AUV sonar image processing based on improved pulse coupled neural network model and morphology

For the problem of Gaussian noise and impulse noise co-exist in acoustic image collected by AUV sonar, based on the improved pulse coupled neural network model, a hybrid filter is proposed using the advantages of median and wiener filtering. It is indicated that captures among neurons act on image filtering to a certain extent through research on the work principle of pulse coupled neural network, and the capability and characteristic of filtering noises are discussed. For filtered sonar image, edge is detected by selecting complex way of generalized morphology opening-closing operation. Then experimental results are given which show that the filter performance of the proposed approach is significantly superior to traditional filter approaches and the proposed morphology edge detection approach can ensure the continuity, integrity and accurate positioning of the edge of underwater sonar image. In a word, it is indicated that the proposed approach can provide effective environment observation information for AUV autonomous navigation.