• Computers and Concrete
• /
• v.32 no.6
• /
• pp.615-623
• /
• 2023

Crack detection is an essential method to ensure the safety of dam concrete structures. Low-quality crack images of dam concrete structures limit the application of neural network methods in crack detection. This research proposes a modified attentional mechanism model to reduce the disturbance caused by uneven light, shadow, and water spots in crack images. Also, the focal loss function solves the small ratio of crack information. The dataset collects from the network, laboratory and actual inspection dataset of dam concrete structures. This research proposes a novel method for crack detection of dam concrete structures based on the U-Net neural network, namely AF-UNet. A mutual comparison of OTSU, Canny, region growing, DeepLab V3+, SegFormer, U-Net, and AF-UNet (proposed) verified the detection accuracy. A binocular camera detects cracks in the experimental scene. The smallest measurement width of the system is 0.27 mm. The potential goal is to achieve real-time detection and localization of cracks in dam concrete structures.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.2
• /
• pp.75-80
• /
• 2024

Research on the visual narrative impact of Unreal Engine's Lumen lighting system in games aims to delve into how Lumen's lighting technology plays a crucial role in game design and gameplay experience, thereby enhancing the visual storytelling of games. Lumen, Unreal Engine's dynamic global illumination solution, calculates lighting and shadows in real-time during gameplay, creating a more realistic and immersive environment. Analysis indicates that Lumen technology not only provides visually realistic and dynamic lighting effects but also significantly enriches the expressiveness and immersion of the game narrative through its changes in light and shadow.

• Environmental and Resource Economics Review
• /
• v.15 no.4
• /
• pp.673-692
• /
• 2006

In order to test for the dynamic optimality condition for the use of nonrenewable resource, it is necessary to estimate the shadow value of the resource in situ. In the previous literatures, a time series for in situ price has been derived either as the difference between marginal revenue and marginal cost or by differentiating with respect to the quantity of ore extracted the restricted cost function in which the quantity of ore is quasi-fixed. However, not only inconsistent estimates are likely to be generated due to the nonmalleability of capital, but the estimate of marginal revenue will be affected by market power. Since firms will likely fail to minimize the cost of the reproducible inputs subject to market prices under realistic circumstances where imperfect factor markets, strikes, or government regulations are present, the shadow in situ values obtained by estimating the restricted cost function can be biased. This paper provides a valid methodology for checking the dynamic optimality condition for a nonrenewable resource by using the input distance function. Our methodology has some advantages over previous ones: only data on quantities of inputs and outputs are required; nor is the maintained hypothesis of cost minimization required; adoption of linear programming enables us to circumvent autocorrelated errors problem caused by use of time series or panel data. The dynamic optimality condition for domestic coal mining does not hold for constant discount rates ranging from 2 to 20 percent over the period 1970~1993. The dynamic optimality condition also does not hold for variable rates ranging from fourth to four times the real interest rate.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.4
• /
• pp.370-376
• /
• 2023

In the underwater image, it is not clear to distinguish the shape of the target due to underwater noise and low resolution. In addition, as an input of deep learning, underwater images require pre-processing and segmentation must be preceded. Even after pre-processing, the target is not clear, and the performance of detection and identification by deep learning may not be high. Therefore, it is necessary to distinguish and clarify the target. In this study, the importance of target shadows is confirmed in underwater images, object detection and target area acquisition by shadows, and data containing only the shape of targets and shadows without underwater background are generated. We present the process of converting the shadow image into a 3-mode image in which the target is white, the shadow is black, and the background is gray. Through this, it is possible to provide an image that is clearly pre-processed and easily discriminated as an input of deep learning. In addition, if the image processing code using Open Source Computer Vision (OpenCV)Library was used for processing, the processing speed was also suitable for real-time processing.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.6
• /
• pp.621-628
• /
• 2015

This paper describes an algorithm for detecting vehicles detection in real time. The proposed algorithm has the technique based on computer vision and image processing. In real, complex environment such as one with road traffic, many algorithms have great difficulty such as low detection rate and increasing computational time due to complex backgrounds and rapid changes. To overcome this problem in this paper, the proposed algorithm consists of the following methods. First, to effectively separate the candidate regions, we use vertical and horizontal edge information, and shadow values from input image sequences. Second, we extracts features by using HOG from the selected candidate regions. Finally, this paper uses the OS fuzzy-ELM based on SLFN to classify the extracted features. The experimental results show that the proposed method perform well for detecting vehicles and improves the accuracy and the computational time of detecting.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.2
• /
• pp.283-290
• /
• 2006

