• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.9
• /
• pp.1825-1838
• /
• 2012

This paper proposes a fast face detection and tracking method which uses depth images as well as RGB images. It consists of the face detection procedure and the face tracking procedure. The face detection method basically uses an existing method, Adaboost, but it reduces the size of the search area by using the depth information and skin color. The proposed face tracking method uses a template matching technique and incorporates an early-termination scheme to reduce the execution time further. The results from implementing and experimenting the proposed methods showed that the proposed face detection method takes only about 39% of the execution time of the existing method. The proposed tracking method takes only 2.48ms per frame. For the exactness, the proposed detection method and previous method showed a same detection ratio but in the error ratio, which is about 0.66%, the proposed method showed considerably improved performance. In all the cases except a special one, the tracking error ratio is as low as about 1%. Therefore, we expect the proposed face detection and tracking methods can be used individually or in combined for many applications that need fast execution and exact detection or tracking.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.2
• /
• pp.251-256
• /
• 2010

This paper aims for developing the intelligent robot emulating human synesthetic skills which associate a color image with sound, so that we are able to build an application system based on the principle of mutual conversion between color image and sound. As the first step, in this study, we have tried to realize a basic system using the color image to sound conversion. This study describes a new conversion method to convert color image into sound, based on the likelihood in the physical frequency information between light and sound. In addition, we present the method of converting color image into sound using color model conversion as well as histograms in the converted color model. In the basis of the method proposed in this study, we built a basic system using Microsoft Visual C++(ver. 6.0). The simulation results revealed that the hue, saturation and intensity elements of a input color image were converted into F0, harmonic and octave elements of a sound, respectively. The converted sound elements were synthesized to generate a sound source with WAV file format using Csound toolkit.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.14 no.5
• /
• pp.31-39
• /
• 2018

Recently, there has been active studies to provide a user-friendly interface in a virtual reality environment by recognizing user hand gestures based on deep learning. However, most studies use separate sensors to obtain hand information or go through pre-process for efficient learning. It also fails to take into account changes in the external environment, such as changes in lighting or some of its hands being obscured. This paper proposes a hand gesture recognition method based on deep learning that is strong in external environments without the need for pre-process of RGB images obtained from general webcam. In this paper we improve the VGGNet and the GoogLeNet structures and compared the performance of each structure. The VGGNet and the GoogLeNet structures presented in this paper showed a recognition rate of 93.88% and 93.75%, respectively, based on data containing dim, partially obscured, or partially out-of-sight hand images. In terms of memory and speed, the GoogLeNet used about 3 times less memory than the VGGNet, and its processing speed was 10 times better. The results of this paper can be processed in real-time and used as a hand gesture interface in various areas such as games, education, and medical services in a virtual reality environment.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.2
• /
• pp.127-133
• /
• 2021

A recent study of people physically falling focused on analyzing the motions of the falls using a recurrent neural network (RNN) and a deep learning approach to get good results from detecting 2D human poses from a single color image. In this paper, we investigate a detection method for estimating the position of the head and shoulder keypoints and the acceleration of positional change using the skeletal keypoints information extracted using PoseNet from an image obtained with a low-cost 2D RGB camera, increasing the accuracy of judgments about the falls. In particular, we propose a fall detection method based on the characteristics of post-fall posture in the fall motion-analysis method. A public data set was used to extract human skeletal features, and as a result of an experiment to find a feature extraction method that can achieve high classification accuracy, the proposed method showed a 99.8% success rate in detecting falls more effectively than a conventional, primitive skeletal data-use method.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.7
• /
• pp.49-55
• /
• 2022

In this paper, we propose an obstacle detection method that can operate robustly even in external environmental factors such as weather. In particular, we propose an obstacle detection system that can accurately inform dangerous situations in AR through DB-based feature matching and RANSAC-based multiplane method. Since the approach to detecting obstacles based on images obtained by RGB cameras relies on images, the feature detection according to lighting is inaccurate, and it becomes difficult to detect obstacles because they are affected by lighting, natural light, or weather. In addition, it causes a large error in detecting obstacles on a number of planes generated due to complex terrain. To alleviate this problem, this paper efficiently and accurately detects obstacles regardless of lighting through DB-based feature matching. In addition, a criterion for classifying feature points is newly calculated by normalizing multiple planes to a single plane through RANSAC. As a result, the proposed method can efficiently detect obstacles regardless of lighting, natural light, and weather, and it is expected that it can be used to secure user safety because it can reliably detect surfaces in high and low or other terrains. In the proposed method, most of the experimental results on mobile devices reliably recognized indoor/outdoor obstacles.

