• The Journal of Korea Robotics Society
• /
• v.14 no.1
• /
• pp.8-13
• /
• 2019

Visual place recognition is widely researched area in robotics, as it is one of the elemental requirements for autonomous navigation, simultaneous localization and mapping for mobile robots. However, place recognition in changing environment is a challenging problem since a same place look different according to the time, weather, and seasons. This paper presents a feature extraction method using a deep convolutional auto-encoder to recognize places under severe appearance changes. Given database and query image sequences from different environments, the convolutional auto-encoder is trained to predict the images of the desired environment. The training process is performed by minimizing the loss function between the predicted image and the desired image. After finishing the training process, the encoding part of the structure transforms an input image to a low dimensional latent representation, and it can be used as a condition-invariant feature for recognizing places in changing environment. Experiments were conducted to prove the effective of the proposed method, and the results showed that our method outperformed than existing methods.

• Journal of Advanced Navigation Technology
• /
• v.24 no.2
• /
• pp.155-162
• /
• 2020

Recently, with the development of computer vision and deep learning technology, research on human action recognition has been actively conducted for video analysis, video surveillance, interactive multimedia, and human machine interaction applications. Diverse techniques have been introduced for human action understanding and classification by many researchers using RGB image, depth image, skeleton and inertial data. However, skeleton-based action discrimination is still a challenging research topic for human machine-interaction. In this paper, we propose an end-to-end skeleton joints mapping of action for generating spatio-temporal image so-called dynamic image. Then, an efficient deep convolution neural network is devised to perform the classification among the action classes. We use publicly accessible UTD-MHAD skeleton dataset for evaluating the performance of the proposed method. As a result of the experiment, the proposed system shows better performance than the existing methods with high accuracy of 97.45%.

• Journal of the Institute of Electronics Engineers of Korea TE
• /
• v.42 no.1
• /
• pp.61-68
• /
• 2005

Image-based rendering is an approach to generate realistic images in real-time without modeling explicit 3D geometry. Especially, owing to its simplicity, TIP(Tour Into the Picture) is preferred to constructing a 3D background scene. Because existing TIP methods have a limitation in that they lack geometrical information, we can not expect a accurate scene if the viewpoint is far from the origin of the TIP. In this paper, we propose the method of constructing a virtual environment of a wide area by blending multiple TIP images. Firstly, we construct multiple TIP models of the virtual environment. Then we interpolate foreground and background objects respectively, to generate a smooth navigation image. The method proposed here can be applied to various industry applications, such as computer game, 3D car navigation, and so on.

• The Journal of the Korea Contents Association
• /
• v.12 no.1
• /
• pp.1-8
• /
• 2012

In this paper, a method of determining the optimal threshold in image binarization for the marker recognition is suggested to resolve the problem that the performances of marker recognition are quite different according to the changes of indoor lighting. The suggested method determines the optimal threshold by considering the average brightness, the standard deviation and the maximum deviation of video image under the various indoor lighting circumstances, such as bright light, dim light, and shadow by unspecified obstacles. In particular, the recognition under the gradation lighting by shadow is improved by applying the weighted value that depends on the brightness of image. The suggested method is experimented to process $720{\times}480$ resolution video images under the various lighting environments, and it shows the fast and high performance, which is suitable for mobile indoor navigation.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.2 s.40
• /
• pp.177-186
• /
• 2006

This paper presents the development of a certain highly efficient authoring tool for constructing realistic 3D virtual space using image-based rendering techniques based on a virtual space map. Unlike conventional techniques such as TIP, for constructing a small 3D virtual space using single image, the authoring tool developed herein produces a wide 3D virtual space using multiple images. This tool is designed for constructing each small 3D virtual space for each input image, and for interconnecting these 3D virtual spaces into a wide 3D virtual space using a virtual space map. The map consists of three elements such as specific room, link point and passageway, and three directions. It contains various information such as the connection structure, the navigation information and so on. Also, the tool contains a user interface that let users construct the wide 3D virtual space easily.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.1
• /
• pp.57-63
• /
• 2012

TIP technology enables navigation of the internal contents of images by extracting geometry information from two-dimensional drawing or a picture and generating three-dimensional effects from extracted information. The technology can be applied to a variety of practical fields including game, entertainment, education, public relations and so on. This paper proposes extended application of TIP technology and realization method for smart devices using OpenGL ES Library for Android platform. Considering problems associated with a foreground object extraction, the proposed method uses vanishing points chosen by the user to facilitate more realistic scene configuration. Then, method acquires three-dimensional background model using OpenGL ES Library, develops three-dimensional virtual space and enables image navigation via camera viewpoint conversion. The experimental image is made on Android 2.1 and OpenGL ES 1.0 using the image taken on devices built on the Android platform. Thus, the proposed technology can be implemented to various smart devices built on the Android platform at lower cost and in less time.

• Journal of Advanced Navigation Technology
• /
• v.25 no.6
• /
• pp.569-575
• /
• 2021

Deep learning shows differences in prediction performance depending on data quality and model. This study uses various input data and multiple deep learning models to build an optimal deep learning model for predicting solar radiation, which has the most influence on power generation prediction. did. As the input data, the weather data of the Korea Meteorological Administration and the clairvoyant meteorological image were used by segmenting the image of the Korea Meteorological Agency. , comparative evaluation, and predicting solar radiation by constructing multiple deep learning models connecting the models with the best error rate in each model. As an experimental result, the RMSE of model A, which is a multiple deep learning model, was 0.0637, the RMSE of model B was 0.07062, and the RMSE of model C was 0.06052, so the error rate of model A and model C was better than that of a single model. In this study, the model that connected two or more models through experiments showed improved prediction rates and stable learning results.

