• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.1
• /
• pp.22-29
• /
• 2010

A real-time detection and tracking of moving objects in video sequences is very important for smart surveillance systems. In this paper, we propose a novel algorithm for the detection of moving objects that is the entropy-based adaptive Gaussian mixture model (AGMM). First, the increment of entropy generally means the increment of complexity, and objects in unstable conditions cause higher entropy variations. Hence, if we apply these properties to the motion segmentation, pixels with large changes in entropy in moments have a higher chance in belonging to moving objects. Therefore, we apply the Clausius entropy theory to convert the pixel value in an image domain into the amount of energy change in an entropy domain. Second, we use an adaptive background subtraction method to detect moving objects. This models entropy variations from backgrounds as a mixture of Gaussians. Experiment results demonstrate that our method can detect motion object effectively and reliably.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.5
• /
• pp.951-959
• /
• 2017

In this paper, we design and implement an Android-based Hangul food menu recognition application that recognizes characters from images captured by a smart phone. Optical Character Recognition (OCR) technology is divided into preprocessing, recognition and post-processing. In the preprocessing process, the characters are extracted using Maximally Stable Extremal Regions (MSER). In recognition process, Tesseract-OCR, a free OCR engine, is used to recognize characters. In the post-processing process, the wrong result is corrected by using the dictionary DB for the food menu. In order to evaluate the performance of the proposed method, experiments were conducted to compare the recognition performance using the actual menu plate as the DB. The recognition rate measurement experiment with OCR Instantly Free, Text Scanner and Text Fairy, which is a character recognizing application in Google Play Store, was conducted. The experimental results show that the proposed method shows an average recognition rate of 14.1% higher than other techniques.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.2 s.46
• /
• pp.123-130
• /
• 2007

The aim of this study was to propose a fusion and registration method with heterogeneous small animal acquisition system in small animal in-vivo study. After an intravenous injection of $^{18}F$-FDG through tail vain and 60 min delay for uptake, mouse was placed on an acryl plate with fiducial markers that were made for fusion between small animal PET (microPET R4, Concorde Microsystems, Knoxville TN) and Discovery LS CT images. The acquired emission list-mode data was sorted to temporally framed sinograms and reconstructed using FORE rebining and 2D-OSEM algorithms without correction of attenuation and scatter. After PET imaging, CT images were acquired by mean of a clinical PET/CT with high-resolution mode. The microPET and CT images were fusion and co-registered using the fiducial markers and segmented lung region in both data sets to perform a point-based rigid co-registration. This method improves the quantitative accuracy and interpretation of the tracer.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.4
• /
• pp.97-103
• /
• 2008

This study is to present a fainting motion recognizing method by using fish-eye lens images to sense emergency situations. The camera with fish-eye lens located at the center of the ceiling of the living room sends images, and then the foreground pixels are extracted by means of the adaptive background modeling method based on the Gaussian complex model, which is followed by tracing of outer points in the foreground pixel area and the elliptical mapping. During the elliptical tracing, the fish-eye lens images are converted to fluoroscope images. the size and location changes, and moving speed information are extracted to judge whether the movement, pause, and motion are similar to fainting motion. The results show that compared to using fish-eye lens image, extraction of the size and location changes. and moving speed by means of the conversed fluoroscope images has good recognition rates.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.10
• /
• pp.326-331
• /
• 2019

In the real world, there are both dynamic objects and static objects, but an autonomous vehicle or mobile robot cannot distinguish between them, even though a human can distinguish them easily. It is important to distinguish static objects from dynamic objects clearly to perform autonomous driving successfully and stably for an autonomous vehicle or mobile robot. To do this, various sensor systems can be used, like cameras and LiDAR. Stereo camera images are used often for autonomous driving. The stereo camera images can be used in object recognition areas like object segmentation, classification, and tracking, as well as navigation areas like 3D world reconstruction. This study suggests a method to distinguish static/dynamic objects using stereo vision for an online autonomous vehicle and mobile robot. The method was applied to a 3D world map reconstructed from stereo vision for navigation and had 99.81% accuracy.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.15 no.4
• /
• pp.40-50
• /
• 2019

In recent years, it is important to visualize an accurate human body model for the low-end system in the medical imaging field where augmented reality technology and virtual reality technology are used. Decreasing the geometry of a model causes a difference from the original shape and considers the difference as an error. So, the error should be minimized while reducing geometry. In this study, the organ areas of a human body in the tomographic images such as CT or MRI is segmented and 3D geometric model is generated, thereby implementing the reconstruction method of multiple resolution level-of-detail model. In the experiment, a virtual reality platform was constructed to verify the shape of the reconstructed model, targeting the spine area. The 3D human body model and patient information can be verified using the virtual reality platform.

