• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.11
• /
• pp.5555-5567
• /
• 2018

State-of-art instance segmentation networks are successful at generating 2D segmentation mask for region proposals with highest classification score, yet 3D object segmentation task is limited to geocentric embedding or detector of Sliding Shapes. To this end, we propose an amodal 3D instance segmentation network called A3IS-CNN, which extends the detector of Deep Sliding Shapes to amodal 3D instance segmentation by adding a new branch of 3D ConvNet called A3IS-branch. The A3IS-branch which takes 3D amodal ROI as input and 3D semantic instances as output is a fully convolution network(FCN) sharing convolutional layers with existing 3d RPN which takes 3D scene as input and 3D amodal proposals as output. For two branches share computation with each other, our 3D instance segmentation network adds only a small overhead of 0.25 fps to Deep Sliding Shapes, trading off accurate detection and point-to-point segmentation of instances. Experiments show that our 3D instance segmentation network achieves at least 10% to 50% improvement over the state-of-art network in running time, and outperforms the state-of-art 3D detectors by at least 16.1 AP.

• Smart Media Journal
• /
• v.9 no.1
• /
• pp.23-29
• /
• 2020

This paper presents an approach for dynamic hand gesture recognition by using algorithm based on 3D Convolutional Neural Network (3D_CNN), which is later extended to 3D Residual Networks (3D_ResNet), and the neural network based key frame selection. Typically, 3D deep neural network is used to classify gestures from the input of image frames, randomly sampled from a video data. In this work, to improve the classification performance, we employ key frames which represent the overall video, as the input of the classification network. The key frames are extracted by SegNet instead of conventional clustering algorithms for video summarization (VSUMM) which require heavy computation. By using a deep neural network, key frame selection can be performed in a real-time system. Experiments are conducted using 3D convolutional kernels such as 3D_CNN, Inflated 3D_CNN (I3D) and 3D_ResNet for gesture classification. Our algorithm achieved up to 97.8% of classification accuracy on the Cambridge gesture dataset. The experimental results show that the proposed approach is efficient and outperforms existing methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.4 no.6
• /
• pp.1209-1221
• /
• 2010

Three dimensional (3D) video is expected to be an important application for broadcast and IP streaming services. One of the main limitations for the transmission of 3D video over IP networks is network bandwidth mismatch due to the large size of 3D data, which causes fatal decoding errors and mosaic-like damage. This paper presents a novel selective frame discard method to address the problem. The main idea of the proposed method is the symmetrical discard of the two dimensional (2D) video frame and the depth map frame. Also, the frames to be discarded are selected after additional consideration of the playback deadline, the network bandwidth, and the inter-frame dependency relationship within a group of pictures (GOP). It enables the efficient utilization of the network bandwidth and high quality 3D IPTV service. The simulation results demonstrate that the proposed method enhances the media quality of 3D video streaming even in the case of bad network conditions.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.43 no.3
• /
• pp.87-94
• /
• 2020

In this study, the factors affecting the efficiency of 48 projects of private R&D institutes were analyzed using the Tobit model. Influencing factors were selected as open R&D network size, IT industry, interaction between R&D network size and IT industry, and type of R&D network cooperation. As a result of Tobit analysis, the R&D network size, the IT industry, and the type of R&D network cooperation were found to be significant. The larger the open R&D network size, the lower the efficiency, and the IT industry showed lower R&D efficiency than other industries. In addition, cooperation with universities and research institutes showed lower R&D efficiency than cooperation with companies. As a result of these studies, companies will be able to select and focus on cooperation with the outside in relations and investment allocation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.3
• /
• pp.1450-1463
• /
• 2019

The problem towards crowd behavior recognition in a serious clustered scene is extremely challenged on account of variable scales with non-uniformity. This paper aims to propose a crowed behavior classification framework based on a transferring hybrid network blending 3D res-net with inception-v3. First, the 3D res-inception network is presented so as to learn the augmented visual feature of UCF 101. Then the target dataset is applied to fine-tune the network parameters in an attempt to classify the behavior of densely crowded scenes. Finally, a transferred entropy function is used to calculate the probability of multiple labels in accordance with these features. Experimental results show that the proposed method could greatly improve the accuracy of crowd behavior recognition and enhance the accuracy of multiple label classification.

