Automated benthic counting of living and non-living components in Ngedarrak Reef, Palau via subsurface underwater video Ma. Shiela Angeli Marcos & Laura David & Eileen Peñaflor & Victor Ticzon & Maricor Soriano Received: 5 March 2007 / Accepted: 30 October 2007 / Published online: 13 December 2007 # Springer Science + Business Media B.V. 2007 Abstract We introduce an automated benthic count- ing system in application for rapid reef assessment that utilizes computer vision on subsurface underwater reef video. Video acquisition was executed by lowering a submersible bullet-type camera from a motor boat while moving across the reef area. A GPS and echo sounder were linked to the video recorder to record bathymetry and location points. Analysis of living and non-living components was implemented through image color and texture feature extraction from the reef video frames and classification via Linear Discriminant Analysis. Compared to common rapid reef assessment protocols, our system can perform fine scale data acquisition and processing in one day. Reef video was acquired in Ngedarrak Reef, Koror, Republic of Palau. Overall success performance ranges from 60% to 77% for depths of 1 to 3 m. 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. Keywords Coral reef . Subsurface video . Automated benthic counting . Color . Texture . Linear discriminant analysis Introduction Reef assessment is an integral aspect in marine ecological studies that aids in the analysis of commu- nity and ecosystem dynamics of reef organisms. Moreover, a reef's health has direct bearing to the earning capacity of fishers and other coastal indus- tries. Rapid reef surveys can give quick and general estimates of reef conditions before or after an ecological threat such as storms, pollution, or thermal stress (Risk et al. 2001). Multi- or hyperspectral imaging with satellite- or air-borne sensors have allowed large scale appraisals of coral reef specifically in determining the popula- tion of different “benthos” and other reef components (Kutser et al. 2003; Mumby et al. 2004). The resolution however is normally in meters or tens of meters which unfortunately excludes spatial variabil- ity of reef components of finer resolution and thus currently miss out many reef health indicators (e.g. point-bleaching, disease, algal competition). Thus, reef identification algorithms require on-site valida- tion, where common methodologies include visual inspection and underwater video recording. Environ Monit Assess (2008) 145:177–184 DOI 10.1007/s10661-007-0027-2 DO00027; No of Pages M. S. A. Marcos : M. Soriano (*) National Institute of Physics, University of the Philippines, Diliman, Quezon City, Philippines e-mail: msoriano@nip.upd.edu.ph L. David : E. Peñaflor : V. Ticzon Marine Science Institute, University of the Philippines, Diliman, Quezon City, Philippines