• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.10
• /
• pp.4098-4116
• /
• 2020

Mobile devices such as smartphones are very attractive targets for augmented reality (AR) services, but their limited resources make it difficult to increase the number of objects to be recognized. When the recognition process is scaled to a large number of objects, it typically requires significant computation time and memory. Therefore, most large-scale mobile AR systems rely on a server to outsource recognition process to a high-performance PC, but this limits the scenarios available in the AR services. As a part of realizing large-scale standalone mobile AR, this paper presents a solution to the problem of accuracy, memory, and speed for large-scale object recognition. To this end, we design our own basic feature and realize spatial locality, selective feature extraction, rough pose estimation, and selective feature matching. Experiments are performed to verify the appropriateness of the proposed method for realizing large-scale standalone mobile AR in terms of efficiency and accuracy.

• Journal of information and communication convergence engineering
• /
• v.21 no.4
• /
• pp.329-336
• /
• 2023

This paper introduces an edge AI-based scene-specific object detection system for long-term traffic management, focusing on analyzing congestion and movement via cameras. It aims to balance fast processing and accuracy in traffic flow data analysis using edge computing. We adapt the YOLOv5 model, with four heads, to a scene-specific model that utilizes the fixed camera's scene-specific properties. This model selectively detects objects based on scale by blocking nodes, ensuring only objects of certain sizes are identified. A decision module then selects the most suitable object detector for each scene, enhancing inference speed without significant accuracy loss, as demonstrated in our experiments.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.14 no.3
• /
• pp.58-67
• /
• 2006

In this paper, fuzzy logic based active ventilation system with security function is proposed and implemented. We can easily experience the situation that inner air is so hot to get start immediately after parking at summer day. Hot temperature is enough to explode a gas lighter or to suffocate a little chid. Proposed system has 1 blower and 2 axial fans to ventilate inner air. Based on the fuzzy logic, speed and direction of each fan are controlled. In addition to controlling fans, controller put down windows and adjust the periods of open time. In order to prevent the theft and security problems, IR sensors are used to detect objects. On detecting objects, controller put up windows. Experimental result shows that implemented system can be effectively ventilate inner air and reduce temperature. Proposed system can be applicable to commercial automobiles.

• Journal of the Semiconductor & Display Technology
• /
• v.15 no.3
• /
• pp.51-56
• /
• 2016

This paper proposes a new image enhancement method for an infrared thermal image. The proposed method uses both Laplacian and Prewitt edge detectors. Without a visible light, it uses an infrared image for the edge detection. The method subtracts contour images from the infrared thermal image. It results black contours of objects in the infrared thermal image. That makes the objects in the infrared thermal image distinguished clearly. The proposed method is implemented using C language in an embedded Linux system for a high-speed real-time image processing. Experiments were conducted by using various infrared thermal images. The results show that the proposed method is successful for image enhancement of an infrared thermal image.

• Proceedings of the KSR Conference
• /
• 2006.11b
• /
• pp.414-419
• /
• 2006

The ballast or other objects may be located on the rail road by a lump of ice, repairing operation on the track, or the strong gust due to the high speed running of the train. When a train operated in this condition, it causes serious damages to the wheel, train, and structures near the track, or the secondary ballast flying. To remove these objects safely, a ballast blower is suggested which was attached under the train. Firstly, the numerical analyses are investigated to find out the basic flow characteristics of the ballast blower. Next, the performance of the ballast blower is verified by wind tunnel experiments. Through these studies, it is expected that the ballast blower can be applied practically.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.10
• /
• pp.2809-2815
• /
• 1999

Level set, and active contour(snakes) models are extensively used for image segmentation or shape extraction in computer vision. Snakes utilize the energy minimization concepts, and level set is based on the curve evolution in order to extract contours from image data. In general, these two models have their own drawbacks. For instance, snake acts pooly unless it is placed close to the wanted shape boundary, and it has difficult problem when image has multiple objects to be extracted. But, level set method is free of initial curve position problem, and has ability to handle topology of multiple objects. Nevertheless, level set method requires much more calculation time compared to snake model. In this paper, we use good points of two described models and also apply multi resolution algorithm in order to speed up the process without decreasing the performance of the shape extraction.

