• Proceedings of the KIEE Conference
• /
• 2005.10b
• /
• pp.61-63
• /
• 2005

Retreiving indoor scene reference image from database using visual information is important issue in Robot Navigation. Scene matching problem in navigation robot is not easy because input image that is taken in navigation process is affinly distorted. We represent probabilistic framework for the feature matching between features in input image and features in database reference images to guarantee robust scene matching efficiency. By reconstructing probabilistic scene matching framework we get a higher precision than the existing feaure-feature matching scheme. To construct probabilistic framework we represent each image as Gaussian Mixture Model using Expectation Maximization algorithm using SIFT(Scale Invariant Feature Transform).

• Journal of Positioning, Navigation, and Timing
• /
• v.8 no.4
• /
• pp.175-181
• /
• 2019

This paper suggests a velocity integration algorithm for Synthetic Aperture Radar (SAR) motion measurement to reduce discontinuity of range error. When using position data from Embedded GPS/INS (EGI) to form SAR image, the discontinuity of the data degrades SAR image quality. In this paper, to reduce the discontinuity of EGI position data, EGI velocity integration is suggested which obtains navigation solution by integrating velocity data from EGI. Simulation shows that the method improves SAR image quality by reducing the discontinuity of range error. INS is a similar algorithm to EGI velocity integration in the way that it also obtains navigation solution by integrating velocity measured by IMU. Comparing INS and EGI velocity integration according to grades of IMU and GPS, EGI velocity integration is more suitable for the real system. Through this, EGI velocity integration is suggested, which improves SAR image quality more than existing algorithms.

• Journal of Ocean Engineering and Technology
• /
• v.27 no.3
• /
• pp.22-28
• /
• 2013

This paper suggests a navigation information display system that is based on augmented reality technology. A navigator always has to confirm the information from marine electronic navigation devices and then compare it with the view of targets outside the windows. This "head down" posture causes discomfort and sometimes near accidents such as collisions or missing objects, because he or she cannot keep an eye on the front view of the windows. Augmented reality can display both virtual and real information in a single display. Therefore, we attempted to adapt AR technology to assist navigators. To analyze the outside view of the bridge window, various computer image processing techniques are required because the sea surface has many noises that disturb computer image processing for object detection, such as waves, wakes, light reflection, and so on. In this study, we investigated an analysis module to extract navigational information from images that are captured by a CCTV camera, and we validated our prototype.

• The Journal of Korea Robotics Society
• /
• v.5 no.4
• /
• pp.367-376
• /
• 2010

This Paper Proposes A Robust Image Stabilization System For A Mobile Robot Using An Extended Kalman Filter (Ekf). Though Image Information Is One Of The Most Efficient Data Used For Robot Navigation, It Is Subjected To Noise Which Is The Result Of Internal Vibration As Well As External Factors Such As Uneven Terrain, Stairs, Or Marshy Surfaces. The Camera Vibration Deteriorates The Image Resolution By Destroying The Image Sharpness, Which Seriously Prevents Mobile Robots From Recognizing Their Environment For Navigation. In This Paper, An Inclinometer Was Used To Measure The Vibration Angle Of The Camera System Mounted On The Robot To Obtain A Reliable Image By Compensating For The Angle Of The Camera Vibration. In Addition The Angle Prediction Obtained By Using The Ekf Enhances The Image Response Analysis For Real Time Performance. The Experimental Results Show The Effectiveness Of The Proposed System Used To Compensate For The Blurring Of The Images.

• Journal of Satellite, Information and Communications
• /
• v.11 no.4
• /
• pp.89-93
• /
• 2016

In this paper, we provide a summary on the core essence of INR (Image Navigation and Registration) System technology which is an essential function of geostationary remote sensing satellites. Its origin and evolution history is reviewed, its core elements and governing concept for each element are described, and a generic INR architecture is suggested which can cover all seemingly conceivable INR systems of the past, the current and the future. By this, we intend to identify and illuminate the core technical contents and the key aspects in the foreseen prospect of the up-coming INR systems and the related technologies.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.10a
• /
• pp.95-97
• /
• 2010

