• Journal of the Korea Computer Graphics Society
• /
• v.20 no.2
• /
• pp.1-11
• /
• 2014

The quality of 2D-to-3D conversion depends on the accuracy of the assigned depth to scene objects. Manual depth painting for given objects is labor intensive as each frame is painted. Specifically, a human is one of the most challenging objects for a high-quality conversion, as a human body is an articulated figure and has many degrees of freedom (DOF). In addition, various styles of clothes, accessories, and hair create a very complex silhouette around the 2D human object. We propose an efficient method to estimate visually pleasing depths of a human at every frame in a monocular video. First, a 3D template model is matched to a person in a monocular video with a small number of specified user correspondences. Our pose estimation with sequential joint angular constraints reproduces a various range of human motions (i.e., spine bending) by allowing the utilization of a fully skinned 3D model with a large number of joints and DOFs. The initial depth of the 2D object in the video is assigned from the matched results, and then propagated toward areas where the depth is missing to produce a complete depth map. For the effective handling of the complex silhouettes and appearances, we introduce a partial depth propagation method based on color segmentation to ensure the detail of the results. We compared the result and depth maps painted by experienced artists. The comparison shows that our method produces viable depth maps of humans in monocular videos efficiently.

• Journal of Digital Contents Society
• /
• v.19 no.6
• /
• pp.1161-1167
• /
• 2018

The development of machine learning has enabled machines to perform delicate tasks that only humans could do, and thus many companies have introduced machine learning based translators. Existing translators have good performances but they have problems in number translation. The translators often mistranslate numbers when the input sentence includes a large number. Furthermore, the output sentence structure completely changes even if only one number in the input sentence changes. In this paper, first, we optimized a neural machine translation model architecture that uses bidirectional RNN, LSTM, and the attention mechanism through data cleansing and changing the dictionary size. Then, we implemented a number-processing algorithm specialized in number translation and applied it to the neural machine translation model to solve the problems above. The paper includes the data cleansing method, an optimal dictionary size and the number-processing algorithm, as well as experiment results for translation performance based on the BLEU score.

• The Journal of Korean society of community based occupational therapy
• /
• v.7 no.1
• /
• pp.9-16
• /
• 2017

Objective : The study was to find out the effect of sleep disorder bt melatonin when we applied the evironmental change to rats wirh sleep disorder. Methods : We performed the study in lab which is located in Gyungbuk. We divided 26 rats into two groups. The experimental group had the environmental change for 3 days. The control group didn't have the change. We checked the level of melatonin of each group. Results : There was a significant difference of the level of melatonin in experimental group after applying the environmental change for 3 days (p=.000). The level of melatonin was increased a little for 3 each day in control group, but there was no significance(p=.212). There was a significant difference of the level of melatonin in both groups before and after applying the environmental change. However, the level of melatonin was increased significantly in experimental group, and the level was decreased significantly in control group. Conclusion : The patients with sleep disorder are increasing in modern society. We made a animal model with sleep disorder to find out the effect of the environmental change. We applied the environment like human's and could know the improvement effect of sleep disorder.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.4
• /
• pp.1824-1832
• /
• 2011

In this paper, a smart home service robot McBot II is newly developed in much more practical and intelligent system than McBot I which we had developed a few years ago. Thus far, vacuum-cleaners have lightened the burden of household chores but the operational labor that vacuum-cleaners entail has been very severe. Recently, a cleaning robot was commercialized to solve but it also was not successful because it still had the problem of mess-cleanup, which pertained to the clean-up of large trash and the arrangement of newspapers, clothes, etc. Hence, we develop a new home mess-cleanup robot McBot II to completely overcome this problem on real environments. The mechanical design and the basic control of McBot II, which performs mess-cleanup function etc. in house, is actually focused in this paper. McBot II is mechanically modeled in the same method that the human works in door by using the waist and the hands. The big-ranged vertical lift and the shoulder joints to be able to forward move are mechanically designed for the operating function as the human's waist when the robot works. The mobility of McBot II is designed in the holonomic mobile robot for the collision avoidance of obstacle and the high speed navigation on the small area in door. Finally, good performance of McBot II, which has been optimally desinged, is confirmed through the experimental results for the control of the robotic body, mobility, arms and hands in this paper.

