• The Journal of Korean Institute of Next Generation Computing
• /
• v.15 no.6
• /
• pp.7-14
• /
• 2019

The automatic monitoring and detection of crowd behavior in the surveillance videos has obtained significant attention in the field of computer vision due to its vast applications such as security, safety and protection of assets etc. Also, the field of crowd analysis is growing upwards in the research community. For this purpose, it is very necessary to detect and analyze the crowd behavior. In this paper, we proposed a deep learning-based method which detects abnormal activities in surveillance cameras installed in a smart city. A fine-tuned VGG-16 model is trained on publicly available benchmark crowd dataset and is tested on real-time streaming. The CCTV camera captures the video stream, when abnormal activity is detected, an alert is generated and is sent to the nearest police station to take immediate action before further loss. We experimentally have proven that the proposed method outperforms over the existing state-of-the-art techniques.

• Journal of Broadcast Engineering
• /
• v.23 no.6
• /
• pp.914-924
• /
• 2018

In this paper, we implement an Android application for infant language education using marker-based augmented reality. Combining animal word markers (noun), size/color word markers (adjective), and action word markers (verb) in puzzle form to make a simple sentence, the application shows virtual contents related to the content of the sentence. For example, when an animal marker is showed up on a camera, the corresponding animal appears. Additionally, when the motion markers are combined, the animal's appearance changes into an animation in which it acts. When a user touched a marker, user can hear the sound of the word, which gives an auditory effect, and by adding the rotation function, user can see the animation in any direction. Our goal is to increase infants' interest in learning language and also increase the effectiveness of education on the meaning of words and the structure of simple sentences, by encouraging them to actively participate in language learning through visual and auditory stimuli.

• Applied Chemistry for Engineering
• /
• v.22 no.5
• /
• pp.522-525
• /
• 2011

In this study, an established enzyme-linked immunosorbent assay and immuno-chromatography technique are combined to fabricate an immuno-strip sensor for the detection of S. aureus. The immuno-strip is manufactured by using four different functional membranes. The capture antibody is immobilized on the nitrocellulose membrane due to the high affinity and the capillary action through porous membranes induces a flow of sample. A colorimetric signal is appeared according to the enzyme reaction and is analyzed by the digital camera (qualitative analysis) and home-made image analysis software (quantitative analysis). Under the optimal conditions, samples with S. aureus in the range of $2.7{\times}10^4{\sim}2.7{\times}10^7CFU/mL$ can be detected by the colorimetric method within 30 min.

• 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.

• Smart Media Journal
• /
• v.11 no.3
• /
• pp.90-101
• /
• 2022

Buses are a popular means of transportation. As such, thorough preparation is needed for passenger safety management. However, the safety system is insufficient because there are accidents such as a death accident occurred when the bus departed without recognizing the elderly approaching to get on in 2018. There is a safety system that prevents pinching accidents through sensors on the back door stairs, but such a system does not prevent accidents that occur in the process of getting on and off like the above accident. If it is possible to predict the intention of bus passengers to get on and off, it will help to develop a safety system to prevent such accidents. However, studies predicting the intention of passengers to get on and off are insufficient. Therefore, in this paper, we propose a 1×1 CNN3D-based getting on and off intention prediction model using skeleton keypoints of passengers extracted from the camera image attached to the bus through UDP-Pose. The proposed model shows approximately 1~2% higher accuracy than the RNN and LSTM models in predicting passenger's getting on and off intentions.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.5
• /
• pp.656-661
• /
• 2022

Password with a combination of 4-digit numbers has been widely adopted for various authentication systems (such as credit card authentication, digital door lock systems and so on). However, this system could not be safe because the 4-digit password can easily be stolen by predicting it from the fingermarks on the keypad or display screen. Furthermore, due to the prolonged COVID-19 pandemic, contactless method has been preferred over contact method in authentication. This paper suggests a new password input method based on eyeblink pattern analysis in video sequence. In the proposed method, when someone stands in front of a camera, the sequence of eyeblink motions is captured (according to counting signal from 0 to 9 or 9 to 0), analyzed and encoded, producing the desired 4-digit decimal numbers. One does not need to touch something like keypad or perform an exaggerated action, which can become a very important clue for intruders to predict the password.

