• Journal of Information Processing Systems
• /
• 제14권6호
• /
• pp.1445-1456
• /
• 2018

Environment perception and three-dimensional (3D) reconstruction tasks are used to provide unmanned ground vehicle (UGV) with driving awareness interfaces. The speed of obstacle segmentation and surrounding terrain reconstruction crucially influences decision making in UGVs. To increase the processing speed of environment information analysis, we develop a CPU-GPU hybrid system of automatic environment perception and 3D terrain reconstruction based on the integration of multiple sensors. The system consists of three functional modules, namely, multi-sensor data collection and pre-processing, environment perception, and 3D reconstruction. To integrate individual datasets collected from different sensors, the pre-processing function registers the sensed LiDAR (light detection and ranging) point clouds, video sequences, and motion information into a global terrain model after filtering redundant and noise data according to the redundancy removal principle. In the environment perception module, the registered discrete points are clustered into ground surface and individual objects by using a ground segmentation method and a connected component labeling algorithm. The estimated ground surface and non-ground objects indicate the terrain to be traversed and obstacles in the environment, thus creating driving awareness. The 3D reconstruction module calibrates the projection matrix between the mounted LiDAR and cameras to map the local point clouds onto the captured video images. Texture meshes and color particle models are used to reconstruct the ground surface and objects of the 3D terrain model, respectively. To accelerate the proposed system, we apply the GPU parallel computation method to implement the applied computer graphics and image processing algorithms in parallel.

• 한국CDE학회논문집
• /
• 제17권2호
• /
• pp.97-110
• /
• 2012

High performance sensors and modern data logging technology with real-time telemetry facilitate system fault diagnosis in a very precise manner. Fault detection, isolation and identification in fault diagnosis systems are typical steps to analyze the root cause of failures. This systematic failure analysis provides not only useful clues to rectify the abnormal behaviors of a system, but also key information to redesign the current system for retrofit. The main barriers to effective failure analysis are: (i) the gathered data (event) logs are too large in general, and further (ii) they usually contain noise and redundant data that make precise analysis difficult. This paper therefore applies suitable pre-processing techniques to data reduction and feature extraction, and then converts the reduced data log into a new format of event sequence information. Finally the event sequence information is decoded to investigate the correlation between specific event patterns and various system faults. The efficiency of the developed pre-filtering procedure is examined with a terminal box data log of a marine diesel engine.

• 제어로봇시스템학회논문지
• /
• 제5권8호
• /
• pp.961-968
• /
• 1999

In this paper we handle a system that transform sensor data to sensor information. Sensor informations from redundant accelerometers are manipulated to represent the configuration of objects carrying sensors. Basic sensor unit of the proposed systme is composed of 3 accelerometers that are aligned along x-y-z coordination axes of motion. To refine the sensor information, at first the sensor data are fused by geometrical optimization to reduce the variance of sensor information. To overcome the error caused from inexact alignment of each sensor to the coordination system, we propose a calibration technique that identifies the transformation between the coordinate axes and real sensor axes. The calibration technique make the sensor information approach real value. Also, we propose a technique that decomposes the accelerometer data into motion acceleration component and gravity acceleration component so that we can get more exact configuration of objects than in the case of raw sensor data. A set of experimental results are given to show the usefulness of the proposed method as well as the experiments in which the proposed techniques are applied to human body motion capture.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1995년도 추계학술대회 논문집 학회본부
• /
• pp.175-177
• /
• 1995

The sensor signal validation and failure detection system must be able to detect, isolate, and identify sensor degradation as well as provide a reconstruction of the measurements. In this study, this is accomplished by combining the neural network, the Generalized Consistency Checking(GCC), and the Sequential Probability Ratio Test(SPRT) method in a decision estimator module. The GCC method is a computationally efficient system for redundant sensors, while the SPRT provides the ability to make decisions based on the degradation history of a sensor. The methodology is also extended to the detection of noise degradation. The acceptability of the proposed method is demonstration by using the simulation data in safety injection accident of nuclear power plants. The results show that the signal validation and sensor failure detection system is able to detect and isolate a bias failure and noise type failures under transient conditions. And also, the system is able to provide the validated signal by reconstructing the measurement signals in the failure conditions considered.

• 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.

