• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.12
• /
• pp.509-516
• /
• 2022

Accurate pose prediction of objects in 3D space is an important visual recognition technique widely used in many applications such as scene understanding in both indoor and outdoor environments, robotic object manipulation, autonomous driving, and augmented reality. Most previous works for object pose estimation have the limitation that they require an exact 3D CAD model for each object. Unlike such previous works, this paper proposes a novel neural network model that can predict the poses of unknown objects based on only their RGB color images without the corresponding 3D CAD models. The proposed model can obtain depth maps required for unknown object pose prediction by using an adaptive depth estimator, AdaBins,. In this paper, we evaluate the usefulness and the performance of the proposed model through experiments using benchmark datasets.

• The Research Journal of the Costume Culture
• /
• v.28 no.3
• /
• pp.299-312
• /
• 2020

The purpose of this study is to create a shirt sloper suitable for an elderly male body shape by producing virtual models using a 3D-virtualization program, making a torso prototype using the Yuka CAD system, and employing 3D simulation to virtualize and calibrate the model. First, the following three types of obese dummies are implemented through the CLO 3D program: Type 1 exhibits body fat in the lower body; Type 2 exhibits an obese abdomen; and Type 3 displays a balanced form of obesity. Second, for the design of the shirt pattern, the waist back length (measured value+1), back armhole depth (C/10+12+3+0.5~1.5), front armhole depth (back armhole depth 0~1), front interscye (2C/10-1+0.5-0.5), armscye depth (C/10+2+3.5+ 0.5), back interscye (2C/10-1+1), front chest C (C/4+2.5+1), back chest C (C/4+2.5-1), front hem C (C/4+2.5+1(+2)), back hem C (C/4+2.5-1(+2)), cap height (AH/3-5), and biceps width (Front AH-1, Back AH-1) are calculated. Third, the virtual attachment of the shirt pattern is resolved by increasing the front and back armhole depths, and the front and rear wrinkles are improved by adding a back armhole dart. The front hem lift and lateral pull caused by the protrusion of the abdomen are amended by increasing the margin of the chest, waist C, and hip C, with the appearance improved by balanced margin distribution in the front, back, and side panels. The improved retail pattern with an increase in the front armholes C was balanced on the torso plate.

• 한국지구물리탐사학회:학술대회논문집
• /
• 2004.06a
• /
• pp.182-188
• /
• 2004

In view of the circular geometry of the Serra da Cangalha impact crater, we have carried out a 3D forward modeling computation for twenty-five MT data in order to obtain the 3D resistivity forward model for the crater region. The 3D resistivity forward model revealed a five-layer model, showing a significant reduction in the basement resistivity. We suggest that this, perhaps, could be due to the structural disturbances that have been caused by the meteorite impact on the crater about 220 million years ago resulting in brecciation, fracturing, alteration and shocked zone filled with fluids. Also, the sensitivity analysis of the 3D model chosen indicates that 3D models having a crater diameter greater than 151 are inconsistent with our data because the 3D model responses are very sensitive to changes in the diameter beyond 15 km. This analysis also reveals that, the depth limits (for the 3D body) causing the anisotropic effects seen on some of our apparent resistivity curves maximally does not extend beyond 1.2 km depth.

• The Journal of Korea Robotics Society
• /
• v.15 no.4
• /
• pp.341-349
• /
• 2020

Recently, interest in ground subsidence in urban areas has increased after a large sinkhole occurred near the high-story building area in Jamsil, Seoul, Korea, in 2014. If a massive sinkhole occurs in an urban area, it is crucial to assess its risk rapidly. Access to humans for on-site safety diagnosis may be difficult because of the additional risk of collapse in the disaster area. Generally, inspection using drones equipped with high-speed lidar sensors can be utilized. However, if the sinkhole is created vertically to a depth of 100 m, similar to the sinkhole in Guatemala, the drone cannot be applied because of the wireless communication limit and turbulence inside the sinkhole. In this study, a three-dimensional (3D) scanning system was fabricated and operated using a towed cable in a massive vertical sinkhole to a depth of 200 m. A high-speed lidar sensor was used to obtain a continuous cross-sectional shape at a certain depth. An inertial-measuring unit was applied to compensate for the error owing to the rotation and pendulum movement of the measuring unit. A reconstruction algorithm, including the compensation scheme, was developed. In a vertical hole with a depth of 180 m in the mining area, the fabricated system was applied to scan 0-165 m depth. The reconstructed shape was depicted in a 3D graph.

