• Journal of the Korea Society for Simulation
• /
• v.20 no.4
• /
• pp.105-114
• /
• 2011

The roadmap-based planning is a path planning method which is used widely for a goal-directed movement in Robotics and has been applied to the world of computer animation such as computer games. However it is unnatural for computer characters to follow the path planned by the roadmap method as it is performed in Robotics. Flocking which is used for realistic and natural movements in computer animation enables character's movement by using a few simple rules without planning unlike the roadmap method. However it is impossible to achieve a goal-directed movement with flocking only because it does not keep states. In this paper we propose a simulation method which combines planning based on the road map with reactive actions for natural movements along the path planned. We define and implement steering behaviors for a leader which are needed to follow the trajectory naturally by analysing characteristics of roadmap-based paths and for the rest of members which follow the leader in various manners by detecting obstacles. The simulations are performed and demonstrated by using the implemented steering behaviors on every possible combination of roadmap-based path planning methods and models of configuration spaces. We also show that the detection of obstacle-collisions can be done effectively because paths are planned in the configuration space in which a moving object is reduced to a point.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.34 no.5
• /
• pp.503-514
• /
• 2016

Delineation of accurate object boundaries is crucial to provide reliable spatial information products such as digital topographic maps, building models, and spatial database. In LiDAR(Light Detection and Ranging) data, real boundaries of the buildings exist somewhere between outer-most points on the roofs and the closest points to the buildings among points on the ground. In most cases, areas of the building footprints represented by LiDAR points are smaller than actual size of the buildings because LiDAR points are located inside of the physical boundaries. Therefore, building boundaries determined by points on the roofs do not coincide with the actual footprints. This paper aims to estimate accurate boundaries that are close to the physical boundaries using airborne LiDAR data. The accurate boundaries are determined from the non-gridded original LiDAR data using initial boundaries extracted from the gridded data. The similar method implemented in this paper is also found in demarcation of the maritime boundary between two territories. The proposed method consists of determining initial boundaries with segmented LiDAR data, estimating accurate boundaries, and accuracy evaluation. In addition, extremely low density data was also utilized for verifying robustness of the method. Both simulation and real LiDAR data were used to demonstrate feasibility of the method. The results show that the proposed method is effective even though further refinement and improvement process could be required.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.9
• /
• pp.2460-2470
• /
• 2009

In this study, the parameter extraction for evaluation of the anesthesia depth in each anesthesia stages was conducted. An object of the this experiment study has studied 5 adult patients (mean $\pm$ SD age:$42{\pm}9.13$), ASA classification I and II, undergoing surgery of obstetrics and gynecology. Anaesthesia was maintained with Enflurane. HRV signal was created by R-peak detection algorithm form ECG signal. The HRV data were preprocessing algorithm. It has tried find out the anesthesia parameter which responds the anesthesia events and shows objective anesthesia depth according to anesthesia stage including pre-anesthesia, induction, maintenance, awake and post-anesthesia. In this study, proposed algorithm to analysis the HRV(heart rate variability) signal using wavelet transform in anesthesia stage. Three sorts of wavelet functions applied to PSD. In the result, all of the results were showed similarly. But experiment results of Daubeches 10 is better. Therefore, this parameter is the best parameter in the evaluation of anesthesia stage.

• Korean Journal of Remote Sensing
• /
• v.14 no.4
• /
• pp.376-391
• /
• 1998

Images from satellites will have 1 to 3 meter ground resolution and will be very useful for analyzing current status of earth surface. An image processing system named GeoWatch with more intelligent image processing algorithms has been designed and implemented to support the detailed analysis of the land surface using high-resolution satellite imagery. The GeoWatch is a valuable tool for satellite image processing such as digitizing, geometric correction using ground control points, interactive enhancement, various transforms, arithmetic operations, calculating vegetation indices. It can be used for investigating various facts such as the change detection, land cover classification, capacity estimation of the industrial complex, urban information extraction, etc. using more intelligent analysis method with a variety of visual techniques. The strong points of this system are flexible algorithm-save-method for efficient handling of large size images (e.g. full scenes), automatic menu generation and powerful visual programming environment. Most of the existing image processing systems use general graphic user interfaces. In this paper we adopted visual program language for remotely sensed image processing for its powerful programmability and ease of use. This system is an integrated raster/vector analysis system and equipped with many useful functions such as vector overlay, flight simulation, 3D display, and object modeling techniques, etc. In addition to the modules for image and digital signal processing, the system provides many other utilities such as a toolbox and an interactive image editor. This paper also presents several cases of image analysis methods with AI (Artificial Intelligent) technique and design concept for visual programming environment.

• Korean Journal of Remote Sensing
• /
• v.22 no.4
• /
• pp.243-253
• /
• 2006

As the ocean and beaches have suffered from the losses of sand, it is necessary to monitor the zones that are prone to erosion continuously with the object of the long-term management. However, each ward offices are busy trying to supply sand without analyzing the marine and beach topographic changes. Therefore a long term effect of erosion has not been shown. In this study, we proposed methods to collect accurate spatial data of the oceans and beaches through sounding and GPS surveys, and detected and analyzed topographic changes quantitatively and qualitatively, by using an integrated RS and GIS techniques. The result of this study revealed that the marine topography has been eroded for 25 years, because of the straight construction of the river and the vast development of urban features, in addition with change of the mean depth 0.40 m, the water surface area 11,028 $m^2$, and submarine volume 2,207,884 $m^3$. The beach topography has accreted for 5 years and the change of the mean elevation is 0.27m, the area 6,501 $m^2$, and volume 25,667 $m^3$, because of the installation of geogrids and the seasonal effect. We conducted monitoring works on the topographic survey of the ocean and beaches and analyzed the present condition of the coastal erosions. Therefore, it is estimated that necessary information on the supply of sand, the safe marine leisure and the management of bating place could be provided.