• Journal of the Korean Society of Industry Convergence
• /
• v.25 no.2_1
• /
• pp.177-184
• /
• 2022

The automatic defect sorting function of machinery parts is being introduced to the automation of the manufacturing process. In the final stage of automation of the manufacturing process, it is necessary to apply computer vision rather than human visual judgment to determine whether there is a defect. In this paper, we introduce a deep learning method to improve the classification performance of typical mechanical parts, such as welding parts, galvanized round plugs, and electro galvanized nuts, based on the results of experiments. In the case of poor welding, the method to further increase the depth of layer of the basic deep learning model was effective, and in the case of a circular plug, the surrounding data outside the defective target area affected it, so it could be solved through an appropriate pre-processing technique. Finally, in the case of a nut plated with zinc, since it receives data from multiple cameras due to its three-dimensional structure, it is greatly affected by lighting and has a problem in that it also affects the background image. To solve this problem, methods such as two-dimensional connectivity were applied in the object segmentation preprocessing process. Although the experiments suggested that the proposed methods are effective, most of the provided good/defective images data sets are relatively small, which may cause a learning balance problem of the deep learning model, so we plan to secure more data in the future.

• Journal of Platform Technology
• /
• v.9 no.4
• /
• pp.71-78
• /
• 2021

Self-driving vehicles are increasing as new alternatives to solving problems such as human safety, environment and aging. And such technology development has a great ripple effect on other industries. However, various problems are occurring. The number of casualties caused by self-driving is increasing. Although the collision of fixed obstacles is somewhat decreasing, on the contrary, the technology by active obstacles is still insignificant. Therefore, in this study, in order to solve the core problem of self-driving vehicles, we propose a method of extracting active obstacles on the road. First, a center scene is extracted from a continuous image. In addition, it was proposed to extract activity obstacles using activity size and activity repeatability information from objects included in the center scene. The center scene is calculated using region segmentation and merging. Based on these results, the size of the frequency for each pixel in the region was calculated and the size of the activity of the obstacle was calculated using information that frequently appears in activity. Compared to the results extracted directly by humans, the extraction accuracy was somewhat lower, but satisfactory results were obtained. Therefore, it is believed that the proposed method will contribute to solving the problems of self-driving and reducing human accidents.

• Journal of IKEEE
• /
• v.27 no.3
• /
• pp.251-257
• /
• 2023

In this paper, we propose a dual-structured self-attention method that improves the lack of regional features of the vision transformer's self-attention. Vision Transformers, which are more computationally efficient than convolutional neural networks in object classification, object segmentation, and video image recognition, lack the ability to extract regional features relatively. To solve this problem, many studies are conducted based on Windows or Shift Windows, but these methods weaken the advantages of self-attention-based transformers by increasing computational complexity using multiple levels of encoders. This paper proposes a dual-structure self-attention using self-attention and neighborhood network to improve locality inductive bias compared to the existing method. The neighborhood network for extracting local context information provides a much simpler computational complexity than the window structure. CIFAR-10 and CIFAR-100 were used to compare the performance of the proposed dual-structure self-attention transformer and the existing transformer, and the experiment showed improvements of 0.63% and 1.57% in Top-1 accuracy, respectively.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.1
• /
• pp.91-97
• /
• 2009

This paper proposes novel FE-CBIRS that finds best position of a cut to be retrieved based on color feature distribution in digital contents of IPTV. Conventional CBIRS have used a method that utilizes both color and shape information together to classify images, as well as a method that utilizes both feature information of the entire region and feature information of a partial region that is extracted by segmentation for searching. Also, in the algorithm, average, standard deviation and skewness values are used in case of color features for each hue, saturation and intensity values respectively. Furthermore, in case of using partial regions, only a few major colors are used and in case of shape features, the invariant moment is mainly used on the extracted partial regions. Due to these reasons, some problems have been issued in CBIRS in processing time and accuracy so far. Therefore, in order to tackle these problems, this paper proposes the FE-CBIRS that makes searching speed faster by classifying and indexing the extracted color information by each class and by using several cuts that are restricted in range as comparative images.