• Journal of Aerospace System Engineering
• /
• v.16 no.5
• /
• pp.70-77
• /
• 2022

This paper proposes database generation and management system for small-pixelized airborne target recognition. The proposed system has five main features: 1) image extraction from in-flight test video frames, 2) automatic image archiving, 3) image data labeling and Meta data annotation, 4) virtual image data generation based on color channel convert conversion and seamless cloning and 5) HOG/LBP-based tiny-pixelized target augmented image data. The proposed framework is Python-based PyQt5 and has an interface that includes OpenCV. Using video files collected from flight tests, an image dataset for airborne target recognition on generates by using the proposed system and system input.

• ETRI Journal
• /
• v.36 no.5
• /
• pp.791-798
• /
• 2014

As a new hybrid broadcasting service, augmented broadcasting shows enhanced broadcasting content on a large TV screen, while augmented reality (AR) on a mobile device augments additional graphical content onto an input image from the device's own camera to provide useful and convenient information for users. A one-sided broadcasting service using AR has already been attempted in virtual advertisements during sport broadcasts. However, because its augmentation is preprocessed before the video image is transmitted, the viewer at home may have no influence on this formation; and no interaction for the user is possible unless the viewer has a direct connection to the content provider. Augmented broadcasting technology enables viewers to watch mixed broadcasting content only when they want such service and to watch original broadcasting content when they do not. To realize an augmented broadcasting service, the most important issue is to resolve the hybrid content synchronization over heterogeneous broadcast and broadband networks. This paper proposes a novel hybrid content synchronization scheme for an augmented broadcasting service and presents its implementation and results in a terrestrial DTV environment.

• Journal of Korea Multimedia Society
• /
• v.22 no.2
• /
• pp.136-145
• /
• 2019

The crowded environment of a domestic pig farm is highly vulnerable to the spread of infectious diseases such as foot-and-mouth disease, and studies have been conducted to automatically analyze behavior of pigs in a crowded pig farm through a video surveillance system using a camera. Although it is required to correctly separate occluding pigs for tracking each individual pigs, extracting the boundaries of the occluding pigs fast and accurately is a challenging issue due to the complicated occlusion patterns such as X shape and T shape. In this study, we propose a fast and accurate method to separate occluding pigs not only by exploiting the characteristics (i.e., one of the fast deep learning-based object detectors) of You Only Look Once, YOLO, but also by overcoming the limitation (i.e., the bounding box-based object detector) of YOLO with the test-time data augmentation of rotation. Experimental results with two-pigs occlusion patterns show that the proposed method can provide better accuracy and processing speed than one of the state-of-the-art widely used deep learning-based segmentation techniques such as Mask R-CNN (i.e., the performance improvement over Mask R-CNN was about 11 times, in terms of the accuracy/processing speed performance metrics).

• The Journal of the Korea Contents Association
• /
• v.21 no.1
• /
• pp.552-560
• /
• 2021

Currently, the domestic aquaculture industry is pursuing smartization, but it is still proceeding with human subjective judgment in many processes in the aquaculture stage. The prerequisite for the smart aquaculture industry is to effectively grasp the condition of fish in the farm. If real-time monitoring is possible by identifying the number of fish populations, size, pathways, and speed of movement, various forms of automation such as automatic feed supply and disease determination can be carried out. In this study, we proposed an algorithm to identify the state of fish in real time using underwater video data. The fish detection performance was compared and evaluated by applying the latest deep learning-based object detection models, and an algorithm was proposed to measure fish object identification, path tracking, and moving speed in continuous image frames in the video using the fish detection results. The proposed algorithm showed 92% object detection performance (based on F1-score), and it was confirmed that it effectively tracks a large number of fish objects in real time on the actual test video. It is expected that the algorithm proposed in this paper can be effectively used in various smart farming technologies such as automatic feed feeding and fish disease prediction in the future.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.46 no.2
• /
• pp.84-91
• /
• 2009

This paper presents an online partial 3D modeling methodology that uses a mobile augmented reality system and aerial photographs, and a tracking methodology that compares the 3D model with a video image. Instead of relying on models which are created in advance, the system generates a 3D model for a real building on the fly by combining frontal and aerial views. A user's initial pose is estimated using an aerial photograph, which is retrieved from a database according to the user's GPS coordinates, and an inertial sensor which measures pitch. We detect edges of the rooftop based on Graph cut, and find edges and a corner of the bottom by minimizing the proposed cost function. To track the user's position and orientation in real-time, feature-based tracking is carried out based on salient points on the edges and the sides of a building the user is keeping in view. We implemented camera pose estimators using both a least squares estimator and an unscented Kalman filter (UKF). We evaluated the speed and accuracy of both approaches, and we demonstrated the usefulness of our computations as important building blocks for an Anywhere Augmentation scenario.

