• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.10
• /
• pp.4108-4125
• /
• 2015

This paper presents a scalable coding method for depth images by considering the quality of synthesized images in virtual views. First, we design a new edge detection algorithm that is based on calculating the depth difference between two neighboring pixels within the depth map. By choosing different thresholds, this algorithm generates a scalable bit stream that puts larger depth differences in front, followed by smaller depth differences. A scalable scheme is also designed for coding depth pixels through a layered sampling structure. At the receiver side, the full-resolution depth image is reconstructed from the received bits by solving a partial-differential-equation (PDE). Experimental results show that the proposed method improves the rate-distortion performance of synthesized images at virtual views and achieves better visual quality.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.4
• /
• pp.209-215
• /
• 2022

This paper proposes a novel approach for training an unsupervised depth estimation algorithm. The objective of unsupervised depth estimation is to estimate pixel-wise distances from camera without external supervision. While most previous works focus on model architectures, loss functions, and masking methods for considering dynamic objects, this paper focuses on the training framework to effectively use depth cue. The main loss function of unsupervised depth estimation algorithms is known as the photometric error. In this paper, we claim that direct depth cue is more effective than the photometric error. To obtain the direct depth cue, we adopt the technique of knowledge distillation which is a teacher-student learning framework. We train a teacher network based on a previous unsupervised method, and its depth predictions are utilized as pseudo labels. The pseudo labels are employed to train a student network. In experiments, our proposed algorithm shows a comparable performance with the state-of-the-art algorithm, and we demonstrate that our teacher-student framework is effective in the problem of unsupervised depth estimation.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2021.05a
• /
• pp.162-163
• /
• 2021

Currently, the depth of cracks is measured using ultrasonic detectors in maintenance practice. This method consists of measuring the depth of cracks by attaching ultrasonic depth measuring equipment to the concrete surface, and there are restrictions on the timing and location of the inspection. These limitations can be addressed through the development of image-based crack depth measurement AI technology. If crack depth measurements are made based on images, restrictions on the timing and location of inspections can be lifted because images acquired with simple filming equipment can be used as input information. To efficiently develop these artificial intelligence technologies, it is essential to identify the interrelationship between crack depth measurements and image characteristic information. Thus, this study is a basic study of the development of image-based crack depth measurement AI technology and aims to identify image characteristic information related to crack depth.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37C no.9
• /
• pp.751-756
• /
• 2012

In this paper, we propose a foreground extraction and depth map generation method using a time-of-flight (TOF) depth camera. Although, the TOF depth camera captures the scene's depth information in real-time, it has a built-in noise and distortion. Therefore, we perform several preprocessing steps such as image enhancement, segmentation, and 3D warping, and then use the TOF depth data to generate the depth-discontinuity regions. Then, we extract the foreground object and generate the depth map as of the color image. The experimental results show that the proposed method efficiently generates the depth map even for the object boundary and textureless regions.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.6
• /
• pp.2730-2747
• /
• 2016

Due to the limitation of the bandwidth resource and capture resolution of depth cameras, low resolution depth maps should be up-sampled to high resolution so that they can correspond to their texture images. In this paper, a novel depth map up-sampling algorithm is proposed by exploiting the fractal internal self-referential feature. Fractal parameters which are extracted from a depth map, describe the internal self-referential feature of the depth map, do not introduce inherent scale and just retain the relational information of the depth map, i.e., fractal transforms provide a resolution-independent description for depth maps and could up-sample depth maps to an arbitrary high resolution. Then, an enhancement method is also proposed to further improve the performance of the up-sampled depth map. The experimental results demonstrate that better quality of synthesized views is achieved both on objective and subjective performance. Most important of all, arbitrary resolution depth maps can be obtained with the aid of the proposed scheme.

