An effective noise filtering method for mine detection

Download
Author
Hong, Bryan Y.
Date
2011-09Advisor
Chu, Peter C.
Second Reader
Betsch, Ronald E.
Metadata
Show full item recordAbstract
Automatic detection of sea mines in coastal regions is difficult due to highly varying sea bottom conditions present in the underwater environment. Detection systems must be able to discriminate objects that vary in size, shape, and orientation from naturally occurring and man-made clutter. Additionally, these automated systems must be computationally efficient to be incorporated into Unmanned Aerial Vehicle (UAV) sensor systems characterized by high sensor data-rates and limited processing abilities. Commonly used noise filters largely depend on the window (or neighborhood) size, which makes the mine detection ineffective. Using the bi-dimensional empirical mode decomposition (BEMD) analysis, an effective, robust sea mine detection system can be created. A family of decomposed images is generated and applied to optical lidar image data from the Rapid, Overt, Airborne, Reconnaissance (ROAR) experiment supplied by Naval Surface Warfare Center, Panama City. These decompositions project key image features, geometrically defined structures with orientations, and localized information into distinct orthogonal components or feature subspaces of the image. Application of the BEMD method to the analysis on side scan sonar data is also provided. Accurate detection and classification of mines is time consuming and requires divers or Autonomous Underwater Vehicles (AUV) in the water. The navy continues to pursue more expedient methods in mine countermeasures, and with airborne lidar, a surf zone (SZ) and landing zone can be quickly surveyed for possible mines. In the near surf zone, all possible mines can be quickly neutralized by dropping guided munitions, eliminating the need to send divers or AUVs to verify contacts. Still, the need for improved methods of detection and classification is needed. BEMD, a relatively new method of signal analysis developed about fifteen years ago, was tested on lidar imagery from the ROAR experiment to look for any improvements in detecting and classifying mines.
Rights
This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.Collections
Related items
Showing items related by title, author, creator and subject.
-
Mine and Mine Like Objects Classifications through Deep Learning Neural Network Systems
Joung, Sang Ki; Song, Kwang Sub; Kim, Moon Hwan; Chu, Peter (2018-04-18);Threats of sea mines are increasing due to recent technology development, such as autonomous systems and computer systems with artificial intelligent capability. There are many solutions to solve MCM problems as far as ... -
Mine and Mine Like Objects Classifications through Deep Learning Neural Network Systems [video]
Joung, Sang Ki; Song, Kwang Sub; Kim, Moon Hwan; Chu, Peter (2018-04-18);Threats of sea mines are increasing due to recent technology development, such as autonomous systems and computer systems with artificial intelligent capability. There are many solutions to solve MCM problems as far as ... -
Fusion of multiple sensor types in computer vision systems
Mayo, Donald R. (Monterey, California. Naval Postgraduate School, 2007-09);This research provides analysis of several approaches to the fusion of multiple dissimilar sensors to supplement simple color vision detection and recognition. Non-visible sensor systems can enhance computer vision systems. ...