• Korean Journal of Remote Sensing
• /
• v.35 no.4
• /
• pp.573-587
• /
• 2019

A multi-temporal approach using remotely sensed time series data obtained over multiple years is a very useful method for monitoring land covers and land-cover changes. While spectral-based methods at any particular time limits the application utility due to instability of the quality of data obtained at that time, the approach based on the temporal profile can produce more accurate results since data is analyzed from a long-term perspective rather than on one point in time. In this study, a multi-temporal approach applying a multi-periodic harmonic model is proposed for classification of remotely sensed data. A harmonic model characterizes the seasonal variation of a time series by four parameters: average level, frequency, phase, and amplitude. The availability of high-quality data is very important for multi-temporal analysis.An satellite image usually have many unobserved data and bad-quality data due to the influence of observation environment and sensing system, which impede the analysis and might possibly produce inaccurate results. Harmonic analysis is also very useful for real-time data reconstruction. Multi-periodic harmonic model is applied to the reconstructed data to classify land covers and monitor land-cover change by tracking the temporal profiles. The proposed method is tested with the MODIS and GOCI NDVI time series over the Korean Peninsula for 5 years from 2012 to 2016. The results show that the multi-periodic harmonic model has a great potential for classification of land-cover types and monitoring of land-cover changes through characterizing annual temporal dynamics.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.725-728
• /
• 2014

Continue to have an increasingly violent crimes against children every year, and as you know all seriousness is classified as a felony. However, efforts to reduce the underlying crime is low. Therefore, it is necessary to solve this problem, the security system. Is to protect the children and adults that exist that can pose a threat to children to identify and monitor tracking method in this paper. Was based on a Korean standard body size of a person, such as keys, arm length, leg length, head vertical length, head width proposed method. Also, separate the adults and children through the comparison of the reference value, the ratio and the ratio of the number of pixels of the detected object, the proposed method. Processing speed is fast because it detects only a specific object region in the entire image in the handling method in the proposed method the five nine minutes. The advantage is to enable comparison of the specific object, through which there is.

• Korean Journal of Acupuncture
• /
• v.38 no.4
• /
• pp.267-274
• /
• 2021

Objectives : Acupoints education is important in that it can determine the clinical competency of Korean Medicine Doctors (KMDs). Accordingly, we aimed to develop a practical simulator for acupoints education, acupoints training, acupoints practice, and acupoints evaluation. Methods : Korean Medicine (KM) SMART Table can be divided into hardware, server and components, and is organically linked. We develop KM SMART Table that combines the hardware of a human-sized table with a UHD display capable of multi-touch in two cases and software that can teach acupoints. We make Augmented Reality (AR) contents linked with KM SMART Table contents and develop applications that can use contents using mobile devices. By developing an AR image tracking module to react with KM SMART Table, it enables acupoint learning according to the mobile device platform and human anatomy. Results : The current system is a prototype where some 3D technology has been implemented, but the AR function will be produced later. New learning using 3D and AR will be required during acupoints education and acupoints practice. It will be used a lot in OSCE (Objective Structured Clinical Examination) practices for strengthening the competency of KMDs, and it will be of great help not only in KM education as a unique simulator of KM, but also in the practice of acupuncture and chuna for musculoskeletal diseases. Conclusions : The KM SMART Table is a technology that combines 3D and AR to learn acupoints, and to conduct acupoints OSCE practice, and we suggest that it can be usefully used for educational evaluation.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.34 no.12
• /
• pp.1087-1092
• /
• 2010

A micro 3D-PTV system has been constructed using a single camera system. Two viewing holes were created behind the object lens of the microscopic system to construct a stereoscopic viewing image. A hybrid recursive PTV algorithm was used. A concept of epipolar line was adopted to eliminate many spurious candidates. Three-dimensional velocity vector fields were obtained by calculating the three-dimensional displacements of particles that were identified as being identical. The system consists of a laser light source (Ar-ion, 500 mW), one high-definition camera ($1028{\times}1024$ pixels, 500 fps), a circular plate with two viewing holes, and a host computer. The performance of the developed algorithm was tested using artificial images. The characteristic of the vector recovery ratio was investigated for the particle numbers. A micro backward-facing step channel ($H{\times}h{\times}W:\;36{\mu}m{\times}70{\mu}m{\times}3000{\mu}m$) was measured using the developed measurement system. The results were in good qualitative agreement with other results.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2013.02a
• /
• pp.73-75
• /
• 2013

