• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.2B
• /
• pp.111-120
• /
• 2009

A local scour around a bridge pier is known as one of important factors of bridge collapse. Two approaches are usually used in estimating a scour depth in practice. One is to use empirical formulas, and the other is to use computational methods. But the use of empirical formulas is limited to predict a scour depth under similar conditions to which the formulas were derived. Computational methods are currently too expensive to be applied to practical engineering problems. This study presented the application of artificial neural networks (ANN) to the prediction of a scour depth around a bridge pier at an equilibrium state. This study also investigated various ANN algorithms for estimating a scour depth, such as Backpropagation Network, Radial Basis Function Network, and Generalized Regression Network. Preliminary study showed that ANN models resulted in very wide range of errors in predicting a scour depth. To solve this problem this study incorporated cluster analysis into ANN. The incorporation of cluster analysis provided better estimations of scour depth up to 42% compared with other approaches.

• IEIE Transactions on Smart Processing and Computing
• /
• v.4 no.6
• /
• pp.379-383
• /
• 2015

This paper presents an approach to detect object distance with the use of the recently developed low-cost Kinect sensor. The technique is based on Kinect color depth-image processing and can be used to design various computer-vision applications, such as object recognition, video surveillance, and autonomous path finding. The proposed technique uses keypoint feature detection in the Kinect depth image and advantages of depth pixels to directly obtain the feature distance in the depth images. This highly reduces the computational overhead and obtains the pixel distance in the Kinect captured images.

• Geomechanics and Engineering
• /
• v.23 no.1
• /
• pp.51-59
• /
• 2020

In this paper, the WEKA platform was used to mine and analyze measured data of floor failure depth and a prediction system of floor failure depth was developed with Java. Based on the standardization and discretization of 35-set measured data of floor failure depth in China, the grey correlation degree analysis on five factors affecting the floor failure depth was carried out. The correlation order from big to small is: mining depth, working face length, floor failure resistance, mining thickness, dip angle of coal seams. Naive Bayes model, neural network model and decision tree model were used for learning and training, and the accuracy of the confusion matrix, detailed accuracy and node error rate were analyzed. Finally, artificial neural network was concluded to be the optimal model. Based on Java language, a prediction system of floor failure depth was developed. With the easy operation in the system, the prediction from measured data and error analyses were performed for nine sets of data. The results show that the WEKA prediction formula has the smallest relative error and the best prediction effect. Besides, the applicability of WEKA prediction formula was analyzed. The results show that WEKA prediction has a better applicability under the coal seam mining depth of 110 m~550 m, dip angle of coal seams of 0°~15° and working face length of 30 m~135 m.

• Korean Journal of Computational Design and Engineering
• /
• v.21 no.3
• /
• pp.296-305
• /
• 2016

This paper proposes a framework to automatically align Dental range image captured by depth sensors like the Microsoft Kinect. Aligning dental images by intraoral scanning technology is a difficult problem for applications requiring accurate model of dental-scan datasets with efficiency in computation time. The most important thing in dental scanning system is accuracy of the dental prosthesis. Previous approaches in intraoral scanning uses a Z-buffer ICP algorithm for fast registration, but it is relatively not accurate and it may cause cumulative errors. This paper proposes additional Alignment using the rough result comes after intraoral scanning alignment. It requires that Each Depth Image of the total set shares some overlap with at least one other Depth image. This research implements the automatically additional alignment system that aligns all depth images into Completed model by computing a network of pairwise registrations. The order of the each individual transformation is derived from a global network and AABB box overlap detection methods.

• KCID journal
• /
• v.19 no.1
• /
• pp.19-29
• /
• 2012

The data of the agricultural water quality survey network was analyzed between from 1990 to 2010 in order to propose effective plans for water quality management by analyzing the characteristics of agricultural lakes and the change of water quality. The result of the analysis shows that there is a correlation between water quality and items that can be a function of water depth such as dam height, dam length, dam height/dam length ratio and active storage/surface area of lake ratio. This means that, Korean agricultural lakes, there is a correlation between water quality and water depth. Water quality of the lakes that have lower than 5m of active storage/surface area of lake ratio (effective water depth) especially tends to get worse rapidly. The Chl-a and COD concentration of Korean agricultural lakes have a tendency to increase between June and September. Therefore, we recommend first taking a water quality improvement project for the lakes preformed watershed management project, and taking a preventive short-term water quality improvement project for the unperformed lakes before June among lakes that have lower than 5m of effective water depth.

