• Journal of the Korean Institute of Navigation
• /
• v.22 no.4
• /
• pp.31-36
• /
• 1998

The whistle is a very important information source for the safety navigation under foggy weather. But navigator has no concern about this, because it must be achived by human hearing sense and considered as a vague signal. If the range and relative bearing of signal source can be detected automatically, it would be very useful system for preventing marine casualties making a lot of economic loss and environment pollution. Before the algorithm of 2-dimensional sound source tracking system was reported. This paper describes the method that can obtain the time lag between three signals and the theory of cross-correlation analysis and subtraction method for cauculating the time lag by using the digital signal data sequences. And a series of experiments were carried out for various position of sound source in the range from 200cm to 530cm. As a result, we have recognized that sound source tracking system is possible to the sea field with improvement of position error.

• Asia pacific journal of information systems
• /
• v.29 no.4
• /
• pp.731-751
• /
• 2019

This study examined the impact of various product photo features on the attention of potential consumers in online apparel retailers' environment. Recently, the method of apparel's product photo representation in online shopping stores has been changed a lot from the classic product photos in the early days. In order to investigate if this shift is effective in attracting consumers' attention, we examined the related theory and verified its effect through laboratory experiments. In particular, experiment data was collected and analyzed using eye tracking technology. According to the results of this study, it was shown that the product photos with asymmetry are more attractive than symmetrical photos, well emphasized object within a photo more attractive than partially emphasized, smiling faces are more attractive for customer than emotionless and sad, and photos with uncentered models focus more consumer's attention than photos with model in the center. These results are expected to help design internet shopping stores to gaze more customers' attention.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2007.06a
• /
• pp.795-796
• /
• 2007

• Journal of Power Electronics
• /
• v.18 no.5
• /
• pp.1470-1478
• /
• 2018

Recently, wireless power transfer (WPT) via coupled magnetic resonances has attracted a lot of attention owing to its long operation distance and high efficiency. However, the WPT systems is over-coupling and a frequency splitting phenomenon occurs when resonators are placed closely, which leads to a decrease in the transfer power. To solve this problem, an adaptive frequency tracking control (AFTC) was used based on a closed-loop control scheme. An improved particle swarm optimization (PSO) algorithm was proposed with the AFTC to track the maximum power point in real time. In addition, simulations were carried out. Finally, a WPT system with the AFTC was demonstrated to experimentally validate the improved PSO algorithm and its tracking performance in terms of optimal frequency.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.2 no.2
• /
• pp.78-85
• /
• 1999

Tracking model of a drifted ship lot the search and rescue mission in southern sea of Korea is studied. In this model, search area is determined by considering standard deviation of position around reference point. The reference point is estimated for a given type of ship when marine environmental conditions such as wind and current are given. A database for environmental data, which is necessary for the real-lime tracking of drilled ship, is gel)elated on southern sea and western sea of Korea. Using this database, the real-time prediction of wind and current is possible. The simulated trajectories and search area of our model ate validated by comparing with reported real data.

• Smart Media Journal
• /
• v.6 no.3
• /
• pp.49-56
• /
• 2017

Images and Videos that include the human face contain a lot of information. Therefore, accurately extracting human face is a very important issue in the field of computer vision. However, in real life, human faces have various shapes and textures. To adapt to these variations, A model-based approach is one of the best ways in which unknown data can be represented by the model in which it is built. However, the model-based approach has its weaknesses when the motion between two frames is big, it can be either a sudden change of pose or moving with fast speed. In this paper, we propose an enhanced human face-tracking model. This approach included human face detection and motion estimation using Cascaded Convolutional Neural Networks, and continuous human face tracking and modeling correction steps using the Active Appearance Model. A proposed system detects human face in the first input frame and initializes the models. On later frames, Cascaded CNN face detection is used to estimate the target motion such as location or pose before applying the old model and fit new target.

• Journal of Korea Multimedia Society
• /
• v.15 no.8
• /
• pp.963-976
• /
• 2012

'Gesture' except for voice is the most intuitive means of communication. Thus, many researches on how to control computer using gesture are in progress. User detection and tracking in these studies is one of the most important processes. Conventional 2D object detection and tracking methods are sensitive to changes in the environment or lights, and a mix of 2D and 3D information methods has the disadvantage of a lot of computational complexity. In addition, using conventional 3D information methods can not segment similar depth object. In this paper, we propose object detection and tracking method using Depth Projection Map that is the cumulative value of the depth and motion information. Simulation results show that our method is robust to changes in lighting or environment, and has faster operation speed, and can work well for detection and tracking of similar depth objects.

• The KIPS Transactions:PartB
• /
• v.17B no.5
• /
• pp.345-354
• /
• 2010

Visual tracking techniques for Augmented Reality are classified as either a marker tracking approach or a natural feature tracking approach. Marker-based tracking algorithms can be efficiently implemented sufficient to work in real-time on mobile devices. On the other hand, natural feature tracking methods require a lot of computationally expensive procedures. Most previous natural feature tracking methods include heavy feature extraction and pattern matching procedures for each of the input image frame. It is difficult to implement real-time augmented reality applications including the capability of natural feature tracking on low performance devices. The required computational time cost is also in proportion to the number of patterns to be matched. To speed up the natural feature tracking process, we propose a novel fast tracking method based on optical flow. We implemented the proposed method on mobile devices to run in real-time and be appropriately used with mobile augmented reality applications. Moreover, during tracking, we keep up the total number of feature points by inserting new feature points proportional to the number of vanished feature points. Experimental results showed that the proposed method reduces the computational cost and also stabilizes the camera pose estimation results.

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.426-428
• /
• 2004

Sensor network supports data delivery from physical world to cyber space Sensors get physical events then wireless network transfers sensor data to service server. We use sensor network technology to manage location information of asset. In ubiquitous computing environment, user localization is basic context for intelligent service. A lot of research group make effort to develop low cost localization technology. In this paper, we propose asset monitoring system using wireless sensor network. It is implemented using ad hoc network technology which can be adopted to smart home and this system can monitor the asset location and movement.

• Proceedings of the KIEE Conference
• /
• 2003.11b
• /
• pp.255-258
• /
• 2003

It is hard to centrol the wheeled mobile robot because of uncertainty of modeling, non-holonomic constraint and so on. To solve the problems, we design the controller of wheeled mobile robot based on fuzzy-neural network algorithm. In this paper, we should research the problem of classical controller for path-tracking algorithm and design of Fuzzy-Neural Network algorithm controller. Classical controller acquired different control value according to change of initial position and direction. In this control value having very difficult and having acquired a lot of trial and error Fuzzy is implemented to adaptive adjust control value by error and change of error and neural network is implemented to adaptive adjust the control gain during the optimization. The computer simulation shows that the proposed fuzzy-neural network controller is effective.