A wireless Sensor Network that use Image Processing for Vineyard Monitoring

The first step to detect when a vineyard has any type of deficiency, pest or disease is to observe its stems, its grapes and/or its leaves. To place a sensor in each leaf of every vineyard is obviously not feasible in terms of cost and deployment. We should thus look for new methods to detect these symptoms precisely and economically. In this paper, we present a wireless sensor network where each sensor node takes images from the field and internally uses image processing techniques to detect any unusual status in the leaves. This symptom could be caused by a deficiency, pest, disease or other harmful agent. When it is detected, the sensor node sends a message to a sink node through the wireless sensor network in order to notify the problem to the farmer. The wireless sensor uses the IEEE 802.11 a/b/g/n standard, which allows connections from large distances in open air. This paper describes the wireless sensor network design, the wireless sensor deployment, how the node processes the images in order to monitor the vineyard, and the sensor network traffic obtained from a test bed performed in a flat vineyard in Spain. Although the system is not able to distinguish between deficiency, pest, disease or other harmful agents, a symptoms image database and a neuronal network could be added in order learn from the experience and provide an accurate problem diagnosis. © 2011 by the authors; licensee MDPI, Basel, Switzerland.Lloret, J.; Bosch Roig, I.; Sendra Compte, S.; Serrano Cartagena, A. (2011). A wireless Sensor Network that use Image Processing for Vineyard Monitoring. Sensors. 11(6):6165-6196. doi:10.3390/s110606165S61656196116http://news.reseau-concept.net/images/oiv_es/Client/Communique_Stats_Tbilissi_ES.pdfhttp://eur-lex.europa.eu/LexUriServ/LexUriServ.do?uri=CELEX:31968L0193:ES:NOThttp://www.europarl.europa.eu/meetdocs/2009_2014/documents/com/com_com%282010%290359_/com_com%282010%290359_en.pdfhttp://www.legislation.nsw.gov.au/sessionalview/sessional/act/1901-14.pdfhttp://www.legislation.govt.nz/act/public/1993/0095/latest/DLM314623.htmlGubler, W. D., Baumgartner, K., Browne, G. T., Eskalen, A., Latham, S. R., Petit, E., & Bayramian, L. A. (2004). Root diseases of grapevines in California and their control. Australasian Plant Pathology, 33(2), 157. doi:10.1071/ap04019Van den Driessche, R. (1974). Prediction of mineral nutrient status of trees by foliar analysis. The Botanical Review, 40(3), 347-394. doi:10.1007/bf02860066Lloret, J., Garcia, M., Bri, D., & Sendra, S. (2009). A Wireless Sensor Network Deployment for Rural and Forest Fire Detection and Verification. Sensors, 9(11), 8722-8747. doi:10.3390/s91108722Chen, Y.-R., Chao, K., & Kim, M. S. (2002). Machine vision technology for agricultural applications. Computers and Electronics in Agriculture, 36(2-3), 173-191. doi:10.1016/s0168-1699(02)00100-xMacedo-Cruz, A., Pajares, G., Santos, M., & Villegas-Romero, I. (2011). Digital Image Sensor-Based Assessment of the Status of Oat (Avena sativa L.) Crops after Frost Damage. Sensors, 11(6), 6015-6036. doi:10.3390/s110606015Liu, L., Ma, H., & Zhang, X. (2011). Coverage analysis for target localization in camera sensor networks. Wireless Communications and Mobile Computing, 12(14), 1239-1250. doi:10.1002/wcm.1051Lloret, J., Sendra, S., Coll, H., & Garcia, M. (2009). Saving Energy in Wireless Local Area Sensor Networks. The Computer Journal, 53(10), 1658-1673. doi:10.1093/comjnl/bxp112Lloret, J., Garcia, M., Tomás, J., & Boronat, F. (2008). GBP-WAHSN: A Group-Based Protocol for Large Wireless Ad Hoc and Sensor Networks. Journal of Computer Science and Technology, 23(3), 461-480. doi:10.1007/s11390-008-9147-6Recommendation UIT-R P.838-3. Specific Attenuation Model for Rain for Use in Prediction Methodshttp://www.itu.int/rec/R-REC-P.838/en/Recommendation UIT-R PN.837-5. Characteristics of Precipitation for Propagation Modelinghttp://www.itu.int/md/R07-WP3J-C-0014/enAurenhammer, F. (1991). Voronoi diagrams---a survey of a fundamental geometric data structure. ACM Computing Surveys, 23(3), 345-405. doi:10.1145/116873.116880Circular Segment Wikipediahttp://en.wikipedia.org/wiki/Circular_segmentOpenWRT Websitehttp://openwrt.org/Open WRT List of Supported Deviceshttp://wiki.openwrt.org/toh/startAtheros AR7161 Information, Atheros Websitehttp://www.atheros.com/networking/brand.php?brand=4&product=68Hercules Classic Webcam Information in Hercules Websitehttp://www.hercules.com/es/webcam/bdd/p/17/hercules-classic-webcam/QuickCam Information in Logitech Websitehttp://logitech-es-emea.custhelp.com/app/answers/detail/a_id/1253/section/troubleshoot/crid/435/lt_product_id/269/tabs/1,3,2,5/cl/es,es/kw/Creative WebCam NX Pro Information in Creative Websitehttp://en.europe.creative.com/products/productarchive.asp?category=218&subcategory=219&product=628&nav=1&listby=Creative WebCam Instant Information in Creative Websitehttp://es.creative.com/products/productarchive.asp?category=269&subcategory=293&product=10410&nav=1&listby=A4tech PKS-635K information in a4tech websitehttp://www.a4tech.de/?q=node/166Bales, M. R., Forsthoefel, D., Valentine, B., Wills, D. S., & Wills, L. M. (2011). BigBackground-Based Illumination Compensation for Surveillance Video. EURASIP Journal on Image and Video Processing, 2011, 1-22. doi:10.1155/2011/171363Woebbecke, D. M., Meyer, G. E., Von Bargen, K., & Mortensen, D. A. (1993). Plant species identification, size, and enumeration using machine vision techniques on near-binary images. Optics in Agriculture and Forestry. doi:10.1117/12.144030Garcia, M., & Lloret, J. (2009). A Cooperative Group-Based Sensor Network for Environmental Monitoring. Cooperative Design, Visualization, and Engineering, 276-279. doi:10.1007/978-3-642-04265-2_4