• International Journal of Advanced Culture Technology
• /
• v.9 no.4
• /
• pp.260-267
• /
• 2021

In this paper, we intend to use a new mixed model of YoloV5 and DeepSort. For fire detection, we want to increase the accuracy by automatically extracting the characteristics of the flame in the image from the training data and using it. In addition, the high false alarm rate, which is a problem of fire detection, is to be solved by using this new mixed model. To confirm the results of this paper, we tested indoors and outdoors, respectively. Looking at the indoor test results, the accuracy of YoloV5 was 75% at 253Frame and 77% at 527Frame, and the YoloV5+DeepSort model showed the same accuracy at 75% at 253 frames and 77% at 527 frames. However, it was confirmed that the smoke and fire detection errors that appeared in YoloV5 disappeared. In addition, as a result of outdoor testing, the YoloV5 model had an accuracy of 75% in detecting fire, but an error in detecting a human face as smoke appeared. However, as a result of applying the YoloV5+DeepSort model, it appeared the same as YoloV5 with an accuracy of 75%, but it was confirmed that the false positive phenomenon disappeared.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.75-78
• /
• 2023

본 논문은 객체탐지 모델 중 주류를 이루고 있는 YOLO의 v1부터 v8까지의 특성을 비교 분석하여 각각의 버전에 최적화할 수 있는 모델에 대한 연구이다. 연구 결과 v1, v2는 정확성이 최우선인 모델에 적합하다. 반면, v3, v4는 속도가 우선인 모델에 적합하다. 또한 v5, v6는 정확도와 속도 사이의 균형이 필요한 모델에 적합하다는 결론을 얻었다. v7, v8은 메모리 및 컴퓨팅 성능에 제약이 있는 경우 주로 적용이 가능하며, 적은 연산과 저 메모리 사용으로 객체를 탐지하여 포즈추정이나 객체 추적 등을 적용할 모델에 적합하다는 결과를 확인하였다.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.115-124
• /
• 2022

In this paper, YOLO and EAST models are tested to analyze their performance in text area detecting for real-world and normal text images. The earl ier YOLO models which include YOLOv3 have been known to underperform in detecting text areas for given images, but the recently released YOLOv4 and YOLOv5 achieved promising performances to detect text area included in various images. Experimental results show that both of YOLO v4 and v5 models are expected to be widely used for text detection in the filed of scene text recognition in the future.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.3
• /
• pp.98-110
• /
• 2018

In this paper, we propose both Dense grid model and Anchor model to improve the recognition rate of dynamic objects. Two experiments are conducted to study the performance of two proposed CNNs models (Dense grid model and Anchor model), which are to detect dynamic objects. In the first experiment, YOLO-v2 network is adjusted, and then fine-tuned on KITTI datasets. The Dense grid model and Anchor model are then compared with YOLO-v2. Regarding to the evaluation, the two models outperform YOLO-v2 from 6.26% to 10.99% on car detection at different difficulty levels. In the second experiment, this paper conducted further training of the models on a new dataset. The two models outperform YOLO-v2 up to 22.40% on car detection at different difficulty levels.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.1
• /
• pp.36-43
• /
• 2021

In this research, the accuracy of YOLO v3 algorithm in object detection during AGV (Automated Guided Vehicle) operation was investigated. First of all, AGV with 2D LiDAR and stereo camera was prepared. AGV was driven along the route scanned with SLAM (Simultaneous Localization and Mapping) using 2D LiDAR while front objects were detected through stereo camera. In order to evaluate the accuracy of YOLO v3 algorithm, recall, AP (Average Precision), and mAP (mean Average Precision) of the algorithm were measured with a degree of machine learning. Experimental results show that mAP, precision, and recall are improved by 10%, 6.8%, and 16.4%, respectively, when YOLO v3 is fitted with 4000 training dataset and 500 testing dataset which were collected through online search and is trained additionally with 1200 dataset collected from the stereo camera on AGV.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.285-286
• /
• 2020

