• Journal of Advanced Navigation Technology
• /
• v.26 no.4
• /
• pp.211-218
• /
• 2022

Continuous wave (CW) radar has the advantage of reliability and accuracy compared to other sensors such as camera and lidar. In addition, binarized neural network (BNN) has a characteristic that dramatically reduces memory usage and complexity compared to other deep learning networks. Therefore, this paper proposes binarized neural network based human identification and motion classification system using CW radar. After receiving a signal from CW radar, a spectrogram is generated through a short-time Fourier transform (STFT). Based on this spectrogram, we propose an algorithm that detects whether a person approaches a radar. Also, we designed an optimized BNN model that can support the accuracy of 90.0% for human identification and 98.3% for motion classification. In order to accelerate BNN operation, we designed BNN hardware accelerator on field programmable gate array (FPGA). The accelerator was implemented with 1,030 logics, 836 registers, and 334.904 Kbit block memory, and it was confirmed that the real-time operation was possible with a total calculation time of 6 ms from inference to transferring result.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.5
• /
• pp.1-9
• /
• 2022

Localization systems can be used with various circumstances like measuring population movement and rescue technology, even in security technology (like infiltration detection system). Vision sensors such as camera often used for localization is susceptible with light and temperature, and can cause invasion of privacy. In this paper, we used ultra-wideband radar technology (which is not limited by aforementioned problems) and machine learning techniques to measure the number and location of occupants in other indoor spaces behind the wall. We used four different algorithms and compared their results, including extremely randomized tree for four different situations; detect the number of occupants in a classroom, split the classroom into 28 locations and check the position of occupant, select one out of the 28 locations, divide it into 16 fine-grained locations, and check the position of occupant, and checking the positions of two occupants (existing in different locations). Overall, four algorithms showed good results and we verified that detecting the number and location of occupants are possible with high accuracy using machine learning. Also we have considered the possibility of service expansion using the oneM2M standard platform and expect to develop more service and products if this technology is used in various fields.

• Journal of the Korea Computer Graphics Society
• /
• v.28 no.3
• /
• pp.79-89
• /
• 2022

With the popularity and the advanced graphics hardware technology of mobile devices, various mobile applications that help children with physical activities have been studied. This paper presents SandUp, a mobile application that guides the play of building sand castles using artificial intelligence and augmented reality(AR) technology. In the process of building the sandcastle, children can interactively explore the target virtual sandcastle through the smartphone display using AR technology. In addition, to help children complete the sandcastle, SandUp informs the sand shape and task required step by step and provides visual and auditory feedback while recognizing progress in real-time using the phone's camera and deep learning classification. We prototyped our SandUp app using Flutter and TensorFlow Lite. To evaluate the usability and effectiveness of the proposed SandUp, we conducted a questionnaire survey on 50 adults and a user study on 20 children aged 4~7 years. The survey results showed that SandUp effectively helps build the sandcastle with proper interactive guidance. Based on the results from the user study on children and feedback from their parents, we also derived usability issues that can be further improved and suggested future research directions.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.12
• /
• pp.363-370
• /
• 2023

Object detection technology that accurately recognizes the road and surrounding conditions is a key technology in the field of autonomous driving. In the field of autonomous driving, object detection technology requires real-time performance as well as accuracy of inference services. Task offloading technology should be utilized to apply object detection technology for accuracy and real-time on resource-constrained devices rather than high-performance machines. In this paper, experiments such as performance comparison of task offloading, performance comparison according to input image resolution, and performance comparison according to camera object resolution were conducted and the results were analyzed in relation to the application of task offloading for real-time object detection of autonomous driving in resource-constrained devices. In this experiment, the low-resolution image could derive performance improvement through the application of the task offloading structure, which met the real-time requirements of autonomous driving. The high-resolution image did not meet the real-time requirements for autonomous driving due to the increase in communication time, although there was an improvement in performance. Through these experiments, it was confirmed that object recognition in autonomous driving affects various conditions such as input images and communication environments along with the object recognition model used.

