• Journal of the Semiconductor & Display Technology
• /
• v.19 no.4
• /
• pp.1-5
• /
• 2020

By adapting black body leadflame and thin film type Green A filter, we successfully demonstrated night vision imaging system (NVIS) Green A compatible LED. Fabricated NVIS compatible LEDs show small form factor compared to that of commercialized NVIS compatible LED. Especially, NVIS radiance and chromaticity of MIL-STD-3009 specification can be satisfied simultaneously and easily by controlling the color temperature of the white LED as well as the concentration of the Green A dye and the thickness of the Green A filter. The optimal dye concentration of the NVIS Green A filter is expected to be about 1 wt%. The results of this study are expected to contribute to miniaturization, weight reduction and localization of avionic display and lighting devices.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.1
• /
• pp.75-78
• /
• 2022

Deep Neural Networks (DNN) has become an essential data processing architecture for the implementation of multiple computer vision tasks. Recently, DNN-based algorithms achieve much higher recognition accuracy than traditional algorithms based on shallow learning. However, training and inference DNNs require huge computational capabilities than daily usage purposes of computers. Moreover, with increased size and depth of DNNs, CPUs may be unsatisfactory since they use serial processing by default. GPUs are the solution that come up with greater speed compared to CPUs because of their Parallel Processing/Computation nature. In this paper, we analyze the inference time complexity of DNNs using well-known computer vision library, OpenCV. We measure and analyze inference time complexity for three cases, CPU, GPU-Float32, and GPU-Float16.

• International Journal of Computer Science & Network Security
• /
• v.24 no.6
• /
• pp.89-98
• /
• 2024

Due to the increase in population and consequently the increase in the production of plastic waste, recovery of this part of the waste is an undeniable necessity. On the other hand, the recycling of plastic waste, if it is placed in a systematic process and controlled, can be effective in creating jobs and maintaining environmental health. Waste collection in many large cities has become a major problem due to lack of proper planning with increasing waste from population accumulation and changing consumption patterns. Today, waste management is no longer limited to waste collection, but waste collection is one of the important areas of its management, i.e. training, segregation, collection, recycling and processing. In this study, a systematic method based on machine vision for sorting plastic bottles in different colors for recycling purposes will be proposed. In this method, image classification and segmentation techniques were presented to improve the performance of plastic bottle classification. Evaluation of the proposed method and comparison with previous works showed the proper performance of this method.

• Journal of Sensor Science and Technology
• /
• v.26 no.1
• /
• pp.39-43
• /
• 2017

Development of vision system as a nondestructive evaluation system can be very useful in screening the defective mechanical parts before they are assembled into the final product. Since the tens of thousands of the mechanical parts are used in an automobile carefully inspecting the quality of the mechanical parts is very important to maximize the performance of the automobile. To sort out the defective mechanical parts before they are assembled, auto parts fabrication companies employ various inspection systems. Nondestructive evaluation systems are getting rapidly popular among various inspection systems. In this study, we have developed a vision system to inspect the inside of the brake caliper, a part that is used to compose a brake which is the most important to the safety of the drivers and the passengers. In a brake caliper, a piston is pushed against the brake disk by oil pressure, causing a friction to damp the rotation of the wheel. Inside the caliper, a groove is positioned to adopt an oil seal to prevent the oil leaks. Inspecting the groove with our vision system, we could examine the existence of the contaminants which are normally the residual tiny pieces from the machining process. We used a high resolution GigE camera, 360 degree lens to look in the inside view of the caliper at once, and a special illumination system in this vision system. We used the edge detection technique to successfully detect the contaminants which were in the form of small metal chips. Labview graphical program was used to process the digital data from the camera and to display the vision and the statistics of the contaminants. We were very successful in detecting the contaminants from the various size calipers. We think we are ready to employ this vision system to the caliper production factories.

• Journal of the Korea Convergence Society
• /
• v.11 no.2
• /
• pp.147-154
• /
• 2020

This study is about the development of ICT-based wearable devices for vision recovery that can cause functional myopia improvement through accommodation training. Vision Training Device(OTUS) is a head mount type wearable device, which naturally stimulates the contraction and relaxation of the ciliary muscles of eye. Users can conduct customized vision training based on personal vision information stored through the device. In the experiment, the effects of improvement of the symptoms by the accommodation training were compared and analysed for the two groups (16 comparative group and 16 accommodation training group) after causing functional myopia. The result showed the functional myopia improved average 0.44D±0.35 (p<0.05) at the accommodation training group compared to the comparative group. This study proved the effectiveness of vision training device(OTUS) on functional myopia, but further clinical trials are judged necessary to prove the possibility of long-term control of the functional myopia.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2004.10a
• /
• pp.277-280
• /
• 2004

In recent die industry, web-based production control system is applied widely because of the improvement of IT technology. In result, many researches are published about remote monitoring at a long distance. The target of this study is to develop Die Discrimination System using web-based vision, and CAD API when client discriminates die in process at a long distance. Special feature of this system is to use 2D vision image and to match with DB. We can get discrimination result enough to want with short time and a little low precision in web-monitoring by development of this system.

• Journal of Korea Multimedia Society
• /
• v.17 no.7
• /
• pp.787-796
• /
• 2014

Many mobile robot navigation methods utilize laser scanners, ultrasonic sensors, vision camera, and so on for detecting obstacles and path following. However, human utilizes only vision(e.g. eye) information for navigation. In this paper, we study a mobile robot control method based on only the camera vision. The Gaussian Mixture Model and a shadow removal technology are used to divide the foreground and the background from the camera image. The mobile robot uses a combined CAMSHIFT and KLT feature tracker algorithms based on the information of the foreground to follow a person. The algorithm is verified by experiments where a person is tracked and followed by a robot in a hallway.

• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.8
• /
• pp.851-858
• /
• 2009

In this study, we propose a new input device using vision technology for positioning of multiple DOFs. The input device is composed of multiple Tags on a transparent table and a vision camera below the table. Vision camera detects LEDs at the bottom of each Tag to derive information of the ID, position and orientation. The information are used to determine position and orientation of remote target DOFs. Our developed approach is very reliable and effective, especially when the corresponding DOFs are from many independent individuals. We show an application example with a SCARA robot to prove the flexibility and extendability.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.16 no.5
• /
• pp.14-23
• /
• 2007

Welding fabrication invariantly involves three district sequential steps: preparation, actual process execution and post-weld inspection. One of the major problems in automating these steps and developing autonomous welding system is the lack of proper sensing strategies. Conventionally, machine vision is used in robotic arc welding only for the correction of pre-taught welding paths in single pass. However, in this paper, multipass tracking more than single pass tracking is performed by conventional seam tracking algorithm and developed one. And tracking performances of two algorithm are compared in multipass tracking. As the result, tracking performance in multi-pass welding shows superior conventional seam tracking algorithm to developed one.

• Journal of Mechanical Science and Technology
• /
• v.14 no.7
• /
• pp.782-788
• /
• 2000

In this paper, we present a new approach to visual feedback control using image-based visual servoing with stereo vision. In order to control the position and orientation of a robot with respect to an object, a new technique is proposed using binocular stereo vision. The stereo vision enables us to calculate an exact image Jacobian not only around a desired location but also at other locations. The suggested technique can guide a robot manipulator to the desired location without providing a priori knowledge such as the relative distance to the desired location or the model of an object even when the initial positioning error is large. This paper describes a model of stereo vision and how to generate feedback commands. The performance of the proposed visual servoing system is illustrated by experimental results and compared with conventional control methods for an assembly robot.