• Journal of Intelligence and Information Systems
• /
• v.18 no.2
• /
• pp.47-60
• /
• 2012

Video data comes in the form of the unstructured and the complex structure. As the importance of efficient management and retrieval for video data increases, studies on the video parsing based on the visual features contained in the video contents are researched to reconstruct video data as the meaningful structure. The early studies on video parsing are focused on splitting video data into shots, but detecting the shot boundary defined with the physical boundary does not cosider the semantic association of video data. Recently, studies on structuralizing video shots having the semantic association to the video scene defined with the semantic boundary by utilizing clustering methods are actively progressed. Previous studies on detecting the video scene try to detect video scenes by utilizing clustering algorithms based on the similarity measure between video shots mainly depended on color features. However, the correct identification of a video shot or scene and the detection of the gradual transitions such as dissolve, fade and wipe are difficult because color features of video data contain a noise and are abruptly changed due to the intervention of an unexpected object. In this paper, to solve these problems, we propose the Scene Detector by using Color histogram, corner Edge and Object color histogram (SDCEO) that clusters similar shots organizing same event based on visual features including the color histogram, the corner edge and the object color histogram to detect video scenes. The SDCEO is worthy of notice in a sense that it uses the edge feature with the color feature, and as a result, it effectively detects the gradual transitions as well as the abrupt transitions. The SDCEO consists of the Shot Bound Identifier and the Video Scene Detector. The Shot Bound Identifier is comprised of the Color Histogram Analysis step and the Corner Edge Analysis step. In the Color Histogram Analysis step, SDCEO uses the color histogram feature to organizing shot boundaries. The color histogram, recording the percentage of each quantized color among all pixels in a frame, are chosen for their good performance, as also reported in other work of content-based image and video analysis. To organize shot boundaries, SDCEO joins associated sequential frames into shot boundaries by measuring the similarity of the color histogram between frames. In the Corner Edge Analysis step, SDCEO identifies the final shot boundaries by using the corner edge feature. SDCEO detect associated shot boundaries comparing the corner edge feature between the last frame of previous shot boundary and the first frame of next shot boundary. In the Key-frame Extraction step, SDCEO compares each frame with all frames and measures the similarity by using histogram euclidean distance, and then select the frame the most similar with all frames contained in same shot boundary as the key-frame. Video Scene Detector clusters associated shots organizing same event by utilizing the hierarchical agglomerative clustering method based on the visual features including the color histogram and the object color histogram. After detecting video scenes, SDCEO organizes final video scene by repetitive clustering until the simiarity distance between shot boundaries less than the threshold h. In this paper, we construct the prototype of SDCEO and experiments are carried out with the baseline data that are manually constructed, and the experimental results that the precision of shot boundary detection is 93.3% and the precision of video scene detection is 83.3% are satisfactory.

• Journal of Intelligence and Information Systems
• /
• v.24 no.3
• /
• pp.1-19
• /
• 2018

Large amount of data is now available for research and business sectors to extract knowledge from it. This data can be in the form of unstructured data such as audio, text, and image data and can be analyzed by deep learning methodology. Deep learning is now widely used for various estimation, classification, and prediction problems. Especially, fashion business adopts deep learning techniques for apparel recognition, apparel search and retrieval engine, and automatic product recommendation. The core model of these applications is the image classification using Convolutional Neural Networks (CNN). CNN is made up of neurons which learn parameters such as weights while inputs come through and reach outputs. CNN has layer structure which is best suited for image classification as it is comprised of convolutional layer for generating feature maps, pooling layer for reducing the dimensionality of feature maps, and fully-connected layer for classifying the extracted features. However, most of the classification models have been trained using online product image, which is taken under controlled situation such as apparel image itself or professional model wearing apparel. This image may not be an effective way to train the classification model considering the situation when one might want to classify street fashion image or walking image, which is taken in uncontrolled situation and involves people's movement and unexpected pose. Therefore, we propose to train the model with runway apparel image dataset which captures mobility. This will allow the classification model to be trained with far more variable data and enhance the adaptation with diverse query image. To achieve both convergence and generalization of the model, we apply Transfer Learning on our training network. As Transfer Learning in CNN is composed of pre-training and fine-tuning stages, we divide the training step into two. First, we pre-train our architecture with large-scale dataset, ImageNet dataset, which consists of 1.2 million images with 1000 categories including animals, plants, activities, materials, instrumentations, scenes, and foods. We use GoogLeNet for our main architecture as it has achieved great accuracy with efficiency in ImageNet Large Scale Visual Recognition Challenge (ILSVRC). Second, we fine-tune the network with our own runway image dataset. For the runway image dataset, we could not find any previously and publicly made dataset, so we collect the dataset from Google Image Search attaining 2426 images of 32 major fashion brands including Anna Molinari, Balenciaga, Balmain, Brioni, Burberry, Celine, Chanel, Chloe, Christian Dior, Cividini, Dolce and Gabbana, Emilio Pucci, Ermenegildo, Fendi, Giuliana Teso, Gucci, Issey Miyake, Kenzo, Leonard, Louis Vuitton, Marc Jacobs, Marni, Max Mara, Missoni, Moschino, Ralph Lauren, Roberto Cavalli, Sonia Rykiel, Stella McCartney, Valentino, Versace, and Yve Saint Laurent. We perform 10-folded experiments to consider the random generation of training data, and our proposed model has achieved accuracy of 67.2% on final test. Our research suggests several advantages over previous related studies as to our best knowledge, there haven't been any previous studies which trained the network for apparel image classification based on runway image dataset. We suggest the idea of training model with image capturing all the possible postures, which is denoted as mobility, by using our own runway apparel image dataset. Moreover, by applying Transfer Learning and using checkpoint and parameters provided by Tensorflow Slim, we could save time spent on training the classification model as taking 6 minutes per experiment to train the classifier. This model can be used in many business applications where the query image can be runway image, product image, or street fashion image. To be specific, runway query image can be used for mobile application service during fashion week to facilitate brand search, street style query image can be classified during fashion editorial task to classify and label the brand or style, and website query image can be processed by e-commerce multi-complex service providing item information or recommending similar item.