• Journal of Cadastre & Land InformatiX
• /
• v.53 no.2
• /
• pp.5-18
• /
• 2023

As the development of drones and sensors accelerates, new services and values are created by fusing data acquired from various sensors mounted on drone. However, the construction of spatial information through data fusion is mainly constructed depending on the image, and the quality of data is determined according to the specification and performance of the hardware. In addition, it is difficult to utilize it in the actual field because expensive equipment is required to construct spatial information of high-quality. In this study, super-resolution was performed by applying deep learning to low-resolution images acquired through RGB and THM cameras mounted on a drone, and quantitative evaluation and feature point extraction were performed on the generated high-resolution images. As a result of the experiment, the high-resolution image generated by super-resolution was maintained the characteristics of the original image, and as the resolution was improved, more features could be extracted compared to the original image. Therefore, when generating a high-resolution image by applying a low-resolution image to an super-resolution deep learning model, it is judged to be a new method to construct spatial information of high-quality without being restricted by hardware.

• Korean Chemical Engineering Research
• /
• v.62 no.1
• /
• pp.27-35
• /
• 2024

Fuel gases such as methane and propane are used in explosion hazardous area of domestic plants and can form non-uniform mixtures with the influence of process conditions due to leakage. The fire-explosion risk assessment using literature data measured under uniform mixtures, damage prediction can be obtained the different results from actual explosion accidents by gas leaks. An explosion characteristics such as explosion pressure and flame velocity of non-uniform gas mixtures with concentration change similar to that of facility leak were examined. The experiments were conducted in a closed 0.82 m long stainless steel duct with observation recorded by color high speed camera and piezo pressure sensor. Also we proposed the quantification method of non-uniform mixtures from a regression analysis model on the change of concentration difference with time in explosion duct. For the non-uniform condition of this study, the area of flame surface enlarged with increasing the concentration non-uniform in the flame propagation of methane and was similar to the wrinkled flame structure existing in a turbulent flame. The time to peak pressure of methane decreased as the non-uniform increased and the explosion pressure increased with increasing the non-uniform. The ranges of K_G (Deflagration index) of methane with the concentration non-uniform were 1.30 to 1.58 [MPa·m/s] and the increase rate of K_G was 17.7% in methane with changing from uniform to non-uniform.

• The Korean Journal of Nuclear Medicine
• /
• v.35 no.5
• /
• pp.324-333
• /
• 2001

Purpose: $^{123}I$-labeled fatty acids have been used in the evaluation of regional myocardial energy metabolism. This study aimed to evaluate the usefulness of $^{123}I$-BMIPP as a liposarcoma-imaging agent. Materials and Methods: We compared in vitro uptakes between liposarcoma(SW872) and glioma(9L) cell lines, and examined biodistribution and in vivo images of $^{123}I$-BMIPP in liposarcoma-bearing nude mice. Cold-BMIPP was labeled with $^{123}I\;using\;Cu^{2+}$ as catalyst. After purification by Sep-pak, radiochemical purity was determined by TLC. We compared cellular uptake between glioma and liposarcoma after incubation of 5, 10, 15, 30, 60, 120, and 180 mins with culture medium containing $^{123}I$-BMIPP. The difference in biodistribution was determined between non-feeding (water only) group for 18 hr and feeding group in normal mice (n=6/group) at 0.5, 2, and 24 hr. In liposarcoma-hearing nude mice model, liposarcoma, SW872, ceil lines were injected subcutaneously into the felt thigh of nude mice. The biodistribution of $^{123}I$-BMIPP was evaluated at 0.5, 2, and 24 hr (n:5 / group) and in vivo Image of $^{123}I$-BMIPP was obtained with gamma camera at 2 and 24 hr in liposarcoma-hearing nude mice. Results: Radiolabeling yield and radiochemical purity were 95% and above 99%, respectively. SW872 cell line showed more increased uptake than 9L with 1.5 times at 180 mins. The clearance of $^{123}I$-BMIPP in various tissues was more delayed in the non-feeding group than in the feeding group, especially at delayed time (24 hr) in normal mice, and the major excreting organ was the gastrointestinal tract. In liposarcoma-bearing nude mice, tumor/blood ratio of $^{123}I$-BMIPP was 0.94, 0.75, and 1.38 and tumor/muscle ratio was 0.66, 1.53, and 1.11 at 0.5, 2, and 24hr, respectively. $^{123}I$-BMIPP was selectively localized in liposarcoma at 24 hr image. Conclusions: These results suggest that $^{123}I$-BMIPP can be used as a liposarcoma-imaging agent.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.11S
• /
• pp.3651-3667
• /
• 2000