Recently, CAN network technology and MOST network are introduced in vehicle to control many electronic devices and to provide entertainment service. Many interconnected devices operate in MOST network which has ring topology such as CD-ROM(DVD), AMP, VIDEO CAMERA, VIDEO DISPLAY, GPS NAVIGATION and so on. In this paper, The input image of CAMERA in the MOST network is used for determining the movement direction of vehicle. Even though the position information was received from GPS, it is difficult to directly determine the direction of moving vehicle in certain areas such as the parallel road structure. This paper designs and implements the method to determine vehicle's direction by real-time matching between CAMERA image and object image base on image DB.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.3
• /
• pp.221-227
• /
• 2024

In autonomous navigation systems, the need for fast and accurate image processing using deep learning and advanced sensor technologies is paramount. These systems rely heavily on the ability to process and interpret visual data swiftly and precisely to ensure safe and efficient navigation. Despite the critical importance of such capabilities, there has been a noticeable lack of research specifically focused on ship image classification for maritime applications. This gap highlights the necessity for more in-depth studies in this domain. In this paper, we aim to address this gap by presenting a comprehensive comparative study of ship image classification using two distinct neural network models: the Feedforward Neural Network (FNN) and the Convolutional Neural Network (CNN). Our study involves the application of both models to the task of classifying ship images, utilizing a dataset specifically prepared for this purpose. Through our analysis, we found that the Convolutional Neural Network demonstrates significantly more effective performance in accurately classifying ship images compared to the Feedforward Neural Network. The findings from this research are significant as they can contribute to the advancement of core source technologies for maritime autonomous navigation systems. By leveraging the superior image classification capabilities of convolutional neural networks, we can enhance the accuracy and reliability of these systems. This improvement is crucial for the development of more efficient and safer autonomous maritime operations, ultimately contributing to the broader field of autonomous transportation technology.

• The Journal of Korea Robotics Society
• /
• v.3 no.3
• /
• pp.245-254
• /
• 2008

Recently, many vision-based navigation methods have been introduced as an intelligent robot application. However, many of these methods mainly focus on finding an image in the database corresponding to a query image. Thus, if the environment changes, for example, objects moving in the environment, a robot is unlikely to find consistent corresponding points with one of the database images. To solve these problems, we propose a novel navigation strategy which uses fast motion estimation and a practical scene recognition scheme preparing the kidnapping problem, which is defined as the problem of re-localizing a mobile robot after it is undergone an unknown motion or visual occlusion. This algorithm is based on motion estimation by a camera to plan the next movement of a robot and an efficient outlier rejection algorithm for scene recognition. Experimental results demonstrate the capability of the vision-based autonomous navigation against dynamic environments.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.772-774
• /
• 2008

A navigation system for virtual environments using low-quality HMD(head mounted display)must quantize images when the system presents true-color image with restricted number of colors. Such navigation system quantizes an image by using fixed palette. If the system represents an image by using a variable palette which is made considering a region around the viewpoint then user can perceive a virtual environments more vividly because human visual system is sensitive to the colors variation in the region around the viewpoint. In this paper we propose a color quantization algorithm that quantize a region around the viewpoint more finely than other regions at each variation of viewpoint for virtual environments navigation system and compose virtual environments navigation system using proposed algorithm. The system quantizes an image at each variation of viewpoint and shows a quantized image to user through HMD. We tested user preferences for our proposed system and the results show that users preferred our system.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.13 no.2
• /
• pp.74-93
• /
• 2010

Nowadays, the navigation system is very popular to general public and the study of landmarks has an important role to develop the cognitive systems for regional navigation. The city image is composed of landmarks that are well-known to regional community and they are the reference frame for place recognition in urban navigation. In general, the case of navigation can be categorized as two kinds. The first is to explore the new region and the second is to navigate the familiar region. In case of latter, the city image has a critical role in place recognition for regional community. Place recognition of a community might be a knowledge-based inference on the basis of city image which is composed of the systematically connected places. In this study, the mental structure of urban image is regarded as a hierarchical knowledge and represents it as domain ontology for the regional navigation of a community. The city image of a community is assumed as the collection of landmarks, which are categorized as anchor, distant and local according to spatial familiarity of community. Representing city image as a regional knowledge using ontology modeling method is an essential step to make the geographical assumption of a regional community explicit and reusable for the regional agents who will provide the regional guide in LBS age.