• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.4
• /
• pp.663-670
• /
• 2019

The modified Canny edge detection algorithm that can detect the boundary between screen door and platform in the subway is proposed in this paper. Generally, in the subway, the boundary line between the platform and the screen door is darker than the surrounding area. Therefore, an edge image is using the modified bottom-hat transform by considering its characteristics. Double thresholded images with strong edge and weak edge through double thresholding are obtained. An algorithm that detects the boundary invasion between the platform and the screen door is proposed by calculating the length by applying the Hough transform to the double thresholded image and comparing the boundary line length between when there is an object such as a person and when there is no object. In this paper, the results of the proposed modified Canny edge detection algorithm using two different input images according to camera height position are shown by computer simulation.

• Journal of IKEEE
• /
• v.23 no.3
• /
• pp.777-784
• /
• 2019

A pre-fire awareness and automatic notification system are required because it is possible to minimize the damage if the fire situation is precisely detected after a fire occurs in a place where people are unusual or in a mountainous area. In this study, we developed a RaspberryPi-based fire recognition system using Faster-recurrent convolutional neural network (F-RCNN) and single shot multibox detector (SSD) and demonstrated a fire alarm system that works with power line communication. Image recognition was performed with a pie camera of RaspberryPi, and the detected fire image was transmitted to a monitoring PC through an inductive power line communication network. The frame rate per second (fps) for each learning model was 0.05 fps for Faster-RCNN and 1.4 fps for SSD. SSD was 28 times faster than F-RCNN.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.8
• /
• pp.936-942
• /
• 2019

Autonomous driving of drone indoor must move along a narrow path and overcome other factors such as lighting, topographic characteristics, obstacles. In addition, it is difficult to operate the drone in the hallway because of insufficient texture and the lack of its diversity comparing with the complicated environment. In this paper, we study an autonomous drone navigation using Convolution Neural Network(CNN) in indoor environment. The proposed method receives an image from the front camera of the drone and then steers the drone by predicting the next path based on the image. As a result of a total of 38 autonomous drone navigation tests, it was confirmed that a drone was successfully navigating in the indoor environment by the proposed method without hitting the walls or doors in the hallway.

• Journal of the Korean Society of Physical Medicine
• /
• v.14 no.2
• /
• pp.53-61
• /
• 2019

PURPOSE: Forward head posture (FHP) is a head-on-trunk malalignment that results in musculoskeletal dysfunction and neck pain. To improve forward head posture, both the craniocervical flexion exercise (CCFE) and the visual guide (VG) technique have been used. This study compared the immediate effects of CCFE and VG combined with CCFE on craniovertebral angle (CVA), as well as on the activity of the sternocleidomastoid (SCM) and anterior scalene (AS) muscles during CCFE in subjects with FHP. METHODS: In total, 16 subjects (nine males, seven females) with FHP were recruited using the G-power software. Each subject conducted CCFE and CCFE combined with VG in random order. The CVA was recorded using a digital camera and the ImageJ image analysis software. The EMG data of SCM and AS were measured by surface electromyography. A paired T-test was used to assess differences between the effects of the CCFE and VG combined with CCFE interventions in the same group. RESULTS: The CVA was significantly greater for CCFE combined with the VG than for CCFE alone (p<.05). The activity of the SCM and AS muscles was also significantly greater when the VG was combined with CCFE than during CCFE alone across all craniocervical flexion exercise phases (p<.05). CONCLUSION: Use of the VG technique combined with CCFE improved FHP in subjects with FHP compared to CCFE alone.

• Journal of the Korean Society of Mineral and Energy Resources Engineers
• /
• v.55 no.6
• /
• pp.614-623
• /
• 2018

The recent occurrence of consecutive large earthquakes in the southeastern part of the Korean peninsula has brought significant attention to the prevention of earthquake damage in Korea. This article aims to explore a technology-based approach for earthquake drills using state-of-the-art visual intelligence and virtual reality technologies. The technical process consists of several stages, including acquisition of image information in living spaces using a camera, recognition of objects from the acquired image information, extraction of three dimensional geometric information, simulation of virtual earthquakes using dynamic modelling techniques such as the discrete element method, and realization of the simulated earthquake in a virtual reality environment. This article provides a comprehensive analysis of the individual processes at each stage of the technical process, a survey on the current status of related technologies, and discussion of the technical challenges in its execution.

