• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.661-663
• /
• 2014

Lighting that installed in large buildings detects a movement of passer using human-detecting sensor or occupancy sensor. It can turn on lighting automatically using sensor when there is any movement and turn off when there is no movement to reduce unnecessary power consumption. However, there is a problem of malfunction due to improper location of the sensor. Also the case of passage, even after passing through the passage, lighting is turned on for a long time. It does not reduce the power consumption efficiently. In this paper, we propose a method to control lighting by estimating the position of the passer. According to the result simulated in one passage, it is confirmed that the time of turning on the lighting is reduced about 7 minute compared to existing methods.

• Korean Journal of Remote Sensing
• /
• v.35 no.5_1
• /
• pp.727-736
• /
• 2019

In this paper, we present how to create a point cloud for a target area using multiple unmanned aerial vehicle images and to remove the gaps and overlapping points between datasets. For this purpose, first, IBA (Incremental Bundle Adjustment) technique was applied to correct the position and attitude of UAV platform. We generate a point cloud by using MDR (Multi-Dimensional Relaxation) matching technique. Next, we register point clouds based on observation vectors between stereo images by doing this we remove gaps between point clouds which are generated from different stereo pairs. Finally, we applied an occupancy grids based integration algorithm to remove duplicated points to create an integrated point cloud. The experiments were performed using UAV images, and our experiments show that it is possible to remove gaps and duplicate points between point clouds generated from different stereo pairs.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.899-904
• /
• 2022

As the world becomes an aging society due to a decrease in the birth rate and an increase in life expectancy, a system for health management of the elderly population is needed. Among them, various studies on occupancy and activity types are being conducted for smart home care services for indoor health management. In this paper, we propose a random forest model that classifies activity type as well as occupancy status through indoor temperature and humidity, CO2, fine dust values and UWB radar positioning for smart home care service. The experiment measures indoor environment and occupant positioning data at 2-second intervals using three sensors that measure indoor temperature and humidity, CO2, and fine dust and two UWB radars. The measured data is divided into 80% training set data and 20% test set data after correcting outliers and missing values, and the random forest model is applied to evaluate the list of important variables, accuracy, sensitivity, and specificity.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.9A
• /
• pp.822-829
• /
• 2005

In this paper, a processing time and trafnc capacity analysis algorithm for RFID system using LBT-Random Searching scheme is proposed. Service time, carrier sensing time, additional delay time required for contiguous frequency channel occupancy, and additional delay time required for the contiguous using the same frequency channel are considered and the processing delay and frequency channel capacity are analyzed for the steady state operation of the system. The simulation results showing maximum capacity of the system and explaining the accuracy of the algorithm are provided.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10a
• /
• pp.106-112
• /
• 1993

A new model for the construction of a sonar map in a specular environment has been developed ad implemented. In a real world where most of the object surfaces are specular ones, a sonar sensor suffers from a multipath effect which results in a wrong interpretation of an objects's location. To reduce this effect and hence to construct a reliable map of a robot's surroundings, a probabilistic approach based on Bayesian reasoning is adopted to both evaluation of object orientations and estimation of an occupancy probability of a cell by an object. The usefulness of this approach is illustrated with the results produced by our mobile robot equipped with ultrasonic sensors.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.11a
• /
• pp.33-35
• /
• 2018

기존의 사람간의 유사성 측정 시스템은 적외선 빔이나 열 감지 영상 장치를 통해 측정하였다. 하지만 이와 같은 방법으로 측정하면 2명 이상의 객체를 분류해내는 기술은 제공하지 않는다. 이에 본 논문은 고정된 카메라를 이용하여 각 사람의 피부색과 옷차림 등의 RGB 정보를 이용한 사람 유사성 측정 기법을 제안한다. RGB카메라 영상을 통하여 객체의 RGB 히스토그램을 얻은 후 각 객체에 대해 Bhattacharyya metric, Cosine similarity, Jensen difference, Euclidean distance로 histogram similarity를 계산하여 객체 추적 및 유사성 측정을 통해 객체를 분류한다. 제안된 시스템은 C/C++를 기반으로 구현하여, 유사성 측정 성능을 평가하였다.

