• 자동차안전학회지
• /
• 제11권2호
• /
• pp.35-43
• /
• 2019

This paper describes the improved environment recognition algorithms using some type of sensors like LiDAR and cameras. Additionally, integrated control algorithm for an autonomous vehicle is included. The integrated algorithm was based on C++ environment and supported the stability of the whole driving control algorithms. As to the improved vision algorithms, lane tracing and traffic sign recognition were mainly operated with three cameras. There are two algorithms developed for lane tracing, Improved Lane Tracing (ILT) and Histogram Extension (HIX). Two independent algorithms were combined into one algorithm - Enhanced Lane Tracing with Histogram Extension (ELIX). As for the enhanced traffic sign recognition algorithm, integrated Mutual Validation Procedure (MVP) by using three algorithms - Cascade, Reinforced DSIFT SVM and YOLO was developed. Comparing to the results for those, it is convincing that the precision of traffic sign recognition is substantially increased. With the LiDAR sensor, static and dynamic obstacle detection and obstacle avoidance algorithms were focused. Therefore, improved environment recognition algorithms, which are higher accuracy and faster processing speed than ones of the previous algorithms, were proposed. Moreover, by optimizing with integrated control algorithm, the memory issue of irregular system shutdown was prevented. Therefore, the maneuvering stability of the autonomous vehicle in severe environment were enhanced.

• Tribology and Lubricants
• /
• 제35권1호
• /
• pp.59-64
• /
• 2019

When slipping occurs between two materials, the coefficients of friction must be considered because these values determine the overall efficiency of the machine or slip characteristics. Therefore, it is important to find the coefficient of friction between two materials. This paper focuses on obtaining the coefficient of friction between an aiming bolt and a retainer located in the headlamps of a vehicle. This bolt supports the headlamp, and if the bolt is loosened by external vibration, the angle of the light will change and block the vision of pedestrians or other drivers. In order to study these situations, the coefficient of friction between aiming bolts and retainers needs to be measured. In addition, the coefficient of friction of materials used in the headlamp should be obtained. To determine these two factors, a new device is designed for two cases: surface-surface contact and surface-line contact. To increase reliability of the results, the device is designed using an air-bearing stage which uses compressed air as lubricant to eliminate the friction of the stage itself. Experiments were carried out by applying various vertical forces, and the results show that the coefficient of friction can be measured consistently. The procedure for designing the device and the results are discussed.

• 해양환경안전학회지
• /
• 제25권1호
• /
• pp.111-116
• /
• 2019

선박의 기관실에서 사용하고 있는 화재 검출기는 연기나 열이 검출기에 도달해야 하지만 기관실의 공기 흐름은 기기의 사용유무에 따라 매우 유동적이기 때문에 상부에 설치된 검출기에 도달하기에는 많은 시간이 필요하다. 이러한 단점을 보완하기 위해 근래에는 영상을 기반으로 화재를 검지하는 연구가 이루어지고 있다. 영상기반의 연기 검지는 공기의 흐름에 영향을 받지 않으며 전송속도가 빠르기 때문에 화재의 초기 검지에 효율적이다. 본 연구는 기관실에서 연기 발생기로 발생시킨 연기의 확산모습을 녹화한 영상으로 실험을 수행하였다. 연기의 질감특징을 추출하는 LBP와 GLCM연산자를 사용하여 생성된 학습 데이터를 기계학습 분류기인 SVM으로 학습한 후 분류하여 검출 성능을 평가함으로서 연기가 상부에 설치되어 있는 검출기까지 상승하지 않더라도 영상기반으로 먼저 검지 가능함을 확인하였다.

