• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.8 no.1
• /
• pp.50-59
• /
• 2007

In this paper, an anchor shot detection method, which is a basic technology for managing news videos for index and retrieval purposes is proposed. To do that, two most popular news program such as 'KBS 9 Hour News' and 'MBC 9 Hour News' are analyzed and 4-step rule based detection method is proposed First, in the preprocessing, video shot boundaries are detected and the 1st frame of each shot is extracted as a key frame. Then, the detected shot is declared as an anchor shot, if all the following 4 conditions are satisfied. 1) There is an anchor face in the key frame of a shot. 2) Spatial distribution of edges in the key frame is adequate. 3) Background color information of the key frame is similar to the color information of an anchor model. 4) Motion rate in the shot is low. In order to show the validity of the proposed method, three 'KBS 9 Hour News' and three 'MBC 9 Hour News', which have total running time of 108 in minute and are broadcasted at different days, are used for experiments. Average detection rates showed 0.97 in precision, 1.0 in recall, and 0.98 in F-measure.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.9
• /
• pp.889-897
• /
• 2010

Recently, a cutting-edge large-scale image database system has demanded these attributes: search with alarming speed, performs with high accuracy, archives efficiently and much more. An image identifier (descriptor) is for measuring the similarity of two images which plays an important role in this system. The extraction method of an image identifier can be roughly classified into two methods: a local and global method. In this paper, the proposed image identifier, LFH(Local Feature's Histogram), is obtained by a histogram of robust and distinctive local descriptors (features) constrained by a district sub-division of a local region. Furthermore, LFH has not only the properties of a local and global descriptor, but also can perform calculations at a magnificent clip to determine distance with pinpoint accuracy. Additionally, we suggested a way to extract LFH via GPU (OpenGL and GLSL). In this experiment, we have compared the LFH with SIFT (local method) and EHD (global method) via storage capacity, extraction and retrieval time along with accuracy.

• KIPS Transactions on Software and Data Engineering
• /
• v.1 no.2
• /
• pp.115-126
• /
• 2012

The artificial captions appearing in videos include information that relates to the videos. In order to obtain the information carried by captions, many methods for caption extraction from videos have been studied. Most traditional methods of detecting caption region have used one frame. However video include not only spatial information but also temporal information. So we propose a method of detection caption region using temporal and spatial information. First, we make improved Text-Appearance-Map and detect continuous candidate regions through matching between candidate-regions. Second, we detect disappearing captions using disappearance test in candidate regions. In case of captions disappear, the caption regions are decided by a merging process which use temporal and spatial information. Final, we decide final caption regions through ANNs using edge direction histograms for verification. Our proposed method was experienced on many kinds of captions with a variety of sizes, shapes, positions and the experiment result was evaluated through Recall and Precision.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.6
• /
• pp.1162-1169
• /
• 2007

In this paper, we proposed a container identifier recognition method for containers used in harbors. After converting a real container image to a gray image, edges are detected from the gray image applying Prewitt mask and candidate identifier area is extracted using morphological features of individual identifier for identifying containers. Because noises are included in the extracted candidate identifier area, noises are eliminated and each identifier is separated using 4-directional edge tracking algorithm and Grassfire algorithm. Each identifier in the noise-free candidate identifier area is recognized using FCM-based row RBF network for discriminating containers. We used 300 real container images for experiment to evaluate the performance of the proposed method, and we could verify the proposed method is better than a conventional method.

• Journal of IKEEE
• /
• v.25 no.3
• /
• pp.430-436
• /
• 2021

The non-contact body temperature measurement system is one of the key factors, which is manage febrile diseases in mass facilities using optical and thermal imaging cameras. Conventional systems can only be used for simple body temperature measurement in the face area, because it is used only a deep learning-based face detection algorithm. So, there is a limit to detecting abnormal symptoms of the infants and young children, who have difficulty expressing their opinions. This paper proposes an improved facial expression recognition algorithm for detecting abnormal symptoms in infants and young children. The proposed method uses an object detection model to detect infants and young children in an image, then It acquires the coordinates of the eyes, nose, and mouth, which are key elements of facial expression recognition. Finally, facial expression recognition is performed by applying a selective sharpening filter based on the obtained coordinates. According to the experimental results, the proposed algorithm improved by 2.52%, 1.12%, and 2.29%, respectively, for the three expressions of neutral, happy, and sad in the UTK dataset.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.36 no.6
• /
• pp.525-534
• /
• 2018