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.3
• /
• pp.51-56
• /
• 2000

Is this paper, we studied on the automatic speech control system in real-time windows environment using voice recognition. The applied reference pattern is the variable DMS model which is proposed to fasten execution speed and the one-stage DP algorithm using this model is used for recognition algorithm. The recognition vocabulary set is composed of control command words which are frequently used in windows environment. In this paper, an automatic speech period detection algorithm which is for on-line voice processing in windows environment is implemented. The variable DMS model which applies variable number of section in consideration of duration of the input signal is proposed. Sometimes, unnecessary recognition target word are generated. therefore model is reconstructed in on-line to handle this efficiently. The Perceptual Linear Predictive analysis method which generate feature vector from extracted feature of voice is applied. According to the experiment result, but recognition speech is fastened in the proposed model because of small loud of calculation. The multi-speaker-independent recognition rate and the multi-speaker-dependent recognition rate is 99.08% and 99.39% respectively. In the noisy environment the recognition rate is 96.25%.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.6
• /
• pp.850-858
• /
• 2022

To deploy Gate Recurrent Units (GRU) on resource-constrained embedded devices, this paper presents a reconfigurable FPGA-based GRU accelerator that enables structured compression. Firstly, a dense GRU model is significantly reduced in size by hybrid quantization and structured top-k pruning. Secondly, the energy consumption on external memory access is greatly reduced by the proposed reuse computing pattern. Finally, the accelerator can handle a structured sparse model that benefits from the algorithm-hardware co-design workflows. Moreover, inference tasks can be flexibly performed using all functional dimensions, sequence length, and number of layers. Implemented on the Intel DE1-SoC FPGA, the proposed accelerator achieves 45.01 GOPs in a structured sparse GRU network without batching. Compared to the implementation of CPU and GPU, low-cost FPGA accelerator achieves 57 and 30x improvements in latency, 300 and 23.44x improvements in energy efficiency, respectively. Thus, the proposed accelerator is utilized as an early study of real-time embedded applications, demonstrating the potential for further development in the future.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.4
• /
• pp.1-10
• /
• 2022

Attempts to interpret human perspectives using computer vision have been developed in various fields. In this paper, we propose a method for evaluating the walking environment through semantic segmentation results of images from road images. First, the Kakao Map API was used to collect road images, and four-way images were collected from about 50,000 points in JeonJu. 20% of the collected images build datasets through crowdsourcing-based paired comparisons, and train various regression models using paired comparison data. In order to derive the walkability score of the image data, the ranking score is calculated using the Trueskill algorithm, which is a ranking algorithm, and the walkability and analysis using various regression models are performed using the constructed data. Through this study, it is shown that the walkability of Jeonju can be evaluated and scores can be derived through the correlation between pixel distribution classification information rather than human vision.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.2
• /
• pp.427-436
• /
• 2021

The purpose of this study is to implement a machine learning language model that learns literary texts. Literary texts have an important characteristic that pairs of question-and-answer are not frequently clearly distinguished. Also, literary texts consist of pronouns, figurative expressions, soliloquies, etc. They hinder the necessity of machine learning using literary texts by making it difficult to learn algorithms. Algorithms that learn literary texts can show more human-friendly interactions than algorithms that learn general sentences. For this goal, this paper proposes three text correction tasks that must be preceded in researches using literary texts for machine learning language model: pronoun processing, dialogue pair expansion, and data amplification. Learning data for artificial intelligence should have clear meanings to facilitate machine learning and to ensure high effectiveness. The introduction of special genres of texts such as literature into natural language processing research is expected not only to expand the learning area of machine learning, but to show a new language learning method.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.9
• /
• pp.21-32
• /
• 2022

Image labeling must be preceded in order to perform object detection, and this task is considered a significant burden in building a deep learning model. Tens of thousands of images need to be trained for building a deep learning model, and human labelers have many limitations in labeling these images manually. In order to overcome these difficulties, this study proposes a method to perform object detection without significant performance degradation, even though labeling some images rather than the entire image. Specifically, in this study, low-resolution oriental painting images are converted into high-quality images using a super-resolution algorithm, and the effect of SSIM and PSNR derived in this process on the mAP of object detection is analyzed. We expect that the results of this study can contribute significantly to constructing deep learning models such as image classification, object detection, and image segmentation that require efficient image labeling.

• Journal of the Ergonomics Society of Korea
• /
• v.26 no.2
• /
• pp.45-59
• /
• 2007

The operating tasks of overhead crane have caused undue stress to the operators from physical, mental, and environmental workload. Existing workload assessment models for musculoskeletal disorders such as OWAS, RULA, and QEC have limited applicability to the crane operating tasks because they focus mainly on physical factors and do not consider the relative importance of each factor. The present study was to develop a workload assessment model customized to overhead crane operation, following a systematic process: (1) analyzing task characteristics, (2) selecting workload factors, (3) developing assessment methods, (4) establishing action levels, and (5) computerizing the assessment model. Based on literature review, worksite survey, and focus group interview, 4 physical factors (awkward posture, static posture, repetitive motion, and excessive force), 6 mental factors (visual demand, auditory demand, task complexity and difficulty, time urgency, work schedule related stress, and safety related stress), and 4 environmental factors (noise, vibration, dust, and temperature) were selected and their rating scales and relative weights were determined. Then, based on the workload assessment results of 8 overhead cranes operated at different workplaces, the action levels of each factor category were established. Finally, the crane operation assessment model was computerized for effective analysis and report preparation. The present approach is applicable to develop a customized workload assessment model for an operating task under consideration.