• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.11
• /
• pp.4290-4309
• /
• 2020

In recent years, advancements in machine learning capabilities have allowed it to see widespread adoption for tasks such as object detection, image classification, and anomaly detection. However, despite their promise, a limitation lies in the fact that a network's performance quality is based on the data which it receives. A well-trained network will still have poor performance if the subsequent data supplied to it contains artifacts, out of focus regions, or other visual distortions. Under normal circumstances, images of the same scene captured from differing points of focus, angles, or modalities must be separately analysed by the network, despite possibly containing overlapping information such as in the case of images of the same scene captured from different angles, or irrelevant information such as images captured from infrared sensors which can capture thermal information well but not topographical details. This factor can potentially add significantly to the computational time and resources required to utilize the network without providing any additional benefit. In this study, we plan to explore using image fusion techniques to assemble multiple images of the same scene into a single image that retains the most salient key features of the individual source images while discarding overlapping or irrelevant data that does not provide any benefit to the network. Utilizing this image fusion step before inputting a dataset into the network, the number of images would be significantly reduced with the potential to improve the classification performance accuracy by enhancing images while discarding irrelevant and overlapping regions.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.35 no.5
• /
• pp.82-91
• /
• 2007

Currently, bridges are regarding as the structure with formative, scenic and environmental values more than their function as simple passageways. Because an attempt to work on the diversity of the bridge types and installation of the large structures on bridge are part of the project of the regional amenity enterprises, a study that harmonizes bridges with landscape is needed at this point in time. This background can influence the direction of bridge landscapes that considers local features by analysis of visual preferences on a bridge simulated scene. The results were as follows: analyzing the change of the simulated landscape image, forest landscape are damaged by the input of a bridge which was natural, harmonic and intimate. On the other hand, when a bridge was inserted into the ocean landscape, it was thought to improve the ocean landscape, especially, upper part form of arch bridge various or suspension bridge were improved in polished and various image. The insertion of a bridge into an urban landscape change from a negative image to a beautiful, harmonic and attractive image. The intimate, harmonic and natural image of a rural landscape was damaged by inserting a bridge. As analysis result about change of landscape preference by input of bridge, there is difference between before and after as input the bridge, and bridge influences as main object in the simulated scene. Visual preference was the highest in the ocean landscape, and the lowest in the suspension bridge in the rural landscape. The complicated shape of bridge follows on the background type difference certainly appear. Thee simulated scene preference except the urban landscape of the simulated scene fell generally Especially, fall of preference of girder bridge in the forest and ocean landscape, suspension bridge in the rural landscape appeared notedly.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.4
• /
• pp.56-62
• /
• 2010

Auto-exposure control automatically calculates and adjusts the exposure for consecutive input image. Recently, this is usually controlled by the sensor gain, however, unsuitable control causes oscillation of luminance for sonsecutive input images, called as flickering. Also, in mobile phone cameras, only simple information, such as the average luminance value, can be utilized due to coarse performance. Therefore, this paper presents a new real-time AE control method using a Look Up Table(LUT) based on Scene-Luminance curves to avoid the generation of flickering. Prior to the AE control, a LUT is constructed, which illustrates the characteristic of outputs for input patches corresponding to sensor gains. The AE control is first performed by estimating a current scene as a patch using the proposed LUT. A new sensor gain is then estimated using also LUT with previously estimated patch. The entire estimation process is performed using linear interpolation to achieve real-time execution. Based on experimental results, the proposed AE control is demonstrated with real-time, flicker-free.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.1
• /
• pp.106-123
• /
• 2024

This article takes the talk show "Beast Town" as an example to introduce the overall technical solution, technical difficulties and countermeasures for the combination of cartoon virtual characters and virtual studio technology, providing reference and experience for the multi-scenario application of digital humans. Compared with the live broadcast that combines reality and reality, we have further upgraded our virtual production technology and digital human-driven technology, adopted industry-leading real-time virtual production technology and monocular camera driving technology, and launched a virtual cartoon character talk show - "Beast Town" to achieve real Perfectly combined with virtuality, it further enhances program immersion and audio-visual experience, and expands infinite boundaries for virtual manufacturing. In the talk show, motion capture shooting technology is used for final picture synthesis. The virtual scene needs to present dynamic effects, and at the same time realize the driving of the digital human and the movement with the push, pull and pan of the overall picture. This puts forward very high requirements for multi-party data synchronization, real-time driving of digital people, and synthetic picture rendering. We focus on issues such as virtual and real data docking and monocular camera motion capture effects. We combine camera outward tracking, multi-scene picture perspective, multi-machine rendering and other solutions to effectively solve picture linkage and rendering quality problems in a deeply immersive space environment. , presenting users with visual effects of linkage between digital people and live guests.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2000.11a
• /
• pp.106-109
• /
• 2000