Camera calibration is the process of determining the parameters such as the focal length of a camera, the position of a principal point, and lens distortions. For this purpose, images of checkerboard have been mainly used. When targets were automatically recognized in checkerboard image, the existing studies had limitations in that the user should have a good understanding of the input parameters for recognizing the target or that all checkerboard should appear in the image. In this study, a methodology for automatic target recognition was proposed. In this method, even if only a part of the checkerboard image was captured using rectangles including eight blobs, four each at the central portion and the outer portion of the checkerboard, the index of the target can be automatically assigned. In addition, there is no need for input parameters. In this study, three conditions were used to automatically extract the center point of the checkerboard target: the distortion of black and white pattern, the frequency of edge change, and the ratio of black and white pixels. Also, the direction and numbering of the checkerboard targets were made with blobs. Through experiments on two types of checkerboards, it was possible to automatically recognize checkerboard targets within a minute for 36 images.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.49 no.9
• /
• pp.729-738
• /
• 2021

Feedback flow control using an artificial neural network was numerically investigated for NACA0015 Airfoil to suppress flow separation on an airfoil. In order to achieve goal of flow control which is aimed to reduce the size of separation on the airfoil, Blowing&Suction actuator was implemented near the separation point. In the system modeling step, the proper orthogonal decomposition was applied to the pressure field. Then, some POD modes that are necessary for flow control are extracted to analyze the unsteady characteristics. NARX neural network based on decomposed modes are trained to represent the flow dynamics and finally operated in the feedback control loop. Predicted control signal was numerically applied on CFD simulation so that control effect was analyzed through comparing the characteristic of aerodynamic force and spatial modes depending on the presence of the control. The feedback control showed effectiveness in pressure drag reduction up to 29%. Numerical results confirm that the effect is due to dramatic pressure recovery around the trailing edge of the airfoil.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.34 no.4
• /
• pp.183-189
• /
• 2021

In recent years, active research has been devoted toward developing a monitoring system using ambient vibration data in order to quantitatively determine the deterioration occurring in a structure over a long period of time. This study developed a low-cost edge computing system that detects the abnormalities in structures by utilizing the dynamic characteristics acquired from the structure over the long term for ensemble learning. The system hardware consists of the Raspberry Pi, an accelerometer, an inclinometer, a GPS RTK module, and a LoRa communication module. The structural abnormality detection afforded by the ensemble learning using dynamic characteristics is verified using a laboratory-scale structure model vibration experiment. A real-time distributed processing algorithm with dynamic feature extraction based on the experiment is installed on the Raspberry Pi. Based on the stable operation of installed systems at the Community Service Center, Pohang-si, Korea, the validity of the developed system was verified on-site.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.6
• /
• pp.313-330
• /
• 2021

In an autonomous driving system equipped with a camera and lidar, depth completion techniques enable dense depth estimation. In particular, using self-supervised learning it is possible to train the depth completion network even without ground truth. In actual autonomous driving, such depth completion should have very short latency as it is the input of other algorithms. So, rather than complicate the network structure to increase the accuracy like previous studies, this paper focuses on network latency. We design a U-Net type network with RegNet encoders optimized for GPU computation. Instead, this paper presents several techniques that can increase accuracy during the process of self-supervised learning. The proposed techniques increase the robustness to unreliable lidar inputs. Also, they improve the depth quality for edge and sky regions based on the semantic information extracted in advance. Our experiments confirm that our model is very lightweight (2.42 ms at 1280x480) but resistant to noise and has qualities close to the latest studies.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.4
• /
• pp.487-494
• /
• 2022

With the recent demand for analysis using data, the size of the knowledge graph, which is the data to be analyzed, gradually increased, reaching about 82 billion edges when extracted from the web as a knowledge graph. A lot of knowledge graphs are represented in the form of Resource Description Framework (RDF), which is a standard of W3C for representing metadata for web resources. Because of the characteristics of RDF, existing RDF storages have the limitations of processing time overhead when converting and storing large amounts of RDF data. To resolve these limitations, in this paper, we propose a method of compressing and converting large amounts of RDF data into integer IDs using MapReduce, and vertically partitioning and storing them. Our proposed method demonstrated a high performance improvement of up to 25.2 times compared to RDF-3X and up to 3.7 times compared to H2RDF+.