• Journal of information and communication convergence engineering
• /
• 제21권1호
• /
• pp.98-102
• /
• 2023

This paper presents a study on how augmenting semi-synthetic image data improves the performance of human detection algorithms. In the field of object detection, securing a high-quality data set plays the most important role in training deep learning algorithms. Recently, the acquisition of real image data has become time consuming and expensive; therefore, research using synthesized data has been conducted. Synthetic data haves the advantage of being able to generate a vast amount of data and accurately label it. However, the utility of synthetic data in human detection has not yet been demonstrated. Therefore, we use You Only Look Once (YOLO), the object detection algorithm most commonly used, to experimentally analyze the effect of synthetic data augmentation on human detection performance. As a result of training YOLO using the Penn-Fudan dataset, it was shown that the YOLO network model trained on a dataset augmented with synthetic data provided high-performance results in terms of the Precision-Recall Curve and F1-Confidence Curve.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2021년도 춘계학술발표대회
• /
• pp.556-559
• /
• 2021

해당 연구는 Insta evo 360° 카메라로 촬영한 Equirectangular 형태의 영상을 활용하여 보행자에게 위험한 차량을 구분한 후 실시간적으로 차량 접근 알림을 주는 시스템에 관한 연구이다. 360° 영상 속 위험 차량 탐지와 추적을 위해 파노라마와 일반도로 이미지 데이터 세트로 전이학습 된 You Look Only Once v5 (YOLOv5), 객체 추적 알고리즘 Simple Online and Realtime Tracking with a Deep Association Metric (DeepSORT), 그리고 실험을 통해 개발한 비 위험 차량 필터링 알고리즘을 활용한다. Insta evo 360° 카메라를 머리 위에 얹어 촬영한 영상을 개발한 최종 시스템에 적용한 결과, 약 90% 정확도로 영상에서 비 위험 차량과 위험 차량을 구분할 수 있고, 위험 차량의 경우 차량의 방향을 시각적으로 알려줄 수 있다. 본 연구를 바탕으로 보행자 시야각 외부의 위험 차량에 대한 경고 알림을 주어 보행자 교통사고 발생 가능성을 줄이고, 전방위를 볼 수 있는 360° 카메라의 활용 분야가 보행 안전 시스템뿐만 아니라 더 다양해질 것으로 기대한다.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2022년도 제65차 동계학술대회논문집 30권1호
• /
• pp.17-18
• /
• 2022

현재 국내에서는 1인 1스마트폰 시대를 맞이하게 되었고 이에 맞춰 많은 종류의 관련 산업들이 발전하고 있다. 특히 멀티미디어와 콘텐츠 산업 또한 크게 성장하고 있다. 이런 상황에서 필수적으로 사용되는 편집 기술을 위하여, 많은 소프트웨어가 등장하고 이용되고 있다. 편집을 자유롭게 이용하기 위해서는 전문적인 인력이 필요하거나 시간이나 자본을 들여서 이해와 학습을 필수적으로 해야 한다. 본 논문에서는 이러한 편집 과정의 수고로움을 덜어줄 수 있도록 인공지능의 객체탐지 기술을 이용하여 특정 상표에 대한 모자이크 처리 작업을 자동으로 할 수 있는 B.A.M.O.S를 개발하였다. YOLO 알고리즘을 이용하여 목표 상표를 학습시켜 이를 B.A.M.O.S에 적용하였고, 목표 상표를 인식하여 모자이크 처리를 하도록 하였다.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2022년도 제65차 동계학술대회논문집 30권1호
• /
• pp.323-324
• /
• 2022

본 논문에서는 사람의 개입 없이 실내 환경에서 마스크 미 착용자를 스스로 발견한 후 방역수칙위반 사실에 대한 경고와 함께 마스크 착용을 권고하는 인공지능 기반의 자율주행 서비스 로봇을 개발한다. 제안한 시스템에서 로봇은 동시적 위치 추적 지도 작성 기법인 SLAM(Simultaneous Localization and Mapping)기술을 이용하여 지도를 작성한 후 사용자가 제공한 웨이포인트(Waypoint)를 기반으로 자율주행한다. 또한, YOLO(You Only Look Once) 알고리즘을 이용한 실시간 객체 인식 기술을 활용하여 보행자의 마스크 착용 여부를 판단한다. 실험을 통해 사전에 작성된 지도에 지정된 웨이포인트를 따라 로봇이 자율주행하는 것을 확인하였다. 또한, 충전소로 이동할 경우, 영상 처리 기법을 활용하여 충전소에 부착된 표식에 근접하도록 이동하여 충전이 진행됨을 확인하였다.