• Journal of KIISE:Software and Applications
• /
• v.30 no.3_4
• /
• pp.285-292
• /
• 2003

Existing MPEG-4 players have limitation of screen blinks and drops of object rendering speed when user insert, delete, and replace objects on scenes. In this paper, an Object Priority Order Composition operated through the MPEG-4 player is proposed. This composition is the method for presentation user can insert, delete, and replace scene objects more efficiently. Therefore, this composition can show the MPEG-4 multimedia scenes without blinks and delays on MPR-4 player may seem random and natural.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.1243-1244
• /
• 2022

In recent years, the growing interest in off-site construction has led to factories scaling up their manufacturing and production processes in the construction sector. Consequently, continuous large-scale site monitoring in low-variability environments, such as prefabricated components production plants (precast concrete production), has gained increasing importance. Although many studies on computer vision-based site monitoring have been conducted, challenges for deploying this technology for large-scale field applications still remain. One of the issues is collecting and transmitting vast amounts of video data. Continuous site monitoring systems are based on real-time video data collection and analysis, which requires excessive computational resources and network traffic. In addition, it is difficult to integrate various object information with different sizes and scales into a single scene. Various sizes and types of objects (e.g., workers, heavy equipment, and materials) exist in a plant production environment, and these objects should be detected simultaneously for effective site monitoring. However, with the existing object detection algorithms, it is difficult to simultaneously detect objects with significant differences in size because collecting and training massive amounts of object image data with various scales is necessary. This study thus developed a large-scale site monitoring system using edge computing and a small-object detection system to solve these problems. Edge computing is a distributed information technology architecture wherein the image or video data is processed near the originating source, not on a centralized server or cloud. By inferring information from the AI computing module equipped with CCTVs and communicating only the processed information with the server, it is possible to reduce excessive network traffic. Small-object detection is an innovative method to detect different-sized objects by cropping the raw image and setting the appropriate number of rows and columns for image splitting based on the target object size. This enables the detection of small objects from cropped and magnified images. The detected small objects can then be expressed in the original image. In the inference process, this study used the YOLO-v5 algorithm, known for its fast processing speed and widely used for real-time object detection. This method could effectively detect large and even small objects that were difficult to detect with the existing object detection algorithms. When the large-scale site monitoring system was tested, it performed well in detecting small objects, such as workers in a large-scale view of construction sites, which were inaccurately detected by the existing algorithms. Our next goal is to incorporate various safety monitoring and risk analysis algorithms into this system, such as collision risk estimation, based on the time-to-collision concept, enabling the optimization of safety routes by accumulating workers' paths and inferring the risky areas based on workers' trajectory patterns. Through such developments, this continuous large-scale site monitoring system can guide a construction plant's safety management system more effectively.

• The Journal of the Korea Contents Association
• /
• v.19 no.9
• /
• pp.666-673
• /
• 2019

In the immersive virtual reality environment, we can select and manipulate various virtual objects. in order to select a virtual object, we generally use Ray-casting method that fires a virtual line in user's view and selects an object when the line and the object match, or Cone-casting method that is widely used to select multiple objects at the same time. However, since the virtual objects used in CAD are composed of small and complex objects in detail, when selecting an object in the user's view by existing methods, there occurs a ambiguity problem that needs additional realignment operation even though an object is selected as a group. in this paper, even if a virtual object is composed of several small virtual objects, it calculates the spatial and logical relationship among objects and expands or shrinks desired objects, so that the user can quickly and accurately select a desired object. in order to evaluate the proposed method, performance comparison were performed using Our and Ray-Casting and Cone-Casting methods. Experimental results show that the proposed method has the fastest speed and the highest accuracy when selecting the desired objects.

• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.6
• /
• pp.519-522
• /
• 2008

As industry of a semiconductor and LCD industry have been rapidly growing, precision technologies of machining such as etching and 3D measurement are required. Stylus has been important measuring method in traditional manufacturing process. However, its disadvantages are low measuring speed and damage possibility at contacting point. To overcome mentioned disadvantage, non-contacting measurement method is needed such as PMP(Phase Measuring Profilometry), WSI(white scanning interferometer) and Confocal Profilometry. Among above 3 well-known methods, WSI started to be applied to FPD(flat panel display) manufacturing process. Even though it overcomes 21t ambiguity of PMP method and can measure objects which has specular surface, the measuring speed and vibration coming from manufacturing machine are one of main issue to apply full automatic total inspection. In this study, We develop high speed WSI system and algorithm to reduce unknown noise. The developing WSI and algorithm are implemented to measure 3D surface of wafer. Experimental results revealed that the proposed system and algorithm are able to measure 3D surface profile of wafer with a good precision and high speed.