• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.04a
• /
• pp.86-87
• /
• 2016

본 논문에서는 optical flow sensor를 이용하여 실내의 바닥 영상인식를 통한 영상처리기법을 이용해 움직임 없는 hovering을 할 수 있는 방법을 제안한다. 또한 optical flow와 BLE finger printing 기법을 혼합해 위치 인식 정밀도를 높일 수 있다. 본 고에서는 optical flow sensor와 BLE finger printing의 두 기술을 혼합하면 드론 스스로 실내에서 정밀도 높은 위치인식이 가능 하며 실외에서만 사용할 수 있는 GPS 비행모드를 대신 할 수 있어 실내에서 자동 경로 비행이 가능하게 하고 위치 안내, 실내 방송촬영, 이동식 CCTV등 질 높은 서비스를 제공하고자 한다.

• The Journal of Engineering Research
• /
• v.7 no.1
• /
• pp.61-70
• /
• 2005

Conventional geological survey utilizes the manual compass for mass amount of measurements of the geologic structure. Portable multifunction digital compass system was required by more detailed geological survey, due to increasing construction for rock slopes and runnels. In this paper, the system was implemented by using Intel PXA 255 embedded board as a system controller, and was composed of tilting sensor, digital azimuth sensor, and Global Positioning System (GPS) module. After the measured location, strike, and the angle of dip with our implemented system were transmitted to Personal Digital Assistant (PDA) or notebook, these data could be used for geologic structure analysis. It is expected that the availability of cheap and improved digital compass will reduce the coast and time of geological survey extensively.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.10a
• /
• pp.659-661
• /
• 2011

In this paper, we propose a study of scheme to detect mobile object. In special zone needed detection, sensor network based system development can provide safety of pedestrian. Instead current CCTV, intelligent sensor network and service can provide reliability to guarantee safe zone. Base on pedestrian characteristic, if unusual situation is detected and it is included in previous agreed scenario, safety service can be provided.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.12
• /
• pp.5873-5877
• /
• 2011

In this paper, we propose a study of analysis to the mobility of object such like pedestrian in safety management zone. If unusual situation is detected in safety management zone, it's designed that previous agreed mission will be processed. By human resource, safety management zone cannot be detected continuously so that through the induction of such detection system the reliability of area can be obtained. Hence, in this paper we propose the reaction scheme to detect special situation by object detection. By using sensor based processing system proposed by this paper, the detection of mobility and unusual situation can be implemented.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.430-433
• /
• 2018

This paper proposes the Kalman filter (KF) with optical flow method to estimate the position and the velocity of unmanned aerial vehicles (UAVs) in the absence of global positioning system (GPS). A downward-looking camera, a gyroscope and an ultrasonic sensor are fused to compensate the measurement from optical-flow method. To overcome the problem of dealing with noise in onboard sensors, the KF is incorporated to efficiently predict the velocity and estimate the position. Basic mechanisms of optical flow and the KF are introduced and experiments are conducted to show how the techniques involved improve the estimations.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.11a
• /
• pp.21-22
• /
• 2009

유비쿼터스 사회(Ubiquitous Society)로의 진입에 발맞추어 USN(Ubiquitous Sensor Network) 기반의 인간 중심적 편의 시스템에 관한 연구가 활발하게 진행되고 있다. 그 중 대형 시장을 갖는 차량 편의시설에 관한 연구는 지능형 차량 시스템(Intelligent Car System)을 중심으로 활발히 이루어지고 있다. 지능형 차량 시스템의 주요 연구는 자동 항법 장치, 사고 예방 장치, 자가 진단 시스템 등 탑승자의 편의성과 안전성을 중심으로 진행되었다. 그러나 탑승자의 사고 발생 시 응급 상황 처리를 위한 지원 시스템은 미미하다. 탑승자 부상으로 사고 신고를 하지 못할 경우, 사고지점 확인, 탑승자의 위급(현재) 상황, 부상 정보와 같은 정보를 얻을 수 없어 응급 상황 대처에 신속하지 못할 수 있다. 따라서 본 논문은 다양한 센서를 이용하여 차량의 정보를 수집하고, 사고 판단 시 차량 위치 정보, 탑승자 상황 정보를 응급 기관에 전달할 수 있는 차량용 스마트 안전장치를 설계 및 구현하였다. 테스트를 위해 Intel PXA255 MCU와 AM-3AXIS(3축 가속 센서), MDSM-1000A(지자기 센서), RX-M800S CDMA, GPS520, Alpha cam, Flex Sensor로 시스템을 제작하였으며 모의 도로 모형에서 테스트 하였다.

