• Journal of IKEEE
• /
• v.27 no.3
• /
• pp.340-344
• /
• 2023

In this paper, we propose a study on the development of deep learning structure to secure visibility of outdoor LED display board according to weather change. The proposed technique secures the visibility of the outdoor LED display board by automatically adjusting the LED luminance according to the weather change using deep learning using an imaging device. In order to automatically adjust the LED luminance according to weather changes, a deep learning model that can classify the weather is created by learning it using a convolutional network after first going through a preprocessing process for the flattened background part image data. The applied deep learning network reduces the difference between the input value and the output value using the Residual learning function, inducing learning while taking the characteristics of the initial input value. Next, by using a controller that recognizes the weather and adjusts the luminance of the outdoor LED display board according to the weather change, the luminance is changed so that the luminance increases when the surrounding environment becomes bright, so that it can be seen clearly. In addition, when the surrounding environment becomes dark, the visibility is reduced due to scattering of light, so the brightness of the electronic display board is lowered so that it can be seen clearly. By applying the method proposed in this paper, the result of the certified measurement test of the luminance measurement according to the weather change of the LED sign board confirmed that the visibility of the outdoor LED sign board was secured according to the weather change.

• Journal of IKEEE
• /
• v.27 no.3
• /
• pp.345-349
• /
• 2023

In this paper, we propose a study on the development of deep learning structure for defective pixel detection of next-generation smart LED display board using imaging device. In this research, a technique utilizing imaging devices and deep learning is introduced to automatically detect defects in outdoor LED billboards. Through this approach, the effective management of LED billboards and the resolution of various errors and issues are aimed. The research process consists of three stages. Firstly, the planarized image data of the billboard is processed through calibration to completely remove the background and undergo necessary preprocessing to generate a training dataset. Secondly, the generated dataset is employed to train an object recognition network. This network is composed of a Backbone and a Head. The Backbone employs CSP-Darknet to extract feature maps, while the Head utilizes extracted feature maps as the basis for object detection. Throughout this process, the network is adjusted to align the Confidence score and Intersection over Union (IoU) error, sustaining continuous learning. In the third stage, the created model is employed to automatically detect defective pixels on actual outdoor LED billboards. The proposed method, applied in this paper, yielded results from accredited measurement experiments that achieved 100% detection of defective pixels on real LED billboards. This confirms the improved efficiency in managing and maintaining LED billboards. Such research findings are anticipated to bring about a revolutionary advancement in the management of LED billboards.

• Smart Structures and Systems
• /
• v.30 no.5
• /
• pp.521-535
• /
• 2022

Efficient management of deteriorating civil infrastructure is one of the most important research topics in many developed countries. In particular, the remote displacement measurement of bridges using linear variable differential transformers, global positioning systems, laser Doppler vibrometers, and computer vision technologies has been attempted extensively. This paper proposes a remote displacement measurement system using closed-circuit televisions (CCTVs) and a computer-vision-based method for in-situ bridge bearings having relatively large displacement due to temperature change in long term. The hardware of the system is composed of a reference target for displacement measurement, a CCTV to capture target images, a gateway to transmit images via a mobile network, and a central server to store and process transmitted images. The usage of CCTV capable of night vision capture and wireless data communication enable long-term 24-hour monitoring on wide range of bridge area. The computer vision algorithm to estimate displacement from the images involves image preprocessing for enhancing the circular features of the target, circular Hough transformation for detecting circles on the target in the whole field-of-view (FOV), and homography transformation for converting the movement of the target in the images into an actual expansion displacement. The simple target design and robust circle detection algorithm help to measure displacement using target images where the targets are far apart from each other. The proposed system is installed at the Tancheon Overpass located in Seoul, and field experiments are performed to evaluate the accuracy of circle detection and displacement measurements. The circle detection accuracy is evaluated using 28,542 images captured from 71 CCTVs installed at the testbed, and only 48 images (0.168%) fail to detect the circles on the target because of subpar imaging conditions. The accuracy of displacement measurement is evaluated using images captured for 17 days from three CCTVs; the average and root-mean-square errors are 0.10 and 0.131 mm, respectively, compared with a similar displacement measurement. The long-term operation of the system, as evaluated using 8-month data, shows high accuracy and stability of the proposed system.

