• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.615-617
• /
• 2023

In recent years, the growing popularity of dogs due to the benefits they bring their owners has contributed to the increase of the number of dogs raised. For owners, it is their responsibility to ensure their dogs' health and safety. However, it is challenging for them to continuously monitor their dogs' activities, which are important to understand and guarantee their wellbeing. In this work, we introduce a camera-based monitoring system to help owners automatically monitor their dogs' activities. The system receives sequences of RGB images and uses YOLOv7 to detect the dog presence, and then applies post-processing to perform dog-centered image cropping on each input sequence. The optical flow is extracted from each sequence, and both sequences of RGB and flow are input to a two-stream EfficientNet to extract their respective features. Finally, the features are concatenated, and a bi-directional LSTM is utilized to retrieve temporal features and recognize the activity. The experiments prove that our system achieves a good performance with the F-1 score exceeding 0.90 for all activities and reaching 0.963 on average.

• International Journal of Computer Science & Network Security
• /
• v.23 no.11
• /
• pp.67-72
• /
• 2023

In the past decade, Autonomous Vehicle Systems (AVS) have advanced at an exponential rate, particularly due to improvements in artificial intelligence, which have had a significant impact on social as well as road safety and the future of transportation systems. The fusion of light detection and ranging (LiDAR) and camera data in real-time is known to be a crucial process in many applications, such as in autonomous driving, industrial automation and robotics. Especially in the case of autonomous vehicles, the efficient fusion of data from these two types of sensors is important to enabling the depth of objects as well as the classification of objects at short and long distances. This paper presents classification of objects using CNN based vision and Light Detection and Ranging (LIDAR) fusion in autonomous vehicles in the environment. This method is based on convolutional neural network (CNN) and image up sampling theory. By creating a point cloud of LIDAR data up sampling and converting into pixel-level depth information, depth information is connected with Red Green Blue data and fed into a deep CNN. The proposed method can obtain informative feature representation for object classification in autonomous vehicle environment using the integrated vision and LIDAR data. This method is adopted to guarantee both object classification accuracy and minimal loss. Experimental results show the effectiveness and efficiency of presented approach for objects classification.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.43 no.9 s.351
• /
• pp.120-127
• /
• 2006

In Korea the vehicle enforcement system(VES) detects speeding vehicle using two inductive loop detectors. And the speed reliability of theirs are evaluated through the analysis of image frame which is captured from video camera. This method is validated to evaluate VES on Korea Laboratory Accreditation Scheme(KOLAS) but it needs much time and expense for the analysis of image frame. Because the number of VES are increasing rapidly, the requirement of new evaluation method is necessary. On this paper, the tape switch sensor as a substitution of existing method was introduced and its application on the site are discussed. On the site test we compared the tape switch sensor on the speed measurement of vehicle with the video image frame. As a result we have founded that the tape switch sensor is evaluated to be feasible system on site in respect to measure the overspeed vehicle.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.3
• /
• pp.246-252
• /
• 2020

Safety accidents have been reported due to falling accumulated snow from cables of cable-supported bridges. In addition to the direct damage caused by falling snow, secondary damage, such as traffic accidents, can occur. Various methods have been proposed to prevent these accidents, but there are still problems in safety and practicality. In this study, a cable robot type was selected as one of the active methods for removing accumulated snow on cables. An attempt was made to increase the climbing ability of the robot to improve the efficiency of snow removal. In addition, the available range of cable diameter for the robot can be adjusted flexibly to be applied to cables used in the field. A high-resolution camera was also installed to check the surface condition of the cable in real time to increase the utility, and be used as a cable inspection robot. A three-axis accelerometer and a tension conversion algorithm were added to measure the tension force of cables. To verify the performance, indoor and field experiments were conducted, and future improvements for the inspection robot were proposed.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.6
• /
• pp.11-18
• /
• 2010

In this paper, it introduced the device that was fabricated for monitoring sleeping positions of infants with 3-axis accelerometer. Sleep monitoring studies has been usually conducted two ways. To monitor sleeping posture by installing a camera and then recording of sleep in the sleeping room continuously is the first one. The other one is monitoring pressure sensor's results data for sleeping. Those two ways' benefits are that are able to get relatively accurate sleeping posture data but, there are many disadvantages like constraints of spaces and places, the installation of sensors or cameras, and high cost. In addition, it has a lot of problems that difficult to solve. For babies, it's not easy to apply, as well as uncomfortable. The proposed method uses a 3-axis accelerometer's X axis, Y axis, Z axis position output values in order to recognize the bad ground sleeping position that use of the buzzer alarm. This method uses a 3-axis acceleration sensor to measure the data and transmit sleeping posture using Bluetooth wireless in real time monitoring. The data is helpful for prevention safety hazard such as choked themselves when they slept back side on.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.7
• /
• pp.622-629
• /
• 2019

Recently, the government is taking new approaches to change the fact that the accident rate and accident death rate of the construction industry account for a high percentage of the whole industry. Especially, it is investing heavily in the development of construction technology that is fused with ICT technology in line with the current trend of the 4th Industrial Revolution. In order to cope with this situation, this paper proposed a concept to recognize and share the work situation information between the construction machine driver and the surrounding worker to enhance the safety in the place where construction machines are operated. In order to realize the part of the concept, we applied image processing technology using camera based on artificial intelligence to earth-moving work. Especially, we implemented an algorithm that can recognize the surrounding worker's circumstance and identify the risk situation through the experiment using the compaction equipment. and image processing algorithm based on YOLO-v3. This algorithm processes 15.06 frames per second in video and can recognize danger situation around construction machine with accuracy of 90.48%. We will contribute to the prevention of safety accidents at the construction site by utilizing this technology in the future.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.6
• /
• pp.222-234
• /
• 2020