• Smart Structures and Systems
• /
• 제32권5호
• /
• pp.309-318
• /
• 2023

The appropriate maintenance of highway roads is critical for the safe operation of road networks and conserves maintenance costs. Multiple methods have been developed to investigate the surface of roads for various types of cracks and potholes, among other damage. Like road surface damage, the condition of expansion joints in concrete pavement is important to avoid unexpected hazardous situations. Thus, in this study, a new system is proposed for autonomous expansion joint monitoring using a vision-based system. The system consists of the following three key parts: (1) a camera-mounted vehicle, (2) indication marks on the expansion joints, and (3) a deep learning-based automatic evaluation algorithm. With paired marks indicating the expansion joints in a concrete pavement, they can be automatically detected. An inspection vehicle is equipped with an action camera that acquires images of the expansion joints in the road. You Only Look Once (YOLO) automatically detects the expansion joints with indication marks, which has a performance accuracy of 95%. The width of the detected expansion joint is calculated using an image processing algorithm. Based on the calculated width, the expansion joint is classified into the following two types: normal and dangerous. The obtained results demonstrate that the proposed system is very efficient in terms of speed and accuracy.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 추계학술발표대회
• /
• pp.579-580
• /
• 2023

본 논문에서는 동물의 십자인대 질환의 진단지표인 경골고원각도(TPA)를 자동으로 측정하는 딥러닝 소프트웨어 기법을 제안한다. 동물 X-ray 영상에서 나타나는 피사체의 위치와 형태에 대한 다양한 변이는 TPA(Tibial Plateau Angle) 지표 산출에 필요한 특징점 검출과정에서 학습 효율을 현저하게 저하시킨다. 이에 본 연구에서는 YOLO(You Only Look Once) 기반 모델을 사용하여 일차적으로 경골영역의 분할 단계를 수행하고, 이어서 경골 상단부의 과간융기와 복사뼈의 중심점을 찾는 과정을 Resnet 기반의 특징점 추출 모듈로서 구현함으로써 학습의 효율과 지표 검출의 정확도를 향상시켰다. 총 201 개의 실제 X-ray 영상을 사용하여 학습 속도와 영역 분할 및 특징점 추출의 정확도 측면을 고려함으로 제안된 이론의 타당성을 실험적으로 평가하였다.

• International journal of advanced smart convergence
• /
• 제12권4호
• /
• pp.182-189
• /
• 2023

A recently research, object detection and segmentation have emerged as crucial technologies widely utilized in various fields such as autonomous driving systems, surveillance and image editing. This paper proposes a program that utilizes the QT framework to perform real-time object detection and precise instance segmentation by integrating YOLO(You Only Look Once) and Mask R CNN. This system provides users with a diverse image editing environment, offering features such as selecting specific modes, drawing masks, inspecting detailed image information and employing various image processing techniques, including those based on deep learning. The program advantage the efficiency of YOLO to enable fast and accurate object detection, providing information about bounding boxes. Additionally, it performs precise segmentation using the functionalities of Mask R CNN, allowing users to accurately distinguish and edit objects within images. The QT interface ensures an intuitive and user-friendly environment for program control and enhancing accessibility. Through experiments and evaluations, our proposed system has been demonstrated to be effective in various scenarios. This program provides convenience and powerful image processing and editing capabilities to both beginners and experts, smoothly integrating computer vision technology. This paper contributes to the growth of the computer vision application field and showing the potential to integrate various image processing algorithms on a user-friendly platform