• Clinical and Experimental Pediatrics
• /
• v.61 no.3
• /
• pp.78-83
• /
• 2018

Purpose: Frequent desaturation due to immature incoordination of suck-swallow-breathing in preterm infants can influence multiple organs such as the heart, lungs, and brain, which can then affect growth and development. Most notably in preterm infants, feeding desaturation may even affect pulmonary function during gavage feeding. Because respiratory muscle activities may reflect the work required during respiration, we evaluated the differences in these activities between full-term and preterm infants with feeding desaturation, and investigated the correlations with clinical variables. Methods: Nineteen preterm infants with feeding desaturation (group 1) and 19 age-matched full-term infants (group 2) were evaluated. Oromotor function was evaluated using video recording. The root-mean-square (RMS) envelope of the electromyography signal was calculated to quantify the activities of muscles involved in respiration. The differences in RMS between both groups and the correlation with clinical variables including gestational age (GA), birth weight (BW), and Apgar scores (AS) at 1 and 5 minutes after birth were evaluated. Results: The RMS values of the diaphragm (RMS-D) and rectus abdominis (RMS-R) were significantly greater in group 1 compared to group 2, and the 1- and 5-min AS were significantly lower in group 1 compared to group 2. RMS-D and RMS-R were inversely correlated with GA, BW, 1- and 5-min AS in all infants. Conclusion: This study showed that respiratory muscle activities were augmented during feeding in preterm infants compared to full-term infants. Additionally, respiratory muscle activities were inversely correlated with all clinical variables.

• Journal of Korea Multimedia Society
• /
• v.23 no.4
• /
• pp.525-538
• /
• 2020

A practical animal face classification system that classifies animals in image and video data is considered as a pivotal topic in machine learning. In this research, we are proposing a novel method of fully connected dual Deep Convolutional Neural Network (DCNN), which extracts and analyzes image features on a large scale. With the inclusion of the state of the art Batch Normalization layer and Exponential Linear Unit (ELU) layer, our proposed DCNN has gained the capability of analyzing a large amount of dataset as well as extracting more features than before. For this research, we have built our dataset containing ten thousand animal faces of ten animal classes and a dual DCNN. The significance of our network is that it has four sets of convolutional functions that work laterally with each other. We used a relatively small amount of batch size and a large number of iteration to mitigate overfitting during the training session. We have also used image augmentation to vary the shapes of the training images for the better learning process. The results demonstrate that, with an accuracy rate of 92.0%, the proposed DCNN outruns its counterparts while causing less computing costs.

• Journal of Advanced Navigation Technology
• /
• v.25 no.1
• /
• pp.115-123
• /
• 2021

Pine nuts are Korea's representative nut forest products and profitable crops. However, pine nuts are harvested by climbing the trees themselves, thus the risk is high. In order to solve this problem, it is necessary to harvest pine nuts using a robot or an unmanned aerial vehicle(UAV). In this paper, we propose a deep learning based detection method for harvesting pine nut in UAV aerial images. For this, a video was recorded in a real pine forest using UAV, and a data augmentation technique was used to supplement a small number of data. As the data for 3D detection, Unity3D was used to model the virtual pine nut and the virtual environment, and the labeling was acquired using the 3D transformation method of the coordinate system. Deep learning algorithms for detection of pine nuts distribution area and 2D and 3D detection of pine nuts objects were used DeepLabV3+, YOLOv4, and CenterNet, respectively. As a result of the experiment, the detection rate of pine nuts distribution area was 82.15%, the 2D detection rate was 86.93%, and the 3D detection rate was 59.45%.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.12
• /
• pp.63-71
• /
• 2020

In this paper, we propose a fire detection technology using YOLOv3 and EfficientDet, the most reliable artificial intelligence detection algorithm recently, an alert service that simultaneously transmits four kinds of notifications: text, web, app and e-mail, and an AWS system that links fire detection and notification service. There are two types of our highly accurate fire detection algorithms; the fire detection model based on YOLOv3, which operates locally, used more than 2000 fire data and learned through data augmentation, and the EfficientDet, which operates in the cloud, has conducted transfer learning on the pretrained model. Four types of notification services were established using AWS service and FCM service; in the case of the web, app, and mail, notifications were received immediately after notification transmission, and in the case of the text messaging system through the base station, the delay time was fast enough within one second. We proved the accuracy of our fire detection technology through fire detection experiments using the fire video, and we also measured the time of fire detection and notification service to check detecting time and notification time. Our AI fire detection and notification service system in this paper is expected to be more accurate and faster than past fire detection systems, which will greatly help secure golden time in the event of fire accidents.

• Journal of the Society of Disaster Information
• /
• v.19 no.3
• /
• pp.665-672
• /
• 2023

Purpose: Underground utility tunnel is facility that is jointly house infrastructure such as electricity, water and gas in city, causing condensation problems due to lack of airflow. This paper aims to prevent electricity leakage fires caused by condensation by detecting whether the control panel door in the underground utility tunnel is open using a deep learning model. Method: YOLO, a deep learning object recognition model, is trained to recognize the opening and closing of the control panel door using video data taken by a robot patrolling the underground utility tunnel. To improve the recognition rate, image augmentation is used. Result: Among the image enhancement techniques, we compared the performance of the YOLO model trained using mosaic with that of the YOLO model without mosaic, and found that the mosaic technique performed better. The mAP for all classes were 0.994, which is high evaluation result. Conclusion: It was able to detect the control panel even when there were lights off or other objects in the underground cavity. This allows you to effectively manage the underground utility tunnel and prevent disasters.