Research Of Multi-sensor Information Fusion Technology

With the continuous improvement of human intelligent multi-sensor system requirements, multi-sensor information fusion technology has attracted more and more attention. The information which is obtained by single-sensor is very limited is one-sided, and local environmental characteristics.Multi-sensor information fusion can be more comprehensive and accurate information on surroundings, which makes up a single sensor for the one-sidedness of the information. Multi-sensor information fusion combines complementary or redundant information of a plurality of sensors, in order to get the consistency description of the object.The combination of information, rather than the individual elements appear in the input information, which derives more information, improves the information intelligent degree of the system. This is the best result of synergy, which is jointly or jointly combined the advantages of the use of multiple sensors to improve the effectiveness of the sensor system, which provides intelligent decision-making information.Multi-sensor information fusion research information which processes from the perspective of information technology,takes full advantage of the computer’s high-speed computing and multi-source information complementary to improve the quality of information.The comprehensive utilization of multi-sensor technology provides an effective means of intelligent information processing.At present, the multi-sensor information fusion system has been widely used in the field of identification, intelligent robots, criminal investigation, industrial monitoring, remote sensing technology, which effectively improve the system of multi-sensor information intelligence degree, reduce the workload of manual processing information, and improve the productivity of human labor, and promote the development of the national economy.The main research contents are as follows:1.Improved weighted information fusion algorithmFor weighted average optimal weighting, adaptive weighted multi-sensor information fusion algorithm, this paper proposes using jackknife combination of information fusion algorithm with adaptive weighted method. The algorithm is based on adaptive weighted full use of the observations and the estimated value of each historical moment, by constructing a pseudo-value on the estimated value of the weighting factor the Quenouille estimated. After jackknife with adaptive weighted combination, the accuracy and robustness of the data processing are superior to ordinary treatment.2.Multi-sensor information fusion based on gray theoryThe multi-sensor information fusion based on gray theory. Gray measure larger for possible conflicts of sensor information, the introduction of reliability weights, gray measure adjust the weights and solitary point, and then the gray fusion algorithm is applied to fully autonomous robot soccer system map building, the application the gray number conceptual representation of the uncertainty of the ultrasonic sensor information, the establishment of a single sub-grid map of the robot, real-time collaboration between the multi-robot multiple sub-grid map obtained gray fusion global grid map. Experimental results show that the robot created a global grid map can reflect the basic situation, obstacles in the environment map building fully autonomous robot soccer system.Finally, the whole thesis of the summary of the main research, pointed out the existing shortcomings and areas for further research.