• Journal of Korean Neurosurgical Society
• /
• v.63 no.2
• /
• pp.237-247
• /
• 2020

Objective : Fixation of the C1-2 segment is challenging because of the complex anatomy in the region and the need for a high degree of accuracy to avoid complications. Preoperative 3D-computed tomography (CT) scans can help reduce the risk of complications in the vertebral artery, spinal cord, and nerve roots. However, the patient may be susceptible to injury if the patient's anatomy does not match the preoperative CT scans. The intraoperative 3D image-based navigation systems have reduced complications in instrument-assisted techniques due to greater accuracy. This study aimed to compare the radiologic outcomes of C1-2 fusion surgery between intraoperative CT image-guided operation and fluoroscopy-guided operation. Methods : We retrospectively reviewed the radiologic images of 34 patients who underwent C1-2 fusion spine surgery from January 2009 to November 2018 at our hospital. We assessed 17 cases each of degenerative cervical disease and trauma in a study population of 18 males and 16 females. The mean age was 54.8 years. A total of 139 screws were used and the surgical procedures included 68 screws in the C1 lateral mass, 58 screws in C2 pedicle, nine screws in C2 lamina and C2 pars screws, four lateral mass screws in sub-axial level. Of the 34 patients, 19 patients underwent screw insertion using intraoperative mobile CT. Other patients underwent atlantoaxial fusion with a standard fluoroscopy-guided device. Results : A total of 139 screws were correctly positioned. We analyzed the positions of 135 screws except for the four screws that performed the lateral mass screws in C3 vertebra. Minor screw penetration was observed in seven cases (5.2%), and major pedicle screw penetration was observed in three cases (2.2%). In one case, the malposition of a C2 pedicle screw was confirmed, which was subsequently corrected. There were no complications regarding vertebral artery injury or onset of new neurologic deficits. The screw malposition rate was lower (5.3%) in patients who underwent intraoperative CT-based navigation than that for fluoroscopy-guided cases (10.2%). And we confirmed that the operation time can be significantly reduced by surgery using intraoperative O-arm device. Conclusion : Spinal navigation using intraoperative cone-beam CT scans is reliable for posterior fixation in unstable C1-2 pathologies and can be reduced the operative time.

• Journal of Distribution Science
• /
• v.12 no.10
• /
• pp.99-108
• /
• 2014

Purpose - The goals of this study are the following. First, this study focused on customer satisfaction of in-flight service. Specifically, in-flight duty free items were considered because of their potential value related with the differentiated strategy of airline companies. Second, this study analyzed feasible strategies that would fence off the aversive attitudes of consumers toward innovation regarding in-flight duty free items. Third, this study strived to discover implicit routes related with the reactions of of consumers to innovation. Fourth, the construal level theory was applied to the context of in-flight service. Psychological distance is expected to promote acceptance of innovation for duty free items. Research design, data, and methodology - This study consisted of three experiments. All data were collected through the participation of university students. First, the experiment employed a 2×2 between-subject design. The first independent variable was temporal distance (long vs. short of navigation time). The second independent variable was innovativeness (innovative duty free items vs. typical items). Further, experiment 2 involved a 2×2 between-subject design. The first independent variable was social distance (typical vs. atypical stewardess image). The second was innovativeness that was based on a pattern similar to that of the prior experiment. The third experiment involved a 2×2×2 design. The first and second independent variables were temporal distance and item innovation, respectively, based on the method of experiment 1. The third independent variable was cognitive depletion (depletion vs. control condition). Results - Experiment 1 demonstrated that the innovation of duty free items would need to consider the journey time of the airline. Specifically, innovative items were preferred in case of a long journey; typical items, however, were liked in a short journey. Further, experiment 2 demonstrated that, in spite of a short journey, innovative items would be preferred if an atypical stewardess was serving. An atypical stewardess was linked with social distance, and the psychological effects would activate a creative and flexible mindset that would fit with innovative duty free items. The final experiment was accomplished for the examination of cognitive processing of psychological distance on innovation-acceptance. Specifically, if the effects were related with systematic processing, then cognitive effort would be needed. In contrast, if they were related with heuristic processing, then such efforts would not be required. The same pattern appeared under both cognitive depletion and control condition; therefore, the effects of psychological distance were implied to be heuristic processing. Conclusions - Managers need to consider the navigation time, stewardess concepts, and depletion of consumers as important factors for innovative strategy regarding in-flight service. Longer journeys are more successful for innovative trials. Further, a more atypical stewardess image is more successful for atypical service. Long navigation and unfamiliar stewardesses may activate creative and flexible thinking. Further, cognitive depletion of consumers is not a dominant factor of psychological distance effects, because the effects are not related with systematic processing, but with heuristic processing.

• Journal of Navigation and Port Research
• /
• v.37 no.3
• /
• pp.245-250
• /
• 2013

As maritime traffic increases and ships get bigger and faster, the risk of maritime accident increases. According to the recent reports on maritime accidents, more than 80% of the maritime accidents occur due to navigational mistakes and/or human errors. Even though many kinds of navigation systems based on new technology have been developed to reduce maritime accidents, we need to research the method for expressing and providing information. The efficient navigation system should be able to display information simply and intuitively to make decision quickly and accurately. In this paper, we proposed augmented reality based navigation system which can be utilized in bridge of the ships and described the services for navigational safety.