• Korean Journal of Remote Sensing
• /
• v.28 no.1
• /
• pp.11-19
• /
• 2012

Air-borne pollen, biogenically created aerosol particle, influences Earth's radiative balance, visibility impairment, and human health. The importance of pollens has resulted in numerous experimental studies aimed at characterizing their dispersion and transport, as well as health effects. There is, however, limited scientific information concerning the optical properties of airborne pollen particles contributing to total ambient aerosols. In this study, for the first time, optical characteristics of pollen such as aerosol backscattering coefficient, aerosol extinction coefficient, and depolarization ratio at 532 nm and their effect to the atmospheric aerosol were studied by lidar remotes sensing technique. Dual-Lidar observations were carried out at the Gwangju Institute of Science & Technology (GIST) located in Gwagnju, Korea ($35.15^{\circ}E$, $126.53^{\circ}N$) for a spring pollen event from 5 to 7 May 2009. The pollen concentration was measured at the rooftop of Gwangju Bohoon hospital where the building is located 1.0 km apart from lidar site by using Burkard trap sampler. During intensive observation period, high pollen concentration was detected as 1360, 2696, and $1952m^{-3}$ in 5, 6, and 7 May, and increased lidar return signal below 1.5km altitude. Pollen optical depth retrieved from depolarization ratio was 0.036, 0.021, and 0.019 in 5, 6, and 7 May, respectively. Pollen particles mainly detected in daytime resulting increased aerosol optical depth and decrease of Angstrom exponent.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.4
• /
• pp.242-255
• /
• 2006

In the recent years, Popularization of mobile devices such as Smart Phones, PDAs and MP3 Players causes rapid increasing necessity of Power management technology because it is most essential factor of mobile devices. On the other hand, despite low price, hard disk has large capacity and high speed. Even it can be made small enough today, too. So it appropriates mobile devices. but it consumes too much power to embed In mobile devices. Due to these motivations, in this paper we had suggested methods of minimizing Power consumption while playing multimedia data in the disk media for real-time and we evaluated what we had suggested. Strict limitation of power consumption of mobile devices has a big impact on designing both hardware and software. One difference between real-time multimedia streaming data and legacy text based data is requirement about continuity of data supply. This fact is why disk drive must persist in active state for the entire playback duration, from power management point of view; it nay be a great burden. A legacy power management function of mobile disk drive affects quality of multimedia playback negatively because of excessive I/O requests when the disk is in standby state. Therefore, in this paper, we analyze power consumption profile of disk drive in detail, and we develop the algorithm which can play multimedia data effectively using less power. This algorithm calculates number of data block to be read and time duration of active/standby state. From this, the algorithm suggested in this paper does optimal scheduling that is ensuring continual playback of data blocks stored in mobile disk drive. And we implement our algorithms in publicly available MPEG player software. This MPEG player software saves up to 60% of power consumption as compared with full-time active stated disk drive, and 38% of power consumption by comparison with disk drive controlled by native power management method.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.46 no.6
• /
• pp.6-15
• /
• 2009

