• Journal of Broadcast Engineering
• /
• v.21 no.4
• /
• pp.569-577
• /
• 2016

Place recognition for LBS (Location Based Service) has been one of the important techniques for user-oriented service. FLANN (Fast Library for performing Approximate Nearest Neighbor) of place recognition with image features is fast, but it is affected much by environmental condition such as occlusions. This paper presents a place recognition method using quad vocabulary tree with SURF (Speeded Up Robust Features). In learning stage, an image is represented with spatial pyramid of three levels and vocabulary trees of their sub-regions are constructed. Query image is matched with the learned vocabulary trees in each level. The proposed method measures homography error of the matched features. By considering the number of inliers in sub-region, we can improve place recognition performance.

• The Journal of Korea Robotics Society
• /
• v.12 no.3
• /
• pp.249-257
• /
• 2017

This paper proposes a method to segment urban scenes semantically based on location prior information. Since major scene elements in urban environments such as roads, buildings, and vehicles are often located at specific locations, using the location prior information of these elements can improve the segmentation performance. The location priors are defined in special 2D coordinates, referred to as road-normal coordinates, which are perpendicular to the orientation of the road. With the help of depth information to each element, all the possible pixels in the image are projected into these coordinates and the learned prior information is applied to those pixels. The proposed location prior can be modeled by defining a unary potential of a conditional random field (CRF) as a sum of two sub-potentials: an appearance feature-based potential and a location potential. The proposed method was validated using publicly available KITTI dataset, which has urban images and corresponding 3D depth measurements.

• Journal of the Institute of Convergence Signal Processing
• /
• v.13 no.4
• /
• pp.187-193
• /
• 2012

An image authentication scheme for gray scale image through embedding a digital watermark by quantization of Integer Wavelet Transform (IWT) coefficients of the image is proposed in this paper. Proposed method is designed to detect modification of an image and to identify tampered location of the image. To embed the watermark mid-frequency band of a second level IWT was used. An approximation of the original image based on LL band was stored in LSB bits of the pixel data as a recovery mark for restoration of the image. Watermarked image has achieved a good PSNR of 40 dB compared to original cover image. Restored image quality was also very good with a PSNR of more than 35 dB compared to unmodified watermarked image even when 25% of the received image is cropped. Thus, the proposed method ensures a proper balance between the fidelity of the watermarked image and the quality of the restored image.

• Archives of design research
• /
• v.19 no.6 s.68
• /
• pp.15-20
• /
• 2006

Despite the SKM Duyree shop's potentials, such as residing over the Samsung-dong, gangnam-gu one of the premier locations in Seoul, and offering a large shopping store, the old 'SKM Dutyfree' symbol [image #2] has become the burden for a company due to its low-profile brand quality and lack of location advertisements. Therefore, first, we have agreed to acquire the popular brand word 'COEX' and replace "SKM Dutyfree" to "COEX Dutyfree", and second, the new visual image has been created in order to create a synergy of the urban-look and the location-information. Therefore, the visual identity design concepts have been utilized in order to achieve such goals; first, promote the existing COEX-image and metropolitan-esque image. Second, unify the international-metropolitan looks of the COEX-mall, hotel, shopping center, exhibition, and airport terminal with location information. Third, deliver the new identity-design [image #1] of the fresh look(compare to competing dutyfree shops) and dynamic images.

