• Journal of Broadcast Engineering
• /
• v.21 no.2
• /
• pp.252-260
• /
• 2016

The performance of human detection system is affected by camera location and view angle. In 2D image acquired from such camera settings, humans are displayed in different sizes. Detecting all the humans with diverse sizes poses a difficulty in realizing a real-time system. However, if the size of a human in an image can be predicted, the processing time of human detection would be greatly reduced. In this paper, we propose a method that estimates human size by constructing an indoor scene in 3D space. Since the human has constant size everywhere in 3D space, it is possible to estimate accurate human size in 2D image by projecting 3D human into the image space. Experimental results validate that a human size can be predicted from the proposed method and that machine-learning based detection methods can yield the reduction of the processing time.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.264-266
• /
• 2022

In order to apply the RNN model to the radio fingerprint-based indoor path generation technology, the data set must be continuous and sequential. However, Wi-Fi radio fingerprint data is not suitable as RNN data because continuity is not guaranteed as characteristic information about a specific location at the time of collection. Therefore, continuity information of sequential positions should be given. For this purpose, clustering is possible through classification of each region based on signal data. At this time, the continuity information between the clusters does not contain information on whether actual movement is possible due to the limitation of radio signals. Therefore, correlation information on whether movement between adjacent clusters is possible is required. In this paper, a deep learning network, a recurrent neural network (RNN) model, is used to predict the path of a moving object, and it reduces errors that may occur when predicting the path of an object by generating continuous location information for path generation in an indoor environment. We propose a method of giving correlation between clustering for generating an improved moving path that can avoid erroneous path prediction that cannot move on the predicted path.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.1 no.1
• /
• pp.35-39
• /
• 2008

In this paper, we have developed a propagation loss prediction software with GUI (Graphic User Interface) functions, based on the geometrical ray optics model, which can predict radio parameters for the deployment of wireless indoor network. The program has two numerical modules consisted with electrical image and ray launching methods to implement UTD theory. The simulated results are compared with reported data measured in the foreign building environments for office and '一' type corridor, and measured and simulated results for the propagation loss agree with each other quite well. Simulation results for '一' type corridor and 'T' type corridor propagation environment are shown for reference.

• Journal of the Korean GEO-environmental Society
• /
• v.12 no.6
• /
• pp.35-42
• /
• 2011

In this paper, model experiments in the laboratory were carried out to predict the effluent concentrations of suspended solid in containment of dumping dredged soils and test results were compared with results estimated by the currently used design method. Model tests of simulating dumping the dredged soils with a pump dredger in field were performed with changing the influent concentration and the length of containment and effluent concentration of suspended solid with time were measured during tests. As results of comparing test results about effluent concentration with those estimated from the design method by US Army COE(1987), they were confirmed to be in relatively good agreements.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.3
• /
• pp.93-102
• /
• 2023

Data processing through the cloud causes many problems, such as latency and increased communication costs in the communication process. Therefore, many researchers study edge computing in the IoT, and autonomous driving is a representative application. In indoor self-driving, unlike outdoor, GPS and traffic information cannot be used, so the surrounding environment must be recognized using sensors. An efficient autonomous driving system is required because it is a mobile environment with resource constraints. This paper proposes a machine-learning method using neural networks for autonomous driving in an indoor environment. The neural network model predicts the most appropriate driving command for the current location based on the distance data measured by the LiDAR sensor. We designed six learning models to evaluate according to the number of input data of the proposed neural networks. In addition, we made an autonomous vehicle based on Raspberry Pi for driving and learning and an indoor driving track produced for collecting data and evaluation. Finally, we compared six neural network models in terms of accuracy, response time, and battery consumption, and the effect of the number of input data on performance was confirmed.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.6
• /
• pp.173-182
• /
• 2012

