Coastal fog detection using visual sensing

Use of visual sensing techniques to detect low visibility conditions may have a number of advantages when combined with other methods, such as satellite based remote sensing, as data can be collected and processed in real or near real time. Camera-enabled visual sensing can provide direct confirmation of modelling and forecasting results. Indeed, fog detection, modelling and prediction are a priority for maritime communities and coastal cities due to economic impacts of fog on aviation, marine, and land transportation. Canadian and Irish coasts are particularly vulnerable to dense fog under certain environmental conditions, and offshore installations related to oil and gas production on the Grand Banks (off the Canadian East Coast) for example can be adversely affected by weather and sea state conditions. In particular, fog can disrupt the transfer of equipment and people to/from the production platforms by helicopter. Such disruptions create delays and the delays cost money. According to offshore oil and gas industry representatives at a recent workshop on metocean monitoring and forecasting for the Newfoundland and Labrador (NL) offshore, there is a real need for improved forecasting of visibility (fog) out to 3 days. The ability to accurately forecast future fog conditions would improve industry's ability to adjust its schedule of operations accordingly. In addition, it was recognised by workshop participants that the physics of the Grand Banks fog formation is not well understood, and that more and better data are needed. In Europe, an EU COST action fog project, with objectives of reducing economic loss and fatalities, has also been created to develop advanced methods for very short-range forecasts of fog and low clouds. Key research objectives of the project included methods for determining the optimal combination of satellite and ground-based observations and measurement techniques of fog. These data were then used to develop estimates of fog risk at high spatial and temporal resolutions, however the focus was on remote satellite observations rather than local visual sensing systems [1].

[1]  J. Ohm The MPEG-7 Color Descriptors , 2005 .

[2]  James Lee Hafner,et al.  Efficient Color Histogram Indexing for Quadratic Form Distance Functions , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Alan F. Smeaton,et al.  Detection and classification of anomalous events in water quality datasets within a smart city-smart bay project , 2014 .

[4]  Thorsten Joachims,et al.  Text Categorization with Support Vector Machines: Learning with Many Relevant Features , 1998, ECML.

[5]  Yiannis S. Boutalis,et al.  FCTH: Fuzzy Color and Texture Histogram - A Low Level Feature for Accurate Image Retrieval , 2008, 2008 Ninth International Workshop on Image Analysis for Multimedia Interactive Services.

[6]  L. M. Bergasa,et al.  Fog detection system based on computer vision techniques , 2009, 2009 12th International IEEE Conference on Intelligent Transportation Systems.

[7]  Trieu-Kien Truong,et al.  Audio classification and categorization based on wavelets and support vector Machine , 2005, IEEE Transactions on Speech and Audio Processing.

[8]  B. S. Manjunath,et al.  Introduction to MPEG-7: Multimedia Content Description Interface , 2002 .

[9]  Ramin Zabih,et al.  Comparing images using joint histograms , 1999, Multimedia Systems.

[10]  Koen E. A. van de Sande,et al.  Evaluating Color Descriptors for Object and Scene Recognition , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Jean-Philippe Tarel,et al.  Automatic fog detection and estimation of visibility distance through use of an onboard camera , 2006, Machine Vision and Applications.

[12]  J. Daugman Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. , 1985, Journal of the Optical Society of America. A, Optics and image science.

[13]  Milan Sonka,et al.  Image Processing, Analysis and Machine Vision , 1993, Springer US.

[14]  Yiannis S. Boutalis,et al.  CEDD: Color and Edge Directivity Descriptor: A Compact Descriptor for Image Indexing and Retrieval , 2008, ICVS.

[15]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[16]  Noel E. O'Connor,et al.  Smart multi-modal marine monitoring via visual analysis and data fusion , 2013, MAED '13.

[17]  Hideyuki Tamura,et al.  Textural Features Corresponding to Visual Perception , 1978, IEEE Transactions on Systems, Man, and Cybernetics.

[18]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.