• International journal of advanced smart convergence
• /
• v.13 no.1
• /
• pp.37-47
• /
• 2024

This study presents the results of designing a system that determines the location of a person in an indoor environment based on a single IMU sensor attached to the tip of a person's shoe in an area where GPS signals are inaccessible. By adjusting for human footfall, it is possible to accurately determine human location and trajectory by correcting errors originating from the Inertial Measurement Unit (IMU) combined with advanced machine learning algorithms. Although there are various techniques to identify stepping, our study successfully recognized stepping with 98.7% accuracy using an artificial intelligence model known as Long Short-Term Memory (LSTM). Drawing upon the enhancements in our methodology, this article demonstrates a novel technique for generating a 200-meter trajectory, achieving a level of precision marked by a 2.1% error margin. Indoor pedestrian navigation systems, relying on inertial measurement units attached to the feet, have shown encouraging outcomes.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.28 no.1
• /
• pp.39-46
• /
• 2010

Sounding data is the essential source for the safety of ships navigation system, and fundamental to the reasonable usage and maintenance of the ocean as well. As IT tech, positioning equipment such as GPS and INS, echo sounder are developed, recently, the precise submarine topography database bas been built by Multi-Beam Echo Sounder. However, MBES data includes some inevitable error caused by several factor, and some data have errors where the terrain is wobble. The error, which causes the $moir\acute{e}$ pattern error is the main factor hindering the accuracy of MBES data results, and therefore it is necessary to figure out the main cause of the error for the improvement of the accuracy by removing error data. On this research, the main cause of the error data is studied by analyzing motion sensor value of data including the $moir\acute{e}$ pattern error. Thus, as the result of examination, it turns out that the $moir\acute{e}$ pattern error is related to the standard deviation of Roll, and error data values are results of the non-correspondence between Swath data and Roll values caused by the drastic change of Roll values. Accordingly, the error data is removed by comparing between the gradient of Swath data and Roll values. Finally, as the result of removing error data, it is expected to be able to estimate the quality of MBES using the standard deviation of Motion sensor's Roll value, and calculate the additive error factor, which minimize non-corresponding data, and also this research must be contributed to improve the accuracy of sounding for small vessels with lots of motion in the bad circumstance for navigation.

• Journal of Korean Society for Geospatial Information Science
• /
• v.15 no.4
• /
• pp.103-109
• /
• 2007

Ortho images and Digital Elevation Model (DEM) have been applied in various fields. It is necessary to acquire Ground Control Points (GCPs) for processing high resolution satellite images. However surveying GCPs require many time and expense. This study was performed to investigate whether GCPs automatically extracted from ortho images and DTED Level 2 can be applied to sensor modeling for high resolution satellite images. We analyzed the performance of the sensor model established by GCPs extracted automatically. We acquired GCPs by matching satellite image against ortho images. We included the height acquired from DTED Level 2 data in these GCPs. The spatial resolution of the DTED Level 2 data is about 30m. Absolution accuracy of this data is below 18m above MSL. The spatial resolution of ortho image is 1m. We established sensor model from IKONOS images using GCPs extracted automatically and generated DEMs from the images. The accuracy of sensor modeling is about $4{\sim}5$ pixel. We also established sensor models using GCPs acquired based on GPS surveying and generated DEMs. Two DEMs were similar. The RMSE of height from the DEM by automatic GCPs and DTED Level 2 is about 9 m. So we think that GCPs by DTED Level 2 and ortho image can use for IKONOS sensor modeling.

• KIISE Transactions on Computing Practices
• /
• v.21 no.1
• /
• pp.64-69
• /
• 2015

Place awareness is an essential for location-based services that are widely provided to smartphone users. However, traditional GPS-based methods are only valid outdoors where the GPS signal is strong and also require symbolic place information of the physical location. In this paper, environmental sounds and images are used to recognize important aspects of each place. The proposed method extracts feature vectors from visual, auditory and location data recorded by a smartphone with built-in camera, microphone and GPS sensors modules. The heterogeneous feature vectors were then learned by an ensemble learning method that learns each group of feature vectors for each classifier respectively and votes to produce the highest weighted result. The proposed method is evaluated for place recognition using a data group of 3000 samples in six places and the experimental results show a remarkably improved recognition accuracy when using all kinds of sensory data comparing to results using data from a single sensor or audio-visual integrated data only.