• Journal of Korea Multimedia Society
• /
• v.19 no.4
• /
• pp.681-688
• /
• 2016

In the intelligent video surveillance, recognizing the moving objects is important issue. However, the conventional moving object recognition methods have some problems, that is, the influence of light, the distinguishing between similar colors, and so on. The recognition methods for the moving objects using depth information have been also studied, but these methods have limit of accuracy because the depth camera cannot measure the depth value accurately. In this paper, we propose a recognition method for the moving objects by using both the depth and the color information. The depth information is used for extracting areas of moving object and then the color information for correcting the extracted areas. Through tests with typical videos including moving objects, we confirmed that the proposed method could extract areas of moving objects more accurately than a method using only one of two information. The proposed method can be not only used in CCTV field, but also used in other fields of recognizing moving objects.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.3
• /
• pp.13-18
• /
• 2011

In this paper, we explain capturing, postprocessing, and depth generation methods using multiple color and depth cameras. Although the time-of-flight (TOF) depth camera measures the scene's depth in real-time, there are noises and lens distortion in the output depth images. The correlation between the multi-view color images and depth images is also low. Therefore, it is essential to correct the depth images and then we use them to generate the depth information of the scene. The results of stereo matching based on the disparity information from the depth cameras showed the better performance than the previous method. Moreover, we obtained the accurate depth information even at the occluded or textureless regions which are the weaknesses of stereo matching.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.4
• /
• pp.1730-1747
• /
• 2018

Multi-view video plus depth (MVD) is a mainstream format of 3D scene representation in free viewpoint video systems. The advanced 3D extension of the high efficiency video coding (3D-HEVC) standard introduces new prediction tools to improve the coding performance of depth video. However, the depth video in 3D-HEVC is time consuming. To reduce the complexity of the depth video inter coding, we propose a fast coding unit (CU) size and mode decision algorithm. First, an off-line trained Bayesian model is built which the feature vector contains the depth levels of the corresponding spatial, temporal, and inter-component (texture-depth) neighboring largest CUs (LCUs). Then, the model is used to predict the depth level of the current LCU, and terminate the CU recursive splitting process. Finally, the CU mode search process is early terminated by making use of the mode correlation of spatial, inter-component (texture-depth), and inter-view neighboring CUs. Compared to the 3D-HEVC reference software HTM-10.0, the proposed algorithm reduces the encoding time of depth video and the total encoding time by 65.03% and 41.04% on average, respectively, with negligible quality degradation of the synthesized virtual view.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.3
• /
• pp.1302-1309
• /
• 2012

In this paper, we propose applying differential techniques for 2D/3D video conversion to the objects grouped by depth information. One of the problems converting 2D images to 3D images using the technique tracking the motion of pixels is that objects not moving between adjacent frames do not give any depth information. This problem can be solved by applying relative height cue only to the objects which have no moving information between frames, after the process of splitting the background and objects and extracting depth information using motion vectors between objects. Using this technique all the background and object can have their own depth information. This proposed method is used to generate depth map to generate 3D images using DIBR(Depth Image Based Rendering) and verified that the objects which have no movement between frames also had depth information.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.635-636
• /
• 2013

In this research, a method that quantize the depth information to improve the quality of the intermediate view images when DIBR (Depth Image Based Rendering) is used. This paper specially describes the uniform quantization that divides the depth information equally and non-uniform quantization that allocates more depth information in certain areas to improve the quality of the area.

• Journal of Information Processing Systems
• /
• v.18 no.6
• /
• pp.794-802
• /
• 2022

The recovery of reasonable depth information from different scenes is a popular topic in the field of computer vision. For generating depth maps with better details, we present an efficacious monocular depth prediction framework with coordinate attention and feature fusion. Specifically, the proposed framework contains attention, multi-scale and feature fusion modules. The attention module improves features based on coordinate attention to enhance the predicted effect, whereas the multi-scale module integrates useful low- and high-level contextual features with higher resolution. Moreover, we developed a feature fusion module to combine the heterogeneous features to generate high-quality depth outputs. We also designed a hybrid loss function that measures prediction errors from the perspective of depth and scale-invariant gradients, which contribute to preserving rich details. We conducted the experiments on public RGBD datasets, and the evaluation results show that the proposed scheme can considerably enhance the accuracy of depth prediction, achieving 0.051 for log10 and 0.992 for δ<1.25³ on the NYUv2 dataset.

• 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 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 Information Technology
• /
• v.17 no.8
• /
• pp.75-83
• /
• 2019

In this paper, we propose a method that can detect and trace the end point of real - time reinforcement steel to various environmental conditions of industrial field by using Median flow and Depth information. We proposed a method to derive two steel end points by using Median filter, Binarization, Morphology, and Blob algorithm on image depth information. The coordinates of the final position were determined by comparing the coordinates of the reinforcement steel endpoints detected in the Depth image and the position tracking coordinates of the reinforcement steel using Median Flow. As a result, when the existing Median Flow method was used, the success rate of the final position determination of reinforcement steel of 75% was increased to 95% when the Depth of reinforcement steel was used.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.5 no.11
• /
• pp.2175-2190
• /
• 2011

This paper presents the effects of depth map quantization for multiview intermediate image generation using depth image-based rendering (DIBR). DIBR synthesizes multiple virtual views of a 3D scene from a 2D image and its associated depth map. However, it needs precise depth information in order to generate reliable and accurate intermediate view images for use in multiview 3D display systems. Previous work has extensively studied the pre-processing of the depth map, but little is known about depth map quantization. In this paper, we conduct an experiment to estimate the depth map quantization that affords acceptable image quality to generate DIBR-based multiview intermediate images. The experiment uses computer-generated 3D scenes, in which the multiview images captured directly from the scene are compared to the multiview intermediate images constructed by DIBR with a number of quantized depth maps. The results showed that there was no significant effect on depth map quantization from 16-bit to 7-bit (and more specifically 96-scale) on DIBR. Hence, a depth map above 7-bit is needed to maintain sufficient image quality for a DIBR-based multiview 3D system.