• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.11
• /
• pp.1098-1102
• /
• 2014

Localization of aerial vehicles and map building of flight environments are key technologies for the autonomous flight of small UAVs. In outdoor environments, an unmanned aircraft can easily use a GPS (Global Positioning System) for its localization with acceptable accuracy. However, as the GPS is not available for use in indoor environments, the development of a SLAM (Simultaneous Localization and Mapping) system that is suitable for small UAVs is therefore needed. In this paper, we suggest a vision-based SLAM system that uses vision sensors and an AHRS (Attitude Heading Reference System) sensor. Feature points in images captured from the vision sensor are obtained by using GPU (Graphics Process Unit) based SIFT (Scale-invariant Feature Transform) algorithm. Those feature points are then combined with attitude information obtained from the AHRS to estimate the position of the small UAV. Based on the location information and color distribution, a Gaussian process model is generated, which could be a map. The experimental results show that the position of a small unmanned aircraft is estimated properly and the map of the environment is constructed by using the proposed method. Finally, the reliability of the proposed method is verified by comparing the difference between the estimated values and the actual values.

• Journal of the Korea Computer Graphics Society
• /
• v.14 no.3
• /
• pp.1-9
• /
• 2008

This paper presents a novel optimization-based saliency-preserving method for converting color images to grayscale in a manner consistent with conventional approaches of black-and-white photographers. In black-and-white photography, a colored filter called a contrast filter has been commonly employed on a camera to lighten or darken selected colors. In addition, local exposure controls such as dodging and burning techniques are typically employed in the darkroom process to change the exposure of local areas within the print without affecting the overall exposure. Our method seeks a digital version of a conventional contrast filter to preserve visually-important image features. Furthermore, conventional burning and dodging techniques are addressed, together with image similarity weights, to give edge-aware local exposure control over the image space. Our method can be efficiently optimized on GPU. According to the experiments, CUDA implementation enables 1 megapixel color images to be converted to grayscale at interactive frames rates.

• The Journal of the Korea Contents Association
• /
• v.14 no.10
• /
• pp.1-9
• /
• 2014

Generally, integral image used for autostereoscopic 3d display is generated for flat lens array, but flat lens array cannot provide a wide range of view for generated integral image because of narrow range of view. To make up for this flat lens array's weak point, curved lens array has been proposed, and due to technical and cost problem, approximate surface lens array composed of several flat lens array is used instead of ideal curved lens array. In this paper, we constructed an approximate surface lens array arranged for $20{\times}8$ square flat lens in 100mm radius sphere, and we could get about twice angle of view compared to flat lens array. Specially, unlike existing researches which manually generate integral image, we propose an OpenCL GPU parallel process algorithm for generating real-time integral image. As a result, we could get 12-20 frame/sec speed about various 3D volume data from $15{\times}15$ approximate surface lens array.

• Journal of Digital Convergence
• /
• v.16 no.10
• /
• pp.205-212
• /
• 2018

With the development of high performance CPU / GPU, artificial intelligence algorithms such as deep neural networks, and a large amount of data, machine learning has been extended to various applications. In particular, a large amount of data collected from the Internet of Things, social network services, web pages, and public data is accelerating the use of machine learning. Learning data sets for machine learning exist in various formats according to application fields and data types, and thus it is difficult to effectively process data and apply them to machine learning. Therefore, this paper studied a method for building a learning data set for machine learning in accordance with standardized procedures. This paper first analyzes the requirement of learning data set according to problem types and data types. Based on the analysis, this paper presents the reference model to build learning data set for machine learning applications. This paper presents the target standardization organization and a standard development strategy for building learning data set.

