Real-Time Underwater Target Classification Method for Multi-resolution imaging Sonar of the AUV

How to accurately and fast classification obstacle is the key of real-time obstacle avoidance and avoidance decision for autonomous underwater vehicle. According to the characteristics of the multi-resolution imaging sonar, we extracted the obstacle information and characteristics from sonar image ， and the AUV can quickly make decision with underwater obstacles classification. Finally, the data of lake test verified that the method of real-time image processing and underwater target classification is feasible and effective