• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.1
• /
• pp.38-48
• /
• 1996

We implemented and evaluated the preformance of a task level pipelined multicomputer "RV860-PIPE(Realtime Vision i860 system using PIPEline)" for computer vision applications. RV860-PIPE is a message-passing MIMD computer having ring interconnection network which is appropriate for vision processing. We designed the node computer of RV860-PIPE using a 64-bit microprocessor to have generality and high processing power for various vision algorithms. Furthermore, to reduce the communication overhead between node computers and between node computer and a frame grabber, we designed dedicated high speed communication channels between them. We showed the practical applicability of the implemented system by evaluting performances of various computer vision applications like edge detection, real-time moving object tracking, and real-time face recognition.

• Journal of Advanced Navigation Technology
• /
• v.14 no.2
• /
• pp.272-277
• /
• 2010

AR(Augmented Reality) needs medium between real and virtual, world, and recognition techniques are necessary to track an object continuously. Optical tracking using marker is mainly used, but it takes time and is inconvenient to attach marker onto the target objects. Therefore, many researchers try to develop markerless tracking techniques nowaday. In this paper, we extract features and 3D position from 3D objects and suggest realtime tracking based on these features and positions, which do not use just coplanar features and 2D position. We extract features using SURF, get rotation matrix and translation vector of 3D object using POSIT with these features and track the object in real time. If the extracted features are nor enough and it fail to track the object, then new features are extracted and re-matched to recover the tracking. Also, we get rotation in matrix and translation vector of 3D object using POSIT and track the object in real time.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.6
• /
• pp.75-83
• /
• 2007

A model based approach of tracking the limbs of a walking human subject is proposed in this paper. The tracking process begins by building a data base composed of conditional probabilities of motions between the limbs of a walking subject. With a suitable amount of video footage from various human subjects included in the database, a probabilistic model characterizing the relationships between motions of limbs is developed. The motion tracking of a test subject begins with identifying and tracking limbs from the surveillance video image using the edge and silhouette detection methods. When occlusion occurs in any of the limbs being tracked, the approach uses the probabilistic motion model in conjunction with the minimum cost based edge and silhouette tracking model to determine the motion of the limb occluded in the image. The method has shown promising results of tracking occluded limbs in the validation tests.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.1
• /
• pp.175-182
• /
• 2021

The purpose of this paper is to develop a machine learning-based marine drone to prevent the farming from harmful birds such as ducks. Existing drones have been developed as marine drones to solve the problem of being lost if they collide with birds in the air or are in the sea. We designed a CNN-based learning algorithm to judge harmful birds that appear on the sea by maritime drones operating by autonomous driving. It is designed to transmit video to the control PC by connecting the Raspberry Pi to the camera for location recognition and tracking of harmful birds. After creating a map linked with the location GPS coordinates in advance at the mobile-based control center, the GPS location value for the location of the harmful bird is received and provided, so that a marine drone is dispatched to combat the harmful bird. A bird fighting drone system was designed and implemented.

• Journal of KIISE:Software and Applications
• /
• v.33 no.12
• /
• pp.1022-1030
• /
• 2006

The location awareness is an important part of many ubiquitous computing systems, but a perfect location system does not exist yet in spite of many researches. Among various location tracking systems, we choose the RFID system due to its wide applications. However, the sensed RSSI signal is too sensitive to the direction of a RFID reader antenna, the orientation of a RFID tag, the human interference, and the propagation media situation. So, the existing location tracking method in spite of using the particle filter is not working well. To overcome this shortcoming, we suggest a robust location tracking method with a double layered structure, where the first layer coarsely estimates a tag's location in the block level using a regression technique or the SVM classifier and the second layer precisely computes the tag's location, velocity and direction using the particle filter technique. Its layered structure improves the location tracking performance by restricting the moving degree of hidden variables. Many extensive experiments show that the proposed location tracking method is so precise and robust to be a good choice for implementing the location estimation of a person or an object in the ubiquitous computing. We also validate the usefulness of the proposed location tracking method by implementing it for a real-time people monitoring system in a noisy and complicate workplace.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.29 no.4
• /
• pp.389-394
• /
• 2023

