• Journal of Advanced Navigation Technology
• /
• v.23 no.5
• /
• pp.400-407
• /
• 2019

In this paper, the shadow detection and reconstruction method are proposed using intrinsic image, which does not change the essential characteristics under the influence of various illuminance, and multi-scale gamma correction. The shadow detection was estimated by the pixel change information between a grayscale and an intrinsic image of the color image, and the brightness of the image were adjusted by gamma correction in the shadow restoration process. Multi-scale gamma correction is performed for each channel of a color image due to the fact that the saturation can be changed by nonlinear adjustment to individual pixel values. Multi-scale gamma values are estimated based on the information of the crossed edge between shadows and non-shadowed regions in the color image, as a result, the shadows are reconstructed by correcting different region features with multi-scale gamma values. Experimental results show that the proposed method effectively reconstructs shadows in a single natural image.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.05a
• /
• pp.631-634
• /
• 2009

Recent advances in wireless communication, electronics, MEMS device, sensor and battery technology have made it possible to manufacture low-cost, low-power, multi-function tiny sensor nodes. A large number of tiny sensor nodes form sensor network through wireless communication. Sensor networks represent a significant improvement over traditional sensors, research on Zigbee wireless image transmission has been a topic in industrial and scientific fields. In this paper, we design a Zigbee wireless image sensor node and multimedia monitoring server system. It consists of embedded processor, memory, CMOS image sensor, image acquisition and processing unit, Zigbee RF module, power supply unit and remote monitoring server system. In the future, we will further improve our Zigbee wireless image sensor node and monitoring server system. Besides, energy-efficient Zigbee wireless image transmission protocol and interworking with mobile network will be our work focus.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.9 no.4
• /
• pp.269-277
• /
• 2019

In this paper, the compatibility analysis on the track record operation center for the regional industry upbringing is presented. The renewable energy sources such as solar, wind and battery energy storage system have been widely spread in these days. Also the requirements on the efficiency, reliability and power demands of these distributed systems are increasing and they can be demands on the construction of the data track record center for renewable energy industries in order to promote the local industries. The analysis on the size of the de-centralized power system are performed based on the technical issues. The necessities, requirements and center goals to meet these missions are presented in the following session. The proposal of the 1 MW operation center construction and operations are presented in the result of the compatibility analysis. And the lists of the required equipments in the operation facilities are suggested to have proper operational capabilities. The results of this research can be applied in the fundamental data to promote the regional renewable industries.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.6
• /
• pp.63-68
• /
• 2018

Offloading is a method of communicating, processing, and receiving results from some of the applications performed on local computers to overcome the limitations of computing resources and computational speed.Recently, it has been applied in mobile games, multimedia data, 360-degree video processing, and image processing for Internet broadcasting to speed up processing and reduce battery consumption in the mobile computing sector. This paper implements a viewer that enables users to convert various flat-panel images and view contents in a wireless Internet environment and presents actual results of an experiment so that users can easily understand the images. The 360 degree spherical image is successfully converted to a plane image with Double Panorama, Quad, Single Rectangle, 360 Overview + 3 Rectangle depending on the image acquisition position of the 360 degree camera through the interface. During the experiment, more than 100 360 degree spherical images were successfully converted into plane images through the interface below.

• Journal of Broadcast Engineering
• /
• v.23 no.6
• /
• pp.780-789
• /
• 2018

Nowadays, gun crimes occur very frequently not only in public places but in alleyways around the world. In particular, it is essential to detect a person armed by a pistol to prevent those crimes since small guns, such as pistols, are often used for those crimes. Because conventional works for armed person detection have treated an armed person as a single object in an input image, their accuracy is very low. The reason for the low accuracy comes from the fact that the gunman is treated as a single object although the pistol is a relatively much smaller object than the person. To solve this problem, we propose a novel algorithm called APDA(Armed Person Detection Algorithm). APDA detects the armed person using in a post-processing the positions of both wrists and the pistol achieved by the CNN-based human body feature detection model and the pistol detection model, respectively. We show that APDA can provide both 46.3% better recall and 14.04% better precision than SSD-MobileNet.

