• Korean Journal of Remote Sensing
• /
• v.37 no.1
• /
• pp.111-122
• /
• 2021

Building footprint extraction is an active topic in the domain of remote sensing, since buildings are a fundamental unit of urban areas. Deep convolutional neural networks successfully perform footprint extraction from optical satellite images. However, semantic segmentation produces coarse results in the output, such as blurred and rounded boundaries, which are caused by the use of convolutional layers with large receptive fields and pooling layers. The objective of this study is to generate visually enhanced building objects by directly extracting the vertices of individual buildings by combining instance segmentation and keypoint detection. The target keypoints in building extraction are defined as points of interest based on the local image gradient direction, that is, the vertices of a building polygon. The proposed framework follows a two-stage, top-down approach that is divided into object detection and keypoint estimation. Keypoints between instances are distinguished by merging the rough segmentation masks and the local features of regions of interest. A building polygon is created by grouping the predicted keypoints through a simple geometric method. Our model achieved an F1-score of 0.650 with an mIoU of 62.6 for building footprint extraction using the OpenCitesAI dataset. The results demonstrated that the proposed framework using keypoint estimation exhibited better segmentation performance when compared with Mask R-CNN in terms of both qualitative and quantitative results.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.6
• /
• pp.367-374
• /
• 2022

The acceleration of neural networks has become an important topic in the field of computer vision. An accelerator is absolutely necessary for accelerating the lightweight model. Most accelerator-supported operators focused on direct convolution operations. If the accelerator does not provide GEMM operation, it is mostly replaced by CPU operation. In this paper, we proposed an optimization technique for 2-stage tiling-based GEMM routines on VTA. We improved performance of the matrix multiplication routine by maximizing the reusability of the input matrix and optimizing the operation pipelining. In addition, we applied the proposed technique to the DarkNet framework to check the performance improvement of the matrix multiplication routine. The proposed GEMM method showed a performance improvement of more than 2.4 times compared to the non-optimized GEMM method. The inference performance of our DarkNet framework has also improved by at least 2.3 times.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.5
• /
• pp.1223-1237
• /
• 2024

Autonomous vehicles use onboard sensors to sense the surrounding environment. In complex autonomous driving scenarios, the detection and recognition capabilities are constrained, which may result in serious accidents. An efficient way to enhance the detection and recognition capabilities is establishing collaborations with the neighbor vehicles. However, the collaborations introduce additional challenges in terms of the data heterogeneity, communication cost, and data privacy. In this paper, a novel personalized federated learning framework is proposed for addressing the challenges and enabling efficient collaborations in autonomous driving environment. For obtaining a global model, vehicles perform local training and transmit logits to a central unit instead of the entire model, and thus the communication cost is minimized, and the data privacy is protected. Then, the inference similarity is derived for capturing the characteristics of data heterogeneity. The vehicles are divided into clusters based on the inference similarity and a weighted aggregation is performed within a cluster. Finally, the vehicles download the corresponding aggregated global model and train a personalized model which is personalized for the cluster that has similar data distribution, so that accuracy is not affected by heterogeneous data. Experimental results demonstrate significant advantages of our proposed method in improving the efficiency of collaborative perception and reducing communication cost.

• Journal of Internet Computing and Services
• /
• v.6 no.6
• /
• pp.139-148
• /
• 2005

The desired level for multimedia services in the mobile web environment, the next generation web environment, is expected to be of PC level quality. And great efforts have been made in the development of hadware technology, communication technology, various kinds of services and standardization to support these services, In the mobile web environment, multimedia contents adaptation services should be available through supporting various kinds of devices, network abilities and users' preferences. It means that due to the variety of both desired devices' hardware specifications, called destinations, and desired QoSes, the QoSes in the destinations are not fixed or defined. If a new user wants to stream multimedia contents in a server through a new kind of terminal device, it should be considered whether the existing transcoders are able to adapt the multimedia contents. However, the existing libraries for multimedia adaptation have heavy transcoder figures which include all adaptive functions in one library, The challenge of universal access is too complex to be solved with these all in one solutions. Therefore, in this paper we propose an application independent multimedia adaptation framework which meets the QoS of new and varied mobile devices. This framework is composed of a group of unit transcoders having only one transcoding function respectively, Instead of heavy transcoders. Also, It includes the transcoder manager supporting the dynamic connections of the unit transcoders in order to satisfy end to end QoS.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.6 s.38
• /
• pp.355-364
• /
• 2005

