• Journal of Korea Game Society
• /
• v.15 no.4
• /
• pp.29-38
• /
• 2015

In the stealth game design, level designers are to develop many interesting game environments with a variety of difficulties. J. Tremblay and his co-authors developed a Unity-based level design tool to help and automate this process. Given a map, if the designer inputs several game factors such as guard paths and velocities, their vision, and the player's initial and goal positions, then the tool visualizes simulation results including (clustered) possible paths a player could take to avoid detection. Thus with the help of this tool, the designer can ensure in realtime if the current game factors result in the intended difficulties and players paths, and if necessary adjust the factors. In this note, we present our improvement on this tool in two aspects. First, we integrate a function that if the designer inputs some vertices in the map, then the tool systematically generates and suggests interesting guard paths containing these vertices of various difficulties, which enhances its convenience and usefulness as a tool. Second, we replace the collision-detection function and the RRT-based (player) path generation function, by our new collision-check function and a Delaunay roadmap-based path generation function, which remarkably improves the simulation process in time-efficiency.

• Journal of IKEEE
• /
• v.9 no.1 s.16
• /
• pp.7-18
• /
• 2005

A key component of an autonomous mobile robot is to localize itself accurately and build a map of the environment simultaneously. In this paper, we propose a vision-based mobile robot localization and mapping algorithm using scale-invariant features. A camera with fisheye lens facing toward to ceiling is attached to the robot to acquire high-level features with scale invariance. These features are used in map building and localization process. As pre-processing, input images from fisheye lens are calibrated to remove radial distortion then labeling and convex hull techniques are used to segment ceiling region from wall region. At initial map building process, features are calculated for segmented regions and stored in map database. Features are continuously calculated from sequential input images and matched against existing map until map building process is finished. If features are not matched, they are added to the existing map. Localization is done simultaneously with feature matching at map building process. Localization. is performed when features are matched with existing map and map building database is updated at same time. The proposed method can perform a map building in 2 minutes on $50m^2$ area. The positioning accuracy is ${\pm}13cm$, the average error on robot angle with the positioning is ${\pm}3$ degree.

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• 2007.11a
• /
• pp.938-942
• /
• 2007

The importance of process improvement under construction has arisen from recent issue, lower productivity in the construction site. The various 3D modeling program is utilized in the procedure of construction as an alternative solution. However, it's still shortage of the consideration about a specific technical application. The purpose of the study in this paper is helpful to improve the productivity of construction site using 3D realization of constructing place as one of extensive modeling technologies, which leads to not only efficient management of construction site allowing people to check the real time situation in the place but also the revitalization of information flow about building process control and prgress, Therefore, I research into modeling algorithm and extensive construction site realization technology. 3D realization of building place would reduce the safety concerns by providing the real time information about construction site, and it could help to access easily to similar project through collecting and appling the database of sites. Furthermore it can be an opportunity to develop the procedure of production in construction industry and to upgrade the image of this field.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.1
• /
• pp.684-692
• /
• 2016

In the manufacturing process of the LQFP/TQFP (Low-profile Quad Flat Package/Thin Quad Flat Package), the requirement of a 3 dimensional inspection is increasing rapidly and a 3D inspection of the shape of a chip has become an important report of quality control. This study developed a 3 dimensional measurement system based on PMP (Phase Measuring Profilometry) for an inspection of the LQFP/TQFP chip and image processing algorithms. The defects of the LQFP/TQFP chip were classified according to the dimensions. The 2 dimensional optical system was designed by the dorm illumination to achieve constant light distribution, In the 3 dimensional optical system, PZT was used for moving 90 degree in phase. The problem of 2 ambiguity was solved from the measured moir? pattern using the ambiguity elimination algorithm that finds the point of ambiguity and refines the phase value. The proposed 3D measurement system was evaluated experimentally.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.22 no.3
• /
• pp.57-68
• /
• 2017

Continuous monitoring of spatial and temporal changes in key marine environmental parameters such as SST (sea surface temperature) near IORS (Ieodo Ocean Research Station) is demanded to investigate the ocean ecosystem, climate change, and sea-air interaction processes. In this study, we aimed to develop the system for continuously measuring SST using a TIR (thermal infrared) sensor mounted at the IORS. New SST algorithm is developed to provide SST of better quality that includes automatic atmospheric correction and emissivity calculation for different oceanic conditions. Then, the TIR-based SST products were validated against in-situ water temperature measurements during May 17-26, 2015 and July 15-18, 2015 at the IORS, yielding the accuracy of 0.72-0.85 R-square, and $0.37-0.90^{\circ}C$ RMSE. This TIR-based SST observing system can be installed easily at similar Ocean Research Stations such as Sinan Gageocho and Ongjin Socheongcho, which provide a vision to be utilized as calibration site for SST remotely sensed from satellites to be launched in future.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.3
• /
• pp.141-148
• /
• 2021

