• Journal of the Korea Society of Computer and Information
• /
• v.26 no.1
• /
• pp.45-55
• /
• 2021

This paper has proposed an algorithm that detecting for dense small vehicle in large image efficiently. It is consisted of two Ensemble Deep-Learning Network algorithms based on Coarse to Fine method. The system can detect vehicle exactly on selected sub image. In the Coarse step, it can make Voting Space using the result of various Deep-Learning Network individually. To select sub-region, it makes Voting Map by to combine each Voting Space. In the Fine step, the sub-region selected in the Coarse step is transferred to final Deep-Learning Network. The sub-region can be defined by using dynamic windows. In this paper, pre-defined mapping table has used to define dynamic windows for perspective road image. Identity judgment of vehicle moving on each sub-region is determined by closest center point of bottom of the detected vehicle's box information. And it is tracked by vehicle's box information on the continuous images. The proposed algorithm has evaluated for performance of detection and cost in real time using day and night images captured by CCTV on the road.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.24 no.2
• /
• pp.102-116
• /
• 2021

For the safe operation of autonomous vehicles, the representative technology of the 4^th industrial revolution era, a combination of various technologies such as sensor technology, software technology and car technology is required. An autonomous vehicle is a vehicle that recognizes current location and situation by using the various sensors, and makes its own decisions without depending on the driver. Perfect recognition technology is required for fully autonomous driving. Since the precise road maps provide various road information including lanes, stop lines, traffic lights and crosswalks, it is possible to minimize the cognitive errors that occur in autonomous vehicles by using the precise road maps with location information of the road facilities. In this study, the definition, necessity and technical trends of the precise road map have been analyzed, and the HD(High Definition) map prototype based on the web GIS has been built in the autonomous driving-specialized areas of Daegu Metropolitan City(Suseong Medical District, about 24km), the Happy City of Sejong Special Self-Governing City(about 33km), and the FMTC(Future Mobility Technical Center) PG(Proving Ground) of Seoul National University Siheung Campus using the MMS(Mobile Mapping System) surveying results given by the National Geographic Information Institute. In future research, the built-in precise road map service will be installed in the autonomous vehicles and control systems to verify the real-time locations and its location correction algorithm.

• Journal of the Microelectronics and Packaging Society
• /
• v.27 no.4
• /
• pp.107-111
• /
• 2020

Recently, as an aging society progresses, a lot of interest in health and diagnosis is increasing, As the field of various bio-imaging systems for guided surgery capable of accurate diagnosis has emerged as important, a Fluorescence imaging system capable of accurate measurement and real-time confirmation has emerged as an important field. Fluorescence images currently being used are mainly in the NIR-I band, but many studies are in progress in the NIR-II band in order to improve resolution and confirm fluorescence deeply and accurately. In this paper, the difference between NIR-I and NIR-II, optical characteristics, and SBR (signal to background ration) of a fluorescent imaging system, was investigated using the finite element (FEM) method. After confirming, it was confirmed that the SBR was 16.2 times higher in the NIR-II area than in the NIR-I by making the skin phantom and measuring the fluorescence. It is confirmed that the enhancement in SBR of the Fluorescence imaging system is more effective in the NIR-II region than in the NIR-I region and expected to be used in application fields such as guided surgery, bio-sensor and also device which can detect the defect of optical devices.