Ubiquitous environment can be supported by various service on networked appliance, sensors and devices. In home network and telematics, open service gateway is widely used for ubiquitous environment and Present environment for service installation, deployment and execution. Service gateway is a middle layer which is located between service and various devices in ubiquitous environment and offers a unique opportunity for pervasive computing as a potential framework for achieving interoperability between various sensors, home appliances. and networked devices. In ubiquitous environments, these services must support the mobility among service gateway because users and devices has a mobility characteristic. However the OSGi framework supports only a remote installation of a bundle, which is a unit that installs and deploys services. This paper develops a system that can manage bundles for supporting this dynamic bundle's mobility between service gateway. This system we are proposing implements a bundle form which can perform in an OSGi framework as well as manage the mobile services. As a result, mobility in a ubiquitous computing environment will be supported more efficiently.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.10
• /
• pp.1767-1772
• /
• 2006

Computer-generated integral imaging system is an auto-stereoscopic display system that users can see and feel the stereoscopic images when they see the pre-rendered elemental images through a lens array. The process of constructing elemental images using computer graphics is called image mapping. Viewpoint vector rendering (VVR) method is one of the image mapping algorithm specially designed for real-time graphics applications, which would not be affected by the size of the rendered objects or the number of elemental lenses used in the integral imaging system. This paper describes a new VVR framework which improved its rendering performance considerably. It also compares the previous VVR implementation with the new VVR work utilizing GPU and shows that newer implementation shows pretty big improvements over the old method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.4
• /
• pp.980-992
• /
• 2011

WSN gateway which runs transmission between WSN (Wireless Sensor Network) based on IEEE 802.15.4 and PN (Public Network) based on TCP/IP belongs to core technology of application based on two network. Because WSN Gateway receives various kinds of packet from many sensor nodes in an uncertain time as well as uses hardware's performance enough, it has high level of complexity about software and it is hard to be implemented. To solve these problems, this paper suggests both efficient event detection scheme for identify packet and implementation unit of protocol called 'Transaction'. The results of applying the proposed network framework, complexity of software reduces. And we provide software development environments of reflect various performance requirements.

• Journal of Advanced Navigation Technology
• /
• v.19 no.5
• /
• pp.411-416
• /
• 2015

The service size of an IoT environment is determined by the various types of sensors. A gateway for relaying sensor information from various sensors is a representative middleware system, and an infographics showing the information with a graphical presentation of data and information is a client system for representing real-time information efficiently, it is necessary a similar test bed with IoT environment to develop a real-time infographics displaying a large amount of information effectively. The testing tools used in developing the existing network systems are mostly made to be suitable for functional testing and performance testing of the driven unit. In this paper, we proposed a mean which is web-based simulation framework to create a variety of information required for real-time infographics development, and evaluate the function of the system proposed by the test function of the comparison with the previous network test tool.

• Journal of the Korean Society for Railway
• /
• v.12 no.6
• /
• pp.996-1010
• /
• 2009

This paper proposed the framework for the Korean transport accounts which is suitable to Korean situation and can be used for international comparison. The framework is composed of the costs, the revenues and the estimation methodology. This framework is applied to both the Korean road and rail transport, respectively. The result showed that the total cost compared to GDP for the road was higher than the Europe's by 3.23% and that for the rail was lower than the Europe's by 0.67%. Also, the result showed that, in terms of the unit cost, the passenger cost per person-kilometer of road transport was 4.8 times higher than that of rail transport and the freight cost per ton-kilometer of road transport was 2.4 times higher than that of rail transport.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.270-273
• /
• 2015

In shipbuilding and marine industry, engineering and design software solutions have upgraded from the original 2D schematic data based CAD system to a modern 3D drawing-based system. Due to the fact that the massive amount of data usage in real time and data volumes of various engineering models including graphic data have increased, several problems such as lack of server resources and improper handling of 3D drawings have been raised. Besides, increasing the number of session connections per server can cause deterioration of server performance. Recently, increasing the yard's sophisticated design capabilities highlighted the need to develop engineering and design system which would not only overcome the network performance issues, but would provide efficient collaborative design environment. This paper presents an overview of the framework for collaborative engineering design system based on the virtual application (Citrix XenApp 6.5)and acceleration hardware technology of 3D graphics (NVIDIA GRID K2 solution).