• East Asian Journal of Business Economics (EAJBE)
• /
• v.8 no.1
• /
• pp.71-80
• /
• 2020

Purpose - The purpose of this paper is to advance the understanding of the relationship between host country image and cultural intelligence (CQ) on the attractiveness of expatriate destinations. Specifically, this study compares the different impacts of CQ on the relationship between host country image and subsidiary attractiveness by comparing a US-based subsidiary and a Vietnam-based one. Research design and methodology - A total of 445 Korean full-time workers responded through an online survey. The survey randomly showed the participants one of two conditions for a potential expatriate location. The participants were asked to answer a series of questions on the organizational attractiveness of the subsidiaries from the perspective of an expatriate candidate and respond to a series of questions on individual CQ. Results - Through a two-way ANOVA test, the results reveal that Korean expatriate candidates perceive that a Vietnam-based subsidiary is a less attractive destination for international assignment when compared to a US-based subsidiary. In addition, the positive moderating effect of cultural intelligence on the relationship between the host location and the subsidiary's attractiveness is stronger when Vietnam, rather than the US, is the assignment location. Conclusions - Drawing upon AUM theory, this study confirmed that unfavorable country image affects subsidiaries' attractiveness for expatriate candidates, due to anxiety. However, this study showed the role of employees' CQ to mitigate these challenges. This study suggests providing information on positive conditions of expatriate locations and building systematic process for enhancing individual CQ for organizations.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.1211-1212
• /
• 2008

In this paper, we propose image process modeling as a part of location based surveillance system for unauthorized target recognition and tracking in harbor, airport, military zone. For this, we compress and store background image in lower resolution and perform object extraction and motion tracking by using sobel edge detection and difference picture method between real images and a background image. In addition to, we use Independent Component Analysis Neural Network for moving target recognition. Experiments are performed for object extraction and tracking of moving targets on road by using static camera in 20m height building and it shows the robust results.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1997.10a
• /
• pp.500-503
• /
• 1997

In this paper, a method for recognizing 3-D objects using the 3-D Hough transform and the robust stereo vision is studied. A 3-D object is recognized through two steps; modeling step and matching step. In modeling step, features of the object are extracted by analyzing the IGES file. In matching step, the values of the sensed image are compared with those of the IGES file which is assumed to location and orientation in the 3-D Hough transform domain. Since we use the 3-D Hough transform domain of the input image directly, the sensitivity to the noise and the high computational complexity could be significantly allcv~ated. Also, the cost efficiency is improved using the robust stereo vision for obtaining depth map image which is needed for 3-D Hough transform. In order lo verify the proposed method, real telephone model is recognized. Thc results of the location and orientation of the model are presented.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2003.04a
• /
• pp.471-476
• /
• 2003

The presence of voids under pavements or behind tunnel linings results in their deterioration. To detect these voids effectively by non-destructive tests, a method using radar was proposed. In this research, not only the detection of shape of voids, but also the location of reinforcing bars by radar image analysis is investigated. The experiments and image processing were conducted to detect voids and to locate reinforcing bars in or under concrete pavements (or tunnel linings) with reinforcing bars. From the results, the fundamental algorithm for tracing the reinforcing bars and voids, improving the horizontal resolution of the object image and detecting shape of objects, was verified.

• Proceedings of the KOSOMBE Conference
• /
• v.1998 no.11
• /
• pp.269-270
• /
• 1998

Image-guided surgery (IGS) system has become well known in the field of neurosurgery and spine surgery. A patient's anatomy is first registered to preoperatively acquired CT/ MRI data using the point matching algorithm. A magnetic field digitizer was used to measure the physical space data and the system was based on Workstation of Unix system. To evaluate the spatial accuracy of interactive IGS system, the phantom consisting of rods varied height and known location was used. The RMS error value between CT/MR images and real location was 3-4mm. For the more convenience of the surgery, we provide various image display modules.

• Journal of Power System Engineering
• /
• v.4 no.4
• /
• pp.78-83
• /
• 2000

It is often necessary to observe the working environment of a robot to control it efficiently in the remote location. The remote sensing data and control commands are transmitted via various media such as radio, microwave, and computer network. The World Wide Web can be used as the infrastructure for teleoperation of mobile robots. In this paper we propose an advanced technique of the remote control of mobile robots on the web. For the real-time control, the image separation algorithm is proposed to transmit the current positions of mobile robots instead of transmitting the full frame image. It is shown by experiments that the proposed algorithm is effective.