• Journal of Internet Computing and Services
• /
• v.22 no.2
• /
• pp.59-68
• /
• 2021

As artificial intelligence(AI) technologies, which have made rapid growth recently, began to be applied to the marine environment such as ships, there have been active researches on the application of CNN-based models specialized for digital videos. In E-Navigation service, which is combined with various technologies to detect floating objects of clash risk to reduce human errors and prevent fires inside ships, real-time processing is of huge importance. More functions added, however, mean a need for high-performance processes, which raises prices and poses a cost burden on shipowners. This study thus set out to propose a method capable of processing information at a high rate while maintaining the accuracy by applying Quantization techniques of a deep learning model. First, videos were pre-processed fit for the detection of floating matters in the sea to ensure the efficient transmission of video data to the deep learning entry. Secondly, the quantization technique, one of lightweight techniques for a deep learning model, was applied to reduce the usage rate of memory and increase the processing speed. Finally, the proposed deep learning model to which video pre-processing and quantization were applied was applied to various embedded boards to measure its accuracy and processing speed and test its performance. The proposed method was able to reduce the usage of memory capacity four times and improve the processing speed about four to five times while maintaining the old accuracy of recognition.

• Journal of Broadcast Engineering
• /
• v.26 no.2
• /
• pp.125-131
• /
• 2021

In recent years, Convolutional Neural Networks (CNNs) have achieved outstanding performance in the fields of computer vision such as image classification, object detection, visual quality enhancement, etc. However, as huge amount of computation and memory are required in CNN models, there is a limitation in the application of CNN to low-power environments such as mobile or IoT devices. Therefore, the need for neural network compression to reduce the model size while keeping the task performance as much as possible has been emerging. In this paper, we propose a method to compress CNN models by combining matrix decomposition methods of LR (Low-Rank) approximation and CP (Canonical Polyadic) decomposition. Unlike conventional methods that apply one matrix decomposition method to CNN models, we selectively apply two decomposition methods depending on the layer types of CNN to enhance the compression performance. To evaluate the performance of the proposed method, we use the models for image classification such as VGG-16, RestNet50 and MobileNetV2 models. The experimental results show that the proposed method gives improved classification performance at the same range of 1.5 to 12.1 times compression ratio than the existing method that applies only the LR approximation.

• Journal of the Korea Convergence Society
• /
• v.10 no.1
• /
• pp.103-113
• /
• 2019

License plate recognition camera is dedicated device designed for acquiring images of the target vehicle for recognizing letters and numbers in a license plate. Mostly, it is used as a part of the system combined with server and image analysis module rather than as a single use. However, building a system for vehicle license plate recognition is costly because it is required to construct a facility with a server providing the management and analysis of the captured images and an image analysis module providing the extraction of numbers and characters and recognition of the vehicle's plate. In this study, we would like to develop an embedded type convergent camera (Edge Base) which can expand the function of the camera to not only the license plate recognition but also the security CCTV function together and to perform two functions within the camera. This embedded type convergence camera equipped with a high resolution 4K IP camera for clear image acquisition and fast data transmission extracted license plate area by applying YOLO, a deep learning software for multi object recognition based on open source neural network algorithm and detected number and characters of the plate and verified the detection accuracy and recognition accuracy and confirmed that this camera can perform CCTV security function and vehicle number plate recognition function successfully.

• Journal of the HCI Society of Korea
• /
• v.14 no.2
• /
• pp.41-47
• /
• 2019

In this study, a smart assistive device is designed to recognize pedestrian signal and to provide audio instructions for visually impaired people in crossing streets safely. Walking alone is one of the biggest challenges to the visually impaired and it deteriorates their life quality. The proposed device has a camera attached on a pair of glasses which can detect traffic lights, recognize pedestrian signals in real-time using a machine learning algorithm on GPU board and provide audio instructions to the user. For the portability, the dimension of the device is designed to be compact and light but with sufficient battery life. The embedded processor of device is wired to the small camera which is attached on a pair of glasses. Also, on inner part of the leg of the glasses, a bone-conduction speaker is installed which can give audio instructions without blocking external sounds for safety reason. The performance of the proposed device was validated with experiments and it showed 87.0% recall and 100% precision for detecting pedestrian green light, and 94.4% recall and 97.1% precision for detecting pedestrian red light.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.6
• /
• pp.77-83
• /
• 2020

The heat treatment facility is in a situation where the scope of application of the remote IOT system is expanding due to the harsh environment caused by high heat and long working hours among the root industries. In this heat treatment process environment, the IOT middleware is required to play a pivotal role in interpreting, managing and controlling data information of IoT devices (sensors, etc.). Until now, the system controlled by the heat treatment remotely was operated with the command of the operator's batch system without overall monitoring of the site situation. However, for the safety and precise control of the heat treatment facility, it is necessary to control various sensors and recognize the surrounding work environment. As a solution to this, the heat treatment safety support system presented in this paper proposes a support system that can detect the access of the work manpower to the heat treatment furnace through thermal image detection and operate safely when ordering work from a remote location. In addition, an OPEN CV-based deterioration analysis system using DNN deep learning network was constructed for faster and more accurate recognition than general fixed hot spot monitoring-based thermal image analysis. Through this, we would like to propose a system that can be used universally in the heat treatment environment and support the safety management specialized in the heat treatment industry.