• Journal of the Korea Society of Computer and Information
• /
• v.24 no.6
• /
• pp.21-28
• /
• 2019

Recent years with the development of artificial intelligence and the success of the deep model, they have been deployed in all fields of computer vision. Action recognition, as an important branch of human perception and computer vision system research, has attracted more and more attention. Action recognition is a challenging task due to the special complexity of human movement, the same movement may exist between multiple individuals. The human action exists as a continuous image frame in the video, so action recognition requires more computational power than processing static images. And the simple use of the CNN network cannot achieve the desired results. Recently, the attention model has achieved good results in computer vision and natural language processing. In particular, for video action classification, after adding the attention model, it is more effective to focus on motion features and improve performance. It intuitively explains which part the model attends to when making a particular decision, which is very helpful in real applications. In this paper, we proposed a 3D dense convolutional network based on attention mechanism(ADD-Net), recognition of human motion behavior in the video.

• Korean Journal of Remote Sensing
• /
• v.27 no.2
• /
• pp.121-130
• /
• 2011

This paper highlights the reconstruction of the rectilinear type of 3D rooftop model from satellite image data using centroid neural network. The main idea of the proposed 3D reconstruction method is based on the grouping of 3D line segments. 3D lines are extracted by 2D lines and DEM (Digital Elevation Map) data evaluated from a pair of stereo images. Our grouping process consists of two steps. We carry out the first grouping process to group fragmented or duplicated 3D lines into the principal 3D lines, which can be used to construct the rooftop model, and construct the groups of lines that are parallel each other in the second step. From the grouping result, 3D rooftop models are reconstructed by the final clustering process. High-resolution IKONOS images are utilized for the experiments. The experimental result's indicate that the reconstructed building models almost reflect the actual position and shape of buildings in a precise manner, and that the proposed approach can be efficiently applied to building reconstruction problem from high-resolution satellite images of an urban area.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.12 no.2
• /
• pp.139-149
• /
• 2012

A 3D stacked IC is made by multiple dies (possibly) with heterogeneous process technologies. Therefore, die-to-die variation in 2D chips renders on-package variation (OPV) in a 3D chip. In spite of the different variation effect in 3D chips, generally, 3D die stacking can produce high yield due to the smaller individual die area and the averaging effect of variation on data path. However, 3D clock network can experience unintended huge clock skew due to the different clock propagation routes on multiple stacked dies. In this paper, we analyze the on-package variation effect on 3D clock networks and show the necessity of a post silicon management method such as body biasing technique for the OPV induced 3D clock skew control in 3D stacked IC designs. Then, we present a parametric yield improvement method to mitigate the OPV induced 3D clock skew.

• Journal of the military operations research society of Korea
• /
• v.34 no.3
• /
• pp.53-66
• /
• 2008

Information Grid that connects Sensor Grid and Shooter Grid with network is the core infrastructure to enable the NCW concept. The U.S. DoD(Department of Defense) has developed the GIG(Global Information Grid) as the Information Grid that connects all of the DoD mission areas. Then the U.S. DoD has incrementally constructed GIG. In this respect, the case of the U.S. DoD's GIG construction refers to materializing ROK Information Grid concept. Therefore we studied the U.S. DoD's GIG construction trend and analyzed ROK's GIG construction trend. In result this paper proposes the way to develop and construct ROK's GIG.

• Journal of the Optical Society of Korea
• /
• v.1 no.1
• /
• pp.52-59
• /
• 1997

In this paper, we propose a system design for a parallel3-dimensional optical interconnection network utilizing variable grating mode liquid crystal devices (VGM LCD's) which are optical transducers capable of performing intensity-to-spatial-frequency conversion. The proposed system performs real-time, reconfigurable, but blocking and nonbroadcasting 3-dimensional optical interconnections. The operating principles of the 3-D optical interconnection network are described, and some of the fundamental limitations are addressed. The system presented in this paper can be directly used as a configuration of switching elements for the 2-D optical perfect-shuffle dynamic interconnection network, as well as for a B-ISDN photonic switching system.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.10a
• /
• pp.348-353
• /
• 2008

Despite the increasing popularity of wireless sensor network, indoor positioning using low power IEEE 802.15.4 compliant radio had attracted an interest of many researchers in the last decade. Old fashionable indoor location sensing information has been presented in dull and unpleasant 2D image standard. This paper focused on visualizing high precision 3 dimensional RSSI-based (received signal strength indication) spatial sensing information in an interactive virtual reality on PDA. The developed system operates by capturing and extracting signal strength information at multiple pre-defined reference nodes to provide information in the area of interest, thus updating user's location in 3D indoor virtual map. VRML (Virtual Reality Modeling Language) which specifically developed for 3D objects modeling is utilized to design 3D indoor environment.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.6
• /
• pp.105-109
• /
• 2021

In this paper, we evaluate Boosted 3-D PCA as a Dataset and evaluate its performance. After that, we will analyze the network features and performance. In this paper, the learning was performed using the 300W-LP data set using the same learning method as Boosted 3-D PCA, and the evaluation was evaluated using the AFLW2000 data set. The results show that the performance is similar to that of the Boosted 3-D PCA paper. This performance result can be learned using the data set of face images freely than the existing Landmark-to-Pose method, so that the poses can be accurately predicted in real-world situations. Since the optimization of the set of key points is not independent, we confirmed the manual that can reduce the computation time. This analysis is expected to be a very important resource for improving the performance of network boosted 3-D PCA or applying it to various application domains.

• Proceedings of the KIEE Conference
• /
• 1999.07b
• /
• pp.560-562
• /
• 1999

The SOFM neural network as the recognizant algorithm of 3-D underwater object with ultrasonic sensor had the recognizant rate of 100%.

• The Journal of the Korea Contents Association
• /
• v.9 no.7
• /
• pp.19-26
• /
• 2009

This paper presents an approach to classify normal and ventricular tachycardia/fibrillation(VT/VF) from the Creighton University Ventricular Tachyarrhythmia Database(CUDB) using the neural network with weighted fuzzy membership functions(NEWFM) and wavelet transforms. In the first step, wavelet transforms are used to obtain the detail coefficients at levels 3 and 4. In the second step, all of detail coefficients d3 and d4 are classified into four intervals, respectively, and then the standard deviations of the specific intervals are used as eight numbers of input features of NEWFM. NEWFM classifies normal and VT/VF beats using eight numbers of input features, and then the accuracy rate is 90.1%.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.10
• /
• pp.4968-4986
• /
• 2017

In this paper, we primarily address the difficulty of automatic generation of a plausible depth map from a single image in an unstructured environment. The aim is to extrapolate a depth map with a more correct, rich, and distinct depth order, which is both quantitatively accurate as well as visually pleasing. Our technique, which is fundamentally based on a preexisting DepthTransfer algorithm, transfers depth information at the level of superpixels. This occurs within a framework that replaces a pixel basis with one of instance-based learning. A vital superpixels feature enhancing matching precision is posterior incorporation of predictive semantic labels into the depth extraction procedure. Finally, a modified Cross Bilateral Filter is leveraged to augment the final depth field. For training and evaluation, experiments were conducted using the Make3D Range Image Dataset and vividly demonstrate that this depth estimation method outperforms state-of-the-art methods for the correlation coefficient metric, mean log10 error and root mean squared error, and achieves comparable performance for the average relative error metric in both efficacy and computational efficiency. This approach can be utilized to automatically convert 2D images into stereo for 3D visualization, producing anaglyph images that are visually superior in realism and simultaneously more immersive.