Multi-target Detection of Underwater Vehicle Based on Multi-sensor Data Fusion

摘要

This paper describes a method of forward-looking sonar, single cameraand ultrasonic proximate sensor data fusion applied for underwatermulti-target identification and positioning. A set of multi-targetdetection approach was proposed based upon the characteristics ofsonar and the geometry of underwater objects. In long distance, multitargetwould be detected by sonar; when targets were in the distance of5m, they would be identified and roughly positioned by integratingsonar and camera image information; in working range 2m of ultrasonicproximate sensor, camera image and ultrasonic proximate sensor datafusion was used to achieve multi-target identification and accuratepositioning. Experimental results obtained in an indoor pooldemonstrated the availability of this method.