• Smart Structures and Systems
• /
• v.24 no.6
• /
• pp.745-757
• /
• 2019

Road surface deteriorations such as potholes have caused motorists heavy monetary damages every year. However, effective road condition monitoring has been a continuing challenge to road owners. Depth cameras have a small field of view and can be easily affected by vehicle bouncing. Traditional image processing methods based on algorithms such as segmentation cannot adapt to varying environmental and camera scenarios. In recent years, novel object detection methods based on deep learning algorithms have produced good results in detecting typical objects, such as faces, vehicles, structures and more, even in scenarios with changing object distances, camera angles, lighting conditions, etc. Therefore, in this study, a Deep Learning Pothole Detector (DLPD) based on the deep region-based convolutional neural network is proposed for autonomous detection of potholes from images. About 900 images with potholes and road surface conditions are collected and divided into training and testing data. Parameters of the network in the DLPD are calibrated based on sensitivity tests. Then, the calibrated DLPD is trained by the training data and applied to the 215 testing images to evaluate its performance. It is demonstrated that potholes can be automatically detected with high average precision over 93%. Potholes can be differentiated from manholes by training and applying a manhole-pothole classifier which is constructed using the convolutional neural network layers in DLPD. Repeated detection of the same potholes can be prevented through feature matching of the newly detected pothole with previously detected potholes within a small region.

• Journal of the Korean Society of Visualization
• /
• v.20 no.2
• /
• pp.78-85
• /
• 2022

In these days, the rapid development in prediction technology using artificial intelligent is being applied in a variety of engineering fields. Especially, dimensionality reduction technologies such as autoencoder and convolutional neural network have enabled the classification and regression of high-dimensional data. In particular, pixel level prediction technology enables semantic segmentation (fine-grained classification), or physical value prediction for each pixel such as depth or surface normal estimation. In this study, the pressure distribution of the ship's surface was estimated at the pixel level based on the artificial neural network. First, a potential flow analysis was performed on the hull form data generated by transforming the baseline hull form data to construct 429 datasets for learning. Thereafter, a neural network with a U-shape structure was configured to learn the pressure value at the node position of the pretreated hull form. As a result, for the hull form included in training set, it was confirmed that the neural network can make a good prediction for pressure distribution. But in case of container ship, which is not included and have different characteristics, the network couldn't give a reasonable result.

• Journal of the Korean Society of Food Culture
• /
• v.24 no.6
• /
• pp.655-665
• /
• 2009

Coupled with the international expansion of Korean culture in recent years, a number of restaurants from Korea have been trying to tap into the global market place. The purpose of this study was to identify the characteristics of non-Korean patrons in Korean Restaurants in New-york city. The survey was conducted at six popular Korean restaurants, all of which had been recognized in the Zagat Survey in recent years, located in prime business districts in Manhattan. The data collected from the six local Korean restaurants that participated in this study were qualitatively and quantitatively analyzed. After employing individual in-depth interviews with restaurant operators, a qualitative analysis identified demographic characteristics, Socioeconomic characteristics and segmentation of restaurant operation. Self-administrated survey questionnaires were used to acquire quantitative data. Primary data were collected from non-Korean patrons at the six participating Korean restaurants in New York City in 2008 (N=245). The patrons who answered the survey indicated that they were highly satisfied with the 'Food'; however, they were not satisfied with the 'Beverage' and 'Value'. In addition, older patrons (55<) were not as content with the 'Food' as the younger patrons. The most influential satisfaction variable that affected a patron's intention to revisit the Korean restaurant was 'Food' and 'Overall experience'. This study findings will help Korean restaurant operators and marketers better understand their patrons and formulate strategies to cater and target segments more effectively.

• Journal of Broadcast Engineering
• /
• v.15 no.6
• /
• pp.723-730
• /
• 2010

Recently, diverse 3D image processing technologies have been applied in industries. Among them, stereoscopic conversion is a technology to generate a stereoscopic image from a conventional 2D image. The technology can be applied to movie and broadcasting contents and the viewer can watch 3D stereoscopic contents. Further the stereoscopic conversion is required to be applied to other fields. Following such trend, the aim of this paper is to apply the stereoscopic conversion to medical fields. The medical images can deliver more detailed 3D information with a stereoscopic image compared with a 2D plane image. This paper presents a novel methodology for converting a 2D medical image into a 3D stereoscopic image. For this, mean shift segmentation, edge detection, intensity analysis, etc are utilized to generate a final depth map. From an image and the depth map, left and right images are constructed. In the experiment, the proposed method is performed on a medical image such as CT (Computed Tomograpy). The stereoscopic image displayed on a 3D monitor shows a satisfactory performance.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.32 no.6
• /
• pp.553-560
• /
• 2020

This paper presents an algorithm for identifying and eliminating errors by seagrasses in coastal bathymetry surveying using drone and HD camera. Survey errors due to seagrasses were identified, segmentated and eliminated using a L∗a∗b color space model. Bathymetry survey using a drone and HD camera has many advantages over conventional survey methods such as ship-board acoustic sounder or manual level survey which are time consuming and expensive. However, errors caused by sea bed reflectance due to seagrasses habitat hamper the development of new surveying tool. Seagrasses are the flowering plants which start to grow in November and flourish to maximum density until April in Korea. We developed a new algorithm for identifying seagrasses habitat locations and eliminating errors due to seagrasses to get the accurate depth survey data. We tested our algorithm at Wolpo beach. Bathymetry survey data which were obtained using a drone with HD camera and calibrated to eliminate errors due to seagrasses, were compared with depth survey data obtained using ship-board multi-beam acoustic sounder. The abnormal bathymetry data which are defined as the excess of 1.5 times of a standard deviation of random errors, are composed of 8.6% of the test site of area of 200 m by 300 m. By applying the developed algorithm, 92% of abnnormal bathymetry data were successfully eliminated and 33% of RMS errors were reduced.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.37 no.2
• /
• pp.169-176
• /
• 2013

