• 농촌계획
• /
• 제28권2호
• /
• pp.87-96
• /
• 2022

As part of strengthening energy security and responding to climate change, the government has promoted various renewable energy measures to increase the development of renewable energy facilities. As a result, small-scale solar installations in rural areas have increased rapidly. The number of complaints from local residents is increasing. Therefore, in this study, deep learning technology is applied to high-resolution aerial images on the internet to detect solar power plants installed in rural areas to determine whether or not solar power plants are installed. Specifically, I examined the solar facility detector generated by training the YOLO(You Only Look Once) v2 object detector and looked at its usability. As a result, about 800 pieces of training data showed a high object detection rate of 93%. By constructing such an object detection model, it is expected that it can be utilized for land use monitoring in rural areas, and it can be utilized as a spatial data construction plan for rural areas using technology for detecting small-scale agricultural facilities.

• 전자공학회논문지 IE
• /
• 제43권2호
• /
• pp.30-38
• /
• 2006

본 논문은 비디오 객체에서 사용자의 조작 없이 실시간적으로 원하는 영상 부분을 분할해 검출할 수 있도록 MPEG-7에서 제시한 컬러 공간 분포 HMMD 모델을 이용하였다. 여기서, 얼굴 이외의 부분을 잡음으로 간주하여, 제거하기 위해 웨이브렛 형태학을 적용하였으며, 러프 집합을 통하여 최적의 합성을 하였다. 본 논문에서 제안된 비디오 객체 검출 시스템은 다양한 크기의 영상에 적용하여 얼굴 객체를 기존의 알고리즘보다 정확하게 검출함으로서 우수함을 확인하였다.

• 한국항행학회논문지
• /
• 제27권6호
• /
• pp.776-781
• /
• 2023

K-UAM은 2035년까지의 성숙기 이후 상용화될 예정이다. UAM 회랑은 기존의 헬리콥터 회랑을 수직 분리하여 사용될 예정이기에 회량 사용량이 증가할 것으로 예상된다. 따라서 회랑을 모니터링하는 시스템도 필요하다. 최근 객체 검출 알고리즘이 크게 발전하였다. 객체 검출 알고리즘은 1단계 탐지와, 2단계 탐지 모델로 나뉜다. 실시간 객체 검출에 있어서 2단계 모델은 너무 느리기에 적합하지 않다. 기존 1단계 모델은 정확도에 문제가 있었지만, 버전 업그레이드를 통해 성능이 향상되었다. 1단계 모델 중 YOLO-V5는 모자이크 기법을 통한 소형 객체 검출 성능을 향상시킨 모델이다. 따라서 YOLO-V5는 넓은 회랑의 실시간 모니터링에 가장 적합하다고 판단된다. 본 논문에서는 YOLO-V5 알고리즘을 학습시켜 궁극적으로 회랑 모니터링 시스템에 대한 적합도를 분석한다.

• 로봇학회논문지
• /
• 제15권2호
• /
• pp.184-189
• /
• 2020

This paper is a study on data augmentation for small dataset by using deep learning. In case of training a deep learning model for recognition and classification of non-mainstream objects, there is a limit to obtaining a large amount of training data. Therefore, this paper proposes a data augmentation method using perspective transform and image synthesis. In addition, it is necessary to save the object area for all training data to detect the object area. Thus, we devised a way to augment the data and save object regions at the same time. To verify the performance of the augmented data using the proposed method, an experiment was conducted to compare classification accuracy with the augmented data by the traditional method, and transfer learning was used in model learning. As experimental results, the model trained using the proposed method showed higher accuracy than the model trained using the traditional method.

• 한국멀티미디어학회논문지
• /
• 제22권2호
• /
• pp.167-177
• /
• 2019

Even though so much progresses have been achieved in Multiple Object Tracking (MOT), most of reported MOT methods are not still satisfactory for commercial embedded products like Pan-Tilt-Zoom (PTZ) camera. In this paper, we propose a real-time multiple pedestrians tracking method for embedded environments. First, we design a new light weight convolutional neural network(CNN)-based pedestrian detector, which is constructed to detect even small size pedestrians, as well. For further saving of processing time, the designed detector is applied for every other frame, and Kalman filter is employed to predict pedestrians' positions in frames where the designed CNN-based detector is not applied. The pose orientation information is incorporated to enhance object association for tracking pedestrians without further computational cost. Through experiments on Nvidia's embedded computing board, Jetson TX2, it is verified that the designed pedestrian detector detects even small size pedestrians fast and well, compared to many state-of-the-art detectors, and that the proposed tracking method can track pedestrians in real-time and show accuracy performance comparably to performances of many state-of-the-art tracking methods, which do not target for operation in embedded systems.

