• Journal of Korea Multimedia Society
• /
• v.24 no.7
• /
• pp.890-902
• /
• 2021

Although the object detection accuracy with still images has been significantly improved with the advance of deep learning techniques, the object detection problem with video data remains as a challenging problem due to the real-time requirement and accuracy drop with occlusion. In this research, we propose a method in pig detection for video monitoring environment. First, we determine a motion, from a video data obtained from a tilted-down-view camera, based on the average size of each pig at each location with the training data, and extract key frames based on the motion information. For each key frame, we then apply YOLO, which is known to have a superior trade-off between accuracy and execution speed among many deep learning-based object detectors, in order to get pig's bounding boxes. Finally, we merge the bounding boxes between consecutive key frames in order to reduce false positive and negative cases. Based on the experiment results with a video data set obtained from a pig farm, we confirmed that the pigs could be detected with an accuracy of 97% at a processing speed of 37fps.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.251-252
• /
• 2019

본 논문에서는 기존의 AGV보다 높은 안전성과 Task Scheduling을 바탕으로 한 효율적인 AGV를 제안하였다. AGV는 객체인식 알고리즘인 YOLO로 다른 AGV를 인식하여 자동으로 피난처로 들어간다. 또한 마커인식 알고리즘인 ar_markers를 이용하여 그 위치가 적재소인지 생산 공정인지를 판단하여 각 마커마다 멈추고 피난처에 해당하는 Marker가 인식되고 다른 AGV가 인식되면 피난처로 들어가는 동작을 한다. 이 모든 로그는 Mobius를 이용해 Spring기반의 웹 홈페이지로 확인할 수 있으며, 작업스케줄 명령 또한 웹 홈페이지에서 내리게 된다. 위 작업스케줄은 외판원, 벨만-포드 알고리즘을 적용한 뒤 강화학습알고리즘 중 하나인 DQN을 이용해 최적 값을 도출해 내고 그 값을 DB에 저장해 AGV가 움직일 수 있도록 한다. 본 논문에서는 YOLO와 Marker 그리고 웹을 사용하는 AGV가 기존의 AGV에 비해 더욱 가볍고 큰 시설이 필요하지 않다는 점에서 우수함을 보인다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.317-318
• /
• 2019

가상/증강현실로 대표되는 공간정보 기반 실감형 콘텐츠에 대한 관심이 증대되면서 객체인식 등의 지능형 공간인지 기술에 대한 연구가 활발히 진행되고 있다. 특히 HMD등의 영상 시각화 장치의 발달 및 5G 통신기술의 출현으로 인해 실시간 대용량 영상정보의 송, 수신 및 가시화 처리 기술의 기반이 구축됨에 따라, $360^{\circ}$ 스트리밍 영상정보 처리와 같은 고자유도 콘텐츠를 위한 관련 연구의 필요성이 증대되고 있다. 하지만 지능형 영상정보 처리의 대표적 연구인 딥 러닝(Deep Learning) 기반 객체 인식 기술의 경우 대부분 일반적인 평면 영상(Planar Image)에 대한 처리를 다루고 있고, 파노라마 영상(Panorama Image) 특히, $360^{\circ}$ 스트리밍 영상 처리를 위한 연구는 미비한 상황이다. 본 논문에서는 딥 러닝을 이용하여 $360^{\circ}$ 스트리밍 영상에서의 객체인식 연구 방법에 대해 서술한다. 이를 위해 $360^{\circ}$ 카메라 영상에서 딥 러닝을 위한 학습 데이터를 획득하고, 실시간 객체 인식이 가능한 YOLO(You Only Look Once)기법을 이용하여 학습을 한다. 실험 결과에서는 학습 데이터를 이용하여 $360^{\circ}$영상에서 객체 인식 결과와, 학습 횟수에 따른 객체 인식에 대한 결과를 보여준다.

