• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.11
• /
• pp.1720-1728
• /
• 2022

The industrial 4.0 era has been opened with the development of artificial intelligence technology, and the realization of smart farms incorporating ICT technology is receiving great attention in the livestock industry. Among them, the quality management technology of livestock products and livestock operations incorporating computer vision-based artificial intelligence technology represent key technologies. However, the insufficient number of livestock image data for artificial intelligence model training and the severely unbalanced ratio of labels for recognizing a specific defective state are major obstacles to the related research and technology development. To overcome these problems, in this study, combining oversampling and adversarial case generation techniques is proposed as a method necessary to effectively utilizing small data labels for successful defect detection. In addition, experiments comparing performance and time cost of the applicable techniques were conducted. Through experiments, we confirm the validity of the proposed methods and draw utilization strategies from the study results.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.4
• /
• pp.144-159
• /
• 2014

Techniques for making a single panoramic image using multiple pictures are widely studied in many areas such as computer vision, computer graphics, etc. The panorama image can be applied to various fields like virtual reality, robot vision areas which require wide-angled shots as an useful way to overcome the limitations such as picture-angle, resolutions, and internal informations of an image taken from a single camera. It is so much meaningful in a point that a panoramic image usually provides better immersion feeling than a plain image. Although there are many ways to build a panoramic image, most of them are using the way of extracting feature points and matching points of each images for making a single panoramic image. In addition, those methods use the RANSAC(RANdom SAmple Consensus) algorithm with matching points and the Homography matrix to transform the image. The SURF(Speeded Up Robust Features) algorithm which is used in this paper to extract featuring points uses an image's black and white informations and local spatial informations. The SURF is widely being used since it is very much robust at detecting image's size, view-point changes, and additionally, faster than the SIFT(Scale Invariant Features Transform) algorithm. The SURF has a shortcoming of making an error which results in decreasing the RANSAC algorithm's performance speed when extracting image's feature points. As a result, this may increase the CPU usage occupation rate. The error of detecting matching points may role as a critical reason for disqualifying panoramic image's accuracy and lucidity. In this paper, in order to minimize errors of extracting matching points, we used $3{\times}3$ region's RGB pixel values around the matching points' coordinates to perform intermediate filtering process for removing wrong matching points. We have also presented analysis and evaluation results relating to enhanced working speed for producing a panorama image, CPU usage rate, extracted matching points' decreasing rate and accuracy.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.2 s.34
• /
• pp.21-30
• /
• 2005

In general, the robust estimation method is well known for a good statistical estimator that is insensitive to small departures from the idealized assumptions for which the estimation is optimized. While there are many existing robust estimation techniques that have been proposed in the literature, two main techniques used in computer vision are M-estimators and least-median of squares (LMS). Among these. we utilized the M-estimators since they are known to provide an optimal estimation of affine motion parameters. The M-estimators have higher statistical efficiency but tolerate much lower percentages of outliers unless properly initialized. To resolve these problems, we proposed an adaptive M-estimators algorithm that effectively separates outliers from non-outliers and estimate affine model parameters, using a continuous sigmoid weight function. The experimental results show the superiority of our method.

• Journal of Convergence for Information Technology
• /
• v.10 no.11
• /
• pp.16-22
• /
• 2020

Since it is difficult for individual power producers and non-professionals who lack basic knowledge to control, manage, and operate facilities through EMS (Energy Management System), augmented reality and virtual reality monitoring systems are applied. However, in the existing systems, data access efficiency is inferior due to the process of analyzing column values for analog signal values collected from sensors and converting data after combining the columns. In addition, high-speed operation processing is difficult due to a large number of indexes for accommodating access patterns for various analog signal waveforms. Therefore, in this paper, a bitmap generator is inserted into a non-tree structure to convert the data collected from power facilities into physical property information, and the converted information is encrypted with a common key, so that the resources for the resources shared between each device are We propose a method of exchanging data for an augmented reality-based power system that is controlled by measurement.

• The Journal of the Korea Contents Association
• /
• v.6 no.6
• /
• pp.1-8
• /
• 2006

This paper presents an intelligent pattern matching method that can be used to acquire the reliable calibration data for automatic PCB pattern inspection. The inaccurate calibration data is often acquired by geometric pattern variations and selecting an inappropriate model manual. It makes low the confidence of inspection and also the inspection processing time has been delayed. In this paper, the geometric features of PCB patterns are utilized to calculate the accurate calibration data. An appropriate model is selected automatically based on the geometric features, and then the calibration data to be invariant to the geometric variations(translation, rotation, scaling) is calculated. The method can save the inspection time unnecessary by eliminating the need for manual model selection. As the result, it makes a fast, accurate and reliable inspection of PCB patterns.