Recently, in the distributed multimedia environments based on internet, as radical growing technologies, the most of researchers focus on both streaming technology and distributed object thchnology, Specially, the studies which are tried to integrate the streaming services on the distributed object technology have been progressing. These technologies are applied to various stream service mamgements and protocols. However, the stream service management mexlels which are being proposed by the existing researches are insufficient for suporting the QoS of stream services. Besides, the existing models have the problems that cannot support the extensibility and the reusability, when the QoS-reiatedfunctions are being developed as a sub-module which is suited on the specific-purpose application services. For solving these problems, in this paper. we suggested a QoS Integrated platform which can extend and reuse using the distributed object technologies, and guarantee the QoS of the stream services. A structure of platform we suggested consists of three components such as User Control Module(UCM), QoS Management Module(QoSM) and Stream Object. Stream Object has Send/Receive operations for transmitting the RTP packets over TCP/IP. User Control ModuleI(UCM) controls Stream Objects via the COREA service objects. QoS Management Modulel(QoSM) has the functions which maintain the QoS of stream service between the UCMs in client and server. As QoS control methexlologies, procedures of resource monitoring, negotiation, and resource adaptation are executed via the interactions among these comiXments mentioned above. For constmcting this QoS integrated platform, we first implemented the modules mentioned above independently, and then, used IDL for defining interfaces among these mexlules so that can support platform independence, interoperability and portability base on COREA. This platform is constructed using OrbixWeb 3.1c following CORBA specification on Solaris 2.5/2.7, Java language, Java, Java Media Framework API 2.0, Mini-SQL1.0.16 and multimedia equipments. As results for verifying this platform functionally, we showed executing results of each module we mentioned above, and a numerical data obtained from QoS control procedures on client and server's GUI, while stream service is executing on our platform.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.171-187
• /
• 2023

When a person's face is recognized through a recording device such as a low-pixel surveillance camera, it is difficult to capture the face due to low image quality. In situations where it is difficult to recognize a person's face, problems such as not being able to identify a criminal suspect or a missing person may occur. Existing studies on face recognition used refined datasets, so the performance could not be measured in various environments. Therefore, to solve the problem of poor face recognition performance in low-quality images, this paper proposes a method to generate high-quality images by performing image quality improvement on low-quality facial images considering various environments, and then improve the performance of facial feature point detection. To confirm the practical applicability of the proposed architecture, an experiment was conducted by selecting a data set in which people appear relatively small in the entire image. In addition, by choosing a facial image dataset considering the mask-wearing situation, the possibility of expanding to real problems was explored. As a result of measuring the performance of the feature point detection model by improving the image quality of the face image, it was confirmed that the face detection after improvement was enhanced by an average of 3.47 times in the case of images without a mask and 9.92 times in the case of wearing a mask. It was confirmed that the RMSE for facial feature points decreased by an average of 8.49 times when wearing a mask and by an average of 2.02 times when not wearing a mask. Therefore, it was possible to verify the applicability of the proposed method by increasing the recognition rate for facial images captured in low quality through image quality improvement.

• Korean Journal of Applied Biomechanics
• /
• v.12 no.2
• /
• pp.179-195
• /
• 2002

The purpose of this research is to provide a proper model by analyzing the sports biomechanical of physical movements on the basis of the two patterns(open-stance and cross-stance) at the ready-to-start pose. The subjects for this study are composed of five male handball players from P university and five female shooting players from S university. Three-way moving actions at start(right, left, and forward) are recorded with two high-speed video cameras and measured with two Force platforms and a EMG system. Three-dimensional action analyzer, GRF system, and Whole body reaction movement system are used to figure out the moving mechanisms at the start pose. The analytic results of the moving mechanism at the start pose were as follows. 1. Through examining the three-way moving actions at start, I have found the cross-stance pose is better for the moving speed of body weight balance than the open-stance one. 175 degree of knee joint angle at "take-off" and 172 degree of hip joint angle were best for the start pose. 2. The Support time and GRF data shows that the quickest center of gravity shift was occurred when cross-stanced male subjects started to move toward his lefthand side. The quickest male's average supporting time of left and right foot is 0.19${\pm}$0.07 sec., 0.26${\pm}$0.06sec. respectively. The supporting time difference between two feet is 0.07sec. 3. Through analyzing GRF of moving actions at start pose, I have concluded that more than 1550N are overloaded on one foot at the open-stance start, and the overloaded force may cause physical injury. However, at the cross-stance pose, The GRF are properly dispersed on both feet, and maximum 1350N are loaded on one foot.