• The Journal of the Korea Contents Association
• /
• v.3 no.2
• /
• pp.11-18
• /
• 2003

In this paper, we propose a fast variable block matching algorithm for motion estimation based on bit-patterns. Motion estimation in the proposed algorithm is peformed after the representation of image sequence is transformed 8-bit pixel values into 1-bit ones by the mean pixel value of search block, which brings a short searching time by reducing the computational complexity. Moreover, adaptive searching methods according to the motion information of the block make the procedure of motion estimation efficient by eliminating unnecessary searching processes of low motion block and deepening a searching procedure in high motion block. Experimental results show that the proposed algorithm provides bettor performance - average 0.5dB PSNR improvement and about 99% savings in the number of operations - than full search Hock matching algorithm with a fixed block size.

• Korean Journal of Remote Sensing
• /
• v.17 no.2
• /
• pp.183-188
• /
• 2001

The NOAA AVHRR remotely sensed SST data, collected by the National Fisheries Research and Development Institute (NFRDI), are analyzed in order to understand the spatial and temporal distributions of SST in the sea near korea. Our study is based on 10-day SST images during last 7 years (1991-1997). For a time series analysis of multiple SST images, all of images must be consistent exactly at the same position by adjusting the scales and positions of each SST image. We devised an algorithm which automatically detects cloud pixels from multiple SST images. The cloud detection algorithm is based on a physical constraint that SST anomalies in the ocean do not exceed certain limits (we used $\pm$3$^{\circ}C$ as a criterion of SST anomalies). The remotely sensed SST data are tuned by comparing remotely sensed data with observed SST at coastal stations. Seasonal variations of SST are studied by harmonic fit of SST normals at each pixel and the SST anomalies are studied by statistical method. It was found that the SST anomalies are rather persistent for one or two months. Utilizing the persistency of SST anomalies, we devised an algorithm for a prediction of future SST. In the Markov lprocess model of SST anomalies, autoregression coefficients of SST anomalies during a time elapse of 10 days are between 0.5 and 0.7. The developed algorithm with automatic cloud pixel detection and rediction of future SST is expected to be incorporated to the operational real time service of SST around Korea.

• Korean Journal of Remote Sensing
• /
• v.19 no.6
• /
• pp.411-419
• /
• 2003

An area corresponding to the spatial resolution of optical remote sensor imagery often includes more than one pure surface material. In such case, a pixel value represents a mixture of spectral reflectance of several materials within it. This study attempts to apply the spectral mixture analysis on forest and to evaluate the information content of endmember fractions resulted from the spectral unmixing. Landsat-7 ETM+ image obtained over the study area in the Kwangneung Experimental Forest was initially geo-referenced and radiometrically corrected to reduce the atmospheric and topographic attenuations. Linear mixture model was applied to separate each pixel by the fraction of six endmember: deciduous, coniferous, soil, built-up, shadow, and rice/grass. The fractional values of six endmember could be used to separate forest cover in more detailed spatial scale. In addition, the soil fraction can be further used to extract the information related to the canopy closure. We also found that the shadow effect is more distinctive at coniferous stands.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.5
• /
• pp.141-147
• /
• 2021

In this paper, in order to improve the utilization of hyperspectral large-capacity data feature information by reducing complex computations by dimension reduction of neural network inputs in embedded systems, the band selection algorithm is applied in each subset. Among feature extraction and feature selection techniques, the feature selection aim to improve the optimal number of bands suitable for datasets, regardless of wavelength range, and the time and performance, more than others algorithms. Through this experiment, although the time required was reduced by 1/3 to 1/9 times compared to the others band selection technique, meaningful results were improved by more than 4% in terms of performance through the K-neighbor classifier. Although it is difficult to utilize real-time hyperspectral data analysis now, it has confirmed the possibility of improvement.

• Phonetics and Speech Sciences
• /
• v.13 no.1
• /
• pp.73-79
• /
• 2021

This study investigated the change in lip movement during speech according to aging. For the study, 15 elderly women with an average of 69 years and 15 young women with an average of 22 years were selected. To measure the movement of the lips, the ratio between the minimum point and the maximum point of movement when pronouncing a double vowel was analyzed in pixel units using image analysis software. For clinical utility, the software was produced by applying an automated algorithm and compared with the results of handwork. This study found that the range of the width and length of lips in double vowel tasks was smaller for the elderly than that of the young. A strong positive correlation was found between manual and automated methods, indicating that both methods are useful for extracting lip contours. Based on the above results, it was found that the range of the lips decreased when ignited as aging progressed. Therefore, monitoring the condition of lip performance by simply measuring the movement of lips before aging progresses, and performing exercises to maintain lip range, will prevent pronunciation problems caused by aging.

• Nuclear Engineering and Technology
• /
• v.54 no.8
• /
• pp.3006-3016
• /
• 2022

In this study, the images of specific prompt gamma (PG)-rays of 719 keV emitted from proton-boron reactions were analyzed using single-photon emission computed tomography (SPECT). Quantitative evaluation of the images verified the detection of anatomical changes in tumors, one of the important factors in daily adaptive proton therapy (DAPT) and verified the possibility of application of the PG-ray images to DAPT. Six scenarios were considered based on various sizes and locations compared to the reference virtual tumor to observe the anatomical alterations in the virtual tumor. Subsequently, PG-rays SPECT images were acquired using the modified ordered subset expectation-maximization algorithm, and these were evaluated using quantitative analysis methods. The results confirmed that the pixel range and location of the highest value of the normalized pixel in the PG-rays SPECT image profile changed according to the size and location of the virtual tumor. Moreover, the alterations in the virtual tumor size and location in the PG-rays SPECT images were similar to the true size and location alterations set in the phantom. Based on the above results, the tumor anatomical alterations in DAPT could be adequately detected and verified through SPECT imaging using the 719 keV PG-rays acquired during treatment.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1853-1858
• /
• 2021

