• Proceedings of the KIEE Conference
• /
• 1999.07g
• /
• pp.2950-2952
• /
• 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) method and OpenGL. The final result image is helpful for the understanding of depth information visually.

• Journal of Korea Multimedia Society
• /
• v.22 no.5
• /
• pp.547-557
• /
• 2019

To extract the depth map from a single image, a number of CNN-based deep learning methods have been performed in recent research. In this study, the GAN structure of Pix2Pix is maintained. this model allows to converge well, because it has the structure of the generator and the discriminator. But the convolution in this model takes a long time to compute. So we change the convolution form in the generator to a depthwise convolution to improve the speed while preserving the result. Thus, the seven down-sizing convolutional hidden layers in the generator U-Net are changed to depthwise convolution. This type of convolution decreases the number of parameters, and also speeds up computation time. The proposed model shows similar depth map prediction results as in the case of the existing structure, and the computation time in case of a inference is decreased by 64%.

• Current Optics and Photonics
• /
• v.4 no.6
• /
• pp.524-529
• /
• 2020

We propose a depth-fused-type three-dimensional (3D) near-eye display implemented using a birefringent lens set that is made of calcite. By using a birefringent lens and image source (28.70 mm × 21.52 mm), which has different focal lengths according to the polarization state of the incident light, the proposed system can present depth-fused three-dimensional images at 4.6 degrees of field of view (FOV) within 1.6 Diopter (D) to 0.4 D, depending on the polarization distributed depth map. The proposed method can be applied to near-eye displays like head-mounted display systems, for a more natural 3D image without vergence-accommodation conflict.

• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• pp.1129-1132
• /
• 2005

In this paper, we proposed real-time stereoscopic image conversion algorithm using object segmentation and motion parallax. The proposed algorithm separates objects using luminance of image, extracts moving object among objects of the image using motion parallax and generates depth map. Parallax process is done based on the depth map. The proposed method has been evaluated using visual test and APD(Absolute Parallx Difference) for comparing the stereoscopic image of the proposed method with that of MTD. The proposed method offers realistic stereoscopic conversion effect regardless of the direction and velocity of the 2-D image.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2001.04a
• /
• pp.590-593
• /
• 2001

In this paper we describe the 6-axes robot's position determination using a stereo vision and an image based control method. When use a stereo vision, it need a additional time to compare with mono vision system. So to reduce the time required, we use the stereo vision not image Jacobian matrix estimation but depth estimation. Image based control is not needed the high-precision of camera calibration by using a image Jacobian. The experiment is executed as devide by two part. The first is depth estimation by stereo vision and the second is robot manipulator's positioning.

• Transactions on Electrical and Electronic Materials
• /
• v.18 no.6
• /
• pp.341-344
• /
• 2017

Infrared (IR) filters were developed to implement integrated three-dimensional (3D) image sensors that are capable of obtaining both color image and depth information at the same time. The combination of light filters applicable to the 3D image sensor is composed of a modified IR cut filter mounted on the objective lens module and on-chip filters such as IR pass filters and color filters. The IR cut filters were fabricated by inorganic $SiO_2/TiO_2$ multilayered thin-film deposition using RF magnetron sputtering. On-chip IR pass filters were synthetized by dissolving various pigments and dyes in organic solvents and by subsequent patterning with photolithography. The fabrication process of the filters is fairly compatible with the complementary metal oxide semiconductor (CMOS) process. Thus, the IR cut filter and IR pass filter combined with conventional color filters are considered successfully applicable to 3D image sensors.

• Transactions of the Society of Information Storage Systems
• /
• v.5 no.1
• /
• pp.36-40
• /
• 2009

We describe the experimental realization of image system using wavefront coding in 3-Mega pixel mobile phone camera. We designed aspheric lens to extend the depth of field (DOF) using wavefront coding. In addition, through the aspheric lens and lens barrel manufacturing, we obtained a raw image from a camera module. In our method, the acquired images are restored in the spatial frequency domain using the proposed filter and the spatial frequency response (SFR) is calculated. The proposed filters are composed of image denoising filter using low band pass filter in frequency domain and restoration filter for image restoration. Finally, we achieve an enhanced image by super-resolution image processing. Visual examples are given to demonstrate the performance of the proposed filter.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.6
• /
• pp.527-532
• /
• 2013

Depth estimation is an essential factor for robot vision, 3D scene modeling, and motion control. The depth estimation method is based on focusing values calculated in a series of images by a single camera at different distance between lens and object. In this paper, we proposed a relative depth estimation method using focus measure. The proposed method is implemented by focus value calculated for each image obtained at different lens position and then depth is finally estimated by considering relative distance of two patterns. We performed various experiments on the effective focus measures for depth estimation by using various patterns and their usefulness.

• Journal of Internet Computing and Services
• /
• v.21 no.3
• /
• pp.113-121
• /
• 2020

Human Pose Estimation (HPE) which localizes the human body joints becomes a high potential for high-level applications in the field of computer vision. The main challenges of HPE in real-time are occlusion, illumination change and diversity of pose appearance. The single RGB image is fed into HPE framework in order to reduce the computation cost by using depth-independent device such as a common camera, webcam, or phone cam. However, HPE based on the single RGB is not able to solve the above challenges due to inherent characteristics of color or texture. On the other hand, depth information which is fed into HPE framework and detects the human body parts in 3D coordinates can be usefully used to solve the above challenges. However, the depth information-based HPE requires the depth-dependent device which has space constraint and is cost consuming. Especially, the result of depth information-based HPE is less reliable due to the requirement of pose initialization and less stabilization of frame tracking. Therefore, this paper proposes a new method of HPE which is robust in estimating self-occlusion. There are many human parts which can be occluded by other body parts. However, this paper focuses only on head self-occlusion. The new method is a combination of the RGB image-based HPE framework and the depth information-based HPE framework. We evaluated the performance of the proposed method by COCO Object Keypoint Similarity library. By taking an advantage of RGB image-based HPE method and depth information-based HPE method, our HPE method based on RGB-D achieved the mAP of 0.903 and mAR of 0.938. It proved that our method outperforms the RGB-based HPE and the depth-based HPE.

• Journal of the Korean Institute of Telematics and Electronics T
• /
• v.35T no.3
• /
• pp.120-127
• /
• 1998

In this paper, ultrasonic images of 25MHz bandwidth were acquired by applying peak value variation, time average and depth profile algorithm to acoustic microscopy and its performance was compared and analysed with each other. In the time average algorithm, total reflecting pulse wave from a spot on the coin was converted to digital data in time domain and average value of the converted 512 data was calculated in computer. Time average image was displayed by gray levels colour of acquired N x N matrix average data in the scanning area on the sample. This technique having smoothing effects in time domain make developed an ultrasonic image on a highly scattering area. In depth profile technique, time difference between the reference and the reflected signal was detected with minimum resolution performance of 2ns, thus we can acquired real 3 dimensional shape of the scanning area in accordance with relative magnitude. Through these experiments, peak value, time average and depth profile images were analysed and advantages of each algorithm were proposed.