• Journal of Advanced Navigation Technology
• /
• v.27 no.5
• /
• pp.580-586
• /
• 2023

AESA radar is able to instantaneously and adaptively position and control the beam, and this enables to greatly improve multi-target tracking capability with high accuracy in comparison to traditional mechanically-scanned radar system. This paper is primarily concerned with the development of an efficient methodology for multi-target managenent with the context of multi-target environment employing AESA radar. In this paper, targets are stratified into two principal categories: currently displayed targets and non-display targets, predicated upon their relative priority. Displayed targets are subsequently stratified into TOI (target of interest), HPT (high priority target), and SAT (situational awareness target), based on the requisite levels of tracking accuracy. It also suggests rules for determining target priority management, especially in air-to-air mode including interleaved mode. This proposed approach was tested and validated in a SIL (system integration lab) environment, applying it to AESA radars mounted on aircraft.

• Journal of Korea Multimedia Society
• /
• v.12 no.5
• /
• pp.745-756
• /
• 2009

An autonomous virtual character can conduct itself like a human after recognizing and interpreting the virtual environment. Artificial vision is mainly used in the recognition of the environment for a virtual character. The present artificial vision that has been developed takes all the information at once from everything that comes into view. However, this can reduce the efficiency and reality of the system by saving too much information at once, and it also causes problems because the speed slows down in the dynamic environment of the game. Therefore, to construct a vision system similar to that of humans, a visual observation system which saves only the required information is needed. For that reason, this research focuses on the descriptive artificial intelligence engine which detects the most important information visually recognized by the character in the virtual world and saves it into the memory by degrees. In addition, a visual system is constructed in accordance with an image transaction theory to make it sense and recognize human feelings. This system finds the attention area of moving objects quickly and effectively through the experiment of the virtual environment with three dynamic dimensions. Also the experiment enhanced processing speed more than 1.6 times.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.279-282
• /
• 2017

Kinect depth sensor, a depth camera developed by Microsoft as a natural user interface for game appeared as a very useful tool in computer vision field. In this paper, due to kinect's depth sensor and its high frame rate, we developed a distance measurement system using Kinect camera to test it for unmanned vehicles which need vision systems to perceive the surrounding environment like human do in order to detect objects in their path. Therefore, kinect depth sensor is used to detect objects in its field of view and enhance the distance measurement system from objects to the vision sensor. Detected object is identified in accuracy way to determine if it is a real object or a pixel nose to reduce the processing time by ignoring pixels which are not a part of a real object. Using depth segmentation techniques along with Open CV library for image processing, we can identify present objects within Kinect camera's field of view and measure the distance from them to the sensor. Tests show promising results that this system can be used as well for autonomous vehicles equipped with low-cost range sensor, Kinect camera, for further processing depending on the application type when they reach a certain distance far from detected objects.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.3
• /
• pp.577-582
• /
• 2021

Recently, with the development of AR, VR, and smart device technologies, the demand for services based on non-face-to-face environments is also increasing in the fitness industry. The non-face-to-face online home training service has the advantage of not being limited by time and place compared to the existing offline service. However, there are disadvantages including the absence of exercise equipment, difficulty in measuring the amount of exercise and chekcing whether the user maintains an accurate exercise posture or not. In this study, we develop a standard exercise program that can compensate for these shortcomings and propose a new non-face-to-face home training application by using a deep learning-based body posture estimation image processing algorithm. This application allows the user to directly watch and follow the trainer of the standard exercise program video, correct the user's own posture, and perform an accurate exercise. Furthermore, if the results of this study are customized according to their purpose, it will be possible to apply them to performances, films, club activities, and conferences

• Geophysics and Geophysical Exploration
• /
• v.26 no.4
• /
• pp.211-228
• /
• 2023

Ground-penetrating radar (GPR) surveys are commonly used to monitor embankments, which is a nondestructive geophysical method. The results of GPR surveys can be complex, depending on the situation, and data processing and interpretation are subject to expert experiences, potentially resulting in false detection. Additionally, this process is time-intensive. Consequently, various studies have been undertaken to detect cavities in GPR survey data using deep learning methods. Deep-learning-based approaches require abundant data for training, but GPR field survey data are often scarce due to cost and other factors constaining field studies. Therefore, in this study, a deep- learning-based model was developed for embankment GPR survey cavity detection using data augmentation strategies. A dataset was constructed by collecting survey data over several years from the same embankment. A you look only once (YOLO) model, commonly used in computer vision for object detection, was employed for this purpose. By comparing and analyzing various strategies, the optimal data augmentation approach was determined. After initial model development, a stepwise process was employed, including box clustering, transfer learning, self-ensemble, and model ensemble techniques, to enhance the final model performance. The model performance was evaluated, with the results demonstrating its effectiveness in detecting cavities in embankment GPR survey data.