In this paper, a new 4-way search window is designed for the high-performance 2D PE architecture in H.264 Motion Estimation(ME) to improve the memory bandwidth. While existing 2D PE architectures reuse the overlapped data of adjacent search windows scanned in 1 or 3-way, the new window utilizes the overlapped data of adjacent search windows as well as adjacent multiple scanning (window) paths to enhance the reusage of retrieved search window data. In order to scan adjacent windows and multiple paths instead of single raster and zigzag scanning of adjacent windows, bidirectional row and column window scanning results in the 4-way(up. down, left, right) search window. The proposed 4-way search window could improve the reuse of overlapped window data to reduce the redundancy access factor by 3.1, though the 1/3-way search window redundantly requires $7.7{\sim}11$ times of data retrieval. Thus, the new 4-way search window scheme enhances the memory bandwidth by $70{\sim}58%$ compared with 1/3-way search window. The 2D PE architecture in H.264 ME for 4-way search window consists of $16{\times}16$ pe array. computing the absolute difference between current and reference frames, and $5{\times}16$ reusage array, storing the overlapped data of adjacent search windows and multiple scanning paths. The reference data could be loaded upward and downward into the new 2D PE depending on scanning direction, and the reusage array is combined with the pe array rotating left as well as right to utilize the overlapped data of adjacent multiple scan paths. In experiments, the new implementation of 4-way search window on Magnachip 0.18um could deal with the HD($1280{\times}720$) video of 1 reference frame, $48{\times}48$ search area and $16{\times}16$ macroblock by 30fps at 149.25MHz.

• Korean Journal of Remote Sensing
• /
• v.35 no.3
• /
• pp.415-431
• /
• 2019

The satellite-viewed cloudiness, a ratio of cloudy pixels to total pixels ($C_{sat,\;prev}$), inevitably differs from the "ground-viewed" cloudiness ($C_{grd}$) due to different viewpoints. Here we develop an algorithm to retrieve the satellite-viewed, but adjusted cloudiness to $C_{grd} (C_{sat,\;adj})$. The key process of the algorithm is to convert the cloudiness projected on the plane surface into the cloudiness on the celestial hemisphere from the observer. For this conversion, the supplementary satellite retrievals such as cloud detection and cloud top pressure are used as they provide locations of cloudy pixels and cloud base height information, respectively. The algorithm is tested for Himawari-8 level 1B data. The $C_{sat,\;adj}$ and $C_{sat,\;prev}$ are retrieved and validated with $C_{grd}$ of SYNOP station over Korea (22 stations) and China (724 stations) during only daytime for the first seven days of every month from July 2016 to June 2017. As results, the mean error of $C_{sat,\;adj}$ (0.61) is less that than that of $C_{sat,\;prev}$ (1.01). The percent of detection for 'Cloudy' scenario of $C_{sat,\;adj}$ (73%) is higher than that of $C_{sat,\;prev}$ (60%) The percent of correction, the accuracy, of $C_{sat,\;adj}$ is 61%, while that of $C_{sat,\;prev}$ is 55% for all seasons. For the December-January-February period when cloudy pixels are readily overestimated, the proportion of correction of $C_{sat,\;adj$ is 60%, while that of $C_{sat,\;prev}$ is 56%. Therefore, we conclude that the present algorithm can effectively get the satellite cloudiness near to the ground-viewed cloudiness.

• Korean Journal of Occupational Health Nursing
• /
• v.3
• /
• pp.54-70
• /
• 1993