• 센서학회지
• /
• 제18권6호
• /
• pp.432-440
• /
• 2009

This paper presents an accelerometer based system for physical activity decision that are capable of recognizing three different types of physical activities, i.e., standing, walking and running, using by rough sets. To collect physical acceleration data, we developed the body sensor node which consists of two custom boards for physical activity monitoring applications, a wireless sensor node and an accelerometer sensor module. The physical activity decision is based on the acceleration data collected from body sensor node attached on the user's chest. We proposed a method to classify physical activities using rough sets which can be generated rules as attributes of the preprocessed data and by constructing a new decision table, rules reduction. Our experimental results have successfully validated that performance of the rule patterns after removing the redundant attribute values are better and exactly same compare with before.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제6권1호
• /
• pp.229-240
• /
• 2012

Advances in MEMS and CMOS technologies have motivated the development of low cost/power sensors and wireless multimedia sensor networks (WMSN). The WMSNs were created to ubiquitously harvest multimedia content. Such networks have allowed researchers and engineers to glimpse at new Machine-to-Machine (M2M) Systems, such as remote monitoring of biosignals for telemedicine networks. These systems require the acquisition of a large number of data streams that are simultaneously generated by multiple distributed devices. This paradigm of data generation and transmission is known as event-streaming. In order to be useful to the application, the collected data requires a preprocessing called data fusion, which entails the temporal alignment task of multimedia data. A practical way to perform this task is in a centralized manner, assuming that the network nodes only function as collector entities. However, by following this scheme, a considerable amount of redundant information is transmitted to the central entity. To decrease such redundancy, data fusion must be performed in a collaborative way. In this paper, we propose a collaborative data alignment approach for event-streaming. Our approach identifies temporal relationships by translating temporal dependencies based on a timeline to causal dependencies of the media involved.

• 한국군사과학기술학회지
• /
• 제23권6호
• /
• pp.639-649
• /
• 2020

Air data systems measure airspeed, pressure altitude, angle of attack and angle of sideslip. These measurements are essential for operating flight control laws to ensure safe flights. Since the loss or corruption of air data measurements is considered as catastrophic, a high level of operational reliability needs to be achieved for air data systems. In the case of unmanned air vehicles, failure of any of air data sensors is more critical due to the absence of onboard pilot decision aid. This paper presents design of a dual redundancy air data system and the integration process for an unmanned air vehicle. The proposed dual-redundant architecture is based on two independent air data probes and redundancy management by central processing in two independent flight control computers. Starting from unit testing of single air data sensor, details are provided of system level tests used to meet overall requirements. Test results from system integration demonstrate the efficiency of the proposed process.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제16권1호
• /
• pp.75-79
• /
• 2010

최근 무선 센서 네트워크는 광범위한 분야에서 적용되어 사용되고 있다. 많은 수의 센서 노드 간의 통신으로 이루어지는 무선 센서 네트워크는 각 센서 노드에 부착된 센서들을 이용하여 주변 환경의 데이터를 획득한다. 네트워크 결함이나 토폴로지 변화와 같은 가변적인 상황에서도 질의 결과의 높은 정확도를 위한 설계 요구조건 및 적합한 라우팅 알고리즘을 구성하는 것은 중요하다. 본 논문에서는 네트워크 결함이나 토폴로지 변화에서도 높은 정확도를 보이는 새로운 라우팅 기법을 제안한다. 응용에 따라 수 개의 단일 경로 기반의 라우팅 트리를 생성하고 수집된 결과에서 가장 높은 정확도를 보이는 데이터를 최종 질의 결과로 반환한다. 제안하는 기법의 우수성을 보이기 위해 시뮬레이션을 통해 기존에 제안된 라우팅 기법과 성능을 비교하였다. 그 결과 기존의 기법과 마찬가지로 정확도가 높은 결과를 보였음에도 데이터 전송량을 약 70% 감소시키는 것을 확인할 수 있었다.

• Spatial Information Research
• /
• 제19권3호
• /
• pp.95-106
• /
• 2011

최근 무선 센서 네트워크에서 센서로부터 원하는 데이타를 가져오는 네트워크 내 집계 질의처리 기법에 대한 연구가 활발히 진행되고 있다. 기존의 대표적인 네트워크 내 집계 질의 처리 기법들은 집계 질의 처리를 위해 라우팅 알고리즘과 데이타 구조를 제안하고 있다. 그러나 이러한 기법들은 센서 노드들의 에너지 소모가 크고, 질의 처리 결과 정확도가 떨어지고, 또한 질의 처리 시간이 오래 걸리는 문제점들을 가지고 있다. 본 논문에서는 이러한 기존 집계 질의 처리 기법들의 문제점을 해결하고 무선 센서 네트워크에서 보다 효율적인 집계 질의 처리를 위해 BPA(Bucket-based Parallel Aggregation)를 제시하였다. BPA는 질의 영역을 센서 노드 분포에 따라 쿼드 트리로 구성하여 집계 질의를 병렬로 처리하고, 각 센서 노드로 하여금 데이타를 이중 전송하게 함으로써 전송 오류로 인한 데이타 손실을 줄인다. 또한, BPA는 집계 질의 처리시 버켓 기반의 데이타 구조를 이용하고 이러한 버켓 데이타 구조를 버켓내 데이타 개수에 따라 적응적으로 분할 및 합병한다. 특히 버켓내 데이타 크기를 줄이기 위해 데이타를 압축하고 데이타 전송 횟수를 줄이기 위해 필터링을 수행한다. 마지막으로 센서 데이타를 이용한 다양한 실험을 통해 본 논문에서 제안하는 BPA의 우수성을 입증하였다.