• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권8호
• /
• pp.3488-3500
• /
• 2020

At the present time, the economy continues to flourish, and private cars have become the means of choice for most people. Therefore, the license plate recognition technology has become an indispensable part of intelligent transportation, with research and application value. In recent years, the convolution neural network for image classification is an application of deep learning on image processing. This paper proposes a strategy to improve the YOLO model by studying the deep learning convolutional neural network (CNN) and related target detection methods, and combines the OpenCV and TensorFlow frameworks to achieve efficient recognition of license plate characters. The experimental results show that target detection method based on YOLO is beneficial to shorten the training process and achieve a good level of accuracy.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1995년도 Proceedings of the Korea Automation Control Conference, 10th (KACC); Seoul, Korea; 23-25 Oct. 1995
• /
• pp.240-243
• /
• 1995

In excavating tunnels, shield tunneling machines having many cutters on their cutter planes are used. Not many observation data being available in the detection system, optimal observation policy is very important. From this viewpoint, we previously considered the optimal location of acoustic sensors on the cutter plane and also the optimal observation policy for the case where three receiving transducers were used, and showed that the optimal sensor location was given as arbitrary equally-spaced points on the cutter plane circle, and that the optimal rotating angles were also found to be arbitrary. In application, however, it is often difficult to locate sensors at arbitrary positions or to use three sensors from the viewpoints of machine structure and cost. This paper considers the optimal observation policy for detecting anomlous plane objects for the case where two receiving transducers are used and the case where three receiving transducers are located only on a diameter of the cutter plane.

• Nuclear Engineering and Technology
• /
• 제52권11호
• /
• pp.2601-2606
• /
• 2020

In this study, we expanded the performance of the existing EXVol code and performed empirical experiments and calculations. A high-resolution gamma spectroscopy system was constructed, and a standard point source and a standard volume source were measured with an HPGe detector with 43.1% relative efficiency. EXVol was verified by quantitative comparison of the detection efficiencies determined by measurements and calculations. To introduce the concept of the detector scanning that occurs in the actual measurement into the EXVol code, a collimator was placed between the source and detector. The detection efficiency was determined in the asymmetric arrangement of the source and detector with a collimator. A collimator made of lead with a diameter of 15 mm and a thickness of 50 mm was installed between the source and the detector to determine the detection efficiency at a specific location. The calculation result was contour plotted so that the distribution of detection efficiency could be visually confirmed. The relative deviation between the measurements and calculations for the coaxial and asymmetric structures was 10%, and that for the collimation structure was 20%. The results of this study can be applied to research using γ-ray measurements.

• 반도체디스플레이기술학회지
• /
• 제4권1호
• /
• pp.61-64
• /
• 2005

This study presents a new algorithm to detect the facial feature in a color image entered from the mobile device with complex backgrounds and undefined distance between camera's location and the face. Since skin color model with Hough transformation spent approximately 90$\%$ of running time to extract the fitting ellipse for detection of the facial feature, we have changed the approach to the simple geometric vector operation, called a TS(Triangle-Square) transformation. As the experimental results, this gives benefit of reduced run time. We have similar ratio of face detection to other methods with fast speed enough to be used on real-time identification system in mobile environments.

• 한국군사과학기술학회지
• /
• 제18권4호
• /
• pp.350-357
• /
• 2015

Many countries have been developing and operating an underwater surveillance system in order to protect their oceanic environment from infiltrating hostile marine forces which intend to lay mines, conduct reconnaissance and destroy friendly ships anchored at the harbor. One of the most efficient methods to detect unidentified submarine approaching harbor is sensing variation of magnetism of target by magnetic sensors. This measurement system has an advantage of high possibility of detection and low probability of false alarm, compared to acoustic sensors, although it has relatively decreased detection range. The contents of this paper mainly cover the analysis of possible effectiveness of magnetic sensors. First of all, environmental characteristics of surveillance area and magnetic information of simulated targets has been analyzed. Subsequently, a signal processing method of separating target from geomagnetic field and methods of estimating target location has been proposed.