• Journal of Auto-vehicle Safety Association
• /
• v.13 no.4
• /
• pp.14-19
• /
• 2021

This paper presents LiDAR static obstacle map based vehicle dynamic state estimation algorithm for urban autonomous driving. In an autonomous driving, state estimation of host vehicle is important for accurate prediction of ego motion and perceived object. Therefore, in a situation in which noise exists in the control input of the vehicle, state estimation using sensor such as LiDAR and vision is required. However, it is difficult to obtain a measurement for the vehicle state because the recognition sensor of autonomous vehicle perceives including a dynamic object. The proposed algorithm consists of two parts. First, a Bayesian rule-based static obstacle map is constructed using continuous LiDAR point cloud input. Second, vehicle odometry during the time interval is calculated by matching the static obstacle map using Normal Distribution Transformation (NDT) method. And the velocity and yaw rate of vehicle are estimated based on the Extended Kalman Filter (EKF) using vehicle odometry as measurement. The proposed algorithm is implemented in the Linux Robot Operating System (ROS) environment, and is verified with data obtained from actual driving on urban roads. The test results show a more robust and accurate dynamic state estimation result when there is a bias in the chassis IMU sensor.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.7
• /
• pp.149-158
• /
• 2024

This study aims to design and develop AirDeep-Room, a multi-sensor system for monitoring air quality in various indoor environments. The system measures CO2, TVOC, particulate matter, temperature, and humidity in real-time. By integrating multiple sensors, AirDeep-Room allows convenient correlation analysis using low data format in real-time. The sensor system was installed in a server room and a classroom. Data analysis showed a negative correlation of -0.24 between temperature and humidity in the server room, and a positive correlation of 0.43 in the classroom, indicating different interactions. A high correlation (r=0.69) between the number of students and concentrations of CO2 and TVOC demonstrated the significant impact of occupancy on air quality. AirDeep-Room effectively manages air quality across various environments and provides essential data for improving air quality in densely populated areas.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.8
• /
• pp.5534-5540
• /
• 2015

This In the railway signaling system, applications of axle counter in addition to track circuit goes on increasing for detecting train position. Consequently, this paper compares sensor methods of axle counter with between geo-magnetism method and proximity sensor method. And it presents differences and results, to improve reliabilities of train detection and axle counting. Also, this article presents an applied result which is based on field experience, with regard to installation, considering attachment condition of sensor part for accurate axle counting. This study acquires expandability that is able to perform not only axle counting function but also various other functions (direction detection of train, speed detection of train, and so on). It was a result of a change of design in order to judge phase difference of sensors, to improve reliability of axle counting. Furthermore, it does not subordinate to characteristics (type, weight of train). And it is confirmed that the omission of axle counting was not occurred in 350km/h. This was the result of Lab test after the construction of transfer equipment of trial axle and Test Bed for axle counting. Both of them are self-productions. Through this, it prepares foundation which is able to apply not only to train detection but also to speed of passing trains, formation number of trains, detector locking condition - when the train passes the section of switch point, and level crossing devices. Furthermore, it would be judged to contribute safety train operation if proximity sensor method applies to the whole railway signaling system from now on.

• Journal of Korea Spatial Information System Society
• /
• v.9 no.1
• /
• pp.79-90
• /
• 2007

In this paper we proposed and implemented an incident detection model which combines fuzzy algorithm and traffic pattern in order to enhance the efficiency of incident detection for the highways with lamps. Most of the existing algorithms dealt with highways without lamps and can not be used for detecting incidents in the highways with lamps. The data used for model building are traffic volume, occupancy, and speed data. They have been collected by a loop sensor at 5 minutes interval at a point in the Internal Circular Highway of Seoul for the period of 3 months. In this model, the three parameters collected by sensor were fuzzified and combined with the daily traffic pattern of the link. The test of efficiency of the propsed model was performed by comparing the result of proposed model with traditional APID algorithm and fuzzy algorithm without the pattern data respectively. The result showed significant amount of improvement in reducing the false incident detection rate by 18%.