Autonomous vehicles are equipped with a wide rage of sensors such as GPS, RADAR, LIDAR, camera, IMU, etc. and are driven by recognizing and judging various transportation systems at intersections in the city. The accident ratio of the intersection of the autonomous vehicles is 88% of all accidents due to the limitation of prediction and judgment of an area outside the sensing distance. Not only research on non-signalized intersection collision avoidance strategies through V2V and V2I is underway, but also research on safe intersection driving in failure situations is underway, but verification and fragments through simple intersection scenarios Only typical V2V failures are presented. In this paper, we analyzed the architecture of the V2V module, analyzed the causal factors for each V2V module, and defined the failure mode. We presented intersection scenarios for various road conditions and traffic volumes. we used the ISO-26262 Part3 Process and performed HARA (Hazard Analysis and Risk Assessment) to analyze the risk of autonomous vehicle based on the simulation. We presented ASIL, which is the result of risk analysis, proposed a monitoring concept for each component of the V2V module, and presented monitoring coverage.

• Journal of the Korean Geotechnical Society
• /
• v.39 no.10
• /
• pp.41-48
• /
• 2023

The presence of abnormalities in the subgrade of roads poses safety risks to users and results in significant maintenance costs. In this study, we aimed to experimentally evaluate the temperature distributions in abnormal areas of subgrade materials using infrared cameras and analyze the data with machine learning techniques. The experimental site was configured as a cubic shape measuring 50 cm in width, length, and depth, with abnormal areas designated for water and air. Concrete blocks covered the upper part of the site to simulate the pavement layer. Temperature distribution was monitored over 23 h, from 4 PM to 3 PM the following day, resulting in image data and numerical temperature values extracted from the middle of the abnormal area. The temperature difference between the maximum and minimum values measured 34.8℃ for water, 34.2℃ for air, and 28.6℃ for the original subgrade. To classify conditions in the measured images, we employed the image analysis method of a convolutional neural network (CNN), utilizing ResNet-101 and SqueezeNet networks. The classification accuracies of ResNet-101 for water, air, and the original subgrade were 70%, 50%, and 80%, respectively. SqueezeNet achieved classification accuracies of 60% for water, 30% for air, and 70% for the original subgrade. This study highlights the effectiveness of CNN algorithms in analyzing subgrade properties and predicting subsurface conditions.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.44 no.1
• /
• pp.1-9
• /
• 2024

Bridges, which are construction structures, have increased from 584 to 38,405 since the 1970s. However, as the number of bridges increases, the number of bridges with a service life of more than 30 years increases to 21,737 (71%) by 2030, resulting in fatal accidents due to basic human resource maintenance of facilities. Accordingly, the importance of bridge safety inspection and maintenance measures is increasing, and the need for decision-making support for supervisors who manage multiple bridges is also required. Currently, the safety inspection and maintenance method of bridges is to write down damage, condition, location, and specifications on the exterior survey map by hand or to record them by taking pictures with a camera. However, errors in notation of damage or defects or mistakes by supervisors are possible, typos, etc. may reduce the reliability of the overall safety inspection and diagnosis. To improve this, this study visualizes damage data recorded in the BIM model in an AR environment and proposes a maintenance plan for bridges with a small number of people through maintenance decision-making support for supervisors.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.14 no.2
• /
• pp.9-16
• /
• 2010

Purpose: With increasing medical use of radiation and radioactive isotopes, there is a need to better manage the risk of radiation exposure. This study aims to grasp and analyze the individual radiation exposure situations of radiation-related workers in a medical facility by specific job, in order to instill awareness of radiation danger and to assist in safety and radiation exposure management for such workers. Materials and Methods: 1 January 2007 to 31 December 2009 to work in medical institutions are classified as radiation workers Nuclear personal radiation dosimeter regularly, continuously administered survey of 40 workers in three years of occupation to target, Imaging Unit beautifully, age, dose sector, job function-related tasks to identify the average annual dose for a deep dose, respectively, were analyzed. The frequency analysis and ANOVA analysis was performed. Results: Imaging Unit beautifully three years the annual dose PET and PET/CT in the work room 11.06~12.62 mSv dose showed the highest, gamma camera injection room 11.72 mSv with a higher average annual dose of occupation by the clinical technicians 8.92 mSv the highest, radiological 7.50 mSv, a nurse 2.61 mSv, the researchers 0.69 mSv, received 0.48 mSv, 0.35 mSv doctors orderly, and detail work employed the average annual dose of the PET and PET/CT work is 12.09 mSv showed the highest radiation dose, gamma camera injection work the 11.72 mSv, gamma camera imaging work 4.92 mSv, treatment and safety management and 2.98 mSv, a nurse working 2.96 mSv, management of 1.72 mSv, work image analysis 0.92 mSv, reading task 0.54 mSv, with receiving 0.51 mSv, 0.29 mSv research work, respectively. Dose sector average annual dose of the study subjects, 15 people (37.5%) than the 1 mSv dose distribution and 5 people (12.5%) and 1.01~5.0 mSv with the dose distribution was less than, 5.01~10.0 mSv in the 14 people (35.0%), 10.01~20.0 mSv in the 6 people (15.0%) of the distribution were analyzed. The average annual dose according to age in occupations that radiological workers 25~34 years old have the highest average of 8.69 mSv dose showed the average annual dose of tenure of 5~9 years in jobs radiation workers in the 9.5 mSv The average was the highest dose. Conclusion: These results suggest that medical radiation workers working in Nuclear Medicine radiation safety management of the majority of the current were carried out in the effectiveness, depending on job characteristics has been found that many differences. However, this requires efforts to minimize radiation exposure, and systematic training for them and for reasonable radiation exposure management system is needed.