• Journal of Broadcast Engineering
• /
• v.27 no.6
• /
• pp.906-913
• /
• 2022

In this paper, we propose a new deep network architecture using nearest neighbor kernel for the estimation of dense depth map from its sparse map and corresponding color information. First, we propose to decompose the depth map signal into the structure and details for easier prediction. We then propose two separate subnetworks for prediction of both structure and details using classification and regression approaches, respectively. Moreover, the nearest neighboring kernel method has been newly proposed for accurate prediction of structure signal. As a result, the proposed method showed better results than other methods quantitatively and qualitatively.

• Journal of Information Processing Systems
• /
• v.18 no.6
• /
• pp.794-802
• /
• 2022

The recovery of reasonable depth information from different scenes is a popular topic in the field of computer vision. For generating depth maps with better details, we present an efficacious monocular depth prediction framework with coordinate attention and feature fusion. Specifically, the proposed framework contains attention, multi-scale and feature fusion modules. The attention module improves features based on coordinate attention to enhance the predicted effect, whereas the multi-scale module integrates useful low- and high-level contextual features with higher resolution. Moreover, we developed a feature fusion module to combine the heterogeneous features to generate high-quality depth outputs. We also designed a hybrid loss function that measures prediction errors from the perspective of depth and scale-invariant gradients, which contribute to preserving rich details. We conducted the experiments on public RGBD datasets, and the evaluation results show that the proposed scheme can considerably enhance the accuracy of depth prediction, achieving 0.051 for log10 and 0.992 for δ<1.25³ on the NYUv2 dataset.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.3
• /
• pp.51-57
• /
• 2021

In this paper, we propose a method to find the DoF(Depth of field) that is blurred in an image by focusing and out-focusing the camera through a efficient convolutional neural network. Our approach uses the RGB channel-based cross-correlation filter to efficiently classify the DoF region from the image and build data for learning in the convolutional neural network. A data pair of the training data is established between the image and the DoF weighted map. Data used for learning uses DoF weight maps extracted by cross-correlation filters, and uses the result of applying the smoothing process to increase the convergence rate in the network learning stage. The DoF weighted image obtained as the test result stably finds the DoF region in the input image. As a result, the proposed method can be used in various places such as NPR(Non-photorealistic rendering) rendering and object detection by using the DoF area as the user's ROI(Region of interest).

• Journal of IKEEE
• /
• v.28 no.1
• /
• pp.65-71
• /
• 2024

This paper proposes a neural network that can reduce the number of parameters while reducing matching errors in occluded regions to increase the accuracy of depth maps in stereo matching. Stereo matching-based object recognition is utilized in many fields to more accurately recognize situations using images. When there are many objects in a complex image, an occluded area is generated due to overlap between objects and occlusion by background, thereby lowering the accuracy of the depth map. To solve this problem, existing research methods that create context information and combine it with the cost volume or RoIselect in the occluded area increase the complexity of neural networks, making it difficult to learn and expensive to implement. In this paper, we create a depthwise seperable neural network that enhances regional feature extraction before cost volume generation, reducing the number of parameters and proposing a neural network that is robust to occlusion errors. Compared to PSMNet, the proposed neural network reduced the number of parameters by 30%, improving 5.3% in color error and 3.6% in test loss.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1997.06a
• /
• pp.27-34
• /
• 1997

In this study , we tried to test the classification performance of a neural netow and thereby to examine its applicability to the signals distorted by a shallow water einvironment . We conducted an acoustic experiment iin a shallow sea near Pohang, Korea in which water depth is about 60m. The signals, on which the network has been tested, is ilinear frequency modulated ones centered on one of the frequencies, 200, 400, 600 and 800 Hz, each being swept up or down with bandwidth 100Hz. we considered two transforms, STFT(short-time Fourier transform) and PWVD (pseudo Wigner-Ville distribution), form which power spectra were derived. The training signals were simulated using an acoutic model based on the Fourier synthesis scheme. When the network has been trained on the measured signals of center frequency 600Hz,it gave a little better results than that trained onthe simulated . With the center frequencies varied, the overall performance reached over 90% except one case of center frequency 800Hz. With the feature extraction techniques(STFT and PWVD) varied,the network showed performance comparable to each other . In conclusion , the signals which have been simulated with water depth were successully applied to training a neural network, and the trained network performed well in classifying the signals distorted by a surrounding environment and corrupted by noise.