According as the automation of clerical work(OA ; Office Automation) develops, the use of VDT(Visual or Video Display Terminal) is increasing suddenly. But, in proportion to the spread of office automation(OA tendency), the self-conciousness syptom attendant upon the work is appearing also (Kim, Jung Tae, Lee, Young Ook, 1990). The apparatuses of office enable the clerical workers to be convenient and perform mass businesses. But, they are increasing the opportunity to be exposed to VDT syndrom, techno stress, computer terminal disease, pain by muscle strain(RSI), bradycausia of noise nature, and electromagnetic waves, etc. which are referred to as the new type of occupational diseases to the workers. It is the real situation that the workers to use VDT is complaining of the physical inconvenience sense in the recent newspaper and literature, it is the point of time that the sydrome to come from VDT use and computer terminal disease, etc. must be classified into the occupational disease(Lee, Kwang Young 1990, Lee, Kyoo Hak 1990, Lee, Won Ho 1991, Lee, Si Young 1991, Lee, Joon 1991, Choi, Young Tae 1991, Heo, Seung Ho 1989). In addition, it is the real situation that the scientifitic study result about the scope that electromagnetic waves has influence on the human body has not been suggested yet, and criticism on the stable exposure permission standard about electromagnetic waves to be emitted from VDT and on the problem in the health about electromagnetic waves is continuing. (IEEE Spectrum, 1990). In addition according to the experience of nursery business of industry field, it is the real situation that the patients who consult complaining of physical and mental inconvenience sence, among the users of apparatus of office automation, are reaching 10% of the patients coming to doctor's room. Therefore, it is necessary to confirm the self-consciousness symptom that the clerical workers complain of multilaterally with the actual state examination about the use of the apparatuses of offices automaton. Thus, this study was tried as th basic data for the cosultation and education for the maintenance and furtherance of the health of workers as the nurse of industry field, by confirming the contents of self-consciousness symptom attendant upon the use of the apparatus for office outomation making the financial institution in which the spparatus for office automation in most frequently used as the subject, and by examining whether there is the difference according to the subject of study, the data were collected, by using the questionnaire method, making 200 workers who consented to the study participation as the subject, among the persons who have spent over 3 months since they used the apparatuses for office automation and didn't receive the treatment in hospital due to the clerical disease for recent 3 years. The period of data collection was from Oct. 9, 1991 to Oct. 12. As for the measurement instrument about the complaint if self-consciousness symptom attendant upon the use of apparatuses fo office automation, the question item on the complaint symptom of health problem attendant upon the treatment of VDT that Kim(1991) developed and on CMI health problem and the question items on the fatigue degree due to industry were used by previous examination to 25 persons. Collected data were analyzed with the statistical method such as percentage, arithmetic mean, Person correlation coeffient, Kai square verfication, t-test, ANOVA, etc. by using SPSS/PC+ program, and the result is as follows : 1. The self-consciousness symptom that the clerical workers complained of most frequetly appeared high in 'My eyes are tired'(99.4%), 'I feel fatigue and weariness'(99.4%), 'I feel that my head is heavy5(90.0%), 'eyesight fell'(88.8%), 'I have a stiff neck'(88.8%), 'I fell pain in the shoulder'(85.0%), 'I feel cold and painful in the eyes'(76.9%), 'I feel the dry sense of eyeball'(76.2%), 'My nerves are edgy, and I an fretful, (75.6%), 'I feel pain in the waist'(73.2%) and 'I fell pain in the back'(72.8%). It emerged that the subject use the apparatuses for office automation complained of self-consciousness symptoms related to visual symptoms and musculoskeletal symptoms. 2. As for the general feature of examination subjects, the result to see the distribution by classifying into sex, age, school career, use career of apparatuses for office automation, skillfulness degree of the use of apparatus for office automation, use hours of the apparatuses for office automation per 1 day, type of business of the apparatus for office automation, rest hours during the use of apparatus for office automation, satifaction degree of business of office automation, and work circumstance, etc. emerged as follows : As for the sex of subjects, the distribution showed that men were 58.8% and women were 41.3%, Age was average 26.9. As the distribution of school career, the distribution showed that4below the graduation of high school' was 58.8%, 'graduation from junior college-university' was 35.0%, and 'over graduate school' was 6.3%. In the question to ask the existence or non-existence of experience of health consultation in connection with the work of office automation, the response that I had the consultation exprience and I feel the necessity emergerd as 90.1% And, the case that the subject who didn't wear the glasses or lens before using the OA apparatus wear glasses or lens after using OA apparatus emerged as 28.3% of whole. As for the existence or non-existence of use career of OA apparatus, the case under 3 years was highest as 52. 7%. As for the skillfulnness degree about the use of apparatus for office automation, most of them are skillful with the fact that 'common' was 44.4%, 'skill' was 42.5%, and 'unskillful' was 13.1% As for the use average hours of the apparatus for office automation per 1 day, the distribution showed that the case under 3-6 hours was 33.1%, the case under 6-9 hours was 28.1%, the case under 3 hours was 30.6%, and the case over 9 hours was 8.1% Main OA business and the use hours for 1 day showed in the order of keeping and retrieval, business of information transmission(162min), business of information transmission(79.3 min), business of document framing(55.5 min), and business of duplication and printing(25.4min). as for the rest during the use of apparatus for affice automation, that I take rest occasion demands the major portion, but that I take after completing the work emerged as 33.8%. Though the subiness gets to be convenient by the use of the apparatus for of office automation, respondents who showed the dissatisfaction about the present OA business emergd high as 78.1%. The work circumstances of each office was good with the fact that the temperature of office was 21.8, noise was average 42.7db, and the illumination was average 364.4 lx, in the light of ANSi/HFS 100 Standard. 3. Sight syptom, musculoskeletal symptom, skin and other symptoms showed the significant difference according to the extent of skillfulness of the apparatus for office automation. All the symptoms exept skin symptom showed the difference according to the use hours of the apparatus for office automation. All the question items exept the sytoms of digestive organs and the rest hours during the apparatus for office automation showed the signicant difference. The question item which showed the signicant difference from the satisfaction degree of present OA business showed the significant difference from all the question item classified into 6 groups. But, age and school career didn't significant difference from the complaint of any self-consciousness symptoms.