• Journal of Internet Computing and Services
• /
• v.16 no.5
• /
• pp.49-57
• /
• 2015

In this Paper, we introduce an efficient on-line software service using an application customized graphic offloading library. The software service based on graphic offloading provides high-end software, like a 3D graphic design tool, as an on-line software service through using a client graphic rendering. When software is executed on server, its graphic works are handled by a client's GPU, while its data works are handled by a server's CPU. To improve the performance, we apply an asynchronous transmission channel scheme to our developed basic graphic offloading engine. Also, we add optimized common module and application specific module to our engine. To do that, we introduce how to implement the application specific module using analyzing patterns of graphic related APIs and messages that are generated by an executed software process. Also, we propose how to design the optimized common module using server side information caching. Finally, through the performance comparison experiment, we show that improved offloading engine has the better performance than old basic offloading engine.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.1
• /
• pp.27-34
• /
• 2021

In this paper, we propose a copyright protection scheme for real-time streaming of HEVC(High Efficiency Video Coding) based realistic content. Previous research uses encryption and modular operation for copyright pre-protection and copyright post-protection, which causes delays in ultra high resolution video. The proposed scheme maximizes parallelism by using thread pool based DRM(Digital Rights Management) packaging with only HEVC's CABAC(Context Adaptive Binary Arithmetic Coding) codec and GPU based high-speed bit operation(XOR), thus enabling real-time copyright protection. As a result of comparing this scheme with previous research at three resolutions, PSNR showed an average of 8 times higher performance, and the process speed showed an average of 18 times difference. In addition, as a result of comparing the robustness of the forensic mark, the filter and noise attack, which showed the largest and smallest difference, with a 27-fold difference in recompression attacks, showed an 8-fold difference.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.6
• /
• pp.313-330
• /
• 2021

In an autonomous driving system equipped with a camera and lidar, depth completion techniques enable dense depth estimation. In particular, using self-supervised learning it is possible to train the depth completion network even without ground truth. In actual autonomous driving, such depth completion should have very short latency as it is the input of other algorithms. So, rather than complicate the network structure to increase the accuracy like previous studies, this paper focuses on network latency. We design a U-Net type network with RegNet encoders optimized for GPU computation. Instead, this paper presents several techniques that can increase accuracy during the process of self-supervised learning. The proposed techniques increase the robustness to unreliable lidar inputs. Also, they improve the depth quality for edge and sky regions based on the semantic information extracted in advance. Our experiments confirm that our model is very lightweight (2.42 ms at 1280x480) but resistant to noise and has qualities close to the latest studies.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.6
• /
• pp.1-7
• /
• 2023

This paper developed a training model to classify normal roads and flooded roads using artificial intelligence technology. We expanded the diversity of learning data using various data augmentation techniques and implemented a model that shows good performance in various environments. Transfer learning was performed using the CNN-based Resnet152v2 model as a pre-learning model. During the model learning process, the performance of the final model was improved through various parameter tuning and optimization processes. Learning was implemented in Python using Google Colab NVIDIA Tesla T4 GPU, and the test results showed that flooding situations were detected with very high accuracy in the test dataset.

• Membrane Journal
• /
• v.28 no.5
• /
• pp.351-360
• /
• 2018

In this study, propylene/propane separation mechanism through NaY zeolite membrane was investigated. As permeation temperature increased, both propylene and propane permeances increased, saturated and decreased again, and a maximum selectivity was shown at around 50 to $60^{\circ}C$. Propane permeance in mixed gas experiment was much smaller than that in single gas experiment, and propylene/propane mixed gas selectivity was much larger than single gas permselectivity. As permeation time increased in transient permeation experiment, propylene permeance initially increased and saturated, while propane permeance decreased and saturated. All the experimental results announced that propylene/propane separation through NaY zeolite membrane was from preferentially adsorbed propylene molecules. The adsorbed propylene molecules efficiently prevented propane molecules from permeating through the membrane, and sufae diffused through the membrane. NaY zeolite capillary membrane prepared in the present study showed a high mixed gas selectivity of 12 and high propylene permeance of 497 GPU for a propylene/propane (89 : 11) mixture at $50^{\circ}C$ and 4 bar. Therefore, it was concluded that NaY zeolite membrane is one of promising membrane materials for propylene/propane separation due to the low cost and high separation performance.

• Journal of the Korea Computer Graphics Society
• /
• v.15 no.1
• /
• pp.17-23
• /
• 2009

We present a simple new idea to improve the quality of exemplar based texture synthesis using multiple rotated input exemplars. Our algorithm successfully obtain rotational synthesis feature variations and manages to reduce the artifacts in the results, especially patch seams due to the structure of the exemplars provided which have been inappropriate for previous neighborhood matching synthesis algorithms. Our algorithm is parallel in nature, thus it is possible to implement our algorithm using GPU or multi-core CPU to accelerate synthesis process.