A Vision Based System for Object Detection in Underwater Images

In this paper, a vision-based system for underwater object detection is presented. The system is able to detect automatically a pipeline placed on the sea bottom, and some objects, e.g. trestles and anodes, placed in its neighborhoods. A color compensation procedure has been introduced in order to reduce problems connected with the light attenuation in the water. Artificial neural networks are then applied in order to classify in real-time the pixels of the input image into different classes, corresponding e.g. to different objects present in the observed scene. Geometric reasoning is applied to reduce the detection of false objects and to improve the accuracy of true detected objects. The results on real underwater images representing a pipeline structure in different scenarios are shown. The presence of seaweed and sand, different illumination conditions and water depth, different pipeline diameter and small variations of the camera tilt angle are considered to evaluate the algorithm performances.

[1]  Tamaki Ura,et al.  A vision-based interactive system for underwater robots , 1995, Proceedings 1995 IEEE/RSJ International Conference on Intelligent Robots and Systems. Human Robot Interaction and Cooperative Robots.

[2]  J. Lucas,et al.  Computer vision control of an underwater manipulator , 1994, Proceedings of OCEANS'94.

[3]  S. Duntley.  Light in the Sea , 1963 .

[4]  Larry S. Shapiro,et al.  A Matching and Tracking Strategy for Independently Moving Objects , 1992 .

[5]  J. M. Hans du Buf,et al.  A review of recent texture segmentation and feature extraction techniques , 1993 .

[6]  Yoshua Bengio,et al.  Pattern Recognition and Neural Networks , 1995 .

[7]  R. K. Hansen.  An acoustic camera for 3D underwater imaging , 1993 .

[8]  K. Vestgard,et al.  Hugin-an untethered underwater vehicle for seabed surveying , 1998, IEEE Oceanic Engineering Society. OCEANS'98. Conference Proceedings (Cat. No.98CH36259).

[9]  Antoni Grau,et al.  Real-time architecture for cable tracking using texture descriptors , 1998, IEEE Oceanic Engineering Society. OCEANS'98. Conference Proceedings (Cat. No.98CH36259).

[10]  Primo Zingaretti,et al.  Real-time inspection by submarine images , 1996, J. Electronic Imaging.

[11]  Larry H. Thiel,et al.  Algorithms for Detecting M-Dimensional Objects in N-Dimensional Spaces , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Ettore Stella,et al.  Autonomous navigation of underwater vehicles , 1998, IEEE Oceanic Engineering Society. OCEANS'98. Conference Proceedings (Cat. No.98CH36259).

[13]  David M. Lane,et al.  Automatic interpretation of sonar imagery using qualitative feature matching , 1994 .

[14]  J. Santos-Victor,et al.  Automatic mosaic creation of the ocean floor , 1998, IEEE Oceanic Engineering Society. OCEANS'98. Conference Proceedings (Cat. No.98CH36259).

[15]  R. S. Davis,et al.  Remote visual inspection in the nuclear, pipeline, and underwater industries , 1990 .

[16]  Martin Herman,et al.  Geometric Reasoning for Constructing 3D Scene Descriptions from Images , 1988, Artif. Intell..

[17]  Stephen M. Rock,et al.  EXPERIMENTAL VALIDATION OF A REAL-TIME VISION SENSOR AND NAVIGATION SYSTEM FOR INTELLIGENT UNDERWATER VEHICLES , 1998 .

[18]  Stewart A. L. Glegg,et al.  Imaging the ocean with ambient noise , 1992, Nature.

[19]  Emanuele Trucco,et al.  Making good features track better , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[20]  X. Xu,et al.  Applications of direct 3D motion estimation for underwater machine vision systems , 1998, IEEE Oceanic Engineering Society. OCEANS'98. Conference Proceedings (Cat. No.98CH36259).

[21]  Gian Luca Foresti,et al.  Autonomous underwater vehicle guidance by integrating neural networks and geometric reasoning , 1999, Int. J. Imaging Syst. Technol..

[22]  Vittorio Murino,et al.  A voting-based approach for fast object recognition in underwater acoustic images , 1997 .

[23]  Don Brutzman,et al.  NPS Phoenix AUV software integration and in-water testing , 1996, Proceedings of Symposium on Autonomous Underwater Vehicle Technology.

[24]  R. L. Marks,et al.  Real-time video mosaicking of the ocean floor , 1995 .