ABSTRACT
A method to monitor New Zealand's native bees using image processing technology is presented. Since most species are solitary ground nesting bees the number of active nests within an area can give a good estimate of the population of a community. The number of native bees in flight around plants can also provide valuable information about the overall health of a community and help to quantify their value in the ecosystem as keystone pollinators. On this basis, images of insects in flight have been collected across one season and the results compared with previous results of active nest counts. Open source software FIJI was used to pre-process and classify images. Accuracies were verified using data mining software WEKA. Performance evaluations showed the fast random forest classifier consistently returned fast, accurate results. Fine differences in images were discriminated that were otherwise impossible to identify with the naked eye and even when training data were unevenly distributed the classifier returned accuracies above 98%. The results are promising and while there are few alternatives to traditional methods, image processing for ecology can provide cost effective, standardized tools to help monitor the population and diversity of native bees in New Zealand.
- T. O'Toole, "Those Other Bees: Changing the Funding Culture," in Pollinating Bees - The Conservation Link Between Agriculture and Nature, P. Kevan and V. L. Imperatriz Fonseca, Eds., ed: Ministry of Environment, 2002, pp. 37--40.Google Scholar
- S. Shavit, A. Dafni and G. Ne'eman, "Competition between honeybees (Apis mellifera) and native solitary bees in the Mediterranean region of Israel - Implications for conservation," Israel Journal of Plant Sciences, vol. 57, pp. 171--183, 2009.Google ScholarCross Ref
- Watson and Son. (2008). Manuka has multi-million dollar potential for the Far North. Available: http://www.watsonandson.co.nz/Google Scholar
- D. W. Roubik, "Ups and Downs in Pollinator Populations: When is there a Decline?," Ecology and Society, vol. 5(1), 2001.Google Scholar
- B. J. Donovan, Apoidea, Fauna of New Zealand vol. 57, 2007.Google Scholar
- P. J. D. Weeks and K. J. Gaston, "Image analysis, neural networks, and the taxonomic impediment to biodiversity studies," Biodiversity and Conservation, vol. 6, pp. 263--274, 1997.Google ScholarCross Ref
- S. Schroder, D. Wittmann, W. Drescher, V. Roth, V. Steinhage and A. B. Cremers, "The New Key to Bees: Automated Identification by Image Analysis of Wings," in Pollinating Bees - The Conservation Link Between Agriculture and Nature - Ministry of Environment, ed Brasília: Kevan P & Imperatriz Fonseca VL, 2002, pp. 209--216.Google Scholar
- K. J. Gaston and M. A. O'Neill, "Automated species identification-why not?," Philosophical Transactions of the Royal Society of London, vol. B, pp. 655--667, 2004.Google Scholar
- K. N. Russell, M. T. Do, J. C. Huff, N. I. Platnick and N. MacLeod, "Introducing Spida-Web: Wavelets, Neural Networks and Internet Accessibility in an Image-Based Automated Identification System"," in Automated Taxon Identification in Systematics: Theory, Approaches and Applications, N. MacLeod, Ed., ed: CRC Press, 2008, pp. 131--152.Google Scholar
- N. Nikolaou, P. Sampaziotis, M. Aplikioti, A. Drakos, I. Kirmitzoglou, N. Papamarkos and V. J. Promponas, "VeSTIS: A Versatile Semi- Automatic Taxon Identification System from Digital Images," in Proceedings of the International Congress, ed. Paris, 2010, pp. 231--236.Google Scholar
- M. Mayo and A. T. Watson, "Automatic species identification of live moths," Knowledge-Based Systems, vol. 20, pp. 195--202 2007. Google ScholarDigital Library
- M. Hall, F. Eibe, G. Holmes, B. Pfahringer, P. Reutemann and I. H. Witten, "The WEKA Data Mining Software: An Update," SIGKDD Explorations, vol. 11, pp. 10--18, 2009. Google ScholarDigital Library
- N. H. Hart and L. Huang, "An image based approach to monitor New Zealand native bees," presented at the IEEE Conference on Robotics, Automation and Mechatronics (RAM), Qingdao, China, 2011.Google Scholar
- J. Schindelin, I. Arganda-Carreras, E. Frise, V. Kaynig, M. Longair, T. Pietzsch, S. Preibisch, C. Rueden, S. Saalfeld, B. Schmid, J.-Y. Tinevez, D. J. White, V. Hartenstein, K. Eliceiri, P. Tomancak and A. Cardona, "Fiji: an open-source platform for biological-image analysis," Nature Methods, vol. 9, pp. 676--682, 2012.Google ScholarCross Ref
- L. Breiman, "Random forests," Machine Learning, vol. 45, pp. 5--32, 2001. Google ScholarDigital Library
- P. Johansson, "Small vessel detection in high quality optical satellite imagery -- using component tree image representation and random forest classification," Course TMS106, Statistical Image Analysis, Chalmers University of Technology, Gothenburg, 2011.Google Scholar
- F. Livingston, "Implementation of Breiman's random forest machine learning algorithm," in ECE591Q Machine Learning Conference, 2005.Google Scholar
- C. Strobl, A.-L. Boulesteix, A. Zeileis and T. Hothorn, "Bias in random forest variable importance measures: Illustrations, sources and a solution," BMC Bioinformatics, vol. 8, pp. 1--21, 2007/01/25 2007.Google ScholarCross Ref
- D. J. Flaspohler, "A technique for sampling flying insects," vol. v. 69, no. 2, p. 201--208, 1998.Google Scholar
Index Terms
- Counting insects in flight using image processing techniques
Recommendations
Vehicle Image Classification Using Data Mining Techniques
CSSE '19: Proceedings of the 2nd International Conference on Computer Science and Software EngineeringThis paper focuses on the application of different data mining techniques to classify images of vehicles into three classes using Weka. The dataset used for this study were collected from Google Image search engine and other dataset websites. In ...
Role of IoT, image processing and machine learning techniques in weed detection: a review
Weed is one of the main reasons that cause damage to the crop. While cultivating the crops, many of the farmers are facing problems due to weed growth. The problems are the damage of the crop, the pest and diseases, cultivation cost, environmental ...
Identification and Counting of Brown Planthopper in Paddy Field using Image Processing Techniques
AbstractMassive paddy crops lost every year due to weather condition, plant disease and pest attack. Pest attack is among the main threat that reducing the quality and quantity of the paddy crops. Pesticide is used to control and eliminate the pest in ...
Comments