A real-time object recognition for forward looking sonar

Automatic target recognition is a challenging task as the response from an underwater target may vary greatly depending on its configuration, sonar parameters and the environment. In forward looking sonar image the target is considered as composed of a few rows and columns of highlight pixels and a few rows and some columns of shadow pixels. We firstly design target-like templet for object in forward looking sonar, then correlation matching method is used for targets detection with the help of the target-like templet, at last the features which are extracted from the objects are used to get rid of the false objects. The algorithm is formulated for real-time execution on limited-memory commercial-of-the-shelf platforms and is capable of detection objects on the seabed-bottom.

[1]  David M. Lane,et al.  A comparison of inter-frame feature measures for robust object classification in sector scan sonar image sequences , 1999 .

[2]  Christophe Collet,et al.  Hierarchical MRF modeling for sonar picture segmentation , 1996, Proceedings of 3rd IEEE International Conference on Image Processing.

[3]  Mike J. Chantler,et al.  Automatic interpretation of sonar image sequences using temporal feature measures , 1997 .

[4]  Yvan Petillot,et al.  Underwater vehicle obstacle avoidance and path planning using a multi-beam forward looking sonar , 2001 .

[5]  Jenhwa Guo,et al.  AUV obstacle avoidance and navigation using image sequences of a sector scanning sonar , 1998, Proceedings of 1998 International Symposium on Underwater Technology.

[6]  Yingchun Lu,et al.  Underwater target's size/shape dynamic analysis for fast target recognition using sonar images , 1998, Proceedings of 1998 International Symposium on Underwater Technology.

[7]  F. L. Thurstone,et al.  Acoustic Speckle: Theory and Experimental Analysis , 1979 .

[8]  David M. Lane,et al.  Classification of sector-scanning sonar image sequences , 1995 .

[9]  N. Karpel,et al.  Recovering scenes by polarization analysis , 2004, Oceans '04 MTS/IEEE Techno-Ocean '04 (IEEE Cat. No.04CH37600).

[10]  Carsten Rother,et al.  DenseCut: Densely Connected CRFs for Realtime GrabCut , 2015, Comput. Graph. Forum.

[11]  S. Guillaudeux,et al.  Optimization of a sonar image processing chain: a fuzzy rules based expert system approach , 1996, OCEANS 96 MTS/IEEE Conference Proceedings. The Coastal Ocean - Prospects for the 21st Century.