• Korean Journal of Agricultural Science
• /
• v.47 no.4
• /
• pp.1109-1122
• /
• 2020

The aim of this study was to develop a marbling classification and prediction model using small parts of sirloin images based on a deep learning algorithm, namely, a convolutional neural network (CNN). Samples were purchased from a commercial slaughterhouse in Korea, images for each grade were acquired, and the total images (n = 500) were assigned according to their grade number: 1++, 1+, 1, and both 2 & 3. The image acquisition system consists of a DSLR camera with a polarization filter to remove diffusive reflectance and two light sources (55 W). To correct the distorted original images, a radial correction algorithm was implemented. Color images of sirloins of Hanwoo (mixed with feeder cattle, steer, and calf) were divided and sub-images with image sizes of 161 × 161 were made to train the marbling prediction model. In this study, the convolutional neural network (CNN) has four convolution layers and yields prediction results in accordance with marbling grades (1++, 1+, 1, and 2&3). Every single layer uses a rectified linear unit (ReLU) function as an activation function and max-pooling is used for extracting the edge between fat and muscle and reducing the variance of the data. Prediction accuracy was measured using an accuracy and kappa coefficient from a confusion matrix. We summed the prediction of sub-images and determined the total average prediction accuracy. Training accuracy was 100% and the test accuracy was 86%, indicating comparably good performance using the CNN. This study provides classification potential for predicting the marbling grade using color images and a convolutional neural network algorithm.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.6
• /
• pp.115-121
• /
• 2020

With the spread of IoT technology, various IoT applications using facial recognition are emerging. This paper describes the design and implementation of a remote control system using deep learning-based face recognition and hand gesture recognition. In general, an application system using face recognition consists of a part that takes an image in real time from a camera, a part that recognizes a face from the image, and a part that utilizes the recognized result. Raspberry PI, a single board computer that can be mounted anywhere, has been used to shoot images in real time, and face recognition software has been developed using tensorflow's FaceNet model for server computers and hand gesture recognition software using OpenCV. We classified users into three groups: Known users, Danger users, and Unknown users, and designed and implemented an application that opens automatic door locks only for Known users who have passed both face recognition and hand gestures.

• Korean Journal of Agricultural Science
• /
• v.47 no.4
• /
• pp.995-1010
• /
• 2020

In this study, a multivariate analysis model of partial least square regression (PLSR) was developed to predict the moisture content of green peppers using hyperspectral imaging (HSI). In HSI, illumination is essential for high-quality image acquisition and directly affects the analytical performance of the visible near-infrared hyperspectral imaging (VIS/NIR-HSI) system. When green pepper images were acquired using a direct lighting system, the specular reflection from the surface of the objects and their intensities fluctuated with time. The images include artifacts on the surface of the materials, thereby increasing the variability of data and affecting the obtained accuracy by generating false-positive results. Therefore, images without glare on the surface of the green peppers were created using a polarization filter at the front of the camera lens and by exposing the polarizer sheet at the front of the lighting systems simultaneously. The results obtained from the PLSR analysis yielded a high determination coefficient of 0.89 value. The regression coefficients yielded by the best PLSR model were further developed for moisture content mapping in green peppers based on the selected wavelengths. Accordingly, the polarization filter helped achieve an uniform illumination and the removal of gloss and artifact glare from the green pepper images. These results demonstrate that the HSI technique with a polarized lighting system combined with chemometrics can be effectively used for high-throughput prediction of moisture content and image-based visualization.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.12
• /
• pp.1574-1580
• /
• 2020

Traditional pose estimation methods include using special devices or images through image processing. The disadvantage of using a device is that the environment in which the device can be used is limited and costly. The use of cameras and image processing has the advantage of reducing environmental constraints and costs, but the performance is lower. CNN(Convolutional Neural Networks) were studied for pose estimation just using only camera without these disadvantage. Various techniques were proposed to increase cognitive performance. In this paper, the effect of the skip connection on the network was experimented by using various skip connections on the joint recognition of the hand. Experiments have confirmed that the presence of additional skip connections other than the basic skip connections has a better effect on performance, but the network with downward skip connections is the best performance.

• The Journal of Korean Institute of Information Technology
• /
• v.17 no.5
• /
• pp.105-116
• /
• 2019

Most of the public and private buildings in Korea are installing CCTV for crime prevention and follow-up action, insider security, facility safety, and fire prevention, and the number of installations is increasing each year. In the questionnaire conducted on the increasing CCTV, many reactions were positive in terms of the prevention of crime that could occur due to the installation, rather than negative views such as privacy violation caused by CCTV shooting. However, CCTV poses a lot of privacy risks, and when the image data is collected using the cloud, the personal information of the subject can be leaked. InseCam relayed the CCTV surveillance video of each country in real time, including the front camera of the notebook computer, which caused a big issue. In this paper, we introduce a system to prevent leakage of private information and enhance the security of the cloud system by processing the privacy technique on image information about a subject photographed through CCTV.