• 융합보안논문지
• /
• 제17권5호
• /
• pp.93-99
• /
• 2017

최근 국내외적으로 사물인터넷(IoT, Internet of Things) 서비스 산업은 매우 빠른 속도로 변화하고 성장해 나가고 있다. 본 논문은 IoT 서비스 산업의 변화와 함께 일어나고 있는 인류의 삶 속에서의 새로운 변화의 원동력이 무엇인가를 찾기 위해 노력하였다. 이렇게 시장 환경이 변화하는 가운데 경쟁도 글로벌 경쟁, 생태계 경쟁으로 그 양상이 확대되고 있으나, 글로벌 기업들의 플랫폼 선점과 고도의 생태계 발전 전략에 비해 국내 기업들의 생태계 구축 비전은 아직 뚜렷하지 않은 상황이다. 또한 IoT 서비스의 확산에 따른 모바일 네트워크에서의 IoT 서비스 연동이 요구되고 있다. IoT 보안 프로토콜은 무선과 유선을 연계하는 게이트웨이(Gateway)에서 전달되는 데이터의 모든 내용이 누출되는 보안상의 취약점이 있어 종단간 보안도 제공하지 못하는 단점이 있다. 이에 본 논문에서는 IoT와 인공지능(AI) 서비스 산업 생태계를 구성하고 있는 제반 요소의 현황을 살펴본 후, 이로부터 얻을 수 있는 보안 산업과 관련한 전략적 시사점을 제시해 보고자 한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권2호
• /
• pp.751-770
• /
• 2019

Action recognition is an essential task in computer vision due to the variety of prospective applications, such as security surveillance, machine learning, and human-computer interaction. The availability of more video data than ever before and the lofty performance of deep convolutional neural networks also make it essential for action recognition in video. Unfortunately, limited crafted video features and the scarcity of benchmark datasets make it challenging to address the multi-person action recognition task in video data. In this work, we propose a deep convolutional neural network-based Effective Hybrid Learning (EHL) framework for two-person interaction classification in video data. Our approach exploits a pre-trained network model (the VGG16 from the University of Oxford Visual Geometry Group) and extends the Faster R-CNN (region-based convolutional neural network a state-of-the-art detector for image classification). We broaden a semi-supervised learning method combined with an active learning method to improve overall performance. Numerous types of two-person interactions exist in the real world, which makes this a challenging task. In our experiment, we consider a limited number of actions, such as hugging, fighting, linking arms, talking, and kidnapping in two environment such simple and complex. We show that our trained model with an active semi-supervised learning architecture gradually improves the performance. In a simple environment using an Intelligent Technology Laboratory (ITLab) dataset from Inha University, performance increased to 95.6% accuracy, and in a complex environment, performance reached 81% accuracy. Our method reduces data-labeling time, compared to supervised learning methods, for the ITLab dataset. We also conduct extensive experiment on Human Action Recognition benchmarks such as UT-Interaction dataset, HMDB51 dataset and obtain better performance than state-of-the-art approaches.

• 한국산업융합학회 논문집
• /
• 제25권2_1호
• /
• pp.177-184
• /
• 2022

The automatic defect sorting function of machinery parts is being introduced to the automation of the manufacturing process. In the final stage of automation of the manufacturing process, it is necessary to apply computer vision rather than human visual judgment to determine whether there is a defect. In this paper, we introduce a deep learning method to improve the classification performance of typical mechanical parts, such as welding parts, galvanized round plugs, and electro galvanized nuts, based on the results of experiments. In the case of poor welding, the method to further increase the depth of layer of the basic deep learning model was effective, and in the case of a circular plug, the surrounding data outside the defective target area affected it, so it could be solved through an appropriate pre-processing technique. Finally, in the case of a nut plated with zinc, since it receives data from multiple cameras due to its three-dimensional structure, it is greatly affected by lighting and has a problem in that it also affects the background image. To solve this problem, methods such as two-dimensional connectivity were applied in the object segmentation preprocessing process. Although the experiments suggested that the proposed methods are effective, most of the provided good/defective images data sets are relatively small, which may cause a learning balance problem of the deep learning model, so we plan to secure more data in the future.

• Journal of Platform Technology
• /
• 제9권4호
• /
• pp.60-70
• /
• 2021

본 논문은 2채널 이상의 다중 카메라를 사용하는 곡면 스크린 사격 시스템에서 패턴 레이저 영상의 좌표를 안정적으로 추적할 수 있는 방법을 제안하였다. 이 방법은 HMD 사격 방식을 대체할 수 있는 다중 스크린 사격 방식에 적용시 매우 효과적으로 타겟점을 추적 및 획득할 수 있다. 개별 카메라로부터 획득한 변형이 심한 곡면 스크린의 영상을 영상 정규화, 영상 이진화 및 노이즈 제거를 통해 보정한다. 이 보정된 영상을 매칭점을 기준으로 사격의 탄착점 추적에 용의한 유클리드 공간 맵으로 생성하여 적용한다. 실험한 결과, 곡면 스크린 사격 시스템에서 패턴 레이저의 영상 좌표를 안정적으로 추출하였고, 실세계 좌표 위치와 광대역 유클리드 맵의 타켓점 위치 오차를 최소화하였다. 실험을 통해 제안한 방법의 신뢰성을 확인하였다.