A recent advance in smart phones is increasing utilization of location information. Existing positioning system was using GPS location for positioning. However, the GPS cannot be used indoors, if GPS location has an incorrectly problem. In order to solve indoor positioning problems of indoor location-based positioning techniques have been investigated. There are a variety of techniques based on indoor positioning techniques like as RFID, UWB, WLAN, etc. But WLAN location positioning techniques take advantage the bond in real life. WLAN indoor positioning techniques have a two kind of method that is centroid and fingerprint method. Among them, the fingerprint technique is commonly used because of the high accuracy. In order to use fingerprinting techniques make a WLAN signal map building that is need to lot of resource. In this paper, we try to solve this problem in an Indoor environment for WLAN-based fingerprint of a virtual building technique, which is proposed. Proposed technique is classified Cell environment in existed Indoor environment, all of fingerprint points are shown virtual grid map in each Cell. Its method can make fingerprint grid map very quickly using estimate virtual signal value. Also built signal value can take different value depending of the real estimate value. To solve this problem using a calibration technique for the Splite-tree is proposed. Through calibration technique that improves the accuracy for short period of time. It also is improved overall accuracy using predicted value of around position in cell.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2012.01a
• /
• pp.227-228
• /
• 2012

실외에서의 위치추적은 GPS(Global Positioning System) 등의 다양한 방법이 활용가능하다. 하지만 실내에서는 사용이 어려워 비전, RFID 및 Zigbee 등을 활용한 다양한 연구가 진행되고 있다. 본 연구에서는 비교적 비용 효과적으로 구축이 가능한 수동형 RFID 태그를 기반 이동형 로봇의 위치 추적 알고리즘을 제안하도록 한다. 총 7 종의 태그에 대하여 각 태그가 가지고 있는 특성을 실험을 통하여 분석하고 분석한 결과에 따라 태그를 배치하여 효과적으로 로봇의 이동에 따른 위치 추적 및 이동방향 예측방법을 기술한다. 제안하는 방법을 실험실 환경에서 레고 마인드스톰을 활용하여 그 효용성을 나타내도록 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.111-112
• /
• 2023

학교, 대형 쇼핑몰, 공항 등과 같은 큰 실내 공간에서는 군중의 동선과 밀도를 파악하고 관리하는 것은 안전사고와 연관되어 있어 매우 중요하다. 와이파이 센싱은 기존에 존재하던 CCTV 카메라나 센서를 활용한 혼잡도 관리보다 효율적이고 정확한 방식으로 추정하는 데 도움이 되며, 설치 및 유지보수 측면에서도 효율적이다. 본 논문에서는 실내 환경에서 군중 수를 추정하기 위해 딥 러닝을 이용한 무선랜 신호 분석 기법을 제안한다. 송수신기가 같은 공간에 위치했던 기존 연구들과는 달리 본 논문에서는 송신기와 수신기가 서로 다른 공간에 배치된 환경에서도 무선랜 수신 신호를 통해 다른 공간의 군중 수를 정확히 예측할 수 있다는 것을 실험으로 검증하였다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.9 no.6
• /
• pp.1653-1658
• /
• 2008

In this paper, it is analyzed propagation distribution characteristics of radio wave, which is radiated on all sides from Access Point device for estimating scheme of wireless AP without GPS receiver environment. To tracking AP device is traced from wireless terminals and wireless terminal is traced from fixed AP devices, above all it is important to analysis the characteristics of receiving power in according to distance. Therefore in this paper, radio propagation characteristics of 2.4GHz wave is analyzed effect extent and quality in according to distance in doors and out doors, and utilized to location estimation.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.19 no.7
• /
• pp.733-740
• /
• 2008

In this paper, an indoor propagation model based on 3d ray tracing is presented for wireless communications. In case of indoor propagation models, various radio propagation paths such as wall-transmitted wave and scattered wave from ceilings, pillars, and furnitures arises and 3-D formulation is needed. To accommodate such scatterers, objects are modeled by triangulated surfaces and ray tubes using those surfaces are introduced and efficient calculation methods using the tubes are presented.