Title :
Study on joint probability density algorithm in multi-sensor data fusion
Author :
Can, Xu ; Zhi, Li
Author_Institution :
Co. of Postgrad. Manage., Acad. of Equip., Beijing, China
Abstract :
Joint probability density algorithm (JPDA) is a novel algorithm in multi-sensor data fusion and it provides a new approach for target localization. Generally, more sensors could make higher precision of localization when JPDA is adopted, but there is no full theoretical support so far. According to the region of interesting (ROI) generated by JPDA in Cartesian coordinates, the information entropy of JPDA is analyzed. The expression of information entropy of multi-sensor which is the theoretical basis of JPDA is deduced. The result indicates that no matter how many sensors there are, the entropy is determined only by the determinant of covariance matrix, more sensors make information entropy lower which is the reason why localization precision is higher. Simulation results verify our analysis.
Keywords :
covariance matrices; entropy; probability; sensor fusion; Cartesian coordinates; JPDA; ROI; covariance matrix; information entropy; joint probability density algorithm; multisensor data fusion; region of interesting; target localization; Coordinate measuring machines; Covariance matrix; Entropy; Information entropy; Joints; Probability density function; Sensors; informatin entropy; joint probabiltiy density; multi-sensor data fusion;
Conference_Titel :
Computer Science and Automation Engineering (CSAE), 2012 IEEE International Conference on
Conference_Location :
Zhangjiajie
Print_ISBN :
978-1-4673-0088-9
DOI :
10.1109/CSAE.2012.6272542