The cellular neural networks have the structure that consists of an array of the same cell which is a simple processing element, and each of the cells has local connectivity and space invariant template properties. So, it has a very suitable structure for the hardware implementation. But, it is impossible to have a one-to-one mapping between the CNN hardware processors and the pixels of the practical large image. In this paper, a $5{\times}5$ CNN hardware processor with pipeline input and output that can be applied to the time-multiplexing processing scheme, which processes the large image with a small CNN cell block, is designed. the operation of the implemented $5{\times}5$ CNN hardware processor is verified from the edge detection and the shadow detection experimentations.

• Journal of the Korea Computer Graphics Society
• /
• v.22 no.3
• /
• pp.89-99
• /
• 2016

One of the fundamental elements in developing mixed reality applications is to effectively analyze and apply the environmental lighting information to image synthesis. In particular, interactive applications require to process dynamically varying lighting sources in real-time, reflecting them properly in rendering results. Previous related works are not often appropriate for this because they are usually designed to synthesize photorealistic images, generating too many, often exponentially increasing, light sources or having too heavy a computational complexity. In this paper, we present a fast light source estimation technique that aims to search for primary light sources on the fly from a sequence of video images taken by a camera equipped with a fisheye lens. In contrast to previous methods, our technique can adust the number of found light sources approximately to the size that a user specifies. Thus, it can be effectively used in Phong-illumination-model-based direct illumination or soft shadow generation through light sampling over area lights.

• Journal of Advanced Navigation Technology
• /
• v.16 no.3
• /
• pp.545-552
• /
• 2012

In this paper, we propose Modified Multi CAMShift Algorithm based on Kalman filter and Weighted Search Windows(KWMCAMShift) that extracts skin color area and tracks several human body parts for real-time human tracking system. We propose modified CAMShift algorithm that generates background model, extracts skin area of hands and head, and tracks the body parts. Kalman filter stabilizes tracking search window of skin area due to changing skin area in consecutive frames. Each occlusion areas is avoided by using weighted window of non-search areas and main-search area. And shadows are eliminated from background model and intensity of shadow. The proposed KWMCAMShift algorithm can estimate human pose in real-time and achieves 96.82% accuracy even in the case of occlusions.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.12
• /
• pp.2665-2674
• /
• 2012

This paper propose the method to recognize the lanes and distance between cars in real-time which detects dangerous situations and helps safe driving in the actual road environment. First of all, it extracts the area of interest corresponding to roads and cars from the road image photographed by using the forward-looking camera. Through the hough transform for the area of interest, this study detects linear components and also selects the lane and conducts filtering by calculating probability. And through the shadow threshold analysis of the cars in front within the area of interest, it extracts the objects of cars in front and calculates the distance from cars in front. According to the result of applying the suggested technology to recognize the lane and distance between cars to the road situation for testing, it showed over 95% recognition rate; thus, it has been proved that it can respond to safe driving.

• Archives of design research
• /
• v.19 no.4 s.66
• /
• pp.71-80
• /
• 2006

Collaboration has become essential in the product design process due to internationalized and specialized business environments. This study presents a real-time collaborative 3D design workspace for distributed designers, focusing on the development and the evaluation of new interaction techniques supporting nonverbal communication such as awareness of participants, shared manipulation and tele-presence. Requirements were identified in terms of shared objects, shared workspaces and awareness through literature reviews and an observational study. An Augmented Reality based collaborative design workspace was developed, in which two main interaction techniques, Turn-table and Virtual Shadow, were incorporated to support shared manipulation and tele-presence. Turn-table provides intuitive shared manipulation of 3D models and physical cues for awareness of remote participants. Virtual shadow supports natural and continuous awareness of location, gestures and pointing of partners. A lab-based evaluation was conducted and the results showed that interaction techniques effectively supported awareness of general pointing and facilitated discussion in 3D model reviews. The workspace and the interaction techniques can facilitate more natural communication and increase the efficiency of collaboration on virtual 3D models between distributed participants (designer-designer, engineer, or modeler) in collaborative design environments.