• Animal Bioscience
• /
• v.34 no.4
• /
• pp.642-651
• /
• 2021

Objective: This study aimed to determine the effects of different roughages in total mixed ration (TMR) inoculated with or without coculture of Lactobacillus acidophilus (L. acidophilus) and Bacillus subtilis (B. subtilis) on in vitro rumen fermentation and microbial population. Methods: Three TMRs formulations composed of different forages were used and each TMR was grouped into two treatments: non-fermented TMR and fermented TMR (F-TMR) (inoculated with coculture of L. acidophilus and B. subtilis). After fermentation, the fermentation, chemical and microbial profile of the TMRs were determined. The treatments were used for in vitro rumen fermentation to determine total gas production, pH, ammonianitrogen (NH3-N), and volatile fatty acids (VFA). Microbial populations were determined by quantitative real-time polymerase chain reaction (PCR). All data were analyzed as a 3×2 factorial arrangement design using the MIXED procedure of Statistical Analysis Systems. Results: Changes in the fermentation (pH, lactate, acetate, propionate, and NH3-N) and chemical composition (moisture, crude protein, crude fiber, and ash) were observed. For in vitro rumen fermentation, lower rumen pH, higher acetate, propionate, and total VFA content were observed in the F-TMR group after 24 h incubation (p<0.05). F-TMR group had higher acetate concentration compared with the non-fermented group. Total VFA was highest (p<0.05) in F-TMR containing combined forage of domestic and imported source (F-CF) and F-TMR containing Italian ryegrass silage and corn silage (F-IRS-CS) than that of TMR diet containing oat, timothy, and alfalfa hay. The microbial population was not affected by the different TMR diets. Conclusion: The use of Italian ryegrass silage and corn silage, as well as the inoculation of coculture of L. acidophilus and B. subtilis, in the TMR caused changes in the pH, lactate and acetate concentrations, and chemical composition of experimental diets. In addition, F-TMR composed with Italian ryegrass silage and corn silage altered ruminal pH and VFA concentrations during in vitro rumen fermentation experiment.

• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.12
• /
• pp.291-306
• /
• 2020

Nowadays, Data-Network-AI (DNA)-based intelligent services and applications have become a reality to provide a new dimension of services that improve the quality of life and productivity of businesses. Artificial intelligence (AI) can enhance the value of IoT data (data collected by IoT devices). The internet of things (IoT) promotes the learning and intelligence capability of AI. To extract insights from massive volume IoT data in real-time using deep learning, processing capability needs to happen in the IoT end devices where data is generated. However, deep learning requires a significant number of computational resources that may not be available at the IoT end devices. Such problems have been addressed by transporting bulks of data from the IoT end devices to the cloud datacenters for processing. But transferring IoT big data to the cloud incurs prohibitively high transmission delay and privacy issues which are a major concern. Edge computing, where distributed computing nodes are placed close to the IoT end devices, is a viable solution to meet the high computation and low-latency requirements and to preserve the privacy of users. This paper provides a comprehensive review of the current state of leveraging deep learning within edge computing to unleash the potential of IoT big data generated from IoT end devices. We believe that the revision will have a contribution to the development of DNA-based intelligent services and applications. It describes the different distributed training and inference architectures of deep learning models across multiple nodes of the edge computing platform. It also provides the different privacy-preserving approaches of deep learning on the edge computing environment and the various application domains where deep learning on the network edge can be useful. Finally, it discusses open issues and challenges leveraging deep learning within edge computing.

• Smart Media Journal
• /
• v.10 no.1
• /
• pp.9-15
• /
• 2021

The eye tracking system designed in this paper is an eye-based computer input device designed to give an easy access for those who are uncomfortable with Lou Gehrig's or various muscle-related diseases. It is an eye-based-computer-using device for users whose potential demand alone amounts to 30,000. Combining the number of Lou Gehrig's patients in Korea estimated at around 1,700, and those who are unable to move their bodies due to various accidents or diseases. Because these eye input devices are intended for a small group of users, many types of commercial devices are available on the market. It is making them more expensive and difficult to use for these potential users, less accessible. For this reason, each individual's economic situation and individual experience with smart devices are slightly different. Therefore, making it difficult to access them in terms of cost or usability to use a commercial eye tracking system. Accordingly, attempts to improve accessibility to IT devices through low-cost but easy-to-use technologies are essential. Thus, this paper proposes a complementary superior performance eye tracking system that can be conveniently used by far more people and patients by improving the deficiencies of the existing system. Through voluntary VoCs(Voice of Customers) of users who have used different kinds of eye tracking systems that satisfies it through various usability tests, and we propose a reduced system that the amount of calculation to 1/15th, and eye-gaze tracking error rate to 0.5~1 degree under.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.1
• /
• pp.51-58
• /
• 2022