• Journal of the Semiconductor & Display Technology
• /
• v.13 no.2
• /
• pp.23-28
• /
• 2014

For the reconstruction of three-dimensional (3D) shape of microscopic objects through shape from focus (SFF) methods, usually a single focus measure operator is employed. However, it is difficult to compute accurate depth map using a single focus measure due to different textures, light conditions and arbitrary object surfaces. Moreover, real images with diverse types of illuminations and contrasts lead to the erroneous depth map estimation through a single focus measure. In order to get better focus measurements and depth map, we have combined focus measure operators by using genetic algorithm. The resultant focus measure is obtained by weighted sum of the output of various focus measure operators. Optimal weights are obtained using genetic algorithm. Finally, depth map is obtained from the refined focus volume. The performance of the developed method is then evaluated by using both the synthetic and real world image sequences. The experimental results show that the proposed method is more effective in computing accurate depth maps as compared to the existing SFF methods.

• Journal of Broadcast Engineering
• /
• v.19 no.3
• /
• pp.362-371
• /
• 2014

Blur variation caused by camera de-focusing provides a proper cue for depth estimation. Depth from Defocus (DFD) technique calculates the blur amount present in an image considering that blur amount is directly related to scene depth. Conventional DFD methods use two defocused images that might yield the low quality of an estimated depth map as well as a reconstructed infocused image. To solve this, a new DFD methodology based on infocused and defocused images is proposed in this paper. In the proposed method, the outcome of Subbaro's DFD is combined with a novel edge blur estimation method so that improved blur estimation can be achieved. In addition, a saliency map mitigates the ill-posed problem of blur estimation in the region with low intensity variation. For validating the feasibility of the proposed method, twenty image sets of infocused and defocused images with 2K FHD resolution were acquired from a camera with a focus control in the experiments. 3D stereoscopic image generated by an estimated depth map and an input infocused image could deliver the satisfactory 3D perception in terms of spatial depth perception of scene objects.

• Proceedings of the KIEE Conference
• /
• 1999.11c
• /
• pp.839-841
• /
• 1999

This paper presents the method of 3D reconstruction of the depth information from the endoscopic stereo scopic images. After camera modeling to find camera parameters, we performed feature-point based stereo matching to find depth information. Acquired some depth information is finally 3D reconstructed using the NURBS(Non Uniform Rational B-Spline) algorithm. The final result image is helpful for the understanding of depth information visually.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.05a
• /
• pp.281-282
• /
• 2018

In this paper, we will analyze the domestic and overseas technology development trends of the multi-view video content Depth Map.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.815-816
• /
• 2008

In this paper, we evaluate depth image preprocessing for 3D data service based on DIBR over T-DMB. We evaluate two preprocessing methods of depth images. These are gaussian smoothing and adaptive smoothing. The results show that adaptive smoothing is more suitable for images with sharp transition of depth.

• Journal of Broadcast Engineering
• /
• v.13 no.4
• /
• pp.427-439
• /
• 2008

This paper proposes a novel method to convert monoscopic soccer videos to stereoscopic videos. Through the soccer video analysis process, we detect shot boundaries and classify soccer frames into long shot or non-long shot. In the long shot case, the depth mapis generated relying on the size of the extracted ground region. For the non-long shot case, the shot is further partitioned into three types by considering the number of ground blocks and skin blocks which is obtained by a simple skin-color detection method. Then three different depth assignment methods are applied to each non-long shot types: 1) Depth estimation by object region extraction, 2) Foreground estimation by using the skin block and depth value computation by Gaussian function, and 3)the depth map generation for shots not containing the skin blocks. This depth assignment is followed by stereoscopic image generation. Subjective evaluation comparing generated depth maps and corresponding stereoscopic images indicate that the proposed algorithm can yield the sense of depth from a single view images.