In recent years, use of machine automation is rising in the industry. Ships also obtain machine condition information from sensor as digital information. However, on ships, crew members regularly surveil the engine room to check the condition of equipment and their information through analog gauges. This is a time-consuming and tedious process and poses safety risks to the crew while on surveillance. To address this, engine room surveillance using an autonomous mobile robot is being actively explored as a solution because it can reduce time, costs, and the safety risks for crew. Analog gauge reading using an autonomous mobile robot requires digitization for the robot to recognize the gauge value. In this study, image processing techniques were applied to achieve this. Analog gauge images were subjected to image preprocessing to remove noise and highlight their features. The center point, indicator point, minimum value and maximum value of the analog gauge were detected through image processing. Through the straight line connecting these points, the angle from the minimum value to the maximum value and the angle from the minimum value to indicator point were obtained. The obtained angle is digitized as the value currently indicated by the analog gauge through a formula. It was confirmed from the experiments that the digitization of the analog gauge using image processing was successful, indicating the equivalent current value shown by the gauge. When applied to surveillance robots, this algorithm can minimize safety risks and time and opportunity costs of crew members for engine room surveillance.

• The KIPS Transactions:PartB
• /
• v.15B no.2
• /
• pp.137-146
• /
• 2008

Fault localization plays a significant role in enormous distributed system because it can identify root cause of observed faults automatically, supporting self-managing which remains an open topic in managing and controlling complex distributed systems to improve system reliability. Although many Artificial Intelligent techniques have been introduced in support of fault localization in recent research especially in increasing complex ubiquitous environment, the provided functions such as diagnosis and prediction are limited. In this paper, we propose fault localization for self-managing in performance evaluation in order to improve system reliability via learning and analyzing real-time streams of system performance events. We use probabilistic reasoning functions based on the basic Bayes' rule to provide effective mechanism for managing and evaluating system performance parameters automatically, and hence the system reliability is improved. Moreover, due to large number of considered factors in diverse and complex fault reasoning domains, we develop an efficient method which extracts relevant parameters having high relationships with observing problems and ranks them orderly. The selected node ordering lists will be used in network modeling, and hence improving learning efficiency. Using the approach enables us to diagnose the most probable causal factor with responsibility for the underlying performance problems and predict system situation to avoid potential abnormities via posting treatments or pretreatments respectively. The experimental application of system performance analysis by using the proposed approach and various estimations on efficiency and accuracy show that the availability of the proposed approach in performance evaluation domain is optimistic.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.42 no.6
• /
• pp.37-48
• /
• 2005

The efficiency of power supply circuits such as DC-DC converters and batteries varies on the trend of the power consumption because their efficiencies are not fixed. To analyze the efficiency of power supply circuits, we need the temporal behavior of the power consumption of the loads, which is dependent on the activity factors of the devices during the operation. Since it is not easy to model every detail of those factors, one of the most accurate power consumption analyses of power supply circuits is measurement of a real system, which is expensive and time consuming. In this paper, we introduce an active load emulator for embedded systems which is capable of power measurement, logging, replaying and synthesis. We adopt a pattern recognition technique for data compression in that long-term behaviors of power consumption consist of numbers of repetitions of short-term behaviors, and the number of short-term behaviors is generally limited to a small number. We also devise a heterogeneous structure of active load elements so that low-speed, high-current active load elements and high-speed, low-current active load elements may emulate large amount and fast changing power consumption of digital systems. For the performance evaluation of our load emulator, we demonstrate power measurement and emulation of a hard drive. As an application of our load emulator, it is used for the analysis of a DC-DC converter efficiency and for the verification of a low-power frequency scaling policy for a real-time task.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.6
• /
• pp.572-577
• /
• 2009

