• Journal of Broadcast Engineering
• /
• v.27 no.1
• /
• pp.31-43
• /
• 2022

Traditional video compression has developed so far based on hybrid compression methods through motion prediction, residual coding, and quantization. With the rapid development of technology through artificial neural networks in recent years, research on image compression and video compression based on artificial neural networks is also progressing rapidly, showing competitiveness compared to the performance of traditional video compression codecs. In this paper, a new method capable of improving the performance of such an artificial neural network-based video compression model is presented. Basically, we take the rate-distortion optimization method using the auto-encoder and entropy model adopted by the existing learned video compression model and shifts some components of the latent information that are difficult for entropy model to estimate when transmitting compressed latent representation to the decoder side from the encoder side, and finally compensates the distortion of lost information. In this way, the existing neural network based video compression framework, MFVC (Motion Free Video Compression) is improved and the BDBR (Bjøntegaard Delta-Rate) calculated based on H.264 is nearly twice the amount of bits (-27%) of MFVC (-14%). The proposed method has the advantage of being widely applicable to neural network based image or video compression technologies, not only to MFVC, but also to models using latent information and entropy model.

• Korea-Australia Rheology Journal
• /
• v.13 no.1
• /
• pp.47-54
• /
• 2001

Prediction of the maximum packing volume fraction with non-spherical particles has been one of the important problems in powder technology. The sphericity of fly ash particles depending on the particle diameter was measured by means of a CCD image processing instrument. An algorithm to predict the maximum packing volume fraction with non-spherical particles is proposed. The maximum packing volume fraction is used to predict the slurry viscosity under well dispersed conditions. For this purpose, Simha's cell model is applied for concentrated slurry with wide particle size distribution. Also, Usui's model developed for aggregative slurries is applied to predict the non-Newtonian viscosity of dense fly ash - water slurry. It is certified that the maximum packing volume fraction for non-spherical particles can be successfully used to predict slurry viscosity. The pressure drop in a pipe flow is predicted by using the non-Newtonian viscosity of dense fly ash-water slurry obtained by the present model. The predicted relationship between pressure drop and flow rate results in a good agreement with the experimented data obtained for a test rig with 50 mm inner diameter tube. Base on the design procedure proposed in this study, a feasibility study of fly ash hydraulic transportation system from a coal-fired power station to a controlled deposit site is carried out to give a future prospect of inexpensive fly ash transportation technology.

• Bulletin of the Korean Space Science Society
• /
• 2009.10a
• /
• pp.49.3-49.3
• /
• 2009

Geostationary Ocean Colour Imager (GOCI) is the first ocean color instrument that will be operating in a geostationary orbit from 2010. GOCI will provide the crucial information of ocean environment around the Korean peninsula in high spatial and temporal resolutions at eight visible bands. We report an on-going development of imaging and radiometric performance prediction model for GOCI with realistic data for reflectance, transmittance, absorption, wave-front error and scattering properties for its optical elements. For performance simulation, Monte Carlo based ray tracing technique was used along the optical path starting from the Sun to the final detector plane for a fixed solar zenith angle. This was then followed by simulation of red-tide evolution detection and their radiance estimation, following the in-orbit operational sequence. The simulation results proves the GOCI flight model is capable of detecting both image and radiance originated from the key ocean phenomena including red tide. The model details and computational process are discussed with implications to other earth observation instruments.