The virtual reality - haptic device is developed for the purpose used in the work that human cannot approach and that need elaborate exercises. To render haptic, the total system is constituted master, haptic device, and slave, remote manipulator. Human operates the remote manipulator. Human operates the remote manipulator relying on the hapti devices and stereo graphic. And then the force and scene of the remote manipulator is fed-back from each haptic devices and virtual devices. The feedback information gets system gain exactly. The system gain provides the most exact haptic and virtual devices. The feedback information gets system gain exactly. The system gain provides the most exact haptic and scene to human by the location, the graphic rendering and the haptic rendering algorithm on real-time. In this research, 3D haptic device is developed for common usage and make human feel the haptic when human contacts virtual object rendered by computer graphic. The haptic device is good for tracing location and producing devices because of the row structure. Also, openGL and Visual Basic is utilized to the algorithms for haptic rendering. The haptic device of this research makes the interface possible not only with virtual reality but also with the real remote manipulator.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.3
• /
• pp.605-613
• /
• 2009

In this paper, we studied for the real-time azimuthal measurement of HMD (Head Mounted Display) to control the tele-operated vision system on the mobile robot. In the preexistence tele-operated vision system, a joystick was used to control the pan-tilt unit of the remote camera system. To give the sense of presence to the tele-operator, we used a HMD to display the remote scene, measured the rotation angle of the HMD on a real time basis, and transmitted the measured rotation angles to the mobile robot controller to synchronize the pan-tilt angles of remote camera with the HMD. In this paper, we suggest an algorithm for the real-time estimation of the HMD rotation angles using feature points extraction from pc-camera image. The simple experiment is conducted to demonstrate the feasibility.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.2
• /
• pp.435-440
• /
• 2011

A touchless user interface system is proposed for real-time mobile devices in this work. The proposed system first recognizes the position of pattern to interact various applications based on the scene taken from mobile camera. Then, the proposed system traces the route of the pattern, which estimates the motion of pattern based on the mean-shift method. Based on this information, we control menu and keypad for the various applications. Differ from other user interface systems, the proposed system provides the new experience to even for the user of low-end mobile without additional hardware. Simulation results demonstrate that the proposed algorithm provides better interaction performances than the conventional method, while achieving real-time user interacting for mobile devices.

• Proceedings of the Korea Contents Association Conference
• /
• 2006.11a
• /
• pp.218-222
• /
• 2006

In making 3D animation with digital technology, it is necessary to increase productivity and reusability by managing production pipeline systematically through standardization of animation content. For this purpose, we try to develop the animation content management system that can manage all kind of information on the production pipeline, based on SCORM of e-teaming by considering production, publication and re-editing. A scene as the unit of visual semantics is standardize into an object that contains meta-data of place, cast, weather, season, time and viewpoint about the scene. The meta-data of content includes a lot of information of copyright, publication, description, etc, so that it plays an important role on the management and the publication. If an effective management system of meta-data such as ontology will be implemented, it is possible to search multimedia contents powerfully. Hence, it will bring on production and publication of UCC. Using the meta-data of content object, user and producer can easily search and reuse the contents. Hence, they can choose the contents object according to their preference and reproduce their own creative animation by reorganizing and packaging the selected objects.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.27 no.12
• /
• pp.1825-1833
• /
• 1990

This paper proposes an efficient algorithm that constructs 3-dimensional solid object from 3 orthogonal views. This algorithm inputs vertex and edge information of 3 orthogonal views and generates 2 dimensional surfaces, 3 dimensional vertices, edges and surfaces and then compares 2 dimensional projections of 3 dimensional surfaces with surfaces from othorgonal views. This algorithm is useful for CAD system, 3 dimensional scene analysis system and object modeling for real-time animation and has been implemented in C language on IRIS workstation. The effectiveness of this algorithm is shown by examples of aircrafts' models.

• Proceedings of the IEEK Conference
• /
• 2003.11a
• /
• pp.233-236
• /
• 2003

In this paper, we propose a method to search the evidence such as a knife found in the crime scene based on GHT from an image database Such objects like knives are simitar in shape. The proposed method utilizes the small shape differences among objects as much as possible to distinguish an object from similar shaped objects. It consists of the GHT based candidate generation and top-down candidate verification. For the fast generation of the candidate 1ist, the GHT operation is performed un the down sampled edge list. The test results show that it can retrieve the correct object even with a pan of object in reasonable time.