• Journal of Korea Multimedia Society
• /
• v.22 no.12
• /
• pp.1457-1465
• /
• 2019

3D convolution is to stack multiple consecutive frames to form a cube, and then apply the 3D convolution kernel in the cube. In this structure, each feature map of the convolutional layer is connected to multiple adjacent sequential frames in the previous layer, thus capturing the motion information. However, due to the changes of pedestrian posture, motion and position, the convolution at the same place is inappropriate, and when the 3D convolution kernel is convoluted in the time domain, only time domain features of three consecutive frames can be extracted, which is not a good enough to get action information. This paper proposes an action recognition method based on feature fusion of 3D convolutional neural network. Based on the VGG16 network model, sending a pre-acquired optical flow image for learning, then get the time domain features, and then the feature of the time domain is extracted from the features extracted by the 3D convolutional neural network. Finally, the behavior classification is done by the SVM classifier.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.5
• /
• pp.60-72
• /
• 1996

In this paper, a enw model-base three-dimensional (3-D) object recognition mehtod using hopfield network is proposed. To minimize deformation of feature values on 3-D rotation, we select 3-D shape features and 3-D relational features which have rotational invariant characteristics. Then these feature values are normalized to have scale invariant characteristics, also. The input features are matched with model features by optimization process of hopjfield network in the form of two dimensional arrayed neurons. Experimental results on object classification and object matching with the 3-D rotated, scale changed, an dpartial oculued objects show good performance of proposed method.

• Journal of IKEEE
• /
• v.16 no.2
• /
• pp.102-108
• /
• 2012

3-dimensional integrated circuits (3D-ICs) have some problems for power delivery network design due to larger supply currents and larger power delivery paths compared to 2D-IC. The power delivery network consists of power bumps & through-silicon-vias (TSVs), and IR-drop at each node varies with the number and location of power bumps & TSVs. It is important to optimize the power bumps & TSVs while IR-drop constraint is satisfied in order to operate chip ordinarily. In this paper, the power bumps & TSVs optimization with optimized power mesh structure for power delivery network in 3D-ICs is proposed.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.4
• /
• pp.357-363
• /
• 2023

In underwater signal processing, separating individual signals from mixed signals has long been a challenge due to low signal quality. The common method using Short-time Fourier transform for spectrogram analysis has faced criticism for its complex parameter optimization and loss of phase data. We propose a Triple-path Recurrent Neural Network, based on the Dual-path Recurrent Neural Network's success in long time series signal processing, to handle three-dimensional tensors from multi-channel sensor input signals. By dividing input signals into short chunks and creating a 3D tensor, the method accounts for relationships within and between chunks and channels, enabling local and global feature learning. The proposed technique demonstrates improved Root Mean Square Error and Scale Invariant Signal to Noise Ratio compared to the existing method.

• Journal of Communications and Networks
• /
• v.11 no.3
• /
• pp.287-296
• /
• 2009

Although asymptotic bounds of wireless network capacity have been heavily pursued, the answers to the following questions are still critical for network planning, protocol and architecture design: Given a three-dimensional (3D) network space with the number of active users randomly located in the space and using the wireless communication technology, what are the expected per-flow throughput, network capacity, and network transport capacity? In addition, how can the protocol parameters be tuned to enhance network performance? In this paper, we focus on the ultra wideband (UWB) based wireless personal area networks (WPANs) and provide answers to these questions, considering the salient features of UWB communications, i.e., low transmission/interference power level, accurate ranging capability, etc. Specifically, we demonstrate how to explore the spatial multiplexing gain of UWB networks by allowing appropriate concurrent transmissions. Given 3D space and the number of active users, we derive the expected number of concurrent transmissions, network capacity and transport capacity of the UWB network. The results reveal the main factors affecting network (transport) capacity, and how to determine the best protocol parameters, e.g., exclusive region size, in order to maximize the capacity. Extensive simulation results are given to validate the analytical results.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.16 no.5
• /
• pp.179-186
• /
• 2021