• 로봇학회논문지
• /
• 제19권1호
• /
• pp.79-91
• /
• 2024

Large warehouses are building automation systems to increase efficiency. However, small warehouses, military bases, and local stores are unable to introduce automated logistics systems due to lack of space and budget, and are handling tasks manually, failing to improve efficiency. To solve this problem, this study designed small loading and unloading equipment that can be mounted on transportation vehicles. The equipment can be controlled remotely and is automatically controlled from the point where pallets loaded with cargo are visible using real-time video from an attached camera. Cargo recognition and control command generation for automatic control are achieved through a newly designed deep learning model. This model is designed to be optimized for loading and unloading equipment and mission environments based on the YOLOv3 structure. The trained model recognized 10 types of palettes with different shapes and colors with an average accuracy of 100% and estimated the state with an accuracy of 99.47%. In addition, control commands were created to insert forks into pallets without failure in 14 scenarios assuming actual loading and unloading situations.

• International Journal of Advanced Culture Technology
• /
• 제10권2호
• /
• pp.300-306
• /
• 2022

Currently, Korea is building traffic infrastructure using Intelligent Transport Systems (ITS), but the pedestrian traffic accident rate is very high. The purpose of this paper is to prevent the risk of traffic accidents by jaywalking pedestrians. The development of this study aims to detect pedestrians who trespass using the public data set provided by the Artificial Intelligence Hub (AIHub). The data set uses training data: 673,150 pieces and validation data: 131,385 pieces, and the types include snow, rain, fog, etc., and there is a total of 7 types including passenger cars, small buses, large buses, trucks, large trailers, motorcycles, and pedestrians. has a class format of Learning is carried out using YOLOv5 as an implementation model, and as an object detection and edge detection method of an input image, a canny edge model is applied to classify and visualize human objects within the detected road boundary range. In this study, it was designed and implemented to detect pedestrians using the deep learning-based YOLOv5 model. As the final result, the mAP 0.5 showed a real-time detection rate of 61% and 114.9 fps at 338 epochs using the YOLOv5 model.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 추계학술대회
• /
• pp.385-387
• /
• 2021

해양 침적 쓰레기는 저서 생태계를 위협하고 유령어업으로 인한 어획량 감소를 초래하여 연간 약 3,700억 원의 피해를 발생시키고 있다. 이를 수거하기 위해서 현재 양방향 음파탐지기와 잠수, 인양틀 등을 이용하여 현황조사를 수행한다. 하지만, 많은 침적 쓰레기를 조사하기엔 조사범위가 적고 인명피해를 불러올 가능성이 있다. 본 논문에서는 실시간 객체 탐지에 적합한 YOLOv5 알고리즘을 활용하여 AI-Hub의 해안 침적 쓰레기 이미지 데이터를 학습시켜 높은 정확도의 해양 침적 쓰레기 감지 인공지능 모델을 구현한 내용을 다룬다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2018년도 춘계학술발표대회
• /
• pp.352-353
• /
• 2018

Many deep learning approaches are studied for face detection in these days. However, there is still a performance problem to run efficiently on devices with limited resources. Our method can enhance the detection speed by decreasing the number of scaling for detection methods that use many different scaling per image to detect the different size of faces. Also, we keep our deep learning model easy to implement and small as possible. Moreover, it can be used for other special object detection problems but not only for face detection.

• 한국인터넷방송통신학회논문지
• /
• 제20권1호
• /
• pp.219-223
• /
• 2020

딥 러닝 기반 객체 탐지 및 영상처리 분야에서 모델의 인식률과 정확도를 보장하기 위해 다량의 데이터 확보는 필수적이다. 본 논문에서는 학습데이터가 적은 경우에도 인공지능 모델의 높은 성능을 도출하기 위해 전이학습 기반 객체탐지 알고리즘을 제안한다. 본 논문에서는 객체탐지를 위해 사전 학습된 Resnet-50 네트워크와 YOLO(You Only Look Once) 네트워크를 결합한 전이학습 네트워크를 구성하였다. 구성된 전이학습 네트워크는 Leeds Sports Pose 데이터셋의 일부를 활용하여 이미지에서 가장 넓은 영역을 차지하고 있는 사람을 탐지하는 네트워크로 학습을 진행하였다. 실험결과는 탐지율 84%, 탐지 정확도 97%를 기록하였다.