This paper presents a method to detect zebra-crossing using deep learning which combines SegNet and ResNet. For the blind, a safe crossing system is important to know exactly where the zebra-crossings are. Zebra-crossing detection by deep learning can be a good solution to this problem and robotic vision-based assistive technologies sprung up over the past few years, which focused on specific scene objects using monocular detectors. These traditional methods have achieved significant results with relatively long processing times, and enhanced the zebra-crossing perception to a large extent. However, running all detectors jointly incurs a long latency and becomes computationally prohibitive on wearable embedded systems. In this paper, we propose a model for fast and stable segmentation of zebra-crossing from captured images. The model is improved based on a combination of SegNet and ResNet and consists of three steps. First, the input image is subsampled to extract image features and the convolutional neural network of ResNet is modified to make it the new encoder. Second, through the SegNet original up-sampling network, the abstract features are restored to the original image size. Finally, the method classifies all pixels and calculates the accuracy of each pixel. The experimental results prove the efficiency of the modified semantic segmentation algorithm with a relatively high computing speed.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.3
• /
• pp.577-582
• /
• 2021

Recently, with the development of AR, VR, and smart device technologies, the demand for services based on non-face-to-face environments is also increasing in the fitness industry. The non-face-to-face online home training service has the advantage of not being limited by time and place compared to the existing offline service. However, there are disadvantages including the absence of exercise equipment, difficulty in measuring the amount of exercise and chekcing whether the user maintains an accurate exercise posture or not. In this study, we develop a standard exercise program that can compensate for these shortcomings and propose a new non-face-to-face home training application by using a deep learning-based body posture estimation image processing algorithm. This application allows the user to directly watch and follow the trainer of the standard exercise program video, correct the user's own posture, and perform an accurate exercise. Furthermore, if the results of this study are customized according to their purpose, it will be possible to apply them to performances, films, club activities, and conferences

• Journal of Internet Computing and Services
• /
• v.23 no.3
• /
• pp.35-45
• /
• 2022

Even in recent years, treatment of first-aid patients is still often delayed due to a shortage of medical resources in marginalized areas. Research on automating the analysis of medical data to solve the problems of inaccessibility for medical services and shortage of medical personnel is ongoing. Computer vision-based medical inspection automation requires a lot of cost in data collection and labeling for training purposes. These problems stand out in the works of classifying lesion that are rare, or pathological features and pathogenesis that are difficult to clearly define visually. Anomaly detection is attracting as a method that can significantly reduce the cost of data collection by adopting an unsupervised learning strategy. In this paper, we propose methods for detecting abnormal images on chest X-RAY images as follows based on existing anomaly detection techniques. (1) Normalize the brightness range of medical images resampled as optimal resolution. (2) Some feature vectors with high representative power are selected in set of patch features extracted as intermediate-level from lesion-free images. (3) Measure the difference from the feature vectors of lesion-free data selected based on the nearest neighbor search algorithm. The proposed system can simultaneously perform anomaly classification and localization for each image. In this paper, the anomaly detection performance of the proposed system for chest X-RAY images of PA projection is measured and presented by detailed conditions. We demonstrate effect of anomaly detection for medical images by showing 0.705 classification AUROC for random subset extracted from the PadChest dataset. The proposed system can be usefully used to improve the clinical diagnosis workflow of medical institutions, and can effectively support early diagnosis in medically poor area.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.4
• /
• pp.621-628
• /
• 2021

This paper proposes a method to calibrate a thermal camera with three different perspectives. In particular, the intrinsic parameters of the camera and re-projection errors were provided to quantify the accuracy of the calibration result. Three lenses of the camera capture the same image, but they are not overlapped, and the image resolution is worse than the one captured by the RGB camera. In computer vision, camera calibration is one of the most important and fundamental tasks to calculate the distance between camera (s) and a target object or the three-dimensional (3D) coordinates of a point in a 3D object. Once calibration is complete, the intrinsic and the extrinsic parameters of the camera(s) are provided. The intrinsic parameters are composed of the focal length, skewness factor, and principal points, and the extrinsic parameters are composed of the relative rotation and translation of the camera(s). This study estimated the intrinsic parameters of thermal cameras that have three lenses of different perspectives. In particular, image enhancement based on a deep learning algorithm was carried out to improve the quality of the calibration results. Experimental results are provided to substantiate the proposed method.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.5
• /
• pp.171-182
• /
• 2022

The safe use of a structure requires it to be maintained in an undamaged state. Thus, a typical factor that determines the safety of a structure is a crack in it. In addition, cracks are caused by various reasons, damage the structure in various ways, and exist in different shapes. Making matters worse, if these cracks are unattended, the risk of structural failure increases and proceeds to a catastrophe. Hence, recently, methods of checking structural damage using deep learning and computer vision technology have been introduced. These methods usually have the premise that there should be a large amount of training image data. However, the amount of training image data is always insufficient. Particularly, this insufficiency negatively affects the performance of deep learning crack detection algorithms. Hence, in this study, a method of augmenting crack image data based on the image translation technique was developed. In particular, this method obtained the crack image data for training a deep learning neural network model by transforming a specific case of a asphalt crack image into a concrete crack image or vice versa . Eventually, this method expected that a robust crack detection algorithm could be developed by increasing the diversity of its training data.