Atomic force microscopy (AFM) [1] can now not only image individual atoms but also construct atom letters using atom manipulation method [2]. Therefore, the AFM is the second generation atomic tool following the well-known scanning tunneling microscopy (STM). The AFM, however, has the advantages that it can image even insulating surfaces with atomic resolution and also measure the atomic force itself between the tip-apex outermost atom and the sample surface atom. Noting these advantages, we have been developing a novel bottom-up nanostructuring system, as shown in Fig. 1, based on the AFM. It can identify chemical species of individual atoms [3] and then manipulate selected atom species to the designed site one-by-one [2] to assemble complex nanostructures consisted of many atom species at room temperature (RT). In this invited talk, we will introduce our results toward atom-by-atom assembly of composite nanomaterials based on the AFM at RT. To identify chemical species, we developed the site-specific force spectroscopy at RT by compensating the thermal drift using the atom tracking. By converting the precise site-specific frequency shift curves, we obtained short-range force curves of selected Sn and Si atoms as shown in Fig. 2(a) and 2(b) [4]. Then using the atom-by-atom force spectroscopy at RT, we succeeded in chemical identification of intermixed three atom species in Pb/Sn/Si(111)-(${\surd}3$'${\surd}3$) surface as shown in Fig. 2(c) [3]. To create composite nanostructures, we found the lateral atom interchange phenomenon at RT, which enables us to exchange embedded heterogeneous atoms [2]. By combining this phenomenon with the modified vector scan, we constructed the atom letters "Sn" consisted of substitutional Sn adatoms embedded in Ge adatoms at RT as shown in Fig. 3(a)~(f) [2]. Besides, we found another kind of atom interchange phenomenon at RT that is the vertical atom interchange phenomenon, which directly interchanges the surface selected Sn atoms with the tip apex Si atoms [5]. This method is an advanced interchangeable single atom pen at RT. Then using this method, we created the atom letters "Si" consisted of substituted Si adatoms embedded in Sn adatoms at RT as shown in Fig. 4(a)~(f) [5]. In addition to the above results, we will introduce the simultaneous evaluation of the force and current at the atomic scale using the combined AFM/STM at RT.

• Journal of the Korea Convergence Society
• /
• v.11 no.12
• /
• pp.39-47
• /
• 2020

In this paper, we proposed a deep learning-based detection method using Saliency Attention to detect salient objects in images. The salient object detection separates the object where the human eye is focused from the background, and determines the highly relevant part of the image. It is usefully used in various fields such as object tracking, detection, and recognition. Existing deep learning-based methods are mostly Autoencoder structures, and many feature losses occur in encoders that compress and extract features and decoders that decompress and extend the extracted features. These losses cause the salient object area to be lost or detect the background as an object. In the proposed method, Saliency Attention is proposed to reduce the feature loss and suppress the background region in the Autoencoder structure. The influence of the feature values was determined using the ELU activation function, and Attention was performed on the feature values in the normalized negative and positive regions, respectively. Through this Attention method, the background area was suppressed and the projected object area was emphasized. Experimental results showed improved detection results compared to existing deep learning methods.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.6
• /
• pp.182-194
• /
• 2017

