• Journal of Korea Multimedia Society
• /
• v.24 no.7
• /
• pp.890-902
• /
• 2021

Although the object detection accuracy with still images has been significantly improved with the advance of deep learning techniques, the object detection problem with video data remains as a challenging problem due to the real-time requirement and accuracy drop with occlusion. In this research, we propose a method in pig detection for video monitoring environment. First, we determine a motion, from a video data obtained from a tilted-down-view camera, based on the average size of each pig at each location with the training data, and extract key frames based on the motion information. For each key frame, we then apply YOLO, which is known to have a superior trade-off between accuracy and execution speed among many deep learning-based object detectors, in order to get pig's bounding boxes. Finally, we merge the bounding boxes between consecutive key frames in order to reduce false positive and negative cases. Based on the experiment results with a video data set obtained from a pig farm, we confirmed that the pigs could be detected with an accuracy of 97% at a processing speed of 37fps.

• Journal of Korea Multimedia Society
• /
• v.22 no.8
• /
• pp.823-831
• /
• 2019

In recent years, there has been developed systems such as a surveillance system and access control using a face recognition function instead of a password or an RFID chip, thereby reducing the risk of falsification. Moreover, deep learning technology has been applied to real-time face recognition technology in video, so it makes possible the development of access control system that improves the accuracy of recognition and efficiency of management. In this paper, we propose a real-time access management system based on face recognition using ResNet. The system is based on web server, which make it possible to manage the access by recognizing the person of the image through the camera and access information stored in the database. It can be accessed by a user application to receive various information. The implemented system identifies a person in real time and allows access control by accurately distinguishing whether they are members or not, and the test results can recognize in 0.2 seconds. The accuracy of recognition rate is up to about 97% depending on the experiment environment. With this system, access can be managed quickly and effectively, even many people rush to it.

• Journal of the Korean Society of Industry Convergence
• /
• v.22 no.2
• /
• pp.105-110
• /
• 2019

Most titanium alloy waste with cutting oil was discarded without recycling process so that it can be caused by metal and oil fires. However, there is no fire management system and studies on the titanium or titanium alloy waste in spite of high fire risk. The purpose of this experimental study is to identify the fire risk of the titanium alloy waste with cutting oil. We collected the 120g waste which was made in the biomedical titanium alloy cutting process. The waste was burned and conducted thermal image analysis with infrared camera. The experimental results which illustrated the process, characteristics, and trends of fire are presented. Firstly, the cutting oil was burned and partially the titanium alloy waste was burned. The maximum temperature of the fire was more than $650^{\circ}C$ in some specific spots. These results means when a lot of titanium alloy waste with cutting oil was ignited, this fire could connect the titanium fire. In other words, the fire has a flammable liquid fire and combustible metal fire at the same time. The experimental study could be used fire prevention, response, and investigation of the titanium alloy waste.

• Annual Conference of KIPS
• /
• 2004.05a
• /
• pp.181-184
• /
• 2004

본 논문을 통하여 개발된 시스템은 라인카메라를 사용하여 터널의 균열 영상을 획득하기 위하여 사용되는 시스템으로, 터널 내부의 균열 영상을 실시간으로 촬영하여 저장하는 시스템이다. 터널 영상은 의료영상과 같이 작은 손실에도 큰 영향을 미칠 수 있다. 이러한 요소 때문에 본 시스템에서는 CCD 방식의 라인 스캔 카메라를 이용하여 터널 영상을 촬영하며, 이를 저장 하는 방법에 있어서는 비손실 압축기법을 사용하였다. 비손실 압축 기법의 사용을 이용하여 영상을 저장하는 방식은 많은 데이터 저장공간을 필요로 한다. 이러한 문제점은 기술 개발의 놀라운 성장과 더불어 기존 테이프 기반의 방식에서 벗어나 로컬 하드디스크로 직접 저장하는 기법을 사용할 수 있게 되었다. 즉, 라인 카메라를 이용하는 기존 시스템의 경우에는 영상데이타를 실시간으로 저장할 수 없는 문제점 때문에 촬영 속도를 느리게 하면서 영상을 획득하였으며, 획득한 영상을 테이프로 저장하도록 설계되었다. 이에 반하여 본 시스템에서는 테이프를 대신하여 로컬 디스크를 사용하여, 대용량의 영상을 실시간으로 저장할 수 있는 시스템을 개발하였다. 예비실험을 통하여 나타난 결과에 따르면 본 논문을 통하여 개발된 시스템은 약 20Km 이상의 속도로 진행하는 열차에서 터널의 영상을 실시간으로 촬영하여 저장할 수 있음을 살펴볼 수 있었다.

• Journal of the Korean Society of Industry Convergence
• /
• v.22 no.4
• /
• pp.447-457
• /
• 2019

The intelligent sensory system is required to ensure the accurate welding performance. This paper describes the development of an intelligent vision sensor for the robotic laser welding. The sensor system includes a PC based vision camera and a stripe-type laser diode. A set of robust image processing algorithms are implemented. The laser-stripe sensor can measure the profile of the welding object and obtain the seam line. Moreover, the working distance of the sensor can be changed and other configuration is adjusted accordingly. The robot, the seam tracking system, and CW Nd:YAG laser are used for the laser welding robot system. The simple and efficient control scheme of the whole system is also presented. The profile measurement and the seam tracking experiments were carried out to validate the operation of the system.

