• Journal of Korea Multimedia Society
• /
• v.20 no.2
• /
• pp.196-204
• /
• 2017

Behavior of intelligent video surveillance system is recognized by analyzing the pattern of the object of interest by using the frame information of video inputted from the camera and analyzes the behavior. Detection of object's certain behaviors in the crowd has become a critical problem because in the event of terror strikes. Recognition of object's certain behaviors is an important but difficult problem in the area of computer vision. As the realization of big data utilizing machine learning, data mining techniques, the amount of video through the CCTV, Smart-phone and Drone's video has increased dramatically. In this paper, we propose a multiple-sliding window method to recognize the cumulative change as one piece in order to improve the accuracy of the recognition. The experimental results demonstrated the method was robust and efficient learning units in the classification of certain behaviors.

• Journal of Korea Multimedia Society
• /
• v.15 no.8
• /
• pp.986-995
• /
• 2012

In this paper we propose a real-time moving object tracking method on a smart phone camera. By considering the limit of non-learning approach on low-performance platforms, we use the sliding-window detection technique based on histogram features. We solve the problem of the time-consuming histogram computation on each sub-window by adapting the integral histogram. For additional speed and tracking performance, we propose a new adaptive bin method. From the experiments on our dataset, we achieved high speed performance demonstrating 34~63 frames per second.

• Smart Structures and Systems
• /
• v.14 no.4
• /
• pp.719-741
• /
• 2014

Monitoring surface cracks is important to ensure the health of concrete structures. However, traditional visual inspection to monitor the concrete cracks has disadvantages such as subjective inspection nature, associated time and cost, and possible danger to inspectors. To alter the visual inspection, a complete procedure for automated crack assessment based on adaptive digital image processing has been proposed in this study. Crack objects are extracted from the images using the subtraction with median filter and the local binarization using the Niblack's method. To adaptively. determine the optimal window sizes for the median filter and the Niblack's method without distortion of crack object an optimal filter size index (OFSI) is proposed. From the extracted crack objects using the optimal size of window, the crack objects are decomposed to the crack skeletons and edges, and the crack width is calculated using 4-connected normal line according to the orientation of the local skeleton line. For an image, a crack width nephogram is obtained to have an intuitive view of the crack distribution. The proposed procedure is verified from a test on a concrete reaction wall with various types of cracks. From the crack images with different crack widths and patterns, the widths of cracks in the order of submillimeters are calculated with high accuracy.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.1-16
• /
• 2022

Despite recent breakthroughs in deep learning and computer vision fields, the pixel-wise identification of tiny objects in high-resolution images with complex disturbances remains challenging. This study proposes a modified U-net for tiny crack segmentation in real-world steel-box-girder bridges. The modified U-net adopts the common U-net framework and a novel Self-Attention-Self-Adaption (SASA) neuron as the fundamental computing element. The Self-Attention module applies softmax and gate operations to obtain the attention vector. It enables the neuron to focus on the most significant receptive fields when processing large-scale feature maps. The Self-Adaption module consists of a multiplayer perceptron subnet and achieves deeper feature extraction inside a single neuron. For data augmentation, a grid-based crack random elastic deformation (CRED) algorithm is designed to enrich the diversities and irregular shapes of distributed cracks. Grid-based uniform control nodes are first set on both input images and binary labels, random offsets are then employed on these control nodes, and bilinear interpolation is performed for the rest pixels. The proposed SASA neuron and CRED algorithm are simultaneously deployed to train the modified U-net. 200 raw images with a high resolution of 4928 × 3264 are collected, 160 for training and the rest 40 for the test. 512 × 512 patches are generated from the original images by a sliding window with an overlap of 256 as inputs. Results show that the average IoU between the recognized and ground-truth cracks reaches 0.409, which is 29.8% higher than the regular U-net. A five-fold cross-validation study is performed to verify that the proposed method is robust to different training and test images. Ablation experiments further demonstrate the effectiveness of the proposed SASA neuron and CRED algorithm. Promotions of the average IoU individually utilizing the SASA and CRED module add up to the final promotion of the full model, indicating that the SASA and CRED modules contribute to the different stages of model and data in the training process.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.13 no.4
• /
• pp.163-170
• /
• 2017

As the usage of smart phones continues to increase, the control UI, which users have to continue to use, sometimes finds a heavy burden on users. Therefore, in this study, we have studied the control user interface structure along with the theoretical background of the control user interface, and we have studied the role and usage of the control component based on it. Typical commonly used controls are button controls for transmission, selection controls for various selections, link controls for navigation, text controls for inputting characters, indicator controls for feedback on progress, A message control that displays information about warnings and errors, and a window control such as a dialog box. The structure of the control should be designed according to the use of the separated control to help the user efficiently use the control user interface. Based on the analysis of the theoretical usage of representative components belonging to the separated controls, we presented a new and correct way to use the control to improve the user experience. The use of improved control components will help to design the control structure efficiently and to improve the user experience.

