• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.625-628
• /
• 1999

In this paper, we consider the problem of finding the depth of a object in two images taken with cameras. For solving this problem, we introduce a spherical concave mirror model. First, a virtual concave mirror is assumed, and then a scene is obtained by camera at two different position which are on the surface of the mirror. The depth of object is calculated from two scenes by using the spherical-mirror equation. The algorithm has been tested on a real scene containing several objects, and showed that it is more useful for farther object.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2021.05a
• /
• pp.197-198
• /
• 2021

The temperature and humidity inside concrete affects the depth of carbonation. In this study, the temperature and humidity inside concrete were predicted by the numerical method under the boundary conditions of ambient temperature, humidity, solar radiation, and wind. Using the results of the thermal humidity analysis, diffusion of carbon dioxide and the reaction of cement hydration products were calculated for carbonation depth.

• Journal of the Korean Society for Precision Engineering
• /
• v.19 no.11
• /
• pp.96-102
• /
• 2002

This study is on the estimation method of toot temperature for different tool nose radius and cutting conditions in turning. Experimental analysis has been performed in different cutting conditions such as cutting speed, feed rate, and depth of cut for the tool nose radius, 0.4R, 0.8R using SMC workpiece materials. Tool temperature is measured using a thermo-couple which is embedded in the insert tip. Using multiple linear regression method, the tool temperature can be determined as an exponential equation with cutting variables and tool nose diameters for the different tool materials. The equations determined in this study show a good correlation for the cutting conditions and can be used for a tool temperature estimation technique. The result indicates that the tool temperature decreases for increasing the tool nose radius in general. Also, nose radius hardly influences on the tool temperature compared with cutting speed, feed rate and depth of cut. This method will be useful for the estimation of tool life and temperature using limited experimental data for given cutting conditions.

• Journal of Computing Science and Engineering
• /
• v.10 no.3
• /
• pp.95-101
• /
• 2016

In this study, we propose a new system for constructing parallel corpora for sign languages, which are generally under-resourced in comparison to spoken languages. In order to achieve scalability and accessibility regarding data collection and corpus construction, our system utilizes deep learning-based techniques and predicts depth information to perform pose estimation on hand information obtainable from video recordings by a single RGB camera. These estimated poses are then transcribed into expressions in SignWriting. We evaluate the accuracy of hand tracking and hand pose estimation modules of our system quantitatively, using the American Sign Language Image Dataset and the American Sign Language Lexicon Video Dataset. The evaluation results show that our transcription system has a high potential to be successfully employed in constructing a sizable sign language corpus using various types of video resources.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2005.03a
• /
• pp.633-640
• /
• 2005

Most existing methods for the footing settlement estimation are for either isolated or strip footings. No sufficient details are available for settlement calculation of footings with different shapes and multiple footing conditions, which are commonly adopted in actual construction projects. In this paper, estimation of footing settlements for various footing conditions of different shapes and multiple conditions is investigated based on Schmertmann's method with focus on values of the strain influence factor $I_z$. In order to examine the effect of multiple footing conditions, field plate load tests are performed in sands using single and double plates. 3D non-linear finite element analyses are also performed for various footing conditions with different footing shape and distance ratios. Results obtained in this study indicate that there are two significant components in the strain influence diagram that need to be taken into account for settlement estimation of rectangular and multiple footings: depth of $I_{zp}$ and depth of strain influence zone. Based on results from experimental and 3D non-linear finite element analyses, improved strain influence diagrams available for various footing conditions are proposed.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.341-350
• /
• 2022

