• Agricultural and Biosystems Engineering
• /
• v.6 no.2
• /
• pp.47-53
• /
• 2005

AMachine vision is a promising tool for the autonomous guidance of farm machinery. Conventional CCD camera for the machine vision needs a desktop PC to install a frame grabber, however, a web camera is ready to use when plugged in the USB port. A web camera with a notebook PC can replace existing camera system. Autonomous steering control system of this research was intended to be used for combine harvester. If the web camera can recognize cut/uncut edge of crop, which will be the reference for steering control, then the position of the machine can be determined in terms of lateral offset and heading angle. In this research, a white line was used as a cut/uncut edge of crop for steering control. Image processing algorithm including capturing image in the web camera was developed to determine the desired travel path. An experimental vehicle was constructed to evaluate the system performance. Since the vehicle adopted differential drive steering mechanism, it is steered by the difference of rotation speed between left and right wheels. According to the position of vehicle, the steering algorithm was developed as well. Evaluation tests showed that the experimental vehicle could travel within an RMS error of 0.8cm along the desired path at the ground speed of $9\sim41cm/s$. Even when the vehicle started with initial offsets or tilted heading angle, it could move quickly to track the desired path after traveling $1.52\sim3.5m$. For turning section, i.e., the curved path with curvature of 3 m, the vehicle completed its turning securely.

• Journal of IKEEE
• /
• v.24 no.1
• /
• pp.225-231
• /
• 2020

In this paper, we propose a method to accelerate BWN based on FPGA with limited resources for embedded system. Because of the limited number of logic elements available, a single computing unit capable of handling Conv-layer, FC-layer of various sizes must be designed and reused. Also, if the input feature map can not be parallel processed at one time, the output must be calculated by reading the inputs several times. Since the number of available BRAM modules is limited, the number of data bits in the BWN accelerator must be minimized. The image classification processing time of the BWN accelerator is superior when compared with a embedded CPU and is faster than a desktop PC and 50% slower than a GPU system. Since the BWN accelerator uses a slow clock of 50MHz, it can be seen that the BWN accelerator is advantageous in performance versus power.

• The KIPS Transactions:PartA
• /
• v.15A no.2
• /
• pp.101-110
• /
• 2008

Ubiquitous computing has extended the computer system into the whole physical space and has ushered the emergence of more dynamic distributed systems. This environment require unique QoS parameters for various devices, resources and user requirements. In this paper, we propose a new hybrid QoS management model which defines a static-dynamic QoS parameter that is more appropriate to the ubiquitous computing environment. This model consists of the QoS Control Management Module(QoS CMM) in the client side and the Resource QoS Management Module (RQoS MM) in the server side. The RQoS MM deals with the static QoS parameters and the whole QoS control of the distributed control(QoS CMM) in order to minimize server load in cases of multiple communication. Finally, we present the experimental result of our location based application using a graphical user interface that shows the multimedia service execution of selected client device types such as desktop PC, notebook and PDA.

• KIISE Transactions on Computing Practices
• /
• v.21 no.8
• /
• pp.531-536
• /
• 2015

The speech recognition is an active research area in the human computer interface (HCI). The objective of this study is to control digital devices with voices. In addition, the mouse is used as a computer peripheral tool which is widely used and provided in graphical user interface (GUI) computing environments. In this paper, we propose a method of controlling the mouse with the real-time speech recognition function of a smartphone. The processing steps include extracting the core voice signal after receiving a proper length voice input with real time, to perform the quantization by using the learned code book after feature extracting with mel frequency cepstral coefficient (MFCC), and to finally recognize the corresponding vowel using hidden markov model (HMM). In addition a virtual mouse is operated by mapping each vowel to the mouse command. Finally, we show the various mouse operations on the desktop PC display with the implemented smartphone application.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.3
• /
• pp.391-397
• /
• 2020

Realistic content such as virtual reality, augmented reality, and mixed reality is emerging as an innovative technology in the education field in that it allows people to safely and efficiently experience dangerous, expensive or impossible situations, such as disaster training or space travel. Recently, as government agencies have supported a lot for producing virtual augmented reality contents about education, various educational contents using virtual augmented reality technology have been developed through the Edutech industry. Many virtual augmented reality-based educational contents are being developed, but mixed reality-based educational contents are very limited which could be more effective for education. This study examines the basic method of producing mixed reality educational contents using Hololens and, on the basis of this, it proposes the method for producing scientific experiment contents. Hololens made it possible to share information in real time without a regular desktop PC, and it is effective for teachers to manage and evaluate students in real time.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2007.04a
• /
• pp.283-287
• /
• 2007

