Groundwork for an area-calibrated computer-automated system for benthic classification through underwater video is presented. Data acquisition through an underwater video camera is fast, less expensive and processing can be done in one day. Two video acquisition schemes were considered: (1) nearreef videos, where height of 30 cm from the reef surface is maintained, and (2) subsurface video of a reef where the camera is fixed 0.2-0.5m below the surface. Rapid classification is implemented via downsampling a reef image into blocks. Benthic components are classified into living and nonliving categories. For near-reef videos, an overall success rate of 79% is achieved even for corals occurring in various morphologies. Color and texture features derived from video stills were used as inputs to the classifier system. For subsurface reef video, an overall recognition rate of 60 – 70% was achieved. A more accurate percent cover is obtained via an area calibration model developed. This model is based on camera optics and removes the need for an underwater reference object for area correction. The development of an automated rapid reef classification system is most promising for reef studies that need fast and frequent data acquisition of percent cover of living and nonliving components.
[1]
T. Done,et al.
Quantitative video sampling of coral reef benthos: large-scale application
,
1995,
Coral Reefs.
[2]
Maricor Soriano,et al.
Classification of coral reef images from underwater video using neural networks.
,
2005,
Optics express.
[3]
R. Kenchington,et al.
Coral reef management handbook
,
1984
.
[4]
E. LeDrew,et al.
Remote sensing of coral reefs and their physical environment.
,
2004,
Marine pollution bulletin.
[5]
Laura David,et al.
Automated benthic counting of living and non-living components in Ngedarrak Reef, Palau via subsurface underwater video
,
2008,
Environmental monitoring and assessment.
[6]
Matti Pietikäinen,et al.
Classification with color and texture: jointly or separately?
,
2004,
Pattern Recognit..
[7]
Matti Pietikäinen,et al.
Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns
,
2002,
IEEE Trans. Pattern Anal. Mach. Intell..
[8]
Subhash C. Bagui,et al.
Combining Pattern Classifiers: Methods and Algorithms
,
2005,
Technometrics.