전 세계적으로 유행하는 COVID-19(코로나19)로 인해 사람들은 대면 접촉을 피하게 되었고, 전염성이 높은 이유로 마스크의 착용이 의무화되고 있고, 이를 검사하는 업무가 증가하고 있다. 그래서, 인공지능 기술을 통해 업무를 도와줄 수 있는 출입자 통계와 출입자 마스크 착용 검사를 할 수 있는 시스템이 필요하다. 이를 위해 본 논문에서는 딥러닝 알고리즘을 활용한 출입자 통계와 마스크 착용 판별 시스템을 제시한다. 또한, 실시간 영상인식에 많이 활용되고 있는 YOLO-v3와 YOLO-v4, YOLO-Tiny 알고리즘을 데스크탑 PC와 Nvidia사의 Jetson Nano에 적용하여 알고리즘별 성능 비교를 통해 적합한 방법을 찾고 적용하였다.

• Smart Media Journal
• /
• v.11 no.4
• /
• pp.46-55
• /
• 2022

It is very important to first detect and remove defective fruits with scratches or bruised areas in the automatic fruit quality screening system. This paper proposes a method of detecting defective areas in fruits using the latest artificial intelligence technology, the Yolo V4 deep learning model in order to overcome the limitations of the method of detecting fruit's defective areas using the existing image processing techniques. In this study, a total of 2,400 defective fruits, including 1,000 defective apples and 1,400 defective fruits with scratch or decayed areas, were learned using the Yolo V4 deep learning model and experiments were conducted to detect defective areas. As a result of the performance test, the precision of apples is 0.80, recall is 0.76, IoU is 69.92% and mAP is 65.27%. The precision of pears is 0.86, recall is 0.81, IoU is 70.54% and mAP is 68.75%. The method proposed in this study can dramatically improve the performance of the existing automatic fruit quality screening system by accurately selecting fruits with defective areas in real time rather than using the existing image processing techniques.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.1
• /
• pp.141-148
• /
• 2021

In some intersections or busy traffic roads, there are more pedestrians in a specific period of time, and there are many traffic accidents caused by road congestion. Especially at the intersection where there are schools nearby, it is particularly important to protect the traffic safety of students in busy hours. In the past, when designing traffic lights, the safety of pedestrians was seldom taken into account, and the identification of motor vehicles and traffic optimization were mostly studied. How to keep the road smooth as far as possible under the premise of ensuring the safety of pedestrians, especially students, will be the key research direction of this paper. This paper will focus on person, motorcycle, bicycle, car and bus recognition research. Through investigation and comparison, this paper proposes to use YOLO v4 network to identify the location and quantity of objects. YOLO v4 has the characteristics of strong ability of small target recognition, high precision and fast processing speed, and sets the data acquisition object to train and test the image set. Using the statistics of the accuracy rate, error rate and omission rate of the target in the video, the network trained in this paper can accurately and effectively identify persons, motorcycles, bicycles, cars and buses in the moving images.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.7
• /
• pp.890-895
• /
• 2021

Recently, the "Act of Serious Disasters, etc" was enacted and institutional and social interest in safety accidents is increasing. In this paper, we analyze statistical data published by government agency on safety accidents that occur in manufacturing sites, and compare various object detection models based on deep learning to build a model to determine dangerous situations to reduce the occurrence of safety accidents. The data-set was directly constructed by collecting images from CCTVs at the manufacturing site, and the YOLO-v4, SSD, CenterNet models were used as training data and evaluation data for learning. As a result, the YOLO-v4 model obtained a value of 81% of mAP. It is meaningful to select a class in an industrial field and directly build a dataset to learn a model, and it is thought that it can be used as an initial research data for a system that determines a risk situation and infers it.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.332-334
• /
• 2021

As fatal accidents due to industrial accidents and deaths due to civil accidents were pointed out as social problems, the Act on Punishment of Serious Accidents Occurred in the Workplace was enacted to ensure the safety of citizens and to prevent serious accidents in advance. Effort is required. In this paper, we propose a distance prediction model in relation to the case where an operator is hit by heavy equipment such as a forklift. For the data, actual forklift trucks and workers roaming environments were directly captured by CCTV, and it was conducted based on the Euclidean distance. It is thought that it will be possible to learn YOLO-v4 by directly building a data-set at the industrial site, and then implement a model that predicts the distance and determines whether it is a dangerous situation, which can be used as basic data for a comprehensive risk situation judgment model.