• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.1161-1162
• /
• 2023

모바일 로봇의 자율주행을 위하여 인터넷이 제약된 환경에서도 가능한 Edge computing 에서의 Object Detection 이 필수적이다. 본 논문에서는 이를 위해 Orin 보드에서 YOLOv7 과 Complex_YOLOv4 를 구현하였다. 직접 취득한 데이터를 통해 YOLOv7 을 구현한 결과 0.56 의 mAP 로 프레임당 133ms 가 소요되었다. Kitti Dataset 을 통해 Complex_YOLOv4 를 구현한 결과 0.88 의 mAP 로 프레임당 236ms 가 소요되었다. Comple_YOLOv4 가 YOLOv7 보다 더 많은 데이터를 예측하기에 시간은 더 소요되지만 높은 정확성을 가지는 것을 확인할 수 있었다.

• Journal of IKEEE
• /
• v.25 no.4
• /
• pp.750-755
• /
• 2021

This paper proposes techniques for detecting the damage status of each part of a vehicle using YOLOv4. The proposed algorithm learns the parts and their damages of the vehicle through YOLOv4, extracts the coordinate information of the detected bounding boxes, and applies the algorithm to determine the relationship between the damage and the vehicle part to derive the damage status for each part. In addition, the technique using VGGNet, the technique using image segmentation and U-Net model, and Weproove.AI deep learning model, etc. are included for objectivity of performance comparison. Through this, the performance of the proposed algorithm is compared and evaluated, and a method to improve the detection model is proposed.

• International journal of advanced smart convergence
• /
• v.11 no.2
• /
• pp.22-29
• /
• 2022

In this paper, for the purpose of designing an real-time unmanned monitoring system, the YOLOv5s (small) object detection model was applied on the NVIDIA TX2^TM AI (Artificial Intelligence) edge computing platform in order to design the fundamental function of an unmanned monitoring system that can detect objects in real time. YOLOv5s was applied to the our real-time unmanned monitoring system based on the performance evaluation of object detection algorithms (for example, R-CNN, SSD, RetinaNet, and YOLOv5). In addition, the performance of the four YOLOv5 models (small, medium, large, and xlarge) was compared and evaluated. Furthermore, based on these results, the YOLOv5s model suitable for the design purpose of this paper was ported to the NVIDIA TX2^TM AI edge computing system and it was confirmed that it operates normally. The real-time unmanned monitoring system designed as a result of the research can be applied to various application fields such as an security or monitoring system. Future research is to apply NMS (Non-Maximum Suppression) modification, model reconstruction, and parallel processing programming techniques using CUDA (Compute Unified Device Architecture) for the improvement of object detection speed and performance.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.5
• /
• pp.443-461
• /
• 2022

Target Detection in synthetic aperture radar(SAR) image is critical for military and national defense. In this paper, we propose YOLOv4-Attention architecture which adds attention modules to YOLOv4 backbone architecture to complement the feature extraction ability for SAR target detection with high accuracy. For training and testing our framework, we present new SAR embedding datasets based on MSTAR SAR public datasets which are about poor environments for target detection such as various clutter, crowded objects, various object size, close to buildings, and weakness of signal-to-clutter ratio. Experiments show that our Attention YOLOv4 architecture outperforms original YOLOv4 architecture in SAR image target detection tasks in poor environments for target detection.

• Journal of Cadastre & Land InformatiX
• /
• v.52 no.1
• /
• pp.81-93
• /
• 2022

Recently, there have been many studies on object recognition around the vehicle and recognition of traffic signs and traffic lights in autonomous driving. In particular, such the recognition of traffic lights is one of the core technologies in autonomous driving. Therefore, many studies for such the recognition of traffic lights have been performed, the studies based on various deep learning models have increased significantly in recent. In addition, as a high-quality AI training data set for voice, vision, and autonomous driving is released on AIHub, it makes it possible to develop a recognition model for traffic lights suitable for the domestic environment using the data set. In this study, we developed a recognition model for traffic lights that can be used in Korea using the AIHub's training data set. In particular, in order to improve the recognition performance, we used various models of YOLOv4 and YOLOv5, and performed our recognition experiments by defining various classes for the training data. In conclusion, we could see that YOLOv5 shows better performance in the recognition than YOLOv4 and could confirm the reason from the architecture comparison of the two models.