For stereo matching based on deep learning, the design of network structure is crucial to the calculation of matching cost, and the time-consuming problem of convolutional neural network in image processing also needs to be solved urgently. In this paper, a method of stereo matching using sparse loss volume in parallax dimension is proposed. A sparse 3D loss volume is constructed by using a wide step length translation of the right view feature map, which reduces the video memory and computing resources required by the 3D convolution module by several times. In order to improve the accuracy of the algorithm, the nonlinear up-sampling of the matching loss in the parallax dimension is carried out by using the method of multi-category output, and the training model is combined with two kinds of loss functions. Compared with the benchmark algorithm, the proposed algorithm not only improves the accuracy but also shortens the running time by about 30%.

• Journal of Broadcast Engineering
• /
• v.19 no.5
• /
• pp.687-698
• /
• 2014

ATSC is currently working on standardization of hybrid 3DTV broadcasting service in heterogenous network environment after completion of service-compatible 3DTV broadcasting service standard based on broadcasting channel. This paper proposes a convergence 3D video broadcasting method on broadcasting and IP network while guaranteeing a Full-HD 3D quality without degrading the image quality of legacy DTV. Specifically, this paper describes transmission of the 3D additional video using the ISO/IEC 23009-1 DASH, robust synchronization method under heterogenous network environments and system target decoder model for hybrid 3DTV receiver. Based on experimental results, we confirm that proposed technologies can be used as a core technology in the hybrid 3DTV standardization and a reference model for a development of hybrid 3DTV encoder and receiver.

• Journal of the Korea Computer Graphics Society
• /
• v.3 no.1
• /
• pp.29-36
• /
• 1997

Most Virtual Reality Systems have been developed to support only a single user on a stand-alone system. With increasing availability of Internet, many people are taking strong interests in distributed Virtual Reality : the virtual environment is shared by many paticipants interacting over the network. To support sharing virtual environment and interactions on a network, we developed novel contributions to 3D world description and a network model. Interactive 3D world description is based on VRML, which is extended to support multi-user interactions. Then network model in our system consists of an architecture and a set of protocols for realizing a multi-user interactive shared 3D environment in IP multicast environment.

• Spatial Information Research
• /
• v.14 no.4 s.39
• /
• pp.391-401
• /
• 2006

We propose a method for geographically enhanced representation of social networks and implement a Web-based 3D visualization of geographical contexts in social networks. A renovated social network graph is illustrated by using two key components: (i) GWCMs (geographically weighted centrality measures) that reflect the differences in interaction intensity and spatial proximity among nodes and (ii) MSNG (map-integrated social network graph) that incorporates the GWCMs and the geographically referenced arrangement of nodes on a choroplethic map. For the integrated 3D visualization of the renovated social network graph, we employ X3D (Extensible 3D), a standard 3D authoring tool for the Web. An experimental case study of regional R&D collaboration provides a visual clue to geographical contexts in social networks including how the social centralization relates to spatial centralization.

• Spatial Information Research
• /
• v.20 no.4
• /
• pp.29-36
• /
• 2012

The low-carbon freight transportation system was introduced due to increase traffic congestion cost and carbon-dioxide for global climate change according to expanding city logistics demands. It is necessary to create 3D-based road network map for representing realistic road geometry with consideration of fuel consumption and carbon emissions. This study propose that 3D road network model expressed to realistic topography and road structure within trunk road for intercity freight through overlaying 2D-based transport-related thematic map and 1m-resolution DEM. The 3D-based road network map for the experimental road sections(Pyeongtaek harbor-Uiwang IC) was verified by GPS/INS survey and fuel consumption simulation. The results corresponded to effectively reflect realistic road geometry (RMSE=0.87m) except some complex structure such as overpass, and also actual fuel consumption. We expect that Green-based freight route planning and navigation system reflected on 3D geometry of complex road structure will be developed for effectively resolving energy and environmental problems.