• 제어로봇시스템학회논문지
• /
• 제21권2호
• /
• pp.121-129
• /
• 2015

This paper presents a multiple vehicle recognition algorithm based on radar and vision sensor fusion for lane change assistance. To determine whether the lane change is possible, it is necessary to recognize not only a primary vehicle which is located in-lane, but also other adjacent vehicles in the left and/or right lanes. With the given sensor configuration, two challenging problems are considered. One is that the guardrail detected by the front radar might be recognized as a left or right vehicle due to its genetic characteristics. This problem can be solved by a guardrail recognition algorithm based on motion and shape attributes. The other problem is that the recognition of rear vehicles in the left or right lanes might be wrong, especially on curved roads due to the low accuracy of the lateral position measured by rear radars, as well as due to a lack of knowledge of road curvature in the backward direction. In order to solve this problem, it is proposed that the road curvature measured by the front vision sensor is used to derive the road curvature toward the rear direction. Finally, the proposed algorithm for multiple vehicle recognition is validated via field test data on real roads.

• 대한기계학회논문집A
• /
• 제39권5호
• /
• pp.517-526
• /
• 2015

본 논문은 쿼드로터 자세제어의 신뢰성 향상을 목적으로 다종 센서 구성 및 다종 센서 데이터 융합 알고리즘 적용을 연구한 결과이다. 먼저, 쿼드로터에 대한 동역학적 모델링에 관한 수식을 도출하였으며, 획득된 수식을 기초로 쿼드로터에 대한 수학적 모델링을 진행하였고 이를 기반으로 신뢰성이 향상된 다종 센서 데이터를 입력으로 하는 컴퓨터 시뮬레이션을 수행하였다. 쿼드로터 자세제어를 위해 다종 센서 데이터의 신뢰성 향상이 필요했으며 이를 위해 다종 센서 데이터 입력에 대한 칼만 필터링를 진행하였고, 이후 쿼드로터의 수학적 모델링에 적용하여 오차를 보상토록 하였다. 관련 컴퓨터 시뮬레이션 결과를 실제 쿼드로터 시스템에 적용하기 위하여 쿼드로터를 짐벌에 장착한 실제 시스템을 구성하였고 이후 쿼드로터를 호버링 상태에서 사용자가 요구하는 각도 변화에 따른 실험을 수행하였다. 실제 실험을 통한 쿼드로터 자세제어 데이터를 산출하였으며, 이를 바탕으로 추가적인 컴퓨터 시뮬레이션을 통한 설계한 다종 센서 및 쿼드로터 자세 제어 시스템의 성능 검증을 진행하였다.

• 대한금속재료학회지
• /
• 제56권11호
• /
• pp.835-843
• /
• 2018

In this work, we report a delta rosette strain sensor based on highly stretchable silver nanowire (AgNW) percolation piezoresistors. The proposed rosette strain sensors were easily prepared by a facile two-step fabrication route. First, three identical AgNW piezoresistive electrodes were patterned in a simple and precise manner on a donor film using a solution-processed drop-coating of the AgNWs in conjunction with a tape-type shadow mask. The patterned AgNW electrodes were then entirely transferred to an elastomeric substrate while embedding them in the polymer matrix. The fabricated stretchable AgNW piezoresistors could be operated at up to 20% strain without electrical or mechanical failure, showing a maximum gauge factor as high as 5.3, low hysteresis, and high linearity ($r^2{\approx}0.996$). Moreover, the sensor responses were also found to be highly stable and reversible even under repeated strain loading/unloading for up to 1000 cycles at a maximum tensile strain of 20%, mainly due to the mechanical stability of the AgNW/elastomer composites. In addition, both the magnitude and direction of the principal strain could be precisely characterized by configuring three identical AgNW piezoresistors in a delta rosette form, representing the potential for employing the devices as a multidimensional strain sensor in various practical applications.

• Smart Structures and Systems
• /
• 제22권5호
• /
• pp.631-641
• /
• 2018

This paper outlines a computational procedure for the effective merging of diverse sensor measurements, displacement and acceleration signals in particular, in order to successfully monitor and simulate the current health condition of civil structures under dynamic loadings. In particular, it investigates a Kalman Filter implementation for the Heterogeneous Data Fusion of displacement and acceleration response signals of a structural system toward dynamic identification purposes. The procedure is perspectively aimed at enhancing extensive remote displacement measurements (commonly affected by high noise), by possibly integrating them with a few standard acceleration measurements (considered instead as noise-free or corrupted by slight noise only). Within the data fusion analysis, a Kalman Filter algorithm is implemented and its effectiveness in improving noise-corrupted displacement measurements is investigated. The performance of the filter is assessed based on the RMS error between the original (noise-free, numerically-determined) displacement signal and the Kalman Filter displacement estimate, and on the structural modal parameters (natural frequencies) that can be extracted from displacement signals, refined through the combined use of displacement and acceleration recordings, through inverse analysis algorithms for output-only modal dynamics identification, based on displacements.

