• Journal of Advanced Navigation Technology
• /
• v.21 no.1
• /
• pp.119-125
• /
• 2017

In this paper, we propose a method that merges and splits players in the MeanShift tracking framework. The MeanShift tracking moves the center of tracking window to the maximum probability location given the target probability distribution. This tracking method has been widely used for real-time tracking problems because of its fast processing speed. However, it hardly handles occlusions in multiple object tracking systems. Occlusions can be usually solved by applying data association methods. In this paper, we propose a method that can be applied before data association methods. The proposed method automatically merges and splits the overlapped players by adjusting the each player's tracking map. We have compared the tracking performance of the MeanSfhit tracking algorithm and the proposed method.

• Journal of Korean Society for Geospatial Information Science
• /
• v.4 no.1 s.6
• /
• pp.103-114
• /
• 1996

A vehicle Control System that is a system combined by a Car Navigation System, a Geograhical Information System, and a Communication Network usually permit a central control room to detect vehicle's locations dynamically and manage these informations synthetically. Therefore, a vehicle control system can be used to control the rapid movement of patrol cars, freight transportation, and so on. In this paper, we designed and implemented a data manager for an application system, such as a vehicle control system, that usually manages road data, vehicle data, vehicle's location data, etc. The data manager that is implemented in this paper consists of system management module, road data management module, vehicle data management module, GPS(Global Positioning System) data management module, and additional data management module. Especially, we use the SHORE(Scalable Heterogeneous Object REpository) system as a storage system of the data manager.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39B no.9
• /
• pp.614-619
• /
• 2014

In WSN (Wireless Sensor Networks) based surveillance system, it needs to know the occurrence of events or objects and their locations, because the data have no meaning without location information. Using traditional 2D localization mechanisms provide good accuracy where altitude is fixed. But the mapping the position estimated by 2D localization to the real world can cause an error. Even though 3D localization mechanisms provide better accuracy than 2D localization, they need four reference nodes at least and high processing overhead. In our surveillance system, it is needed to estimate the height of the detected object in order to determine if the object is human. In this paper, we propose a height estimation mechanism which does not require many reference nodes and high complexity. Finally, we verify the performance of our proposed mechanism through various experiments.

• Journal of KIISE
• /
• v.42 no.1
• /
• pp.138-143
• /
• 2015

In this paper we develop a novel human action recognition system based on communication between an ear-mounted Bluetooth camera and an action recognition server to aid scene recognition for the blind. First, if the blind capture an image of a specific location using the ear-mounted camera, the captured image is transmitted to the recognition server using a smartphone that is synchronized with the camera. The recognition server sequentially performs human detection, object detection and action recognition by analyzing human poses. The recognized action information is retransmitted to the smartphone and the user can hear the action information through the text-to-speech (TTS). Experimental results using the proposed system showed a 60.7% action recognition performance on the test data captured in indoor and outdoor environments.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.1
• /
• pp.75-80
• /
• 2021

Positioning technology is performing important functions in augmented reality, smart factory, and autonomous driving. Among the positioning techniques, the positioning method using beacons has been considered a challenging task due to the deviation of the RSSI value. In this study, the position of a moving object is predicted by training a neural network that takes the RSSI value of the receiver as an input and the distance as the target value. To do this, the measured distance versus RSSI was collected. A neural network was introduced to create synthetic data from the collected actual data. Based on this neural network, the RSSI value versus distance was predicted. The real value of RSSI was obtained as a neural network for generating synthetic data, and based on this value, the coordinates of the object were estimated by learning a neural network that tracks the location of a terminal in a virtual environment.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.11
• /
• pp.5459-5473
• /
• 2017

Recently, a tracking algorithm called the spatial-temporal context model has been proposed to locate a target by using the contextual information around the target. This model has achieved excellent results when the target undergoes slight occlusion and appearance changes. However, the target location in the current frame is based on the location in the previous frame, which will lead to failure in the presence of fast motion because of the lack of a prediction mechanism. In addition, the spatial context model is updated frame by frame, which will undoubtedly result in drift once the target is occluded continuously. This paper proposes two improvements to solve the above two problems: First, four possible positions of the target in the current frame are predicted based on the displacement between the previous two frames, and then, we calculate four confidence maps at these four positions; the target position is located at the position that corresponds to the maximum value. Second, we propose a target reliability criterion and design an adaptive threshold to regulate the updating speed of the model. Specifically, we stop updating the model when the reliability is lower than the threshold. Experimental results show that the proposed algorithm achieves better tracking results than traditional STC and other algorithms.