• Journal of Broadcast Engineering
• /
• v.26 no.3
• /
• pp.258-268
• /
• 2021

Point cloud content is immersive content that represents real-world objects with three-dimensional (3D) points. In the process of acquiring point cloud data or encoding and decoding point cloud data, the resolution of point cloud content could be degraded. In this paper, we propose a method of progressively enhancing the resolution of sequential point cloud contents through inter-frame registration. To register a point cloud, the iterative closest point (ICP) algorithm is commonly used. Existing ICP algorithms can transform rigid bodies, but there is a disadvantage that transformation is not possible for non-rigid bodies having motion vectors in different directions locally, such as point cloud content. We overcome the limitations of the existing ICP-based method by registering regions with motion vectors in different directions locally between the point cloud content of the current frame and the previous frame. In this manner, the resolution of the point cloud content with geometric movement is enhanced through the process of registering points between frames. We provide four different point cloud content that has been enhanced with our method in the experiment.

• Journal of Broadcast Engineering
• /
• v.26 no.1
• /
• pp.70-78
• /
• 2021

Estimating 3D information from a single image is one of the essential problems in numerous applications. Since a 2D image inherently might originate from an infinite number of different 3D scenes, thus 3D reconstruction from a single image is notoriously challenging. This challenge has been overcame by the advent of recent deep convolutional neural networks (CNNs), by modeling the mapping function between 2D image and 3D information. However, to train such deep CNNs, a massive training data is demanded, but such data is difficult to achieve or even impossible to build. Recent trends thus aim to present deep learning techniques that can be trained in a weakly-supervised manner, with a meta-data without relying on the ground-truth depth data. In this article, we introduce recent developments of weakly-supervised deep learning technique, especially categorized as scene 3D reconstruction and object 3D reconstruction, and discuss limitations and further directions.

• Journal of Korea Game Society
• /
• v.21 no.1
• /
• pp.3-24
• /
• 2021

This paper deals with on the game's way of embodying the society at the end of the century. Resident Evil, Parasite Eve, and Silent Hill are the targets of the analysis. First, I examine the world view of each game and its own language that conveys its contents. Second, I analyze the specific parts of reality that the three games imitate and the way they are represented. Third, I consider the connection between the real world and the world embodied in the game. Fourth, I suggest the possibility of providing an 'alternative perspective' of game media that reveals the hidden aspects of reality in a way of representation. In conclusion, the image of the game becomes 'the eye' that complements our perspective, captures the hidden aspects of reality, obtains a meaningful part, and even presents its blueprint.

• Journal of Broadcast Engineering
• /
• v.27 no.2
• /
• pp.207-215
• /
• 2022

The latest volumetric technology's high geometrical accuracy and realism ensure a high degree of correspondence between the real object and the captured 3D model. Nevertheless, since the 3D model obtained in this way constitutes a sequence as a completely independent 3D model between frames, the consistency of the model surface structure (geometry) is not guaranteed for every frame, and the density of vertices is very high. It can be seen that the interconnection node (Edge) becomes very complicated. 3D models created using this technology are inherently different from models created in movie or video game production pipelines and are not suitable for direct use in applications such as real-time rendering, animation and simulation, and compression. In contrast, our method achieves consistency in the quality of the volumetric 3D model sequence by linking re-meshing, which ensures high consistency of the 3D model surface structure between frames and the gradual deformation and texture transfer through correspondence and matching of non-rigid surfaces. And It maintains the consistency of volumetric 3D model sequence quality and provides post-processing automation.

• Journal of Broadcast Engineering
• /
• v.27 no.2
• /
• pp.174-184
• /
• 2022

3D human pose estimation models can be classified into a multi-view model and a single-view model. In general, the multi-view model shows superior pose estimation performance compared to the single-view model. In the case of the single-view model, the improvement of the 3D pose estimation performance requires a large amount of training data. However, it is not easy to obtain annotations for training 3D pose estimation models. To address this problem, we propose a method to generate pseudo ground-truths of multi-view human pose data from a multi-view model and exploit the resultant pseudo ground-truths to train a single-view model. In addition, we propose a multi-view consistency loss function that considers the consistency of poses estimated from multi-view images, showing that the proposed loss helps the effective training of single-view models. Experiments using Human3.6M and MPI-INF-3DHP datasets show that the proposed method is effective for training single-view 3D human pose estimation models.