• Journal of Korea Multimedia Society
• /
• v.22 no.3
• /
• pp.349-356
• /
• 2019

When a prescription change occurs in the hospital depending on a patient's improvement status, pharmacists directly classify manually returned pills which are not taken by a patient. There are hundreds of kinds of pills to classify. Because it is manual, mistakes can occur and which can lead to medical accidents. In this study, we have compared YOLO, Faster R-CNN and RetinaNet to classify and detect pills. The data consisted of 10 classes and used 100 images per class. To evaluate the performance of each model, we used cross-validation. As a result, the YOLO Model had sensitivity of 91.05%, FPs/image of 0.0507. The Faster R-CNN's sensitivity was 99.6% and FPs/image was 0.0089. The RetinaNet showed sensitivity of 98.31% and FPs/image of 0.0119. Faster RCNN showed the best performance among these three models tested. Thus, the most appropriate model for classifying pills among the three models is the Faster R-CNN with the most accurate detection and classification results and a low FP/image.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.12
• /
• pp.4816-4834
• /
• 2020

This paper proposes transfer learning and fine-tuning techniques for a deep learning model to detect three distinct brain tumors from Magnetic Resonance Imaging (MRI) scans. In this work, the recent YOLOv4 model trained using a collection of 3064 T1-weighted Contrast-Enhanced (CE)-MRI scans that were pre-processed and labeled for the task. This work trained with the partial 29-layer YOLOv4-Tiny and fine-tuned to work optimally and run efficiently in most platforms with reliable performance. With the help of transfer learning, the model had initial leverage to train faster with pre-trained weights from the COCO dataset, generating a robust set of features required for brain tumor detection. The results yielded the highest mean average precision of 93.14%, a 90.34% precision, 88.58% recall, and 89.45% F1-Score outperforming other previous versions of the YOLO detection models and other studies that used bounding box detections for the same task like Faster R-CNN. As concluded, the YOLOv4-Tiny can work efficiently to detect brain tumors automatically at a rapid phase with the help of proper fine-tuning and transfer learning. This work contributes mainly to assist medical experts in the diagnostic process of brain tumors.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.3
• /
• pp.167-175
• /
• 2022

With the recent expansion of electric kickboards and bicycle sharing services, more and more people use them. In addition, the rapid growth of the delivery business due to the COVID-19 has significantly increased the use of two-wheeled vehicles and personal mobility. As the accident rate increases, the rule related to the two-wheeled vehicles is changed to 'mandatory helmets for kickboards and single-person transportation' and was revised to prevent boarding itself without driver's license. In this paper, we propose a wearable smart safety equipment, called SafetyHelmet, that can keep helmet-wearing duty and lower the accident rate with the communication between helmets and mobile devices. To make this function available, we propose a safe driving assistance function by notifying the driver when an object that interferes with driving such as persons or other vehicles are detected by applying the YOLO v5 object detection algorithm. Therefore it is intended to provide a safer driving assistance by reducing the failure rate to identify dangers while driving single-person transportation.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.20 no.12
• /
• pp.1-7
• /
• 2021

The deep learning image processing technique was used to prevent accidents in lathe work caused by worker negligence. During lathe operation, when the chuck is rotated, it is very dangerous if the operator's hand is near the chuck. However, if the chuck is stopped during operation, it is not dangerous for the operator's hand to be in close proximity to the chuck for workpiece measurement, chip removal or tool change. We used YOLO (You Only Look Once), a deep learning image processing program for object detection and classification. Lathe work images such as hand, chuck rotation and chuck stop are used for learning, object detection and classification. As a result of the experiment, object detection and class classification were performed with a success probability of over 80% at a confidence score 0.5. Thus, we conclude that the artificial intelligence deep learning image processing technique can be effective in preventing incidents resulting from worker negligence in future manufacturing systems.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.01a
• /
• 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.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.01a
• /
• 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.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.3
• /
• pp.275-284
• /
• 2023

Land monitoring involves systematically understanding changes in land use, leveraging spatial information such as satellite imagery and aerial photographs. Recently, the integration of deep learning technologies, notably object detection and semantic segmentation, into land monitoring has spurred active research. This study developed a web service to facilitate such integrations, allowing users to analyze aerial and drone images using CNN models. The web service architecture comprises AI, WEB/WAS, and DB servers and employs three primary deep learning models: DeepLab V3, YOLO, and Rotated Mask R-CNN. Specifically, YOLO offers rapid detection capabilities, Rotated Mask R-CNN excels in detecting rotated objects, while DeepLab V3 provides pixel-wise image classification. The performance of these models fluctuates depending on the quantity and quality of the training data. Anticipated to be integrated into the LX Corporation's operational network and the Land-XI system, this service is expected to enhance the accuracy and efficiency of land monitoring.