• 대한원격탐사학회지
• /
• 제28권6호
• /
• pp.611-622
• /
• 2012

This study proposed two multisensor fusion methods for segment-based image classification utilizing a region-growing segmentation. The proposed algorithms employ a Gaussian-PDF measure and an evidential measure respectively. In remote sensing application, segment-based approaches are used to extract more explicit information on spatial structure compared to pixel-based methods. Data from a single sensor may be insufficient to provide accurate description of a ground scene in image classification. Due to the redundant and complementary nature of multisensor data, a combination of information from multiple sensors can make reduce classification error rate. The Gaussian-PDF method defines a regional measure as the PDF average of pixels belonging to the region, and assigns a region into a class associated with the maximum of regional measure. The evidential fusion method uses two measures of plausibility and belief, which are derived from a mass function of the Beta distribution for the basic probability assignment of every hypothesis about region classes. The proposed methods were applied to the SPOT XS and ENVISAT data, which were acquired over Iksan area of of Korean peninsula. The experiment results showed that the segment-based method of evidential measure is greatly effective on improving the classification via multisensor fusion.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제8권2호
• /
• pp.105-110
• /
• 2008

Human being recognizes emotion fusing information of the other speech signal, expression, gesture and bio-signal. Computer needs technologies that being recognized as human do using combined information. In this paper, we recognized five emotions (normal, happiness, anger, surprise, sadness) through speech signal and facial image, and we propose to method that fusing into emotion for emotion recognition result is applying to multimodal method. Speech signal and facial image does emotion recognition using Principal Component Analysis (PCA) method. And multimodal is fusing into emotion result applying fuzzy membership function. With our experiments, our average emotion recognition rate was 63% by using speech signals, and was 53.4% by using facial images. That is, we know that speech signal offers a better emotion recognition rate than the facial image. We proposed decision fusion method using S-type membership function to heighten the emotion recognition rate. Result of emotion recognition through proposed method, average recognized rate is 70.4%. We could know that decision fusion method offers a better emotion recognition rate than the facial image or speech signal.

• 로봇학회논문지
• /
• 제3권3호
• /
• pp.176-185
• /
• 2008

In this paper, new filtering method for sensor registration is provided to estimate and correct error of registration parameters in multiple sensor environments. Sensor registration is based on filtering method to estimate registration parameters in multiple sensor environments. Accuracy of sensor registration can increase performance of data fusion method selected. Due to various error sources, the sensor registration has registration errors recognized as multiple objects even though multiple sensors are tracking one object. In order to estimate the error parameter, new nonlinear information filtering method is developed using minimum mean square error estimation. Instead of linearization of nonlinear function like an extended Kalman filter, information estimation through unscented prediction is used. The proposed method enables to reduce estimation error without a computation of the Jacobian matrix in case that measurement dimension is large. A computer simulation is carried out to evaluate the proposed filtering method with an extended Kalman filter.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2002년도 Proceedings of International Symposium on Remote Sensing
• /
• pp.400-406
• /
• 2002

Recently, the enormous increase in the volume of remotely sensed data is being acquired by an ever-growing number of earth observation satellites. The combining of diversely sourced imagery together is an important requirement in many applications such as data fusion, city modeling and object recognition. Aerial triangulation is a procedure to reconstruct object space from imagery. However, since the different kinds of imagery have their own sensor model, characteristics, and resolution, the previous approach in aerial triangulation (or georeferencing) is performed on a sensor model separately. This study evaluated the advantages of aerial triangulation of large number of images from multi-sensors simultaneously. The incorporated multi-sensors are frame, push broom, and whisky broom cameras. The limits and problems of push-broom or whisky broom sensor models can be compensated by combined triangulation with frame imagery and vise versa. The reconstructed object space from multi-sensor triangulation is more accurate than that from a single model. Experiments conducted in this study show the more accurately reconstructed object space from multi-sensor triangulation.

• 대한원격탐사학회지
• /
• 제19권3호
• /
• pp.255-261
• /
• 2003

Recently, the enormous increase in the volume of remotely sensed data is being acquired by an ever-growing number of earth observation satellites. The combining of diversely sourced imagery together is an important requirement in many applications such as data fusion, city modeling and object recognition. Aerial triangulation is a procedure to reconstruct object space from imagery. However, since the different kinds of imagery have their own sensor model, characteristics, and resolution, the previous approach in aerial triangulation (or georeferencing) is purformed on a sensor model separately. This study evaluated the advantages of aerial triangulation of large number of images from multi-sensors simultaneously. The incorporated multi-sensors are frame, push broom, and whisky broom cameras. The limits and problems of push-broom or whisky broom sensor models can be compensated by combined triangulation with other sensors The reconstructed object space from multi-sensor triangulation is more accurate than that from a single model. Experiments conducted in this study show the more accurately reconstructed object space from multi-sensor triangulation.

• 환경영향평가
• /
• 제27권4호
• /
• pp.378-393
• /
• 2018

국내의 미세먼지 문제가 심각해짐에 따라 개인이 활동하는 주변공간의 미세먼지 농도를 알고자 하는 욕구 또한 증가하여 직접 미세먼지의 실시간 농도를 측정할 수 있는 휴대용 미세먼지측정센서에 대한 수요가 증가하고 있다. 그러나 시중에 판매되는 미세먼지 간이측정기는 정해진 인증기준 없이 제작 판매되고 있다. 본 연구에서는 최근 판매가 급증하고 있는 휴대용 미세먼지 측정센서의 농도값을 어느 정도 신뢰할 수 있는지와 이러한 센서들이 어떠한 경우에 활용될 수 있는 지에 대해 일반적인 시민의 입장에서 고찰할 필요가 있다고 판단하였다. 이를 위해, 1) 기기 간 상호비교 및 보다 정확한 장비와의 비교를 수행하고, 2) 휴대용 기기를 활용하여 미세먼지의 영향을 저감할 수 있는 방안들에 대한 검증실험을 수행해 보았다. 그 결과 휴대용센서들의 농도 절대값을 그대로 신뢰하기엔 문제가 있었지만, 그 재현성과 선형성은 실생활에서 활용되기에 유용하다고 판단되었다. 또한 휴대용 미세먼지 측정센서를 사용함으로써 사용자들은 자기 주변의 변화하는 미세먼지 농도에 대해 빠르게 인지하고 대처 할 수 있을 것으로 판단되어, 미세먼지 오염의 피해를 줄이는 데 활용할 수 있을 것이라 기대된다.