• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.1
• /
• pp.280-286
• /
• 2024

In this paper, layered UNet with warmup and dropout tricks was used to segment teeth instantly by using data labeled for each individual tooth and increase performance of the result. The layered UNet proposed before showed very good performance in tooth segmentation without distinguishing tooth number. To do instance segmentation of teeth, we labeled teeth CBCT data according to tooth numbering system which is devised by FDI World Dental Federation notation. Colors for labeled teeth are like AI-Hub teeth dataset. Simulation results show that layered UNet does also segment very well for each tooth distinguishing tooth number by color. Layered UNet model using warmup trick was the best with IoU values of 0.80 and 0.77 for training, validation data. To increase the performance of instance segmentation of teeth, we need more labeled data later. The results of this paper can be used to develop medical software that requires tooth recognition, such as orthodontic treatment, wisdom tooth extraction, and implant surgery.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.07a
• /
• pp.306-307
• /
• 2015

본 논문에서는 ATSC (Advanced Television Systems Committee) 3.0 시스템을 위한 LDM (Layered Division Multiplexing) 기술을 제안하고, 그 성능을 전산실험을 통해 분석한다. 제안된 LDM 시스템은 기존의 TDM (Time Division Multiplexing) / FDM (Frequency Division Multiplexing) 기술에 비해 약 3 에서 9 dB 의 성능 이득을 나타낸다.

• ETRI Journal
• /
• v.27 no.1
• /
• pp.102-105
• /
• 2005

In this letter, we present a layered structure of the Korean terrestrial Digital Multimedia Broadcasting (TDMB) transmission system for multimedia broadcasting service and introduce a device called the Ensemble Remultiplexer which is designed to remultiplex the Ensemble Transport Interface (ETI) for T-DMB service. This letter describes the remultiplexing process of the Ensemble Remultiplexer.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.14 no.4
• /
• pp.29-37
• /
• 2014

Since multi-view video exists a number of camera color image and depth image, it has a huge of data. Thus, a new compression technique is indispensable for reducing this data. Recently, the effective compression encoding technique for multi-view video that used in layered depth image concepts is a remarkable. This method uses several view point of depth information and warping function, synthesizes multi-view color and depth image, becomes one data structure. In this paper we use actual distance for solving overlap in layered depth image that reduce required data for reconstructing in color-based transform. In experimental results, we confirmed high compression performance and good quality of reconstructed image.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.14 no.2
• /
• pp.43-51
• /
• 2014

Multi-view video including depth image is necessary to develop a new compression encoding technique for storage and transmission, because of a huge amount of data. Layered depth image is an efficient representation method of multi-view video data. This method makes a data structure that is synthesis of multi-view color and depth image. This efficient method to compress new contents is suggested to use layered depth image representation and to apply for video compression encoding by using 3D warping. This paper proposed enhanced compression method using layered depth image representation and H.264/AVC video coding technology. In experimental results, we confirmed high compression performance and good quality of reconstructed image.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2006.11a
• /
• pp.307-312
• /
• 2006

Protection to the multimedia contents is inevitable to ensure that only authorized users be able to access the protected contents for consumption. Since protection mechanisms need to be designed efficiently by exploiting the type of the contents, we propose a protection scheme for the video bitstream encoded by Scalable Video Coding (SVC) technique. Our scheme exploits the property of SVC in which a video is encoded into spatial, temporal, and quality scalability layers. By applying our proposed protection scheme to the appropriate scalability layers we can effectively control the SVC contents completely or partially. Each layer can be flexibly protected with different encryption keys or even with different encryption algorithms. The algorithms that are used to protect each layer are described by the standardized protection description tool, which is the MPEG-21 Intellectual Property Management and Protection (IPMP) Components. In this paper, we present the design of the proposed layered SVC protection scheme, its implementation and experimental results. The experiment result shows that the proposed layered SVC protection scheme is very effective and can easily be applied.

• Journal of information and communication convergence engineering
• /
• v.6 no.3
• /
• pp.266-269
• /
• 2008

Layered structure of the Korean terrestrial Digital Multimedia Broadcasting (TDMB) transmission system for multimedia broadcasting service is presented in this paper. We made a switching module which is called the Ensemble Remultiplexer. It is designed to remultiplex the Ensemble Transport Interface (ETI) for T-DMB service. This paper describes the remultiplexing process of the Ensemble Remultiplexer.

• ETRI Journal
• /
• v.30 no.1
• /
• pp.13-20
• /
• 2008

We evaluate the sink capacity of wireless code division multiple access (CDMA) sensor networks with layered architecture. We introduce a model of interference at a sink considering two kinds of interference: multiple access interference (MAI) and node interference (NI). We also investigate the activity of sensor nodes around the sink in relation to gathering data under a layered architecture. Based on the interference model and the activity of sensor nodes around the sink, we derive the failure probability of the transmission from a source node located one hop away from the sink using Gaussian approximation. Under the requirement of 1% failure probability of transmission, we determine the sink capacity, which is defined as the maximum number of concurrent sensor nodes located one hop away from the sink. We demonstrate that as the node activity of the MAI decreases, the variation of the sink capacity due to the node activity of the NI becomes more significant. The analysis results are verified through computer simulations.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.9 no.1
• /
• pp.53-59
• /
• 2009

Multi-view video is necessary to develop a new compression encoding technique for storage and transmission, because of a huge amount of data. Layered depth image is an efficient representation method of multi-view video data. This method makes a data structure that is synthesis of multi-view color and depth image. This paper proposed enhanced compression method by presentation of efficient layered depth image using real distance comparison, solution of overlap problem, and interpolation. In experimental results, confirmed high compression performance.

• Journal of Satellite, Information and Communications
• /
• v.5 no.2
• /
• pp.40-44
• /
• 2010

A layered coding scheme is one of the adaptive receiving techniques for unidirectional services such as multimedia broadcasting and multicasting services (MBMS), where we cannot utilize feedback information. The layered coding scheme can be used with hierarchical modulations by combining suitable code rates and modulation orders of each. In addition, it has been reported that hybrid and/or integrated satellite systems can effectively achieve transmit diversity gains by appropriate utilization of space time coding combined with turbo codes. This paper proposes a layered turbo coding schemes for hybrid and/or integrated satellite systems. We first introduce the system architecture and operational principle of the proposed scheme, and discuss the applicability.