• Ecology and Resilient Infrastructure
• /
• v.9 no.4
• /
• pp.218-227
• /
• 2022

This study attempted classification through deep learning-based image training for land cover classification in river spaces which is one of the important data for efficient river management. For this purpose, land cover classification analysis with the RGB image of the target section based on the category classification index of major land cover map was conducted by using the learning outcomes from the result of labeling. In addition, land cover classification of the river spaces was performed by unsupervised and supervised classification from Sentinel-2 satellite images provided in an open format, and this was compared with the results of deep learning-based image classification. As a result of the analysis, it showed more accurate prediction results compared to unsupervised classification results, and it presented significantly improved classification results in the case of high-resolution images. The result of this study showed the possibility of classifying water areas and wetlands in the river spaces, and if additional research is performed in the future, the deep learning based image train method for the land cover classification could be used for river management.

• Journal of Bio-Environment Control
• /
• v.31 no.4
• /
• pp.270-278
• /
• 2022

This study was conducted using deep learning technology to classify for 'Mihwang' peach maturity with RGB images and fruit quality attributes during fruit development and maturation periods. The 730 images of peach were used in the training data set and validation data set at a ratio of 8:2. The remains of 170 images were used to test the deep learning models. In this study, among the fruit quality attributes, firmness, Hue value, and a^* value were adapted to the index with maturity classification, such as immature, mature, and over mature fruit. This study used the CNN (Convolutional Neural Networks) models for image classification; VGG16 and InceptionV3 of GoogLeNet. The performance results show 87.1% and 83.6% with Hue left value in VGG16 and InceptionV3, respectively. In contrast, the performance results show 72.2% and 76.9% with firmness in VGG16 and InceptionV3, respectively. The loss rate shows 54.3% and 62.1% with firmness in VGG16 and InceptionV3, respectively. It considers increasing for adapting a field utilization with firmness index in peach.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.6
• /
• pp.392-399
• /
• 2023

This paper proposes a deep learning model to determine the region and depth of cabbage cores for robotic automation of the cabbage core removal process during the kimchi manufacturing process. In addition, rather than predicting the depth of the measured cabbage, a model was presented that simultaneously detects and classifies the area by converting it into a discrete class. For deep learning model learning and verification, RGB images of the harvested cabbage 522 were obtained. The core region and depth labeling and data augmentation techniques from the acquired images was processed. MAP, IoU, acuity, sensitivity, specificity, and F1-score were selected to evaluate the performance of the proposed YOLO-v4 deep learning model-based cabbage core area detection and classification model. As a result, the mAP and IoU values were 0.97 and 0.91, respectively, and the acuity and F1-score values were 96.2% and 95.5% for depth classification, respectively. Through the results of this study, it was confirmed that the depth information of cabbage can be classified, and that it can be used in the development of a robot-automation system for the cabbage core removal process in the future.

• Journal of the Korean earth science society
• /
• v.39 no.3
• /
• pp.241-249
• /
• 2018

As the international trade increases, vessel traffics around the Korean Peninsula are also increasing. Maritime accidents hence take place more frequently in the southern coast of Korea where many big and small ports are located. Accidents involving ship collision and sinking result in a substantial human and material damage as well as the marine environmental pollution. Therefore, it is necessary to locate the ships quickly when such accidents occur. In this study, we suggest a new ship detection index by comparing and analyzing the reflectivity of each channel of the Korea MultiPurpose SATellite-2 (KOMPSAT-2) images of the area around the Gwangyang Bay. A threshold value of 0.1 is set based on a histogram analysis, and all vessels are detected when compared with RGB composite images. After selecting a relatively large ship as a representative sample, the distribution of spatial reflectivity around the ship is studied. Uniform shadows are detected on the northwest side of the vessel. This indicates that the sun is in the southeast, the azimuth of the actual satellite image is $144.80^{\circ}$, and the azimuth angle of the sun can be estimated using the shadow position. The reflectivity of the shadows is 0.005 lower than the surrounding sea and ship. The shadow height varies with the position of the bow and the stern, perhaps due to the relative heights of the ship deck and the structure. The results of this study can help search technology for missing vessels using optical satellite images in the event of a marine accident around the Korean Peninsula.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.4 no.4
• /
• pp.250-257
• /
• 2011

This experiment present the automatic detection algorithm of gastric cancer that take second place among all cancers. If an inflammation and a cancer are not examined carefully, early ones have difficulty in being diagnosed as illnesses than advanced ones. For diagnosis of gastric cancer, and progressing cancer in this study, present 4 algorithm. research team extracted an abnormal part in stomach through the endoscope image. At first, decide to use shading technique or not in each endoscope image for study. it make easy distinguish to whether tumor is existing or not by putting shading technique in or eliminate it by the color. Second. By passing image subjoin shading technique to erosion filter, eliminate noise and make give attention to diagnose. Third. Analyzing out a line and fillet graph from image adding surface shade and detect RED value according to degree of symptoms. Fourth. By suggesting this algorithm, that making each patient's endscope image into subdivision graph including RED graph value, afterward revers the color, revealing the position of tumor, this study desire to help to diagnosing gastric, other cancer and inflammation.