Submitted to: International Federation of Automatic Control (IFAC) Symposium
Publication Type: Proceedings
Publication Acceptance Date: November 22, 2009
Publication Date: November 2, 2009
Citation: Cui, D., Zhang, Q., Li, M., Hartman, G.L., Bowen, C.R. 2009. Detection of sudden death syndrome using a multispectral imaging sensor [abstract]. International Federation of Automatic Control (IFAC) Symposium. Septemer 10-11, 2009, Champaign, IL. 2009 CD ROM. Technical Abstract: Sudden death syndrome (SDS), caused by the fungus Fusarium solani f. sp. glycines, is a widespread mid- to late-season disease with distinctive foliar symptoms. This paper reported the development of an image analysis based method to detect SDS using a multispectral image sensor. A hue, saturation and intensity color analysis model was formulated as the core of this method. A diagnostic parameter, namely the ratio of infected area RIA, was defined for detecting the existence of SDS infection on a plant. A method of using the frequency distribution of hue values of infected leaf area to measure the severity degree of SDS infection was also developed. Preliminary results obtained from validation tests demonstrated that the developed method could provide a feasible means of detecting SDS in real-time field scouting.