• Journal of KIISE:Computing Practices and Letters
• /
• v.14 no.1
• /
• pp.1-12
• /
• 2008

In this paper, we present a real-time algorithm for recognizing the vehicle color from the indoor and outdoor vehicle images based on GPU (Graphics Processing Unit) acceleration. In the preprocessing step, we construct feature victors from the sample vehicle images with different colors. Then, we combine the feature vectors for each color and store them as a reference texture that would be used in the GPU. Given an input vehicle image, the CPU constructs its feature Hector, and then the GPU compares it with the sample feature vectors in the reference texture. The similarities between the input feature vector and the sample feature vectors for each color are measured, and then the result is transferred to the CPU to recognize the vehicle color. The output colors are categorized into seven colors that include three achromatic colors: black, silver, and white and four chromatic colors: red, yellow, blue, and green. We construct feature vectors by using the histograms which consist of hue-saturation pairs and hue-intensity pairs. The weight factor is given to the saturation values. Our algorithm shows 94.67% of successful color recognition rate, by using a large number of sample images captured in various environments, by generating feature vectors that distinguish different colors, and by utilizing an appropriate likelihood function. We also accelerate the speed of color recognition by utilizing the parallel computation functionality in the GPU. In the experiments, we constructed a reference texture from 7,168 sample images, where 1,024 images were used for each color. The average time for generating a feature vector is 0.509ms for the $150{\times}113$ resolution image. After the feature vector is constructed, the execution time for GPU-based color recognition is 2.316ms in average, and this is 5.47 times faster than the case when the algorithm is executed in the CPU. Our experiments were limited to the vehicle images only, but our algorithm can be extended to the input images of the general objects.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.131-145
• /
• 2020

In line with the trend of industrial innovation, IoT technology utilized in a variety of fields is emerging as a key element in creation of new business models and the provision of user-friendly services through the combination of big data. The accumulated data from devices with the Internet-of-Things (IoT) is being used in many ways to build a convenience-based smart system as it can provide customized intelligent systems through user environment and pattern analysis. Recently, it has been applied to innovation in the public domain and has been using it for smart city and smart transportation, such as solving traffic and crime problems using CCTV. In particular, it is necessary to comprehensively consider the easiness of securing real-time service data and the stability of security when planning underground services or establishing movement amount control information system to enhance citizens' or commuters' convenience in circumstances with the congestion of public transportation such as subways, urban railways, etc. However, previous studies that utilize image data have limitations in reducing the performance of object detection under private issue and abnormal conditions. The IoT device-based sensor data used in this study is free from private issue because it does not require identification for individuals, and can be effectively utilized to build intelligent public services for unspecified people. Especially, sensor data stored by the IoT device need not be identified to an individual, and can be effectively utilized for constructing intelligent public services for many and unspecified people as data free form private issue. We utilize the IoT-based infrared sensor devices for an intelligent pedestrian tracking system in metro service which many people use on a daily basis and temperature data measured by sensors are therein transmitted in real time. The experimental environment for collecting data detected in real time from sensors was established for the equally-spaced midpoints of 4×4 upper parts in the ceiling of subway entrances where the actual movement amount of passengers is high, and it measured the temperature change for objects entering and leaving the detection spots. The measured data have gone through a preprocessing in which the reference values for 16 different areas are set and the difference values between the temperatures in 16 distinct areas and their reference values per unit of time are calculated. This corresponds to the methodology that maximizes movement within the detection area. In addition, the size of the data was increased by 10 times in order to more sensitively reflect the difference in temperature by area. For example, if the temperature data collected from the sensor at a given time were 28.5℃, the data analysis was conducted by changing the value to 285. As above, the data collected from sensors have the characteristics of time series data and image data with 4×4 resolution. Reflecting the characteristics of the measured, preprocessed data, we finally propose a hybrid algorithm that combines CNN in superior performance for image classification and LSTM, especially suitable for analyzing time series data, as referred to CNN-LSTM (Convolutional Neural Network-Long Short Term Memory). In the study, the CNN-LSTM algorithm is used to predict the number of passing persons in one of 4×4 detection areas. We verified the validation of the proposed model by taking performance comparison with other artificial intelligence algorithms such as Multi-Layer Perceptron (MLP), Long Short Term Memory (LSTM) and RNN-LSTM (Recurrent Neural Network-Long Short Term Memory). As a result of the experiment, proposed CNN-LSTM hybrid model compared to MLP, LSTM and RNN-LSTM has the best predictive performance. By utilizing the proposed devices and models, it is expected various metro services will be provided with no illegal issue about the personal information such as real-time monitoring of public transport facilities and emergency situation response services on the basis of congestion. However, the data have been collected by selecting one side of the entrances as the subject of analysis, and the data collected for a short period of time have been applied to the prediction. There exists the limitation that the verification of application in other environments needs to be carried out. In the future, it is expected that more reliability will be provided for the proposed model if experimental data is sufficiently collected in various environments or if learning data is further configured by measuring data in other sensors.