• Korean Journal of Remote Sensing
• /
• v.35 no.6_1
• /
• pp.933-944
• /
• 2019

This study analyzes the tide deformation of land boundary regions on the east (Region A) and west (Region B) sides of the Ross Ice Shelf in Antarctica using Double-Differential Interferometric Synthetic Aperture Radar (DDInSAR). A total of seven Sentinel-1A SAR images acquired in 2015-2016 were used to estimate the accuracy of tide prediction model and Young's modulus of ice shelf. First, we compared the Ross Sea Height-based Tidal Inverse (Ross_Inv) model, which is a representative tide prediction model for the Antarctic Ross Sea, with the tide deformation of the ice shelf extracted from the DDInSAR image. The accuracy was analyzed as 3.86 cm in the east region of Ross Ice Shelf and it was confirmed that the inverse barometric pressure effect must be corrected in the tide model. However, in the east, it is confirmed that the tide model may be inaccurate because a large error occurs even after correction of the atmospheric effect. In addition, the Young's modulus of the ice was calculated on the basis of the one-dimensional elastic beam model showing the correlation between the width of the hinge zone where the tide strain occurs and the ice thickness. For this purpose, the grounding line is defined as the line where the displacement caused by the tide appears in the DDInSAR image, and the hinge line is defined as the line to have the local maximum/minimum deformation, and the hinge zone as the area between the two lines. According to the one-dimensional elastic beam model assuming a semi-infinite plane, the width of the hinge region is directly proportional to the 0.75 power of the ice thickness. The width of the hinge zone was measured in the area where the ground line and the hinge line were close to the straight line shown in DDInSAR. The linear regression analysis with the 0.75 power of BEDMAP2 ice thickness estimated the Young's modulus of 1.77±0.73 GPa in the east and west of the Ross Ice Shelf. In this way, more accurate Young's modulus can be estimated by accumulating Sentinel-1 images in the future.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.16 no.5
• /
• pp.209-214
• /
• 2021

Panoptic segmentation, which is now widely used in computer vision such as medical image analysis, and autonomous driving, helps understanding an image with holistic view. It identifies each pixel by assigning a unique class ID, and an instance ID. Specifically, it can classify 'thing' from 'stuff', and provide pixel-wise results of semantic prediction and object detection. As a result, it can solve both semantic segmentation and instance segmentation tasks through a unified single model, producing two different contexts for two segmentation tasks. Semantic segmentation task focuses on how to obtain multi-scale features from large receptive field, without losing low-level features. On the other hand, instance segmentation task focuses on how to separate 'thing' from 'stuff' and how to produce the representation of detected objects. With the advances of both segmentation techniques, several panoptic segmentation models have been proposed. Many researchers try to solve discrepancy problems between results of two segmentation branches that can be caused on the boundary of the object. In this survey paper, we will introduce the concept of panoptic segmentation, categorize the existing method into two representative methods and explain how it is operated on two methods: top-down method and bottom-up method. Then, we will analyze the performance of various methods with experimental results.

• Nuclear Engineering and Technology
• /
• v.53 no.7
• /
• pp.2312-2322
• /
• 2021

In recent studies, the creep rate of Zircaloy-4, one of the basic property parameters of the nuclear fuel code, has been commonly used with the axial creep model proposed by Rosinger et al. However, in order to calculate the circumferential deformation of the fuel cladding, there is a limitation that a difference occurs depending on the anisotropic coefficients used in deriving the circumferential creep equation by using the axial creep equation. Therefore, in this study, the existing axial creep law and the derived circumferential creep results were analyzed through a circumferential creep test by the internal pressurization method in the isothermal conditions. The circumferential creep deformation was measured through the optical image analysis method, and the results of the experiment were investigated through constructed IDECA (In-situ DEformation Calculation Algorithm based on creep) code. First, preliminary tests were performed in the isotropic β-phase. Subsequently in the anisotropic α-phase, the correlations obtained from a series of circumferential creep tests were compared with the axial creep equation, and optimized anisotropic coefficients were proposed based on the performed circumferential creep results. Finally, the IDECA prediction results using optimized anisotropic coefficients based on creep tests were validated through tube burst tests in transient conditions.

• International Journal of Contents
• /
• v.18 no.3
• /
• pp.11-20
• /
• 2022

Human Emotion Recognition is an exciting topic that has been attracting many researchers for a lengthy time. In recent years, there has been an increasing interest in exploiting contextual information on emotion recognition. Some previous explorations in psychology show that emotional perception is impacted by facial expressions, as well as contextual information from the scene, such as human activities, interactions, and body poses. Those explorations initialize a trend in computer vision in exploring the critical role of contexts, by considering them as modalities to infer predicted emotion along with facial expressions. However, the contextual information has not been fully exploited. The scene emotion created by the surrounding environment, can shape how people perceive emotion. Besides, additive fusion in multimodal training fashion is not practical, because the contributions of each modality are not equal to the final prediction. The purpose of this paper was to contribute to this growing area of research, by exploring the effectiveness of the emotional scene gist in the input image, to infer the emotional state of the primary target. The emotional scene gist includes emotion, emotional feelings, and actions or events that directly trigger emotional reactions in the input image. We also present an attention-based fusion network, to combine multimodal features based on their impacts on the target emotional state. We demonstrate the effectiveness of the method, through a significant improvement on the EMOTIC dataset.