Drivable area detection, one of the main functions of advanced driver assistance systems, means detecting an area where a vehicle can safely drive. The drivable area detection is closely related to the safety of the driver and it requires high accuracy with real-time operation. To satisfy these conditions, V-disparity-based method is widely used to detect a drivable area by calculating the road disparity value in each row of an image. However, the V-disparity-based method can falsely detect a non-road area as a road when the disparity value is not accurate or the disparity value of the object is equal to the disparity value of the road. In a road environment including vegetation, such as a highway and a country road, the vegetation area may be falsely detected as the drivable area because the disparity characteristics of the vegetation are similar to those of the road. Therefore, this paper proposes a drivable area detection method and hardware architecture with a high accuracy in road environments including vegetation areas by reducing the number of false detections caused by V-disparity characteristic. When 289 images provided by KITTI road dataset are used to evaluate the road detection performance of the proposed method, it shows an accuracy of 90.12% and a recall of 97.96%. In addition, when the proposed hardware architecture is implemented on the FPGA platform, it uses 8925 slice registers and 7066 slice LUTs.

• Smart Media Journal
• /
• v.11 no.3
• /
• pp.39-53
• /
• 2022

Cloud of Things (CoT) can provide IoT applications with unlimited storage functions and processing power supported by cloud services. However, in a centralized cloud of things, it can create a single point of failure that can lead to bottleneck problems, outages of the CoT network. In this paper, to solve the problem of centralized cloud of things and interoperate between different service domains, we propose an IoT service interoperability system using distributed fog computing and blockchain technology. Distributed fog is used to provide real-time data processing and services in fog systems located at a geographically close distance to IoT devices, and to enable service interoperability between each fog using smart contracts and distributed ledgers of the blockchain. The proposed system provides services within a region close to the distributed fog entrusted with the service from the cloud, and it is possible to access the services of other fogs without going through the cloud even between fogs. In addition, by sharing a service right token issuance information between the cloud and fog nodes using a blockchain network, the integrity of the token can be guaranteed and reliable service interoperability between fog nodes can be performed.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.5
• /
• pp.7-15
• /
• 2022

Since the direct and indirect damage caused by the fire in the underground utility tunnel will cause great damage to society as a whole, it is necessary to make efforts to prevent and control it in advance. The most of the fires that occur in cables are caused by short circuits, earth leakage, ignition due to over-current, overheating of conductor connections, and ignition due to sparks caused by breakdown of insulators. In order to find the cause of fire at an early stage due to the characteristics of the underground utility tunnel and to prevent disasters and safety accidents, we are constantly managing it with a detection system using image analysis and making efforts. Among them, a case of developing a fire detection system using CCTV-based deep learning image analysis technology has been reported. However, CCTV needs to be supplemented because there are blind spots. Therefore, we would like to develop a high-performance acoustic-based deep learning model that can prevent fire by detecting the spark sound before spark occurs. In this study, we propose a method that can collect sound in underground utility tunnel environments using microphone sensor through development and experiment of prototype module. After arranging an acoustic sensor in the underground utility tunnel with a lot of condensation, it verifies whether data can be collected in real time without malfunction.

• Journal of Appropriate Technology
• /
• v.7 no.2
• /
• pp.196-205
• /
• 2021

As industrial safety increases, various industrial accident prevention technologies using smart factory technology are being studied. However, small and medium enterprises (SMEs), which account for the majority of industrial accidents, are having difficulties in preventing industrial accidents by applying these smart factory technologies due to practical problems. In this study, customized monitoring and warning systems for each type of industrial accident were developed and applied to the actual field. Through this, we demonstrated industrial accident prevention technology through appropriate smart factory technology used by SMEs. A customized monitoring system using vision, current, temperature, and gas sensors was established for the four major disaster types: worker body access, short circuit and overcurrent, fire and burns due to high temperature, and emission of hazardous gas. In addition, a notification method suitable for each work environment was applied so that the monitored risk factors could be recognized quickly, and real-time data transmission and display enabled workers and managers to understand the disaster risk effectively. Through the application and demonstration of these appropriate smart factory technologies, the spread of these industrial safety technologies is to be discussed.