough working space for the operations. It was observed that visual sensor was necessary for harvesting, bagging and berry-thinning operations and that spraying operation requires another sensor for keeping certain distance between trellis and end-effector. From the experimental results, it was considered that multi-operations by the same robot could be appropriately done on the same or similar plant training system changing some robot components . One of the important results on having function of multi-operation was to be able to make working period of the robot longer.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.30 no.1
• /
• pp.31-38
• /
• 2012

The geo-referencing accuracy of the images acquired by a UAV based multi-sensor system is affected by the accuracy of the mounting parameters involving the relationship between a camera and a GPS/INS system as well as the performance of a GPS/INS system. Therefore, the estimation of the accurate mounting parameters of a multi-sensor system is important. Currently, we are developing a low altitude multi-sensor system based on a UAV, which can monitor target areas in real time for rapid responses for emergency situations such as natural disasters and accidents. In this study, we suggest a system calibration method for the estimation of the mounting parameters of a multi-sensor system like our system. We also generate simulation data with the sensor specifications of our system, and derive an effective flight configuration and the number of ground control points for accurate and efficient system calibration by applying the proposed method to the simulated data. The experimental results indicate that the proposed method can estimate accurate mounting parameters using over five ground control points and flight configuration composed of six strips. In the near future, we plan to estimate mounting parameters of our system using the proposed method and evaluate the geo-referencing accuracy of the acquired sensory data.

• 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.