• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.328-335
• /
• 2022

With the advance of robot capabilities and functionalities, construction robots assisting construction workers have been increasingly deployed on construction sites to improve safety, efficiency and productivity. For close-proximity human-robot collaboration in construction sites, robots need to be aware of the context, especially construction worker's behavior, in real-time to avoid collision with workers. To recognize human behavior, most previous studies obtained 3D human poses using a single camera or an RGB-depth (RGB-D) camera. However, single-camera detection has limitations such as occlusions, detection failure, and sensor malfunction, and an RGB-D camera may suffer from interference from lighting conditions and surface material. To address these issues, this study proposes a novel method of 3D human pose estimation by extracting 2D location of each joint from multiple images captured at the same time from different viewpoints, fusing each joint's 2D locations, and estimating the 3D joint location. For higher accuracy, the probabilistic representation is used to extract the 2D location of the joints, considering each joint location extracted from images as a noisy partial observation. Then, this study estimates the 3D human pose by fusing the probabilistic 2D joint locations to maximize the likelihood. The proposed method was evaluated in both simulation and laboratory settings, and the results demonstrated the accuracy of estimation and the feasibility in practice. This study contributes to ensuring human safety in close-proximity human-robot collaboration by providing a novel method of 3D human pose estimation.

• Journal of the Korea Computer Graphics Society
• /
• v.29 no.3
• /
• pp.93-103
• /
• 2023

The problem of reconstructing three-dimensional models of people and objects from color and depth images captured by low-cost RGB-D cameras has long been an active research area in computer graphics. Color and depth images captured by low-cost RGB-D cameras are represented as point clouds in three-dimensional space, which correspond to discrete values in a continuous three-dimensional space and require additional surface reconstruction compared to rendering using polygonal models. In this paper, we propose an effective ray-tracing based technique for visualizing point clouds rather than polygonal models. In particular, our method shows the possibility of an effective rendering method even in mobile environment which has limited performance due to processor heat and lack of battery.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.27 no.5
• /
• pp.432-441
• /
• 2007

Image processing methods for an extraction of a nuclear fuel rod image and visualization methods of the RGB color data were studied with a sectional image of spent fuel assembly. The fuel rod images could be extracted by using a histogram analysis, an edge detection and RGB rotor data. In these results, a size of the spent fuel assembly could be measured by using a histogram analysis method and a shape of the spent fuel rod could be observed by using an edge detection method. Finally, a various analyses were established for status of the spent fuel assembly by realized various 3D images for the color data in an image of a spent fuel assembly.

• International Journal of Internet, Broadcasting and Communication
• /
• v.13 no.1
• /
• pp.54-60
• /
• 2021

AR (Augmented Reality) is a technology that provides virtual content to the real world and provides additional information to objects in real-time through 3D content. In the past, a high-performance device was required to experience AR, but it was possible to implement AR more easily by improving mobile performance and mounting various sensors such as ToF (Time-of-Flight). Also, the importance of mobile augmented reality is growing with the commercialization of high-speed wireless Internet such as 5G. Thus, this paper proposes a system that can provide AR services via GNN (Graph Neural Network) using cameras and sensors on mobile devices. ToF of mobile devices is used to capture depth maps. A 3D point cloud was created using RGB images to distinguish specific colors of objects. Point clouds created with RGB images and Depth Map perform downsampling for smooth communication between mobile and server. Point clouds sent to the server are used for 3D object detection. The detection process determines the class of objects and uses one point in the 3D bounding box as an anchor point. AR contents are provided through app and web through class and anchor of the detected object.

• 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.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.4
• /
• pp.187-194
• /
• 2015

In this paper, we present an effective visual odometry estimation system to track the real-time pose of a camera moving in 3D space. In order to meet the real-time requirement as well as to make full use of rich information from color and depth images, our system adopts a feature-based sparse odometry estimation method. After matching features extracted from across image frames, it repeats both the additional inlier set refinement and the motion refinement to get more accurate estimate of camera odometry. Moreover, even when the remaining inlier set is not sufficient, our system computes the final odometry estimate in proportion to the size of the inlier set, which improves the tracking success rate greatly. Through experiments with TUM benchmark datasets and implementation of the 3D scene reconstruction application, we confirmed the high performance of the proposed visual odometry estimation method.

• Journal of the Korea Computer Graphics Society
• /
• v.24 no.1
• /
• pp.27-33
• /
• 2018

This paper presents a new adaptive LSB steganography for high capacity in spatial color images. The number of least signi ficant bit (LSB) of each RGB component in a color image pixel, to replace with the data bits to be hidden, was determine d through analysis of the worst case peak signal noise ratio (PSNR). In addition, the combination of the number of bits is determined adaptively according to image content. That is, 70% of the data to be hidden is proposed to be replaced with 3 bit LSB of two components, 2 bit LSB of the rest component, and 30% be replaced with 4 bit LSB of each RGB compon ent. To find edge areas in an image, delta sorting in local area is also suggested. Using the proposed method, the data cap acity is 9.2 bits per pixel (bpp). The average PSNR value of the tested images with concealed data of up to 60Kbyte was 43.9 db and also natural histograms were generated.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38C no.10
• /
• pp.920-927
• /
• 2013

Chroma key technique which composes images by separating an object from its background in specific color has restrictions on color and space. Especially, unlike general chroma key technique, image composition for stereo 3D display requires natural image composition method in 3D space. The thesis attempted to compose images in 3D space using depth keying method which uses high resolution depth information. High resolution depth map was obtained through camera calibration between the DSLR and Kinect sensor. 3D mesh model was created by the high resolution depth information and mapped with RGB color value. Object was converted into point cloud type in 3D space after separating it from its background according to depth information. The image in which 3D virtual background and object are composed obtained and played stereo 3D images using a virtual camera.

• Journal of Advanced Navigation Technology
• /
• v.20 no.6
• /
• pp.625-630
• /
• 2016

Recently, various types of image contents are being produced, and interest in copyright protection technology is increasing. In this paper, we propose an image encryption technology for color images. This technique divides the image into RGB color components and then performs quad-tree decomposition based on the edge of image. After the quad-tree partitioning, encryption is performed on the selected blocks. Encryption is performed on color components to measure encryption efficiency, and encryption efficiency is measured even after reconstitution into a color image. The encryption efficiency uses a visual measurement method and an objective image quality evaluation method. The PSNR values were measured as 7~10 dB for color difference components and 16~19 dB for color images. The proposed image encryption technology will be used to protect copyright of various digital image contents in the future.

• Journal of Korea Multimedia Society
• /
• v.4 no.2
• /
• pp.108-115
• /
• 2001

In this paper we are attempted to quantitative classification of the three object color regions on a RGB image using of an improved ML(Maximum Likelihood) classification method. A RGB color image consists of three bands i.e., red, green and blue. Therefore it has a 3 dimensional structure in view of the spectral and spatial elements. The 3D structural yokels were projected in RGB cube wherefrom the ML method applied. Between the conventionally and easily usable Box classification and the statistical ML classification based on Bayesian decision theory, we compared and reviewed. Using the ML method we obtained a good segmentation result to classify positive cell nucleus, negative cell Nucleus and background un a immuno-histological breast carcinoma image. Hopefully it is available to diagnosis and prognosis for cancer patients.