• Journal of Korean Society on Water Environment
• /
• v.37 no.4
• /
• pp.275-285
• /
• 2021

Algal bloom is an important issue in maintaining the safety of the drinking water supply system. Fast detection and classification of algae images are essential for the management of algal blooms. Conventional visual identification using a microscope is a labor-intensive and time-consuming method that often requires several hours to several days in order to obtain analysis results from field water samples. In recent decades, various deep learning algorithms have been developed and widely used in object detection studies. YOLO is a state-of-the-art deep learning algorithm. In this study the third version of the YOLO algorithm, namely, YOLOv3, was used to develop an algae image detection model. YOLOv3 is one of the most representative one-stage object detection algorithms with faster inference time, which is an important benefit of YOLO. A total of 1,114 algae images for 30 genera collected by microscope were used to develop the YOLOv3 algae image detection model. The algae images were divided into four groups with five, 10, 20, and 30 genera for training and testing the model. The mean average precision (mAP) was 81, 70, 52, and 41 for data sets with five, 10, 20, and 30 genera, respectively. The precision was higher than 0.8 for all four image groups. These results show the practical applicability of the deep learning algorithm, YOLOv3, for algae image detection.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.4
• /
• pp.771-780
• /
• 2024

In this study, we implemented a real-time pest detection and prediction system for a strawberry farm using a computer vision model based on the YOLOv5 architecture and an Isolation Forest Classifier. The model performance evaluation showed that the YOLOv5 model achieved a mean average precision (mAP 0.5) of 78.7%, an accuracy of 92.8%, a recall of 90.0%, and an F1-score of 76%, indicating high predictive performance. This system was designed to be applicable not only to strawberry farms but also to other crops and various environments. Based on data collected from a tomato farm, a new AI model was trained, resulting in a prediction accuracy of over 85% for major diseases such as late blight and yellow leaf curl virus. Compared to the previous model, this represented an improvement of more than 10% in prediction accuracy.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.154-155
• /
• 2023

오픈 소스인 YOLO(You Only Look Once) 객체 탐지 알고리즘이 공개된 이후, 산업 현장에서는 고성능 컴퓨터에서 벗어나 효율과 특수한 환경에 사용하기 위해 임베디드 시스템에 도입하고 있다. 그러나, NVIDIA의 Jetson nano의 경우, Pytorch의 YOLOv7 딥러닝 모델에 대한 추론이 진행되지 않는다. 따라서 제한적인 전력과 메모리, 연산능력 최적화 과정은 필수적이다. 본 논문은 NVIDIA의 임베디드 플랫폼 Jetson 계열의 Xavier NX, Orin AGX, Nano에서 딥러닝 모델을 적용하기 위한 최적화 과정과 플랫폼에서 다양한 크기의 YOLOv7의 PyTorch 모델들을 Tensor RT로 변환하여 FPS(Frames Per Second)를 측정 및 비교한다. 측정 결과를 통해, 각 임베디드 플랫폼에서 YOLOv7 모델의 추론은 Tensor RT는 Pytorch에서 약 4.1배 적은 FPS 변동성과 약 2.25배 정도의 FPS 속도향상을 보였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.1215-1217
• /
• 2023

가정에서 대형 폐기물을 배출하고 수거하는 과정에서 폐기물을 수동적으로 분류를 하는 것은 시간이 많이 소요되는 작업이다. 본 논문에서는 YOLOv4, 5, 7 모델을 비교하여 실생활에 사용가능한 대형 폐기물 탐지에 가장 적합한 모델을 찾는다. 이미지 증강 전 결과는 YOLOv7이 가장 좋은 성능을 보였다. 배출자가 촬영하는 각도나 위치, 시간 등의 변수를 고려하고자 증강을 시도하였고 증강 후 탐지 결과도 YOLOv7이 F1-score 93 %, mAP 96.6% 로 다른 모델보다 전체적으로 더 좋은 성능을 보였다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.6
• /
• pp.157-165
• /
• 2020

Aiming at the development of neural network and self-driving data set, it is also an idea to improve the performance of network model to detect moving objects by dividing the data set. In Darknet network framework, the YOLOv4 (You Only Look Once v4) network model was used to train and test Udacity data set. According to 7 proportions of the Udacity data set, it was divided into three subsets including training set, validation set and test set. K-means++ algorithm was used to conduct dimensional clustering of object boxes in 7 groups. By adjusting the super parameters of YOLOv4 network for training, Optimal model parameters for 7 groups were obtained respectively. These model parameters were used to detect and compare 7 test sets respectively. The experimental results showed that YOLOv4 can effectively detect the large, medium and small moving objects represented by Truck, Car and Pedestrian in the Udacity data set. When the ratio of training set, validation set and test set is 7:1.5:1.5, the optimal model parameters of the YOLOv4 have highest detection performance. The values show mAP50 reaching 80.89%, mAP75 reaching 47.08%, and the detection speed reaching 10.56 FPS.