Similar articles

Abstract: Underwater imaging is being used increasingly by marine biologists as a means to assess the abundance of marine resources and their biodiversity. Previously, we developed the first automatic approach for estimating the abundance of Norway lobsters and counting their burrows in video sequences captured using a monochrome camera mounted on trawling gear. In this paper, an alternative framework is proposed and tested using deep-water video sequences acquired via a remotely operated vehicle. The proposed framework consists of four modules: (1) pre-processing, (2) object detection and classification, (3) object-tracking, and (4) quantification. Encouraging results were obtained from available test videos for the automatic video-based abundance estimation in comparison with manual counts by human experts (ground truth). For the available test set, the proposed system achieved 100% precision and recall for lobster counting, and around 83% precision and recall for burrow detection.

深水遥控潜水器影片自动分析在挪威龙虾丰度估算中的应用

[1]Akbani R, Kwek S, Japkowicz N, 2004. Applying support vector machines to imbalanced datasets. Proc 15^th European Conf on Machine Learning, p.39-50.

[2]Badekas E, Papamarkos N, 2005. Automatic evaluation of document binarization results. Proc 10^th Iberoamerican Congress Conf on Progress in Patt Recognition, Image Analysis and Applications, p.1005-1014.

[3]Ben-Hur A, Weston J, 2010. A user’s guide to support vector machines. In: Carugo O, Eisenhaber F (Eds.), Data Mining Techniques for the Life Sciences. Humana Press, New York, p.223-239.

[4]Bernardin K, Stiefelhagen R, 2008. Evaluating multiple object tracking performance: the CLEAR MOT metrics. EURASIP J Image Video Process, 2008:246309.

[5]Bouguet JY, 2000. Pyramidal Implementation of the Lucas Kanade Feature Tracker Description of the Algorithm. Intel Corporation Microprocessor Research Labs, Santa Clara, USA.

[6]Correia PL, Lau PY, Fonseca P, et al., 2007. Underwater video analysis for Norway lobster stock quantification using multiple visual attention features. Proc 15^th European Signal Processing Conf, p.1764-1768.

[7]Denise S, 2007. Homework Helpers: Calculus (Homework Helpers). Career Press, Wayne.

[8]Fonseca P, Correia PL, Campos A, et al., 2008. Fishery-independent estimation of benthic species density—a novel approach applied to Norway lobster Nephrops norvegicus. Mar Ecol Prog Ser, 369:267-271.

[9]Howard FG, 1989. The Norway lobster. Scott Fisher Inform Pamphl, No. 7.

[10]Johnsen S, Sosik H, 2004. Shedding light on light in the ocean. Ocean Mag, bf43(2):1-5.

[11]Kuhn HW, 1955. The Hungarian method for the assignment problem. Nav Res Log Q, 2(1-2):83-97.

[12]Lau PY, Correia PL, Fonseca P, et al., 2008. I2N2: a software for the classification of benthic habitats characteristics. Proc 16^th European Signal Processing Conf, p.1-5.

[13]Lau PY, Correia PL, Fonseca P, et al., 2012. Estimating Norway lobster abundance from deep-water videos: an automatic approach. IET Image Process, 6(1):22-30.

[14]Morello EB, Froglia C, Atkinson RJA, 2007. Underwater television as a fishery-independent method for stock assessment of Norway lobster ( Nephrops norvegicus) in the central Adriatic Sea (Italy). ICES J Mar Sci, 64(6):1116-1123.

[15]Sardà F, Aguzzi J, 2012. A review of burrow counting as an alternative to other typical methods of assessment of Norway lobster populations. Rev Fish Biol Fisher, 22(2):409-422.

[16]Sauvola J, Pietikäinen M, 2000. Adaptive document image binarization. Patt Recogn, 33(2):225-236.

[17]Shafait F, Keysers D, Breuel TM, 2008. Efficient implementation of local adaptive thresholding techniques using integral images. Proc SPIE, 6815:10.

[18]Sooknanan K, Doyle J, Wilson J, et al., 2013. Mosaics for burrow detection in underwater surveillance video. OCEANS, p.1-6.

[19]Struc V, Vesnicer B, Pavesic N, 2008. The phase-based Gabor fisher classifier and its application to face recognition under varying illumination conditions. Proc 2^nd Int Conf on Signal Processing and Communication Systems, p.1-6.

[20]Suzuki S, Be K, 1985. Topological structural analysis of digitized binary images by border following. Comput Vis Graph Image Process, 30(1):32-46.

[21]Tan CS, Lau PY, Low TJ, et al., 2014. Detection of marine species on underwater video images. Int Workshop on Advanced Image Technology, p.192-196.

[22]Tan CS, Lau PY, Correia PL, et al., 2015. A tracking scheme for Norway lobster and burrow abundance estimation in underwater video sequences. Proc Int Workshop on Advanced Image Technology.

[23]Yang CJ, Duraiswami R, Davis L, 2005. Fast multiple object tracking via a hierarchical particle filter. Proc IEEE Int Conf on Computer Vision, p.212-219.