• The Journal of Korea Robotics Society
• /
• v.14 no.1
• /
• pp.50-57
• /
• 2019

This work presents a design and control method for a flexible robot arm operated by a wire drive that follows human gestures. When moving the robot arm to a desired position, the necessary wire moving length is calculated and the motors are rotated accordingly to the length. A robotic arm is composed of a total of two module-formed mechanism similar to real human motion. Two wires are used as a closed loop in one module, and universal joints are attached to each disk to create up, down, left, and right movements. In order to control the motor, the anti-windup PID was applied to limit the sudden change usually caused by accumulated error in the integral control term. In addition, master/slave communication protocol and operation program for linking 6 motors to MYO sensor and IMU sensor output were developed at the same time. This makes it possible to receive the image information of the camera attached to the robot arm and simultaneously send the control command to the robot at high speed.

• Journal of Korea Multimedia Society
• /
• v.22 no.2
• /
• pp.136-145
• /
• 2019

The crowded environment of a domestic pig farm is highly vulnerable to the spread of infectious diseases such as foot-and-mouth disease, and studies have been conducted to automatically analyze behavior of pigs in a crowded pig farm through a video surveillance system using a camera. Although it is required to correctly separate occluding pigs for tracking each individual pigs, extracting the boundaries of the occluding pigs fast and accurately is a challenging issue due to the complicated occlusion patterns such as X shape and T shape. In this study, we propose a fast and accurate method to separate occluding pigs not only by exploiting the characteristics (i.e., one of the fast deep learning-based object detectors) of You Only Look Once, YOLO, but also by overcoming the limitation (i.e., the bounding box-based object detector) of YOLO with the test-time data augmentation of rotation. Experimental results with two-pigs occlusion patterns show that the proposed method can provide better accuracy and processing speed than one of the state-of-the-art widely used deep learning-based segmentation techniques such as Mask R-CNN (i.e., the performance improvement over Mask R-CNN was about 11 times, in terms of the accuracy/processing speed performance metrics).

• Journal of the Korean Society of Visualization
• /
• v.17 no.1
• /
• pp.60-68
• /
• 2019

Flow visualizations have been carried out to analyze the characteristics of bubby flows exhausted from a venturi-type bubble generator with an air vent. For various design parameters and operating conditions of the bubble generator, the images of bubbly flows was recorded using a high-speed camera and a microscope. Then the amount and size distribution of bubble was evaluated by an image processing technique. The results show that for increasing the amount of bubble, it is more effective to reduce the venturi throat than to enlarge the air vent diameter. If the water flow rate increases, the bubble generation rate increases but reaches a status of saturation, whose condition depends on Reynolds number at a given air vent diameter. The bubble size increases as the diameter of venturi throat decreases and Reynolds number increases. However, the air vent diameter is not a significant factor on bubble size.

• Smart Media Journal
• /
• v.8 no.3
• /
• pp.53-61
• /
• 2019

In this paper, designing and implementing multi-communication middleware in multi-thread environmet through event-based synchronization method are proposed for stable data transmission of electronic optical equipment, which requires combining camera and various sensors to process multiple high-speed data. To verify the performance of the implemented communication middleware, image data and sensor data were sent to compare differences in reception-based and transmission-based cycles, and the maximum number of communication possibilities to transmit and process multiple was measured and analyzed. In addition, the proposed communication middleware's performance was verified through experiments such as validating the integrity of the transmitted data and measuring the Round Trip Time.

• Journal of Multimedia Information System
• /
• v.6 no.1
• /
• pp.23-30
• /
• 2019

A communications profile is a system that acquires information from communication links to an ambulance or other vehicle moving on a road and compiles a database based on this information. The equipment (six sets of HDTVs, fish-eye camera, satellite antenna with tracking system, and receiving power from the satellite beacon of the N-star) mounted on the roof of the vehicle, image data were obtained at Yokohama Japan. From these data, the polygon of the building was actually produced and has arranged on the map of the Geographical Survey Institute of a 50 m-mesh. The optical study (relationship between visibility rate and elevation angle) were performed on actual data taken by fish-eye lens, and simulated data by 3D-Map with polygons. There was no big difference. This 3D map system then predicts the communication links that will be available at a given location. For line-of-sight communication, optical analysis allows approximation if the frequency is sufficiently high. For non-line-of-sight communication, previously obtained electric power data can be used as reference information for approximation in certain cases when combined with predicted values calculated based on a 3D map. 3D maps are more effective than 2D maps for landing emergency medical helicopters on public roadways in the event of a disaster. Using advanced imaging technologies, we have produced a semi-automatic creation of a high-precision 3D map at Yokohama Yamashita Park and vicinity and assessed its effectiveness on telecommunications and ambulatory merits.