• Journal of Korea Multimedia Society
• /
• v.22 no.1
• /
• pp.44-54
• /
• 2019

Recently, image-based object detection has made great progress with the introduction of Convolutional Neural Network (CNN). Many trials such as Region-based CNN, Fast R-CNN, and Faster R-CNN, have been proposed for achieving better performance in object detection. YOLO has showed the best performance under consideration of both accuracy and computational complexity. However, these data-driven detection methods including YOLO have the fundamental problem is that they can not guarantee the good performance without a large number of training database. In this paper, we propose a data sampling method using CycleGAN to solve this problem, which can convert styles while retaining the characteristics of a given input image. We will generate the insufficient data samples for training more robust object detection without efforts of collecting more database. We make extensive experimental results using the day-time and night-time road images and we validate the proposed method can improve the object detection accuracy of the night-time without training night-time object databases, because we converts the day-time training images into the synthesized night-time images and we train the detection model with the real day-time images and the synthesized night-time images.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.12
• /
• pp.45-53
• /
• 2020

The purpose of this paper is to reduce the ratio of the patient accidents that may occur in nursing hospitals. In other words, it determines whether the person approaching the dangerous area is a elderly (patient uniform) group or a practitioner(Casual Clothing) group, based on the clothing displayed by CCTV. We collected the basic learning data from web crawling techniques and nursing hospitals. Then model training data was created with Image Generator and Labeling program. Due to the limited performance of CCTV, it is difficult to create a good model with both high accuracy and speed. Therefore, we implemented the ResNet model with relatively excellent accuracy and the YOLO3 model with relatively excellent speed. Then we wanted to allow nursing hospitals to choose a model that they wanted. As a result of the study, we implemented a model that can distinguish patient and casual clothes with appropriate accuracy. Therefore, it is believed that it will contribute to the reduction of safety accidents in nursing hospitals by preventing the elderly from accessing the danger zone.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.12
• /
• pp.1581-1587
• /
• 2020

With the emergence of convolutional neural network in the field of machine learning, the model for solving image processing problems has seen rapid development. However, the computing resources required are also rising, making it difficult to learn from a typical environment. Attention mechanism is originally proposed to prevent the gradient vanishing problem of the recurrent neural network, but this can also be used in a direction favorable to learning of the convolutional neural network. In this paper, attention mechanism is applied to convolutional neural network, and the excellence of the proposed method is demonstrated through the comparison of learning time and performance difference at this time. The proposed model showed that both learning time and performance were superior in object detection based on YOLO compared to models without attention mechanism, and experimentally demonstrated that learning time could be significantly reduced. In addition, this is expected to increase accessibility to machine learning by end users.

• Journal of Aerospace System Engineering
• /
• v.15 no.1
• /
• pp.102-110
• /
• 2021

Recently, multi-copters equipped with various collision avoidance sensors have been introduced to improve flight stability. LiDAR is used to recognize a three-dimensional position. Multiple cameras and real-time SLAM technology are also used to calculate the relative position to obstacles. A three-dimensional depth sensor with a small process and camera is also used. In this study, a small collision-avoidance multi-copter system capable of in-door flight was developed as a platform for the development of collision avoidance software technology. The multi-copter system was equipped with LiDAR, 3D depth sensor, and small image processing board. Object recognition and collision avoidance functions based on the YOLO algorithm were verified through flight tests. This paper deals with recent trends in drone collision avoidance technology, system design/manufacturing process, and flight test results.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.8
• /
• pp.1117-1123
• /
• 2021

Object recognition is to identify the location and class of a specific object by analyzing the given image when a specific image is input. One of the fields in which object recognition technology is actively applied in recent years is autonomous vehicles, and this paper describes the trend of image-based object recognition artificial intelligence technology in autonomous vehicles. The image-based object detection algorithm has recently been narrowed down to two methods (a single-step detection method and a two-step detection method), and we will analyze and organize them around this. The advantages and disadvantages of the two detection methods are analyzed and presented, and the YOLO/SSD algorithm belonging to the single-step detection method and the R-CNN/Faster R-CNN algorithm belonging to the two-step detection method are analyzed and described. This will allow the algorithms suitable for each object recognition application required for autonomous driving to be selectively selected and R&D.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1762-1769
• /
• 2021