To generate the walking path of a humanoid robot in an unknown environment, the shapes of obstacles around the robot should be detected accurately. However, doing so incurs a very large computational cost. Therefore this study proposes a method to classify the obstacle shape into three types: a shape small enough for the robot to go over, a shape planar enough for the robot foot to make contact with, and an uncertain shape that must be avoided by the robot. To classify the obstacle shape, first, the range and the number of the obstacles is detected. If an obstacle can make contact with the robot foot, the shape of an obstacle is accurately derived. If an obstacle has uncertain shape or small size, the shape of an obstacle is not detected to minimize the computational load. Experimental results show that the proposed algorithm efficiently classifies the shapes of obstacles around the robot in real time with low computational load.

• International Commerce and Information Review
• /
• v.19 no.1
• /
• pp.99-126
• /
• 2017

The Indonesian e-commerce market has grown significantly due to sustained economic growth, middle class growth, rapid increase in Internet and SNS users, and increase in accessibility of mobile broadband services. In particular, consumers' online shopping through mobile and SNS has been increasing rapidly based on the expansion of the popularity of smart phone devices. This research suggested the strategies for expanding exports of Indonesia through e-commerce platform to the Korean firms, with deep analysis of the current status and features, problems, cases, and implications etc. of Indonesia's e-commerce market. As an export expansion strategy utilizing Indonesia's e-commerce platform, this study showed the Korean firms have to build a local online distribution network, establish a logistics & delivery and payment system, acquire Halal certification for Muslim market, carry out the in-depth market research, actively implement Hanryu marketing strategy, develop a creative product, set up market segmentation strategies, and develop SNS mobile marketing.

• Journal of Korea Multimedia Society
• /
• v.17 no.2
• /
• pp.132-142
• /
• 2014

Stereo camera is drawing attention as an essential sensor for future intelligence robot system since it has the advantage of acquiring not only distance but also other additive information for an object. However, it cannot match correlated point on target image for low textured region or periodic patterned region such as wall of building or room. In this paper, we propose a stereo matching technique that increase the matching performance by fusing belief propagation stereo matching algorithm and local distance measurements of 2D-laser range finder in order to overcome this kind of limitation. The proposed technique adds laser measurements by referring quad-tree based segment information on to the local-evidence of belief propagation stereo matching algorithm, and calculates compatibility function by reflecting over-segmented information. Experimental results of the proposed method using simulation and real test images show that the distance information for some low textured region can be acquired and the discontinuity of depth information is preserved by using segmentation information.

• Fashion & Textile Research Journal
• /
• v.20 no.2
• /
• pp.128-142
• /
• 2018

This study explores newborn clothing with regard to clothing type, construction, textiles, design, size, and label placement. Related consumer complaints are also analyzed. Analysis of 50 newborn clothing items revealed six types of newborn clothing: baenaet jeogori, baenaet gown, bodysuit, one-piece, shirt and pants set, and pants. The baenaet jeogori was the most common type, and the most commonly used fasteners were ties and snaps. The following characteristics were commonly observed: front opening, long raglan sleeves, mitten cuffs, cotton fabric, white/ivory color, animal print, contrast hem, $appliqu{\acute{e}}$, and size 60. In-depth interviews of 12 mothers with children under 24 months revealed that the baenaet jeogori was the most unsatisfactory type; the shirt and pants set and bodysuit were preferred. Interviewees were dissatisfied with types of openings, expressing a preference for snaps and complaining about ties, too many snaps, metal snaps, and shoulder openings. Overly wide or narrow sleeves resulted in improper fit, and long sleeves made it difficult to dress the baby. Interviewees required diverse sleeve length options. They were dissatisfied with heavy fabric for hot and warm seasons, and with labels attached inside clothing or outside near the neckline. Mothers with particularly small or big babies complained about limited sizes. To improve current newborn clothing, additional items such as shirt and pants sets or individual pants, front opening clothing with few snaps, proper sleeve fit with diverse length options, lightweight fabric for hot and warm seasons, label placement that avoids skin irritation, and size segmentation are recommended.

• Journal of KIISE:Software and Applications
• /
• v.30 no.7_8
• /
• pp.610-617
• /
• 2003

Similarity matching in video database is of growing importance in many new applications such as video clustering and digital video libraries. In order to provide efficient access to relevant data in large databases, there have been many research efforts in video indexing with diverse spatial and temporal features. however, most of the previous works relied on sequential matching methods or memory-based inverted file techniques, thus making them unsuitable for a large volume of video databases. In order to resolve this problem, this paper proposes an effective and scalable indexing technique using a trie, originally proposed for string matching, as an index structure. For building an index, we convert each frame into a symbol sequence using a window order heuristic and build a disk-resident trie from a set of symbol sequences. For query processing, we perform a depth-first search on the trie and execute a temporal segmentation. To verify the superiority of our approach, we perform several experiments with real and synthetic data sets. The results reveal that our approach consistently outperforms the sequential scan method, and the performance gain is maintained even with a large volume of video databases.