• The Korean Journal of Nuclear Medicine
• /
• v.33 no.3
• /
• pp.316-326
• /
• 1999

Purpose: We evaluated the feasibility of extracting pure left ventricular blood pool and myocardial time-activity curves (TACs) and of generating factor images from human dynamic N-13 ammonia PET using factor analysis. The myocardial blood flow (MBF) estimates obtained with factor analysis were compared with those obtained with the user drawn region-of-interest (ROI) method. Materials and Methods: Stress and rest N-13 ammonia cardiac PET imaging was acquired for 23 min in 5 patients with coronary artery disease using GE Advance tomograph. Factor analysis generated physiological TACs and factor images using the normalized TACs from each dixel. Four steps were involved in this algorithm: (a) data preprocessing; (b) principal component analysis; (c) oblique rotation with positivity constraints; (d) factor image computation. Area under curves and MBF estimated using the two compartment N-13 ammonia model were used to validate the accuracy of the factor analysis generated physiological TACs. The MBF estimated by factor analysis was compared to the values estimated by using the ROI method. Results: MBF values obtained by factor analysis were linearly correlated with MBF obtained by the ROI method (slope = 0.84, r = 0.91), Left ventricular blood pool TACs obtained by the two methods agreed well (Area under curve ratio: 1.02 ($0{\sim}1min$), 0.98 ($0{\sim}2min$), 0.86 ($1{\sim}2min$)). Conclusion: The results of this study demonstrates that MBF can be measured accurately and noninvasively with dynamic N-13 ammonia PET imaging and factor analysis. This method is simple and accurate, and can measure MBF without blood sampling, ROI definition or spillover correction.

• Journal of Broadcast Engineering
• /
• v.22 no.2
• /
• pp.193-206
• /
• 2017

In this paper, we propose a rate control method based on the $R-{\lambda}$ model that supports a parallel encoding structure in GOP levels or IDR period levels for 4K UHD input video in real-time. For this, a slice-level bit allocation method is proposed for parallel encoding instead of sequential encoding. When a rate control algorithm is applied in the GOP level or IDR period level parallelism, the information of how many bits are consumed cannot be shared among the frames belonging to a same frame level except the lowest frame level of the hierarchical B structure. Therefore, it is impossible to manage the bit budget with the existing bit allocation method. In order to solve this problem, we improve the bit allocation procedure of the conventional ones that allocate target bits sequentially according to the encoding order. That is, the proposed bit allocation strategy is to assign the target bits in GOPs first, then to distribute the assigned target bits from the lowest depth level to the highest depth level of the HEVC hierarchical B structure within each GOP. In addition, we proposed a processing method that is used to improve subjective image qualities by allocating the bits according to the coding complexities of the frames. Experimental results show that the proposed bit allocation method works well for frame-level parallel HEVC software encoders and it is confirmed that the performance of our rate controller can be improved with a more elaborate bit allocation strategy by using the preprocessing results.

• The Korean Journal of Nuclear Medicine
• /
• v.38 no.1
• /
• pp.30-40
• /
• 2004

Purpose: The aims of this study were to find brain regions in which gray matter volume was reduced and to show the capability of voxel-based morphometry (VBM) analysis for lateralizing epileptogenic zones in medial temporal lobe epilepsy (mTLE). The findings were compared with fluorodeoxyglucose positron omission tomography (FDG PET). Materials and Methods: MR T1-weighted images of 12 left mTLE and 11 right mTLE patients were compared with those of 37 normal controls. Images were transformed to standard MNI space and averaged in order to create study-specific brain template. Each image was normalized to this local template and brain tissues were segmented. Modulation VBM analysis was performed in order to observe gray matter volume change. Gray matter was smoothed with a Gaussian kernel. After these preprocessing, statistical analysis was peformed using statistical parametric mapping software (SPM99). FDG PET images were compared with those of 22 normal controls using SPM. Results: Gray matter volume was significantly reduced in the left amygdala and hippocampus in left mTLE. In addition, volume of cerebellum, anterior cingulate, and fusiform gyrus in both sides and left insula was reduced. In right mTLE, volume was reduced significantly in right hippocampus. In contrast, FDG uptake was decreased in broad areas of left or right temporal lobes in left TLE and right TLE, respectively. Conclusions: Gray matter loss was found in the ipsilateral hippocampus by modulation VBM analysis in medial temporal lobe epilepsy. This VBM analysis might be useful in lateralizing the epileptogenic zones in medial temporal lobe epilepsy, while SPM analysis of FDG PET disclosed hypometabolic epileptogenic zones.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.143-174
• /
• 2023

With the development of deep learning technologies, Artificial Intelligence powered Optical Character Recognition (AI-OCR) has evolved to read multiple languages from various forms of images accurately. For the financial industry, where a large number of diverse documents are processed through manpower, the potential for using AI-OCR is great. In this study, we present a configuration and a design of an AI-OCR modality for use in the financial industry and discuss the platform construction with application cases. Since the use of financial domain data is prohibited under the Personal Information Protection Act, we developed a deep learning-based data generation approach and used it to train the AI-OCR models. The AI-OCR models are trained for image preprocessing, text recognition, and language processing and are configured as a microservice architected platform to process a broad variety of documents. We have demonstrated the AI-OCR platform by applying it to financial domain tasks of document sorting, document verification, and typing assistance The demonstrations confirm the increasing work efficiency and conveniences.