• Journal of Animal Science and Technology
• /
• 제65권4호
• /
• pp.748-758
• /
• 2023

This study was conducted to investigate the change in activity and mounting behavior in Hanwoo (Korean Native Cattle) during the peri-estrus period and its application to estrus detection. A total of 20 Hanwoo cows were fitted with a neck-collar accelerometer device, which measured the location and acceleration of cow movements and recorded the number of instances of mounting behavior by the altitude data. The data were analyzed in three periods (24-, 6-, and 2-h periods). Blood samples were collected for 5 days after the prostaglandin F2α (PGF2α) injection, and the concentrations of estradiol, progesterone, follicle-stimulating hormone, and luteinizing hormone were determined by enzyme-linked immunosorbent assays. Activity and mounting behavior recorded over 2-h periods significantly increased as estrus approached and were more efficient at detecting estrus than over 24- and 6-h periods (p < 0.05). Endocrine patterns did not differ with the variation of individual cows during the peri-estrus period (p > 0.05). Activity was selected as the best predictor through stepwise discriminant analysis. However, activity alone is not enough to detect estrus. We suggest that a combination of activity and mounting behavior may improve estrus detection efficiency in Hanwoo. Further research is necessary to validate the findings on a larger sample size.

• Journal of Positioning, Navigation, and Timing
• /
• 제2권1호
• /
• pp.91-100
• /
• 2013

This paper introduces an indoor sensor fusion wireless communication device which provides the Location Based Service (LBS) using fire prevention facility. The proposed system can provide information in real time by optimizing the hardware of Wi-Fi technology. The proposed system can be applied to a fire prevention facility (i.e., emergency exit) and provide information such as escape way, emergency exit location, and accident alarm to smart phone users, dedicated terminal holders, or other related organizations including guardians, which makes them respond instantly with lifesaving, emergency mobilization, etc. Also, the proposed system can be used as a composite fire detection sensor node with additional fire and motion detect sensors.

• 한국인터넷방송통신학회논문지
• /
• 제24권1호
• /
• pp.197-205
• /
• 2024

자율주행 자동차 개발 및 상용화에 있어서 주행안전도 확보가 가장 중요한 시점에서 이를 위해 전방 및 주행차량 주변에 존재하는 다양한 정적/동적 차량의 인식과 검출 성능을 고도화 및 최적화하기 위한 AI, 빅데이터 기반 알고리즘개발 등이 연구되고 있다. 하지만 레이더와 카메라의 고유한 장점을 활용하여 동일한 차량으로 인식하기 위한 연구 사례들이 많이 있지만, 딥러닝 영상 처리 기술을 이용하지 않거나, 레이더의 성능상의 문제로 짧은 거리만 동일한 표적으로 감지하고 있다. 따라서 레이더 장비와 카메라 장비에서 수집할 수 있는 데이터셋을 구성하고, 데이터셋의 오차를 계산하여 동일한 표적으로 인식하는 융합 기반 차량 인식 방법이 필요하다. 본 논문에서는 레이더와 CCTV(영상) 설치 위치에 따라 동일한 객체로 판단하기에 데이터 오차가 발생하기 때문에 설치한 위치에 따라 위치 정보를 연동할 수 있는 기술 개발을 목표로 한다.

• Journal of information and communication convergence engineering
• /
• 제22권2호
• /
• pp.109-120
• /
• 2024

Trash or garbage is one of the most dangerous health and environmental problems that affect pollution. Pollution affects nature, human life, and wildlife. In this paper, we propose modern solutions for cleaning the environment of trash pollution by enforcing strict action against people who dump trash inappropriately on streets, outside the home, and in unnecessary places. Artificial Intelligence (AI), especially Deep Learning (DL), has been used to automate and solve issues in the world. We availed this as an excellent opportunity to develop a system that identifies trash using a deep convolutional neural network (CNN). This paper proposes a real-time garbage identification system based on a deep CNN architecture with eight distinct classes for the training dataset. After identifying the garbage, the CCTV camera captures a video of the individual placing the trash in the incorrect location and sends an alert notice to the relevant authority.

• Nuclear Engineering and Technology
• /
• 제54권8호
• /
• pp.3006-3016
• /
• 2022

In this study, the images of specific prompt gamma (PG)-rays of 719 keV emitted from proton-boron reactions were analyzed using single-photon emission computed tomography (SPECT). Quantitative evaluation of the images verified the detection of anatomical changes in tumors, one of the important factors in daily adaptive proton therapy (DAPT) and verified the possibility of application of the PG-ray images to DAPT. Six scenarios were considered based on various sizes and locations compared to the reference virtual tumor to observe the anatomical alterations in the virtual tumor. Subsequently, PG-rays SPECT images were acquired using the modified ordered subset expectation-maximization algorithm, and these were evaluated using quantitative analysis methods. The results confirmed that the pixel range and location of the highest value of the normalized pixel in the PG-rays SPECT image profile changed according to the size and location of the virtual tumor. Moreover, the alterations in the virtual tumor size and location in the PG-rays SPECT images were similar to the true size and location alterations set in the phantom. Based on the above results, the tumor anatomical alterations in DAPT could be adequately detected and verified through SPECT imaging using the 719 keV PG-rays acquired during treatment.