• Proceedings of the KSME Conference
• /
• 2004.11a
• /
• pp.1116-1121
• /
• 2004

In this study, the effect of central fuel injection on a coaxial laminar $CH_{4}/air$ flame was experimented at the defined premixing condition(${\Phi}=1.90$, ${\sigma}=50/75/100%$, x/D=10). The partial premixing parameter are the equivalence ratio that total fuel is fixed at 200cc/min, the fuel split degree which means the percentage of fuel entering the outer tube to the total amount, and the mixing distance indicating the nonreactant mixture's homogeneity between inner tube top and burner exit. The object is to investigate the flame structure and chemiluminescence characteristics of laminar partial premixed flame as changing mixing parameters. The radical signal was acquired from ICCD camera and PMT. Each intensity was compared with Abel inverted value for measuring the effect of background light on the peak signal location and the intensity at central preheat zone. The results show that the peak location of each radical was broaden as the fuel split degree increasing because the mixing quality was enhanced. and $OH^{\ast}$ is a good indicator for flame front between reaction and preheat zone. At last $CH_{2}^{\ast}$ has the same tendency with $CH^{\ast}$ but a thinner reaction zone than $CH^{\ast}$ due to a rapid decay on the burned gas side.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39C no.5
• /
• pp.407-412
• /
• 2014

Concerns and demands for the Location Based Services (LBS) using Global Positioning System (GPS) and Wi-Fi are largely increased in the world in the present. In some experimental results, it was noted that many errors are frequently occurred when the distances between an anchor node and a mobile node acre measured in indoor localization environment of Wireless Personal Area Network (WPAN). In this paper, localization compensation algorithm based on maximum measurement value ($LCA_{MMV}$) for moving objects in WPAN is proposed, and the performance of the algorithm is analyzed by experiments on three scenarios for movement of mobile nodes. From the experiments, it was confirmed that the average localization accuracy of suggested algorithm was more increased than Symmetric Double-Sided Two-Way Ranging (SDS-TWR) and triangulation as average 40.9cm, 77.6cm and 6.3cm, respectively on scenario 1-3.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.5
• /
• pp.971-978
• /
• 2008

This paper designs a service-oriented wireless sensor network ontology model which can be used as a knowledge base in future ubiquitous computing. In contrast to legacy approaches, this paper defines the new service classes (ServiceProperty, LocationProperty, and PhysicalProperty), as well as their properties and constraints that enable the service-oriented service based on service items. The service item merging between the proposed model and the legacy ontology was processed using the "equivalentClass" object property of OWL. The Protege 3.3.1 and RACER 1.9.0 inference tools were used for the validation and consistency check of the proposed ontology model, respectively, and the results of service query was applied to the newly defined property in SPARQL language without reference to the properties of legacy ontology.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.9 no.2
• /
• pp.195-202
• /
• 2014

The Global Positioning System (GPS), which has various military and commercial applications, is designed to estimate the location of the specific user or object. In order to accurately estimate the location, GPS requires at least four satellite signals. The GPS receiver operates on extremely low signal-to-noise ratio (SNR) environment and it may suffer from various interference signals with the extremely high power. In this paper, we introduce a blind adaptive receiver based on the modified despreader, which suppress interference signals and detect GPS signals of interest without requiring explicit angle-of-arrival (AOA) information. We, also, provide the mathematical analysis for the signal-to-interference and noise ratio (SINR) of the modified despeader beamformer output. A representative computer simulation example is presented to illustrate the interference suppression performance of the considered GPS receiver and mathematical analysis of the SINR.