O-rings fill the gaps between mechanical parts. Until now, the sorting of defective products has been performed visually and manually, so classification errors often occur. Therefore, a camera-based defect classification system without human intervention is required. However, a binarization process is required to separate the required region from the background in the camera input image. In this paper, an adaptive binarization technique that considers the surrounding pixel values is applied to solve the problem that single-threshold binarization is difficult to apply due to factors such as changes in ambient lighting or reflections. In addition, the convex hull technique is also applied to compensate for the missing pixel part. And the learning model to be applied to the separated region applies the residual error-based deep learning neural network model, which is advantageous when the defective characteristic is non-linear. It is suggested that the proposed system through experiments can be applied to the automation of O-ring defect detection.

• Smart Structures and Systems
• /
• v.32 no.3
• /
• pp.135-151
• /
• 2023

Using 3D asphalt pavement surface data, a deep and multiscale network named CrackNet-M is proposed in this paper for pixel-level crack detection for improvements in both accuracy and robustness. The CrackNet-M consists of four function-specific architectural modules: a central branch net (CBN), a crack map enhancement (CME) module, three pooling feature pyramids (PFP), and an output layer. The CBN maintains crack boundaries using no pooling reductions throughout all convolutional layers. The CME applies a pooling layer to enhance potential thin cracks for better continuity, consuming no data loss and attenuation when working jointly with CBN. The PFP modules implement direct down-sampling and pyramidal up-sampling with multiscale contexts specifically for the detection of thick cracks and exclusion of non-crack patterns. Finally, the output layer is optimized with a skip layer supervision technique proposed to further improve the network performance. Compared with traditional supervisions, the skip layer supervision brings about not only significant performance gains with respect to both accuracy and robustness but a faster convergence rate. CrackNet-M was trained on a total of 2,500 pixel-wise annotated 3D pavement images and finely scaled with another 200 images with full considerations on accuracy and efficiency. CrackNet-M can potentially achieve crack detection in real-time with a processing speed of 40 ms/image. The experimental results on 500 testing images demonstrate that CrackNet-M can effectively detect both thick and thin cracks from various pavement surfaces with a high level of Precision (94.28%), Recall (93.89%), and F-measure (94.04%). In addition, the proposed CrackNet-M compares favorably to other well-developed networks with respect to the detection of thin cracks as well as the removal of shoulder drop-offs.

• Structural Engineering and Mechanics
• /
• v.91 no.5
• /
• pp.443-457
• /
• 2024

At present, the traditional concrete surface inspection methods based on artificial vision have the problems of high cost and insecurity, while the computer vision methods rely on artificial selection features in the case of sensitive environmental changes and difficult promotion. In order to solve these problems, this paper introduces deep learning technology in the field of computer vision to achieve automatic feature extraction of structural damage, with excellent detection speed and strong generalization ability. The main contents of this study are as follows: (1) A method based on DeepLabV3+ convolutional neural network model is proposed for surface detection of post-earthquake structural damage, including surface damage such as concrete cracks, spaling and exposed steel bars. The key semantic information is extracted by different backbone networks, and the data sets containing various surface damage are trained, tested and evaluated. The intersection ratios of 54.4%, 44.2%, and 89.9% in the test set demonstrate the network's capability to accurately identify different types of structural surface damages in pixel-level segmentation, highlighting its effectiveness in varied testing scenarios. (2) A semantic segmentation model based on DeepLabV3+ convolutional neural network is proposed for the detection and evaluation of post-earthquake structural components. Using a dataset that includes building structural components and their damage degrees for training, testing, and evaluation, semantic segmentation detection accuracies were recorded at 98.5% and 56.9%. To provide a comprehensive assessment that considers both false positives and false negatives, the Mean Intersection over Union (Mean IoU) was employed as the primary evaluation metric. This choice ensures that the network's performance in detecting and evaluating pixel-level damage in post-earthquake structural components is evaluated uniformly across all experiments. By incorporating deep learning technology, this study not only offers an innovative solution for accurately identifying post-earthquake damage in civil engineering structures but also contributes significantly to empirical research in automated detection and evaluation within the field of structural health monitoring.

• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.447-454
• /
• 2024

Construction site monitoring is pivotal for overseeing project progress to ensure that projects are completed as planned, within budget, and in compliance with applicable laws and safety standards. Additionally, it seeks to improve operational efficiency for better project execution. To achieve this, many researchers have utilized computer vision technologies to conduct automatic site monitoring and analyze the operational status of equipment. However, most existing studies estimate real-world 3D information (e.g., object tracking, work status analysis) based only on 2D pixel-based information of images. This approach presents a substantial challenge in the dynamic environments of construction sites, necessitating the manual recalibration of analytical rules and thresholds based on the specific placement and the field of view of cameras. To address these challenges, this study introduces a novel method for 3D visualization and status analysis of construction site objects using 3D reconstruction technology. This method enables the analysis of equipment's operational status by acquiring 3D spatial information of equipment from single-camera images, utilizing the Sam-Track model for object segmentation and the One-2-3-45 model for 3D reconstruction. The framework consists of three main processes: (i) single image-based 3D reconstruction, (ii) 3D visualization, and (iii) work status analysis. Experimental results from a construction site video demonstrated the method's feasibility and satisfactory performance, achieving high accuracy in status analysis for excavators (93.33%) and dump trucks (98.33%). This research provides a more consistent method for analyzing working status, making it suitable for practical field applications and offering new directions for research in vision-based 3D information analysis. Future studies will apply this method to longer videos and diverse construction sites, comparing its performance with existing 2D pixel-based methods.