• Transactions of Materials Processing
• /
• v.32 no.6
• /
• pp.321-328
• /
• 2023

To ensure driver safety, high-strength steel pipes are utilized in the chassis and internal structures design of automobiles. ERW(electric resistance welding) pipes, fabricated through welding at joints using electrical resistance, form a Heat-Affected Zone (HAZ) during the welding process. Due to characteristics such as increased hardness and reduced ductility compared to the base material, HAZ poses challenges in finite element analysis (FEA) for pipe shapes. In this study, for FEA considering HAZ properties, mechanical properties were measured through uniaxial tensile testing and digital image correlation (DIC) techniques after specimen fabrication. These measurements were validated using reverse engineering methods. Furthermore, hardness measurements and gaussian functions were employed to ascertain the hardness distribution within the HAZ, serving as a basis for subdividing the HAZ and modeling the pipe shape. To validate the effectiveness of the HAZ modeling approach, models were interpreted incorporating only base material properties and models incorporating average-calculated HAZ properties. Comparative analysis was performed, revealing that the model subdividing the HAZ based on hardness measurements closely approximated experimental values. This validation offered a methodology for HAZ modeling in FEA.

• Journal of Information Processing Systems
• /
• v.20 no.2
• /
• pp.149-158
• /
• 2024

Traditional manual identification of crop leaf diseases is challenging. Owing to the limitations in manpower and resources, it is challenging to explore crop diseases on a large scale. The emergence of artificial intelligence technologies, particularly the extensive application of deep learning technologies, is expected to overcome these challenges and greatly improve the accuracy and efficiency of crop disease identification. Crop leaf disease identification models have been designed and trained using large-scale training data, enabling them to predict different categories of diseases from unlabeled crop leaves. However, these models, which possess strong feature representation capabilities, require substantial training data, and there is often a shortage of such datasets in practical farming scenarios. To address this issue and improve the feature learning abilities of models, this study proposes a deep transfer learning adaptation strategy. The novel proposed method aims to transfer the weights and parameters from pre-trained models in similar large-scale training datasets, such as ImageNet. ImageNet pre-trained weights are adopted and fine-tuned with the features of crop leaf diseases to improve prediction ability. In this study, we collected 16,060 crop leaf disease images, spanning 12 categories, for training. The experimental results demonstrate that an impressive accuracy of 98% is achieved using the proposed method on the transferred ResNet-50 model, thereby confirming the effectiveness of our transfer learning approach.

• Proceedings of the KIEE Conference
• /
• 2000.07d
• /
• pp.2843-2845
• /
• 2000

A lane detection based on a road model or feature all need correct acquirement of information on the lane in a image, It is inefficient to implement a lane detection algorithm through the full range of a image when being applied to a real road in real time because of the calculating time. This paper defines two searching range of detecting lane in a road, First is searching mode that is searching the lane without any prior information of a road, Second is recognition mode, which is able to reduce the size and change the position of a searching range by predicting the position of a lane through the acquired information in a previous frame. It is allow to extract accurately and efficiently the edge candidates points of a lane as not conducting an unnecessary searching. By means of removing the perspective effect of the edge candidate points which are acquired by using the inverse perspective transformation, we transform the edge candidate information in the Image Coordinate System(ICS) into the plane-view image in the World Coordinate System(WCS). We define linear approximation filter and remove the fault edge candidate points by using it This paper aims to approximate more correctly the lane of an actual road by applying the least-mean square method with the fault-removed edge information for curve fitting.