The final goal of this study is to develop a system that can analyze whether a wanted vehicle is a criminal vehicle from images collected from black boxes, smartphones, CCTVs, and so on. Data collection was collected using a self-developed black box. The used data in this study has used a total of 83,753 cases such as the eight vehicle types(truck, RV, passenger car, van, SUV, bus, sports car, electric vehicle) and 434 vehicle models. As a result of vehicle recognition using YOLO v5, mAP was found to be 80%. As a result of identifying the vehicle model with ReXNet using the self-developed black box, the accuracy was found to be 99%. The result was verified by surveying field police officers. These results suggest that improving the accuracy of data labeling helps to improve vehicle recognition performance.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.1
• /
• pp.91-98
• /
• 2022

In this study, Pukyong National University's floating population survey and analysis were conducted using Raspberry Pie, an open source hardware, and object detection algorithms based on deep learning technology. After collecting images using Raspberry Pie, the person detection of the collected images using YOLO3's IMAGEAI and YOLOv5 models was performed, and Haar-like features and HOG models were used for accuracy comparison analysis. As a result of the analysis, the smallest floating population was observed due to the school anniversary. In general, the floating population at the entrance was larger than the floating population at the exit, and both the entrance and exit were found to be greatly affected by the school's anniversary and events.

• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.468-474
• /
• 2022

In this paper, we propose a method to implement a real-time fire alarm system using deep learning. The deep learning image dataset for fire alarms acquired 1,500 sheets through the Internet. If various images acquired in a daily environment are learned as they are, there is a disadvantage that the learning accuracy is not high. In this paper, we propose a fire image data expansion method to improve learning accuracy. The data augmentation method learned a total of 2,100 sheets by adding 600 pieces of learning data using brightness control, blurring, and flame photo synthesis. The expanded data using the flame image synthesis method had a great influence on the accuracy improvement. A real-time fire detection system is a system that detects fires by applying deep learning to image data and transmits notifications to users. An app was developed to detect fires by analyzing images in real time using a model custom-learned from the YOLO V4 TINY model suitable for the Edge AI system and to inform users of the results. Approximately 10% accuracy improvement can be obtained compared to conventional methods when using the proposed data.

• Journal of the Korean Society for Heat Treatment
• /
• v.35 no.6
• /
• pp.327-336
• /
• 2022

In this study, a model for automatically recognizing several steel parts through a camera before charging materials was developed under the assumption that the temperature distribution in the pre-air atmosphere was known. For model development, datasets were collected in random environments and factories. In this study, the YOLO-v5 model, which is a YOLO model with strengths in real-time detection in the field of object detection, was used, and the disadvantages of taking a lot of time to collect images and learning models was solved through the transfer learning methods. The performance evaluation results of the derived model showed excellent performance of 0.927 based on mAP 0.5. The derived model will be applied to the model development study, which uses the model to accurately recognize the material and then match it with the temperature distribution in the atmosphere to determine whether the material layout is suitable before charging materials.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.11
• /
• pp.411-418
• /
• 2022

Incorrectly loaded containers can easily knock down by strong winds. Container collapse accidents can lead to material damage and paralysis of the port system. In this paper, We propose a deep learning-based container loading state and accident risk detection technique. Using Darknet-based YOLO, the container load status identifies in real-time through corner casting on the top and bottom of the container, and the risk of accidents notifies the manager. We present criteria for classifying container alignment states and select efficient learning algorithms based on inference speed, classification accuracy, detection accuracy, and FPS in real embedded devices in the same environment. The study found that YOLOv4 had a weaker inference speed and performance of FPS than YOLOv3, but showed strong performance in classification accuracy and detection accuracy.