Improving multi-modal data fusion by anomaly detection

Šimánek, Jakub; Kubelka, Vladimír; Michal, R.

doi:10.1007/s10514-015-9431-6

Cited by 26 publications

(15 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, his method is unsuitable in a broad environment. Simanek [5] designed a multi-mode data fusion algorithm based on the extended Kalman filter. The algorithm could accurately identify abnormal data and realize standard statistical test of filter residual, but the influence of the filter gain matrix on the algorithm was neglected.…”

Section: State Of the Artmentioning

confidence: 99%

Mobile Robot Self-localization Based on Multi-sensor Fusion Using Limited Memory Kalman Filter with Exponential Fading Factor

Cheng¹,

Liu²,

Meng³

et al. 2018

JESTR

View full text Add to dashboard Cite

Accumulative errors can be retained all the time when classical Kalman filtering is adopted for odometer-based dead reckoning, thereby affecting self-localization accuracy of the robot. A mobile robot self-localization method based on limited memory Kalman filtering (LMKF) with exponential fading factor was proposed to reduce accumulative errors of the odometer and improve localization accuracy of the mobile robot. The self-localization system of mobile robot was built. A mathematical model was established based on LMKF with exponential fading factor. A dead reckoning method fusing multi-sensor information was proposed. The model accuracy was verified through simulation and test. Results indicate that the LMKF method with exponential fading factor positively affects the tracking of high-speed maneuvering dynamic targets, and its localization error is reduced by 42.5% compared with the odometer-based dead reckoning. The tracking accuracy of the mobile robot is stable at 0.5 m. This study can provide references for mobile robot selflocalization using multi-sensor.

show abstract

Section: State Of the Artmentioning

confidence: 99%

Mobile Robot Self-localization Based on Multi-sensor Fusion Using Limited Memory Kalman Filter with Exponential Fading Factor

Cheng¹,

Liu²,

Meng³

et al. 2018

JESTR

View full text Add to dashboard Cite

show abstract

“…Due to only eliminating the obvious noise point of a large area manually during the data processing without smoothing and streamlining, the data processing errors are negligible. After the multi-sensor data fusion, the transformation error is decreased and can be also ignored relative to the measurement error of the laser tracker and the handheld laser scanning sensor [ 22 , 23 ]. The maximum length of the workpiece is 560 mm, and thus the measurement error is:

…”

Section: Error Analysis and Synthesismentioning

confidence: 99%

Fast Measurement and Reconstruction of Large Workpieces with Freeform Surfaces by Combining Local Scanning and Global Position Data

Chen

Zhang

et al. 2015

Sensors

View full text Add to dashboard Cite

In this paper, we propose a new approach for the measurement and reconstruction of large workpieces with freeform surfaces. The system consists of a handheld laser scanning sensor and a position sensor. The laser scanning sensor is used to acquire the surface and geometry information, and the position sensor is utilized to unify the scanning sensors into a global coordinate system. The measurement process includes data collection, multi-sensor data fusion and surface reconstruction. With the multi-sensor data fusion, errors accumulated during the image alignment and registration process are minimized, and the measuring precision is significantly improved. After the dense accurate acquisition of the three-dimensional (3-D) coordinates, the surface is reconstructed using a commercial software piece, based on the Non-Uniform Rational B-Splines (NURBS) surface. The system has been evaluated, both qualitatively and quantitatively, using reference measurements provided by a commercial laser scanning sensor. The method has been applied for the reconstruction of a large gear rim and the accuracy is up to 0.0963 mm. The results prove that this new combined method is promising for measuring and reconstructing the large-scale objects with complex surface geometry. Compared with reported methods of large-scale shape measurement, it owns high freedom in motion, high precision and high measurement speed in a wide measurement range.

show abstract

“…The multisensor data fusion model uses computer technology to analyze and process the observed information from multiple sensors to obtain a decision and the estimated value of a tested sample. Compared with single sensor information, the multisensor fusion method derives more useful information by combining multiple data sources; thus, both decision and estimation accuracy are both improved . The evaluation of tea quality is a complex process involving color, size, shape, taste and aroma; few studies have investigated the relationship between the various tea quality parameters that can be used as a reference for sensor data fusion in tea discrimination.…”

Section: Introductionmentioning

confidence: 99%

“…Compared with single sensor information, the multisensor fusion method derives more useful information by combining multiple data sources; thus, both decision and estimation accuracy are both improved. 14,15 The evaluation of tea quality is a complex process involving color, size, shape, taste and aroma; few studies have investigated the relationship between the various tea quality parameters that can be used as a reference for sensor data fusion in tea discrimination. In addition, data fusion is a new research field; the relevant literature has not yet determined the best statistical processing and analysis methods for obtaining the maximum benefits from multisensor data fusion.…”

Section: Introductionmentioning

confidence: 99%

Evaluating green tea quality based on multisensor data fusion combining hyperspectral imaging and olfactory visualization systems

Xie

Ning

et al. 2018

J Sci Food Agric

View full text Add to dashboard Cite

show abstract

Improving multi-modal data fusion by anomaly detection

Cited by 26 publications

References 46 publications

Mobile Robot Self-localization Based on Multi-sensor Fusion Using Limited Memory Kalman Filter with Exponential Fading Factor

Mobile Robot Self-localization Based on Multi-sensor Fusion Using Limited Memory Kalman Filter with Exponential Fading Factor

Fast Measurement and Reconstruction of Large Workpieces with Freeform Surfaces by Combining Local Scanning and Global Position Data

Evaluating green tea quality based on multisensor data fusion combining hyperspectral imaging and olfactory visualization systems

Contact Info

Product

Resources

About