• Journal of Industrial Convergence
• /
• v.21 no.2
• /
• pp.117-123
• /
• 2023

In the fintech environment, Smart phones are mainly used for various service. User authentication technology is required to use safe services. Authentication is performed by transmitting authentication information to the server when the PIN or password is entered and touch the button completing authentication. But A post-attack is possible because the smudge which is the trace of using screen remains instead of recording attack with a camera or SSA(Shoulder Surfing Attack). To prevent smudge attacks, users must erase their fingerprints after authentication. In this study, we proposed a technique to determine whether to erase fingerprints. The proposed method performed erasing fingerprint which is the trace of touching after entering PIN and designed the security keypads that processes instead of entering completion button automatically when determined whether the fingerprint has been erased or not. This method suggests action that must erase the fingerprint when entering password. By this method, A user must erase the fingerprint to complete service request and can block smudge attack.

• Journal of The Korean Society of Integrative Medicine
• /
• v.11 no.2
• /
• pp.207-219
• /
• 2023

Purpose : This study was conducted to investigate the changes in trunk movement and ground reaction during sit to stand motion using visual feedback. Methods : Fifteen adults (average age: 23.53±1.77 years) participated in this study. An infrared reflective marker was attached to the body each participant for motion analysis, and the participants performed sit to stand motion while wearing a hat attached with a laser pointer, which provided visual feedback. First, the sit to stand action was repeated thrice without obtaining any visual feedback, followed by a three minute break. Next, the laser pointers attached to hats were irradiated on a whiteboard, located at a distance of 5 m in front of the chairs, on which the participants sat; a baseline was set, and the participants performed stand up movements three times under this condition. A visual feedback was provided to the participants to prevent the laser pointers from crossing the set baseline. During each stand-up movement, the position of the reflective marker attached to the subject's body was recorded in real time using an infrared camera for motion analysis. The trunk movement and ground reaction force were extracted through recorded data and analyzed according to the presence or absence of visual feedback. Results : The results indicated that in the presence of a visual feedback during the sit-to-stand movements, the range of motion of the trunk and hip joints decreased, whereas that of the knee and ankle joints increased in the sagittal plane. The rotation angle of the trunk in the horizontal plane decreased. The left and right movement speed of the center of pressure increased, the pressing force decreased, and the forward and backward movement speed of the trunk decreased. Conclusion : The results suggest that the efficiency and stability of the stand up movement of a body increase when a visual feedback is provided.

• International conference on construction engineering and project management
• /
• 2020.12a
• /
• pp.313-322
• /
• 2020

The recognition of the risk hazards is a vital step to effectively prevent accidents on a construction site. The advanced development in computer vision systems and the availability of the large visual database related to construction site made it possible to take quick action in the event of human error and disaster situations that may occur during management supervision. Therefore, it is necessary to analyze the risk factors that need to be managed at the construction site and review appropriate and effective technical methods for each risk factor. This research focuses on analyzing Occupational Safety and Health Agency (OSHA) related to risk zone identification rules that can be adopted by the image recognition technology and classify their risk factors depending on the effective technical method. Therefore, this research developed a pattern-oriented classification of OSHA rules that can employ a large scale of safety hazard recognition. This research uses joint reasoning of risk zone Identification and numeric input by utilizing a stereo camera integrated with an image detection algorithm such as (YOLOv3) and Pyramid Stereo Matching Network (PSMNet). The research result identifies risk zones and raises alarm if a target object enters this zone. It also determines numerical information of a target, which recognizes the length, spacing, and angle of the target. Applying image detection joint logic algorithms might leverage the speed and accuracy of hazard detection due to merging more than one factor to prevent accidents in the job site.

• The Journal of Korea Robotics Society
• /
• v.19 no.3
• /
• pp.293-310
• /
• 2024

In this paper, we propose an agent model for Language-Driven Zero-Shot Object Navigation (L-ZSON) tasks, which takes in a freeform language description of an unseen target object and navigates to find out the target object in an inexperienced environment. In general, an L-ZSON agent should able to visually ground the target object by understanding the freeform language description of it and recognizing the corresponding visual object in camera images. Moreover, the L-ZSON agent should be also able to build a rich spatial context map over the unknown environment and decide efficient exploration actions based on the map until the target object is present in the field of view. To address these challenging issues, we proposes AML (Agent Model for L-ZSON), a novel L-ZSON agent model to make effective use of AI foundation models such as Large Language Model (LLM) and Vision-Language model (VLM). In order to tackle the visual grounding issue of the target object description, our agent model employs GLEE, a VLM pretrained for locating and identifying arbitrary objects in images and videos in the open world scenario. To meet the exploration policy issue, the proposed agent model leverages the commonsense knowledge of LLM to make sequential navigational decisions. By conducting various quantitative and qualitative experiments with RoboTHOR, the 3D simulation platform and PASTURE, the L-ZSON benchmark dataset, we show the superior performance of the proposed agent model.