• 한국의류산업학회지
• /
• 제24권5호
• /
• pp.647-654
• /
• 2022

Wearable devices come in a variety of shapes and sizes in numerous fields in numerous fields and are available in various forms. They can be integrated into clothing, gloves, hats, glasses, and bags and used in healthcare, the medical field, and machine interfaces. These devices keep track individuals' biological and behavioral data to help with health communication and are often used for injury prevention. Those with hearing loss or impaired vision find it more difficult to recognize an approaching person or object; these sensing devices are particularly useful for such individuals, as they assist them with injury prevention by alerting them to the presence of people or objects in their immediate vicinity. Despite these obvious preventive benefits to developing Internet of Things based devices for the disabled, the development of these devices has been sluggish thus far. In particular, when compared with people without disabilities, people with hearing impairment have a much higher probability of averting danger when they are able to notice it in advance. However, research and development remain severely underfunded. In this study, we incorporated a wearable detection system, which uses an infrared proximity sensor, into a backpack. This system helps its users recognize when someone is approaching from behind through visual and tactile notification, even if they have difficulty hearing or seeing the objects in their surroundings. Furthermore, this backpack could help prevent accidents for all users, particularly those with visual or hearing impairments.

• 한국정보통신학회논문지
• /
• 제26권10호
• /
• pp.1477-1482
• /
• 2022

안개는 매우 작은 물방울이 대기 중에 떠돌아다니는 국지적인 기상현상으로 지역에 따라 안개 양과 특성이 다를 수도 있다. 특히 이러한 안개로 인해 가시거리가 줄어들어 항공 교통 방해와 차량 교통사고를 유발할 수 있으며, 보안용 CCTV 등 의 화질을 저하시킨다. 따라서 최근 10년간 안개로 인한 피해를 줄이기 위해 안개제거 연구가 활발히 진행되고 있다. 본 연구에서는 안개가 없을 경우, 안개가 고르게 분포한 경우, 그리고 안개가 국지적으로 다른 경우에 적응적으로 대응할 수 있도록 흐릿함 농도 평가기를 이용한 가중치 생성을 통해 국부적인 안개 제거를 수행한다. 그리고 입력 영상에 안개가 있다고 가정하고 안개를 제거하는 기존의 정적인 방식의 안개제거 방법의 한계점을 개선시킨다. 또한 벤치마크 알고리즘과의 정량 및 정성적 성능 평가를 통해 제안하는 방법의 우수성을 증명한다.

• International Journal of Computer Science & Network Security
• /
• 제22권10호
• /
• pp.257-261
• /
• 2022

Diseases of agricultural plants in recent years have spread greatly across the regions of the Kyrgyz Republic and pose a serious threat to the yield of many crops. The consequences of it can greatly affect the food security for an entire country. Due to force majeure, abnormal cases in climatic conditions, the annual incomes of many farmers and agricultural producers can be destroyed locally. Along with this, the rapid detection of plant diseases also remains difficult in many parts of the regions due to the lack of necessary infrastructure. In this case, it is possible to pave the way for the diagnosis of diseases with the help of the latest achievements due to the possibilities of feedback from the farmer - developer in the formation and updating of the database of sick and healthy plants with the help of advances in computer vision, developing on the basis of machine and deep learning. Currently, model training is increasingly used already on publicly available datasets, i.e. it has become popular to build new models already on trained models. The latter is called as transfer training and is developing very quickly. Using a publicly available data set from PlantVillage, which consists of 54,306 or NewPlantVillage with a data volumed with 87,356 images of sick and healthy plant leaves collected under controlled conditions, it is possible to build a deep convolutional neural network to identify 14 types of crops and 26 diseases. At the same time, the trained model can achieve an accuracy of more than 99% on a specially selected test set.