• Journal of the Korea Society of Computer and Information
• /
• v.26 no.3
• /
• pp.51-57
• /
• 2021

In this paper, we propose a method to find the DoF(Depth of field) that is blurred in an image by focusing and out-focusing the camera through a efficient convolutional neural network. Our approach uses the RGB channel-based cross-correlation filter to efficiently classify the DoF region from the image and build data for learning in the convolutional neural network. A data pair of the training data is established between the image and the DoF weighted map. Data used for learning uses DoF weight maps extracted by cross-correlation filters, and uses the result of applying the smoothing process to increase the convergence rate in the network learning stage. The DoF weighted image obtained as the test result stably finds the DoF region in the input image. As a result, the proposed method can be used in various places such as NPR(Non-photorealistic rendering) rendering and object detection by using the DoF area as the user's ROI(Region of interest).

• Journal of IKEEE
• /
• v.24 no.4
• /
• pp.1050-1057
• /
• 2020

Immersive 360-degree media has a problem of slowing down the video recognition speed when the video is processed by the conventional method using a variety of rendering methods, and the video size becomes larger with higher quality and extra-large volume than the existing video. In addition, in most cases, only one scene is captured by fixing the camera in a specific place due to the characteristics of the immersive 360-degree media, it is not necessary to extract feature information from all scenes. In this paper, we propose a reference frame selection method for immersive 360-degree media and describe its application process to copyright protection technology. In the proposed method, three pre-processing processes such as frame extraction of immersive 360 media, frame downsizing, and spherical form rendering are performed. In the rendering process, the video is divided into 16 frames and captured. In the central part where there is much object information, an object is extracted using an RGB vector per pixel and deep learning, and a reference frame is selected using object feature information.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.5
• /
• pp.17-22
• /
• 2022

In this paper, we design a lightweight embedded device that can support intelligent edge computing, and show that the device quickly detects an object in an image input from a camera device in real time. The proposed system can be applied to environments without pre-installed infrastructure, such as an intelligent video control system for industrial sites or military areas, or video security systems mounted on autonomous vehicles such as drones. The On-Device AI(Artificial intelligence) technology is increasingly required for the widespread application of intelligent vision recognition systems. Computing offloading from an image data acquisition device to a nearby edge device enables fast service with less network and system resources than AI services performed in the cloud. In addition, it is expected to be safely applied to various industries as it can reduce the attack surface vulnerable to various hacking attacks and minimize the disclosure of sensitive data.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.5
• /
• pp.221-228
• /
• 2022

With the application of artificial intelligence technology, robots can provide efficient services in real life. Unlike industrial manipulators that do simple repetitive work, this study presented design methods of 6 degree of freedom robot arm and intelligent object search and movement methods for use alone or in collaboration with no place restrictions in the service robot field and verified performance. Using a depth camera and deep learning in the ROS environment of the embedded board included in the robot arm, the robot arm detects objects and moves to the object area through inverse kinematics analysis. In addition, when contacting an object, it was possible to accurately hold and move the object through the analysis of the force sensor value. To verify the performance of the manufactured robot arm, experiments were conducted on accurate positioning of objects through deep learning and image processing, motor control, and object separation, and finally robot arm was tested to separate various cups commonly used in cafes to check whether they actually operate.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.12
• /
• pp.77-84
• /
• 2021

In this paper, we propose a system that uses image data and beacon data to classify authorized and unauthorized perosn who are allowed to enter a group facility. The image data collected through the IP camera uses YOLOv4 to extract a person object, and collects beacon signal data (UUID, RSSI) through an application to compose a fingerprinting-based radio map. Beacon extracts user location data after CNN-LSTM-based learning in order to improve location accuracy by supplementing signal instability. As a result of this paper, it showed an accuracy of 93.47%. In the future, it can be expected to fusion with the access authentication process such as QR code that has been used due to the COVID-19, track people who haven't through the authentication process.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.237-250
• /
• 2022