• Journal of Korea Society of Industrial Information Systems
• /
• v.2 no.1
• /
• pp.73-87
• /
• 1997

Multilayer neural network using a modified beackpropagation learning algorithm was introduced to achieve automatic identification of different types of aircraft in a variety of 3-D orientations. A 3-D shape of an aircraft can be described by a library of 2-D images corresponding to the projected views of an aircraft. From each 2-D binary aircraft image we extracted 2-D invariant (L, Φ) feature vector to be used for training neural network aircraft classifier. Simulations concerning the neural network classification rate was compared using nearest-neighbor classfier (NNC) which has been widely served as a performance benchmark. And we also introduced reliability measure of the designed neural network classifier.

• Journal of Korea Game Society
• /
• v.6 no.1
• /
• pp.21-28
• /
• 2006

This study focused on design and implementation of Mobile 3D Bluetooth Engine based on OpenGL-ES. In Mobile 3D network game so far, there is a form the mainstream of wireless internet game using WAP and VM. But, VM game are popular because of an excessive communication expense problem for this mobile network game that occur when connect to wireless internet as point out to problem by it, that is, stand-alone game are very popular. This study introduce a mobile 3D Bluetooth Engine which is based on mobile 3D standard using OpenGL-ES to solve a mobile network game generally that occurs when connect to take pleasure a wireless internet from some people into a short distance.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.3
• /
• pp.602-612
• /
• 2015

Current IEEE 802.11p which is suggested for vehicle to vehicle communication supports one hop communication. Thus, it has a limitation to carry out efficient data dissemination. In this thesis, we suggest LTE-D2D based vehicle network to provide efficient data dissemination in the vehicle environment. In this network architecture, we use name based message with IP packet options and we put the intermediate vehicle node called 'super vehicle node' and each normal vehicle node in the cell requests data to the super vehicle node. The super vehicle node responses data to the normal vehicle node. Performance analysis is based mathematical modeling. We compare LTE cellular network to LTE-D2D based vehicle network about throughput according to packet delivery time.

• Smart Media Journal
• /
• v.10 no.2
• /
• pp.30-37
• /
• 2021

Recently, 3D contents used in various fields have been attracting people's attention due to the development of virtual reality and augmented reality technology. In order to produce 3D contents, it is necessary to model the objects as vertices. However, high-quality modeling is time-consuming and costly. In order to convert a 2D character into a 3D model, it is necessary to express it as line drawings through feature line extraction. The extraction of consistent line drawings from 2D cartoon cartoons is difficult because the styles and techniques differ depending on the designer who produces them. Therefore, it is necessary to extract the line drawings that show the geometrical characteristics well in 2D cartoon shapes of various styles. This study proposes a method of automatically extracting line drawings. The 2D Cartoon shading image and line drawings are learned by using adversarial network model, which is artificial intelligence technology and outputs 2D cartoon artwork of various styles. Experimental results show the proposed method in this research can be obtained as a result of the line drawings representing the geometric characteristics when a 2D cartoon painting as input.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.5
• /
• pp.205-212
• /
• 2019

Scene graph is a kind of knowledge graph that represents both objects and their relationships found in a image. This paper proposes a 3D scene graph generation model for three-dimensional indoor environments. An 3D scene graph includes not only object types, their positions and attributes, but also three-dimensional spatial relationships between them, An 3D scene graph can be viewed as a prior knowledge base describing the given environment within that the agent will be deployed later. Therefore, 3D scene graphs can be used in many useful applications, such as visual question answering (VQA) and service robots. This proposed 3D scene graph generation model consists of four sub-networks: object detection network (ObjNet), attribute prediction network (AttNet), transfer network (TransNet), relationship prediction network (RelNet). Conducting several experiments with 3D simulated indoor environments provided by AI2-THOR, we confirmed that the proposed model shows high performance.