Large corpus-based concatenating Text-to-Speech (TTS) systems can generate natural synthetic speech without additional signal processing. To prune the redundant speech segments in a large speech segment DB, we can utilize a decision-tree based triphone clustering algorithm widely used in speech recognition area. But, the conventional methods have problems in representing the acoustic transitional characteristics of the phones and in applying context questions with hierarchic priority. In this paper, we propose a new clustering algorithm to downsize the speech DB. Firstly, three 13th order MFCC vectors from first, medial, and final frame of a phone are combined into a 39 dimensional vector to represent the transitional characteristics of a phone. And then the hierarchically grouped three question sets are used to construct the triphone trees. For the performance test, we used DTW algorithm to calculate the acoustic similarity between the target triphone and the triphone from the tree search result. Experimental results show that the proposed method can reduce the size of speech DB by 23% and select better phones with higher acoustic similarity. Therefore the proposed method can be applied to make a small sized TTS.

• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.23-46
• /
• 2021

Collaborative filtering, which is often used in personalization recommendations, is recognized as a very useful technique to find similar customers and recommend products to them based on their purchase history. However, the traditional collaborative filtering technique has raised the question of having difficulty calculating the similarity for new customers or products due to the method of calculating similaritiesbased on direct connections and common features among customers. For this reason, a hybrid technique was designed to use content-based filtering techniques together. On the one hand, efforts have been made to solve these problems by applying the structural characteristics of social networks. This applies a method of indirectly calculating similarities through their similar customers placed between them. This means creating a customer's network based on purchasing data and calculating the similarity between the two based on the features of the network that indirectly connects the two customers within this network. Such similarity can be used as a measure to predict whether the target customer accepts recommendations. The centrality metrics of networks can be utilized for the calculation of these similarities. Different centrality metrics have important implications in that they may have different effects on recommended performance. In this study, furthermore, the effect of these centrality metrics on the performance of recommendation may vary depending on recommender algorithms. In addition, recommendation techniques using network analysis can be expected to contribute to increasing recommendation performance even if they apply not only to new customers or products but also to entire customers or products. By considering a customer's purchase of an item as a link generated between the customer and the item on the network, the prediction of user acceptance of recommendation is solved as a prediction of whether a new link will be created between them. As the classification models fit the purpose of solving the binary problem of whether the link is engaged or not, decision tree, k-nearest neighbors (KNN), logistic regression, artificial neural network, and support vector machine (SVM) are selected in the research. The data for performance evaluation used order data collected from an online shopping mall over four years and two months. Among them, the previous three years and eight months constitute social networks composed of and the experiment was conducted by organizing the data collected into the social network. The next four months' records were used to train and evaluate recommender models. Experiments with the centrality metrics applied to each model show that the recommendation acceptance rates of the centrality metrics are different for each algorithm at a meaningful level. In this work, we analyzed only four commonly used centrality metrics: degree centrality, betweenness centrality, closeness centrality, and eigenvector centrality. Eigenvector centrality records the lowest performance in all models except support vector machines. Closeness centrality and betweenness centrality show similar performance across all models. Degree centrality ranking moderate across overall models while betweenness centrality always ranking higher than degree centrality. Finally, closeness centrality is characterized by distinct differences in performance according to the model. It ranks first in logistic regression, artificial neural network, and decision tree withnumerically high performance. However, it only records very low rankings in support vector machine and K-neighborhood with low-performance levels. As the experiment results reveal, in a classification model, network centrality metrics over a subnetwork that connects the two nodes can effectively predict the connectivity between two nodes in a social network. Furthermore, each metric has a different performance depending on the classification model type. This result implies that choosing appropriate metrics for each algorithm can lead to achieving higher recommendation performance. In general, betweenness centrality can guarantee a high level of performance in any model. It would be possible to consider the introduction of proximity centrality to obtain higher performance for certain models.