• International Journal of Computer Science & Network Security
• /
• 제24권5호
• /
• pp.53-63
• /
• 2024

Alzheimer's disease is a brain disorder that worsens over time and affects millions of people around the world. It leads to a gradual deterioration in memory, thinking ability, and behavioral and social skills until the person loses his ability to adapt to society. Technological progress in medical imaging and the use of artificial intelligence, has provided the possibility of detecting Alzheimer's disease through medical images such as magnetic resonance imaging (MRI). However, Deep learning algorithms, especially convolutional neural networks (CNNs), have shown great success in analyzing medical images for disease diagnosis and classification. Where CNNs can recognize patterns and objects from images, which makes them ideally suited for this study. In this paper, we proposed to compare the performances of Alzheimer's disease detection by using two deep learning methods: You Only Look Once (YOLO), a CNN-enabled object recognition algorithm, and Visual Geometry Group (VGG16) which is a type of deep convolutional neural network primarily used for image classification. We will compare our results using these modern models Instead of using CNN only like the previous research. In addition, the results showed different levels of accuracy for the various versions of YOLO and the VGG16 model. YOLO v5 reached 56.4% accuracy at 50 epochs and 61.5% accuracy at 100 epochs. YOLO v8, which is for classification, reached 84% accuracy overall at 100 epochs. YOLO v9, which is for object detection overall accuracy of 84.6%. The VGG16 model reached 99% accuracy for training after 25 epochs but only 78% accuracy for testing. Hence, the best model overall is YOLO v9, with the highest overall accuracy of 86.1%.

• 한국산업융합학회 논문집
• /
• 제24권6_2호
• /
• pp.699-706
• /
• 2021

Existing license plate recognition system is used as an optical character recognition method, but a method of using deep learning has been proposed in recent studies because it has problems with image quality and Korean misrecognition. This requires a lot of data collection, but the collection of license plates is not easy to collect due to the problem of the Personal Information Protection Act, and labeling work to designate the location of individual license plates is required, but it also requires a lot of time. Therefore, in this paper, to solve this problem, five types of license plates were created using a virtual Korean license plate generation program according to the notice of the Ministry of Land, Infrastructure and Transport. And the generated license plate is synthesized in the license plate part of collectable vehicle images to construct 10,147 learning data to be used in deep learning. The learning data classifies license plates, Korean, and numbers into individual classes and learn using YOLOv5. Since the proposed method recognizes letters and numbers individually, if the font does not change, it can be recognized even if the license plate standard changes or the number of characters increases. As a result of the experiment, an accuracy of 96.82% was obtained, and it can be applied not only to the learned license plate but also to new types of license plates such as new license plates and eco-friendly license plates.

• Journal of Animal Science and Technology
• /
• 제63권6호
• /
• pp.1453-1463
• /
• 2021

Feeding is the most important behavior that represents the health and welfare of weanling pigs. The early detection of feed refusal is crucial for the control of disease in the initial stages and the detection of empty feeders for adding feed in a timely manner. This paper proposes a real-time technique for the detection and recognition of small pigs using a deep-leaning-based method. The proposed model focuses on detecting pigs on a feeder in a feeding position. Conventional methods detect pigs and then classify them into different behavior gestures. In contrast, in the proposed method, these two tasks are combined into a single process to detect only feeding behavior to increase the speed of detection. Considering the significant differences between pig behaviors at different sizes, adaptive adjustments are introduced into a you-only-look-once (YOLO) model, including an angle optimization strategy between the head and body for detecting a head in a feeder. According to experimental results, this method can detect the feeding behavior of pigs and screen non-feeding positions with 95.66%, 94.22%, and 96.56% average precision (AP) at an intersection over union (IoU) threshold of 0.5 for YOLOv3, YOLOv4, and an additional layer and with the proposed activation function, respectively. Drinking behavior was detected with 86.86%, 89.16%, and 86.41% AP at a 0.5 IoU threshold for YOLOv3, YOLOv4, and the proposed activation function, respectively. In terms of detection and classification, the results of our study demonstrate that the proposed method yields higher precision and recall compared to conventional methods.