• Journal of Biomedical Engineering Research
• /
• v.31 no.5
• /
• pp.407-411
• /
• 2010

During the cardiopulmonary resuscitation (CPR), the correct chest compression depth and period are very important to increase the resuscitation possibility. For the feedback of chest compression depth, the depth monitoring device based on the accelerometer is developed and widely used. But this method tends to overestimate the compression depth on the bed. To overcome this limitation, the chest compression depth estimation method using two accelerometers is suggested With the additional accelerometer between the patient and mattress on the bed, the compression of the mattress is also measured and it is used to compensate the overestimation error. The experimental results show that the single accelerometer estimates as 61.4mm for the actual compression depth of 43.6mm on the mattress. The depth estimation with the dual accelerometer was 44.6mm which is close to the actual depth. With the automatic zeroing in every single compression, the integration error for the depth can be reduced. The dual accelerometer method is effective to increase the accuracy of the chest compression depth estimation.

• Journal of Acupuncture Research
• /
• v.32 no.4
• /
• pp.11-16
• /
• 2015

Objectives : The purpose of this study is to determine the safe needling depth of Pungbu($GV_{16}$) retrospectively by using magnetic resonance imaging (MRI). Methods : We chose 114 Brain or C-spine MRI images from the Sang-Ji hospital picture archiving communication system. We measured the shortest distance from skin to cerebral dura mater passing by posterior edge of the foramen magnum on the sagittal view for the depth of Pungbu. We analyzed the differences between male and female measured values by using a student t-test. Results : The average depth of male insertion was $49.71{\pm}6.32mm$ and the shortest depth of insertion was 36.29 mm. The average depth of female insertion was $39.84{\pm}5.25mm$ and the shortest depth of insertion was 30.02 mm. The results showed a significant difference according to gender (p=0.00). Conclusions : The depth of male insertion is deeper than that of female, and the safe needling depth in the case of males is 36.29-67.35 mm, while the safe needling depth in the of females is 30.02-52.18 mm.

• International Journal of Internet, Broadcasting and Communication
• /
• v.13 no.1
• /
• pp.152-160
• /
• 2021

The purpose of this study was to investigate the difference in the number of repetitions and the change in electromyographic response during the maximum speed squat exercise according to the depth conditions and the maximum speed squat exercise according to the time of each depth. Ten men in their 20s were selected as subjects and the maximum speed squat was performed for one minute in three environmental conditions (ground, knee depth, waist depth). We found that the number of repetitions according to the depth of water showed a significant difference, and as a result of the post-mortem comparison, the number of repetitions was higher in the ground condition and the knee depth than in the waist depth. And the muscle activity of rectus abdominis, erector spinae, rectus femoris, biceps femoris was increased during ground squat exercise, activity of all muscle was decreased during knee depth squat exercise, and activity of rectus abdominis, erector spinae, biceps femoris, tibialis anterior, gastrocnemius was decreased during waist depth squat. In conclusion, muscle activity of lower extremities during squat exercise in underwater environment can be lowered as the depth of water is deep due to buoyancy, but muscle activity of trunk muscles can be increased rather due to the effect of viscosity and drag.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38C no.10
• /
• pp.875-880
• /
• 2013

When we generate 3D video that provides immersive and realistic feeling to users, depth information of the scene is essential. Since the resolution of the depth map captured by a depth sensor is lower than of the color image, we need to upsample the low-resolution depth map for high-resolution 3D video generation. In this paper, we propose a depth upsampling method using depth-discontinuity information. Using the high-resolution color image and the low-resolution depth map, we detect depth-discontinuity regions. Then, we define an energy function for the depth map upsampling and optimize it using the belief propagation method. Experimental results show that the proposed method outperforms other depth upsampling methods in terms of the bad pixel rate.

• Proceedings of the IEEK Conference
• /
• 1999.06a
• /
• pp.627-630
• /
• 1999

For depth extraction from the focus and recovery the shape, determination of criterion function for focus measure and size of the criterion window are very important. However, Texture, illumination, and magnification have an effect on focus measure. For that reason, depth map has a partial high and low peak. In this paper, we propose a depth extraction method from focused images using the error interpolation. This method is modified the error depth into mean value between two normal depth in order to improve the depth map.