In this paper, we propose a deep learning based on-device augmented reality (AR) system in which multiple input images are used to implement the correct occlusion in a real environment. The proposed system is composed of three technical steps; camera pose estimation, depth estimation, and object augmentation. Each step employs various mobile frameworks to optimize the processing on the on-device environment. Firstly, in the camera pose estimation stage, the massive computation involved in feature extraction is parallelized using OpenCL which is the GPU parallelization framework. Next, in depth estimation, monocular and multiple image-based depth image inference is accelerated using the mobile deep learning framework, i.e. TensorFlow Lite. Finally, object augmentation and occlusion handling are performed on the OpenGL ES mobile graphics framework. The proposed augmented reality system is implemented as an application in the Android environment. We evaluate the performance of the proposed system in terms of augmentation accuracy and the processing time in the mobile as well as PC environments.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2010.07a
• /
• pp.241-243
• /
• 2010

Previous approaches to the 2D to 3D conversion problem require heavy computation or considerable amount of user input. In this paper, we propose a rather simple method in estimating the depth map from a single image using a monocular depth cue: haze. Using the haze imaging model, we obtain the distance information and estimate a reliable depth map from a single scenery image. Using the depth map, we also suggest an algorithm that converts the single image to 3D stereoscopic images. We determine a disparity value for each pixel from the original 'left' image and generate a corresponding 'right' image. Results show that the algorithm gives well refined depth maps despite the simplicity of the approach.

• The Journal of Korea Robotics Society
• /
• v.19 no.1
• /
• pp.16-22
• /
• 2024

Robotic grasping in unstructured environments poses a significant challenge, demanding precise estimation of gripping positions for diverse and unknown objects. Generative Grasping Convolution Neural Network (GG-CNN) can estimate the position and direction that can be gripped by a robot gripper for an unknown object based on a three-dimensional depth map. Since GG-CNN uses only a depth map as an input, the precision of the depth map is the most critical factor affecting the result. To address the challenge of depth map precision, we integrate the Segment Anything Model renowned for its robust zero-shot performance across various segmentation tasks. We adjust the components corresponding to the segmented areas in the depth map aligned through external calibration. The proposed method was validated on the Cornell dataset and SurgicalKit dataset. Quantitative analysis compared to existing methods showed a 49.8% improvement with the dataset including surgical instruments. The results highlight the practical importance of our approach, especially in scenarios involving thin and metallic objects.

• The KIPS Transactions:PartB
• /
• v.12B no.3 s.99
• /
• pp.247-256
• /
• 2005

One of the classic research problems in computer vision is that of stereo, i.e., the reconstruction of three dimensional shape from two or more images. This paper deals with the problem of extracting depth information of non-rigid dynamic 3D scenes from general 2D video sequences taken by monocular camera, such as movies, documentaries, and dramas. Depth of the blocks are extracted from the resultant block motions throughout following two steps: (i) calculation of global parameters concerned with camera translations and focal length using the locations of blocks and their motions, (ii) calculation of each block depth relative to average image depth using the global parameters and the location of the block and its motion, Both singular and non-singular cases are experimented with various video sequences. The resultant relative depths and ego-motion object shapes are virtually identical to human vision.

• Journal of Korea Water Resources Association
• /
• v.30 no.5
• /
• pp.477-485
• /
• 1997

Recent internal and external bridge failures due to pier and abutment scour have emphasized the need for better methods of scour depth estimation. This paper compares the hydraulic analysis of the Namhan River Bridge over the Namhan River using one-dimensional models. WSPRO & HEC-2, and the two-dimensional model. TABS-MD based on the procedures presented in HEC-18 published by the U.S. FEdral Highway Administration. A comparison of estimated scour depth for this research based on the results from both one-dimensional and two-dimensional model is presented. At the same time, field measurement has been performed before and after flood using sounding instrument. Fathometer (DE-719C). A comparison between estimated and measured scour depth at bridge is also presented. Result shows that there is all the difference between estimated and measured scour depth due to dissimilarity between laboratory and field conditions. Also, it is difficult to measure the maximum scour depth accurately due to refilling. Therefore development of scour measuring equipment which can be used during peak flood, and derivation of empirical model appropriate for internal river system seems urgent.