Structural health monitoring (SHM) plays an important role in ensuring the safety and functionality of critical civil infrastructure. In recent years, numerous researchers have conducted studies to develop computer vision and machine learning techniques for SHM purposes, offering the potential to reduce the laborious nature and improve the effectiveness of field inspections. However, high-quality vision data from various types of damaged structures is relatively difficult to obtain, because of the rare occurrence of damaged structures. The lack of data is particularly acute for fatigue crack in steel bridge girder. As a result, the lack of data for training purposes is one of the main issues that hinders wider application of these powerful techniques for SHM. To address this problem, the use of synthetic data is proposed in this article to augment real-world datasets used for training neural networks that can identify fatigue cracks in steel structures. First, random textures representing the surface of steel structures with fatigue cracks are created and mapped onto a 3D graphics model. Subsequently, this model is used to generate synthetic images for various lighting conditions and camera angles. A fully convolutional network is then trained for two cases: (1) using only real-word data, and (2) using both synthetic and real-word data. By employing synthetic data augmentation in the training process, the crack identification performance of the neural network for the test dataset is seen to improve from 35% to 40% and 49% to 62% for intersection over union (IoU) and precision, respectively, demonstrating the efficacy of the proposed approach.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1890-1897
• /
• 2021

People counting is an important technology to provide application services such as smart home, smart building, smart car, etc. Due to the social distancing of COVID-19, the people counting technology attracted public attention. People counting system can be implemented in various ways such as camera, sensor, wireless, etc. according to service requirements. People counting system using WiFi AP uses WiFi CSI data that reflects multipath information. This technology is an effective solution implementing indoor with low cost. The conventional WiFi CSI-based people counting technologies have low accuracy that obstructs the high quality service. This paper proposes a deep learning people counting system based on WiFi CSI data. Data preprocessing using auto-encoder, data augmentation that transform WiFi CSI data, and a proposed deep learning model improve the accuracy of people counting. In the experimental result, the proposed approach shows 89.29% accuracy in 6 subjects.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.1
• /
• pp.111-120
• /
• 2022

It is essential to make a purchase decision to make sure that the furniture matches well with other structures in the room. Moreover, in the Untact Marketing situation caused by the COVID-19 crisis, this is becoming an even more impact factor. Accordingly, methods of measuring length using AR(Augmented Reality) are emerging with the advent of AR open sources such as ARCore and ARKit for furniture arrangement interior simulation. Since this existing method using AR generates a Depth Map based on a flat camera image and it also involves complex three-dimensional calculations, limitations are revealed in work that requires the information of accurate room size using a smartphone. In this paper, we propose a method to accurately measure the size of a room using only the accelerometer and gyroscope sensors built in smartphones without using ARCore or ARKit. In addition, as an example of application using the presented technique, a method for applying a pre-designed room interior to each room is presented.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.3
• /
• pp.1-8
• /
• 2022

Recently, Google MedeiaPipe presents a novel approach for neural network-based hair segmentation from a single camera input specifically designed for real-time, mobile application. Though neural network related to hair segmentation is relatively small size, it produces a high-quality hair segmentation mask that is well suited for AR effects such as a realistic hair recoloring. However, it has undesirable segmentation effects according to hair styles or in case of containing noises and holes. In this study, the energy function of the test image is constructed according to the estimated prior distributions of hair location and hair color likelihood function. It is further optimized according to graph cuts algorithm and initial hair region is obtained. Finally, clustering algorithm and image post-processing techniques are applied to the initial hair region so that the final hair region can be segmented precisely. The proposed method is applied to MediaPipe hair segmentation pipeline.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.8
• /
• pp.95-101
• /
• 2023

Colmap is one of the innovative artificial intelligence technologies, highly effective as a tool in 3D reconstruction tasks. Moreover, it excels at constructing intricate 3D models by utilizing images and corresponding metadata. Colmap generates 3D models by merging 2D images, camera position data, depth information, and so on. Through this, it achieves detailed and precise 3D reconstructions, inclusive of objects from the real world. Additionally, Colmap provides rapid processing by leveraging GPUs, allowing for efficient operation even within large data sets. In this paper, we have presented a method of collecting 2D images of traditional Korean towers and reconstructing them into 3D models using Colmap. This study applied this technology in the restoration process of traditional stone towers in South Korea. As a result, we confirmed the potential applicability of Colmap in the field of cultural heritage restoration.