A systems approach to data fusion

McKerrow, P.J.; Volk, S.J.

doi:10.1109/adfs.1996.581109

Cited by 18 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specification [1] Measurement range 100*100mm 2 [2] Accuracy 0.05mm [3] COMS-camera1 2 3 4 1/1.8＂1280＊1024 5.2*5.2um 2 Camera1 3---lens f: 35mm F/1.7 Camera2 4---lens f: 25mm F/1.4 [4] width of strip laser beam <0.5mm [5] Horizontal sliding way range:50mm positioning accuracy:0.005mm [6] Vertical sliding way range:800mm positioning accuracy:0 005mm…”

Section: Itemsmentioning

confidence: 99%

“…Multisensor data fusion techniques have been successful in military and nonmilitary applications [1][2][3] .It combine data from multiple sensors to achieve improved accuracies and more specific inferences by analyzing related information from them . Data fusion techniques also has wide applications and bring great benefit in 3-D profile measurement field.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Development of a multi-resolution measurement system based on light sectioning method

et al. 2008

View full text Add to dashboard Cite

With the rapid development of shape measurement technique, multi-resolution approach becomes one of valid way to enhance the accuracy. There are, however, still some key techniques such as simultaneous calibration and data fusion of several sensors being further studied. A multi-resolution system, which use light sectioning method, is developed and has been successful in many application areas for blade of aviation engine example. It can measure the shape of blade at high speed and high accuracy. The system is composed of four laser linear light sources, four or five cameras and three highprecision mechanical movement devices. Two cameras have relatively low amplifying ratios, and focus on the basin or back of blade where the radius of curvature is large. Other cameras have high amplifying ratios, and fix on the entering or ending edge of blade where the radius of curvature is small. So the system has 360 0 measurement range and can carry out multi-resolution 3-D shape measurement with greatly different amplifying ratios of cameras. One measurement process has been finished when the blade mounted on mechanical movement device move up or down one time. Also the model building and principle of the measurement system, an algorithm of calibration and data fusion of several cameras are presented that calculate 3-D coordinates of one section of blade. The result shows that the accuracy of the system is about 0.05mm for the sectional circumradius approximately 50 mm measurement range, and also proves the system is feasible and efficient.

show abstract

Section: Itemsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Development of a multi-resolution measurement system based on light sectioning method

et al. 2008

View full text Add to dashboard Cite

show abstract

“…Data fusion methods have many kinds, such as neural network fusion, D-S evidence theory, Kalman filter method, fuzzy fusion and etc. and Bayes decision theory [2,3] Data fusion refers to a wide range of information processing techniques and methodologies to achieve more accurate and reliable information [4,5].…”

Section: Introductionmentioning

confidence: 99%

Study on Measurement System of Underwater Autonomous Robot

Yang

Sun

Liu

2008

2008 IEEE Conference on Robotics, Automation and Mechatronics

View full text Add to dashboard Cite

Measure system is important part for an autonomous mobile robot. Move-in-mud robot is a new kind of autonomous underwater robot, which is used to dig hole in the mud. Measure system of move-in-mud robot is designed in the paper and measure principle of move-in-mud robot is analysed. Data fusion methods combine multi-sensor information to obtain the uniform description or the understanding to the measured object according to a certain criterion. Kalman filter is chosen as the data fusion method of the measure system to improve the accuracy of measure system. The depth error with fusion is smaller than the direct measure and indirect measure. The simulation results indicate that fusion improves the accuracy of the robot depth obviously.

show abstract

“…Data fusion is the process of combining data from several sources into a single unified description of a situation [5]. It applied to a measuring system can reduce effectively overall uncertainty and increase the accuracy.…”

Section: Introductionmentioning

confidence: 99%

Data Fusion Modeling of Lumber Moisture Content Sensors Using Chebyshev Functional Link Networks

Zhang¹,

Sun²,

Cao³

The 2006 IEEE International Joint Conference on Neural Network Proceedings

View full text Add to dashboard Cite

Lumber moisture content sensors operating in harsh environment are easily influenced by ambient factor parameters. Data fusion technique is proposed to combine data from several sources into a single unified description. A novel single layer functional link network (FLN) using Chebyshev polynomials is used for this purpose to compensate for the nonlinear response characteristics and complex nonlinear dependency of the environmental parameters on the sensor characteristics. FLN eliminates the hidden layers of conventional neural networks by expanding the input pattern into a high order dimensional space. Compared to the multilayer perceptron (MLP), Chebyshev FLN has the similar performance and less computational complexity.

show abstract

A systems approach to data fusion

Cited by 18 publications

References 6 publications

Development of a multi-resolution measurement system based on light sectioning method

Development of a multi-resolution measurement system based on light sectioning method

Study on Measurement System of Underwater Autonomous Robot

Data Fusion Modeling of Lumber Moisture Content Sensors Using Chebyshev Functional Link Networks

Contact Info

Product

Resources

About