Most of the drone (Unmanned Aerial Vehicle) research in terms of traffic management involves detecting and tracking roads or vehicles. The purpose of analyzing image footage in the transportation sector is to overcome the limitations of the existing traffic data collection system (vehicle detectors, DSRC, etc.). With regards to this, drones are the good alternatives. However, due to limitation in their maximum flight time, they are appropriate to use as a complementary rather than replacing the existing collection system. Therefore, further research is needed for utilizing drones for transportation analysis purpose. Traffic problems often arise from one particular section or a point that expands to the whole road network and drones can be fully utilized to analyze these particular sections. Based on the study on the uses of traffic survey analysis, this study is conducted by extracting traffic flow parameters from video images(range 800~1000m) of highway unit segments that were taken by drones. In addition, video images were taken at a high altitude with the development of imaging technologies.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.6
• /
• pp.1099-1110
• /
• 2023

The recognition system of autonomous driving and robot navigation performs vision work such as object recognition, tracking, and lane detection after multi-sensor fusion to improve performance. Currently, research on a deep learning model based on the fusion of a camera and a lidar sensor is being actively conducted. However, deep learning models are vulnerable to adversarial attacks through modulation of input data. Attacks on the existing multi-sensor-based autonomous driving recognition system are focused on inducing obstacle detection by lowering the confidence score of the object recognition model.However, there is a limitation that an attack is possible only in the target model. In the case of attacks on the sensor fusion stage, errors in vision work after fusion can be cascaded, and this risk needs to be considered. In addition, an attack on LIDAR's point cloud data, which is difficult to judge visually, makes it difficult to determine whether it is an attack. In this study, image scaling-based camera-lidar We propose an attack method that reduces the accuracy of LCCNet, a fusion model (camera-LiDAR calibration model). The proposed method is to perform a scaling attack on the point of the input lidar. As a result of conducting an attack performance experiment by size with a scaling algorithm, an average of more than 77% of fusion errors were caused.

• Progress in Medical Physics
• /
• v.25 no.4
• /
• pp.264-270
• /
• 2014

This study developed a portable respiratory training device to improve breathing stability, which is an important element in using the CyberKnife Synchrony respiratory tracking device, one of the typical Stereotactic Radiation Therapy (SRT) devices. It produced an interface for users to be able to select one of two displays, a graph type and a bar type, supported an auditory system that helps them expect next respiration by improving a sense of rhythm of their respiratory period, and provided comfortable respiratory inducement. By targeting 5 applicants and applying individual respiratory period detected through a self-developed program, it acquired signal data of 'guide respiration' that induces breathing through signal data gained from 'free respiration' and an auditory system, and evaluated the usability by comparing deviation average values of respiratory period and respiratory amplitude. It could be identified that respiratory period decreased $55.74{\pm}0.14%$ compared to free respiration, and respiratory amplitude decreased $28.12{\pm}0.10%$ compared to free respiration, which confirmed the consistency and stability of respiratory. SBRT, developed based on these results, using the portable respiratory training device, for liver cancer or lung cancer, is evaluated to be able to help reduce delayed treatment time due to respiratory instability and improve treatment accuracy, and if it could be applied to developing respiratory training applications targeting an android-based portable device in the future, even use convenience and economic efficiency are expected.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.19 no.1
• /
• pp.95-107
• /
• 2017

In this study, a preliminary study was undertaken for development of a tunnel incident automatic detection system based on a machine learning algorithm which is to detect a number of incidents taking place in tunnel in real time and also to be able to identify the type of incident. Two road sites where CCTVs are operating have been selected and a part of CCTV images are treated to produce sets of training data. The data sets are composed of position and time information of moving objects on CCTV screen which are extracted by initially detecting and tracking of incoming objects into CCTV screen by using a conventional image processing technique available in this study. And the data sets are matched with 6 categories of events such as lane change, stoping, etc which are also involved in the training data sets. The training data are learnt by a resilience neural network where two hidden layers are applied and 9 architectural models are set up for parametric studies, from which the architectural model, 300(first hidden layer)-150(second hidden layer) is found to be optimum in highest accuracy with respect to training data as well as testing data not used for training. From this study, it was shown that the highly variable and complex traffic and incident features could be well identified without any definition of feature regulation by using a concept of machine learning. In addition, detection capability and accuracy of the machine learning based system will be automatically enhanced as much as big data of CCTV images in tunnel becomes rich.