%0 Journal Article %A Su, Jinya %A Liu, Cunjia %A Coombes, Matthew %A Hu, Xiaoping %A Wang, Conghao %A Xu, Xiangming %A Li, Qingdong %A Guo, Lei %A Chen, Wen-Hua %D 2018 %T Wheat yellow rust monitoring by learning from multispectral UAV aerial imagery %U https://repository.lboro.ac.uk/articles/journal_contribution/Wheat_yellow_rust_monitoring_by_learning_from_multispectral_UAV_aerial_imagery/9225737 %2 https://repository.lboro.ac.uk/ndownloader/files/16805258 %K Wheat yellow rust %K Multispectral image %K Spectral vegetation index (SVI) %K Unmanned Aerial Vehicle (UAV) %K Random forest %K Engineering not elsewhere classified %X The use of a low-cost five-band multispectral camera (RedEdge, MicaSense, USA) and a low-altitude airborne platform is investigated for the detection of plant stress caused by yellow rust disease in winter wheat for sustainable agriculture. The research is mainly focused on: (i) determining whether or not healthy and yellow rust infected wheat plants can be discriminated; (ii) selecting spectral band and Spectral Vegetation Index (SVI) with a strong discriminating capability; (iii) developing a low-cost yellow rust monitoring system for use at farmland scales. An experiment was carefully designed by infecting winter wheat with different levels of yellow rust inoculum, where aerial multispectral images under different developmental stages of yellow rust were captured by an Unmanned Aerial Vehicle at an altitude of 16–24m with a ground resolution of 1–1.5cm/pixel. An automated yellow rust detection system is developed by learning (via random forest classifier) from labelled UAV aerial multispectral imagery. Experimental results indicate that: (i) good classification performance (with an average Precision, Recall and Accuracy of 89.2%, 89.4% and 89.3%) was achieved by the developed yellow rust monitoring at a diseased stage (45 days after inoculation); (ii) the top three SVIs for separating healthy and yellow rust infected wheat plants are RVI, NDVI and OSAVI; while the top two spectral bands are NIR and Red. The learnt system was also applied to the whole farmland of interest with a promising monitoring result. It is anticipated that this study by seamlessly integrating low-cost multispectral camera, low-altitude UAV platform and machine learning techniques paves the way for yellow rust monitoring at farmland scales. %I Loughborough University