Pine Wilt Disease (Bursaphelenchus Xylophilus) has been attacked since 1988, then it becomes very serious problem of the all over the country. Government has been invested a lot of money to prevent but it is hard to survey the damaged area and ineffectively control the process of prevention. Therefore, this study is focused on development of Pine Wilt Disease (Bursaphelenchus Xylophilus) Prevention System using GIS and GPS through constructiong database of digital map, satellite imagery and attribute data and development component for desktop PC, internet and mobile system to realtime data transmission between project manager and field worker. Especially, we developed the mobile system that can transmit field conditions in realtime using GPS, GIS and CCD camera, the telecommunication control server that transmit received field condition data to web connecting module and system manager, the web system for end user to notify prevention details, the control system lot manager to recognize filed conditions and to control field workers and the wireless telecommunication module to connect in realtime between field and control center.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.3
• /
• pp.1058-1070
• /
• 2014

There are two major ways to implement depth estimation, multiple image depth estimation and single image depth estimation, respectively. The former has a high hardware cost because it uses multiple cameras but it has a simple software algorithm. Conversely, the latter has a low hardware cost but the software algorithm is complex. One of the recent trends in this field is to make a system compact, or even portable, and to simplify the optical elements to be attached to the conventional camera. In this paper, we present an implementation of depth estimation with a single image using a graphics processing unit (GPU) in a desktop PC, and achieve real-time application via our evolutional algorithm and parallel processing technique, employing a compute shader. The methods greatly accelerate the compute-intensive implementation of depth estimation with a single view image from 0.003 frames per second (fps) (implemented in MATLAB) to 53 fps, which is almost twice the real-time standard of 30 fps. In the previous literature, to the best of our knowledge, no paper discusses the optimization of depth estimation using a single image, and the frame rate of our final result is better than that of previous studies using multiple images, whose frame rate is about 20fps.

• ETRI Journal
• /
• v.37 no.2
• /
• pp.348-358
• /
• 2015

Mobile devices have been widespread and become very popular with connectivity to the Internet, and a lot of desktop PC applications are now aggressively ported to them. Unfortunately, mobile devices are often vulnerable to malicious attacks due to their common usage and connectivity to the Internet. Therefore, the demands on the development of mobile security systems increase in accordance with advances in mobile computing. However, it is very hard to run a security program on a mobile device all of the time due the device's limited computational power and battery life. To overcome these problems, we propose a novel mobile security scheme that migrates heavy computations on mobile devices to cloud servers. An efficient data transmission scheme for reducing data traffic between devices and servers over networks is introduced. We have evaluated the proposed scheme with a mobile device in a cloud environment, whereby it achieved a maximum speedup of 13.4 compared to a traditional algorithm.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.2
• /
• pp.111-117
• /
• 2012

With the rapid growth of smart phone technologies, mobile user's demands for using services provided by existing web or portal cites are highly increased. These services, however, are designed for the environment of desktop PCs or laptops in general, so it requires lots of costs for corrections and has difficulties for system protection to use in current mobile devices. In this paper, we design and implement a middleware for android-based smart phone apps to cooperate with a portal system with minimum corrections and function configuration. Our middleware system is working as an interface between an existing portal system and mobile devices to provide harmonious usage and safe system protection.

• Journal of Korea Multimedia Society
• /
• v.19 no.12
• /
• pp.2014-2023
• /
• 2016

Web presence is one of the key issues for extensive deployment of Internet-of-Things (IoT). An obstacle to overcome for Web presence is relatively low computing power of IoT devices. In this paper, we present implementation of an IoT platform based on Constrained Application Protocol (CoAP) which is a web transfer protocol proposed by Internet Engineering Task Force (IETF) for the low performance IoT devices such as Wireless Sensor Network (WSN) nodes and micro-controllers. To qualify the performance of CoAP-based IoT system for such an application as smart grid, we designed a test platform consisting of Raspberry Pi2, Kmote WSN node and a desktop PC. Using open source softwares, CoAP was implemented on top of the platform. Leveraging the GET command defined at CoAP specification, performance of the system was measured in terms of round-trip time (RTT) from web application to the Kmote sensor node. To investigate abnormal cases among the test results, hop-by-hop delays were measured to analyze resulting data. The average response time of CoAP-based communication except the abnormal data was reduced by 23% smaller than the previous research result.