• Journal of Korean Society for Quality Management
• /
• v.49 no.4
• /
• pp.569-579
• /
• 2021

Purpose: The purpose of this study is the time series analysis for predicting the yield of crops applicable to each farm using environmental variables measured by smart farms cultivating tomato. In addition, it is intended to confirm the influence of environmental variables using a deep learning model that can be explained to some extent. Methods: A time series analysis was performed to predict production using environmental variables measured at 75 smart farms cultivating tomato in two periods. An LSTM-based encoder-decoder model was used for cases of several farms with similar length. In particular, Dual Attention Mechanism was applied to use environmental variables as exogenous variables and to confirm their influence. Results: As a result of the analysis, Dual Attention LSTM with a window size of 12 weeks showed the best predictive power. It was verified that the environmental variables has a similar effect on prediction through wieghtss extracted from the prediction model, and it was also verified that the previous time point has a greater effect than the time point close to the prediction point. Conclusion: It is expected that it will be possible to attempt various crops as a model that can be explained by supplementing the shortcomings of general deep learning model.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.435-436
• /
• 2022

창문은 건물의 필수 구조물이지만 창문을 통해서 미세먼지, 빗물 등이 들어올 수 있어 창문을 열고 나가지 못하고 불안해하는 경우가 많다. 최근 들어 미세먼지가 급증하면서 사람들의 불안감이 더욱 증가하고 있으며, 보안에 취약한 창문들이 범죄에 취약하기 때문에 불안해 할 수 있다. 또한, 실내에서도 가스누출 등으로 인해 인명피해까지 이어지는 심각한 상황을 초래할 수 있기 때문이다. 이러한 사람들의 불안감을 없애기 위하여 아두이노를 이용하여 실외의 미세먼지와 빗물, 인체감지등을 통해 원격으로 창문을 제어하고 실내의 온도와 습도량, 가스량의 표시를 어플리케이션을 통해 확인할 수 있으며 원격으로 제어 또한 가능하도록 '실내외 환경맞춤 스마트 윈도우'를 개발하게 되었다.

• Journal of Practical Engineering Education
• /
• v.12 no.1
• /
• pp.117-125
• /
• 2020

According to the government's smart factory promotion project for small and medium-sized enterprises, more than 10,000 intelligent factories are scheduled or already built in the country and the government-led goal is to nurture 100,000 skilled workers by 2022. Smart Factory introduces numerous types of education and training courses from the supplier's point of view, such as training institutions belonging to local governments, some universities, and public organizations, in the form of an efficient resource management system and ICT technology convergence in the automated manufacturing equipment. The lack of linkage with the NCS, the standard for training, seems to have room for rethinking and direction. Results of survey is provided for the family companies of K-University in the metropolitan area and Chungnam area, and analyzes job demands by identifying whether or not they want to introduce smart factories. Defining the practitioners who will serve as a window for the introduction of smart factory technology within the company, setting up a training goal in consideration of the career path, and including the level of training required competency units, optional competency units, and training time suitable for introducing and operating smart factories. Author would like to present an NCS-based qualification design plan.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.25 no.2
• /
• pp.261-270
• /
• 2015

In information security devices, such as Smart Cards, vulnerabilities of the RSA algorithm which is used to protect the data were found in the Side Channel Analysis. The RSA is especially vulnerable to Power Analysis which uses power consumption when the algorithm is working. Typically Power Analysis is divided into SPA(Simple Power Analysis) and DPA(Differential Power Analysis). On top of this, there is a CA(Collision Analysis) which is a very powerful attack. CA makes it possible to attack using a single waveform, even if the algorithm is designed to secure against SPA and DPA. So Message blinding, which applies the window method, was considered as a countermeasure. But, this method does not provide sufficient safety when the window size is small. Therefore, in this paper, we propose a new countermeasure that provides higher safety against CA. Our countermeasure is a combination of message and exponent blinding which is applied to the window method. In addition, through experiments, we have shown that our countermeasure provides approximately 124% higher attack complexity when the window size is small. Thus it can provide higher safety against CA.

• The Journal of Society for e-Business Studies
• /
• v.17 no.3
• /
• pp.129-147
• /
• 2012

In this paper, we research on the personal information protection system in smart-phone based on mobile environment. This paper proposes the enhanced personal location privacy mechanism in location-based service environment of a smart phone operating system(iOS, Android) for the relevant regulations on location-based protection and utilization. Also, the result verified that possibility on a self-control mechanism of the personal information protection system's subject in the window platform throughout the experiment. Therefore, this study have drew a method that user positively can cope with a protection of personal location information by having a user's self-control method in the system under development or done by illegal location-based service providers and illegal application developer.