• Smart Media Journal
• /
• v.1 no.3
• /
• pp.29-35
• /
• 2012

A depth image-based rendering (DIBR) technique is one of the rendering processes of virtual views with a color image and the corresponding depth map. The most important issue of DIBR is that the virtual view has no information at newly exposed areas, so called dis-occlusion. In this paper, we propose an intermediate view generation algorithm using the Kinect depth camera that utilizes the infrared structured light. After we capture a color image and its corresponding depth map, we pre-process the depth map. The pre-processed depth map is warped to the virtual viewpoint and filtered by median filtering to reduce the truncation error. Then, the color image is back-projected to the virtual viewpoint using the warped depth map. In order to fill out the remaining holes caused by dis-occlusion, we perform a background-based image in-painting operation. Finally, we obtain the synthesized image without any dis-occlusion. From experimental results, we have shown that the proposed algorithm generated very natural images in real-time.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.29 no.4
• /
• pp.247-249
• /
• 2016

In this study, we investigated the color change of the normal light gray granite as the high value color granite. By coating the metal catalyst liquid on the surface of granite stone, the metal particles were penetrated into the granite and the color of granite was changed permanently through the annealing treatment. To increase penetration depth into the granite, we used DC (direct current) bias. Two kinds of bias were used such as DC bias and pulse DC bias. And the penetration time was changed as 30 and 60 min. In all cases, the color granite were successfully obtained. Regardless of the catalyst reaction time, the penetration depth was increased by using the bias treatment. We obtained a penetration depth of 21 mm with the DC pulse bias during 60 min.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.1
• /
• pp.81-90
• /
• 2010

This paper presents H.264 coding schemes for multi-view video using the concept of layered depth image(LDI) representation and efficient compression technique for LDI. After converting those data to the proposed representation, we encode color, depth, and auxiliary data representing the hierarchical structure, respectively, Two kinds of preprocessing approaches are proposed for multiple color and depth components. In order to compress auxiliary data, we have employed a near lossless coding method. Finally, we have reconstructed the original viewpoints successfully from the decoded approach that is useful for dealing with multiple color and depth data simultaneously.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.2C
• /
• pp.186-193
• /
• 2009

Multi-view video is necessary to develop a new compression encoding technique for storage and transmission, because of a huge amount of data. Layered depth image is an efficient representation method of multi-view video data. This method makes a data structure that is synthesis of multi-view color and depth image. This paper proposed enhanced compression method by presentation of efficient layered depth image using real distance comparison, solution of overlap problem, and YCrCb color transformation. In experimental results, confirmed high compression performance and good reconstructed image.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.12C
• /
• pp.1147-1153
• /
• 2009

We propose a novel image segmentation and segment-based stereo matching technique using color, depth, and motion information. Proposed technique firstly splits reference images into foreground region or background region using depth information from depth camera. Then each region is segmented into small segments with color information. Moreover, extracted segments in current frame are tracked in the next frame in order to maintain depth consistency between frames. The initial depth from the depth camera is also used to set the depth search range for stereo matching. Proposed segment-based stereo matching technique was compared with conventional one without foreground and background separation and other conventional one without motion tracking of segments. Simulation results showed that the improvement of segment extraction and depth estimation consistencies by proposed technique compared to conventional ones especially at the static background region.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.3
• /
• pp.1121-1141
• /
• 2020

We propose a robust visual object tracking algorithm fusing a convolutional neural network tracker trained offline from a large number of video repositories and a color histogram based tracker to track objects for mixing immersive audio. Our algorithm addresses the problem of occlusion and large movements of the CNN based GOTURN generic object tracker. The key idea is the offline training of a binary classifier with the color histogram similarity values estimated via both trackers used in this method to opt appropriate tracker for target tracking and update both trackers with the predicted bounding box position of the target to continue tracking. Furthermore, a histogram similarity constraint is applied before updating the trackers to maximize the tracking accuracy. Finally, we compute the depth(z) of the target object by one of the prominent unsupervised monocular depth estimation algorithms to ensure the necessary 3D position of the tracked object to mix the immersive audio into that object. Our proposed algorithm demonstrates about 2% improved accuracy over the outperforming GOTURN algorithm in the existing VOT2014 tracking benchmark. Additionally, our tracker also works well to track multiple objects utilizing the concept of single object tracker but no demonstrations on any MOT benchmark.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2009.10a
• /
• pp.1152-1153
• /
• 2009

Although motion impression is weak with isoluminant color stimuli, it has been shown that color signals influence motion perception. We discuss similarities and differences between color motion and luminance motion, focusing on temporal characteristics of the perception of the 2D and 3D motion.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2017.11a
• /
• pp.65-66
• /
• 2017

Early-frost damages easily take place in smaller and thinner walls and slabs. In case of slabs, it is difficult to visually determine the depth of early-frost damage. As such, the current study aims to determine the depth of early-frost damage caused to concrete structures due to bad curing in the winter. As a result, the study found that the depth of early-frost damages increased from the top as the atmospheric temperature on the concrete surface decreased. The changes in the color allowed the observer to easily identify the depth of early-frost damage with the naked eye. In particular, the color difference between potentially damaged parts and undamaged parts were the greatest around thirty minutes of drying after wetting.

• International Journal of Contents
• /
• v.10 no.3
• /
• pp.9-16
• /
• 2014

Depth-image-based rendering is generally used in real-time 2D-to-3D conversion for 3DTV. However, inaccurate depth maps cause flickering issues between image frames in a video sequence, resulting in eye fatigue while viewing 3DTV. To resolve this flickering issue, we propose a new 2D-to-3D conversion scheme based on fast and robust depth-map generation from a 2D video sequence. The proposed depth-map generation algorithm divides an input video sequence into several cuts using a color histogram. The initial depth of each cut is assigned based on a hypothesized depth-gradient model. The initial depth map of the current frame is refined using color and motion information. Thereafter, the depth map of the next frame is updated using the difference image to reduce depth flickering. The experimental results confirm that the proposed scheme performs real-time 2D-to-3D conversions effectively and reduces human eye fatigue.

• Textile Coloration and Finishing
• /
• v.26 no.4
• /
• pp.290-296
• /
• 2014

In order to produce black disperse dye which has high heat resistance and depth color for polyester(PET), an orange disperse dye was designed and synthesized with pyridine based derivatives to get high heat resistance. Disperse blue dye adopts heterocycles structure for high molar extinction coefficient and long wavelength absorption. Synthesized disperse dye is micronized to an particle size of $0.7{\mu}m$. The mixing condition for black color using commercial disperse violet 93 is blue dye 30%, red dye 21%, and orange dye 21%, respectively. Dyed PET fabric with synthesized dye has quiet good color fastness to sublimation(grade 3-4) and has excellent rubbing, washing and light fastness grade 4-5.