This item is available under a Creative Commons License for non-commercial use only
Computer Sciences, Information Science, Agriculture
In an era of climate change and global population growth, deep learning based multi-spectral imaging has the potential to significantly assist in production management across a wide range of agricultural and food production domains. A key challenge however in applying state-of-the-art methods is that they, unlike classical hand crafted methods, are usually thought of as being only useful when significant amounts of data are available. In this paper we investigate this hypothesis by examining the performance of state-of-the-art deep learning methods when applied to a restricted data set that is not easily bootstrapped through pre-trained image processing networks. We demonstrate that significant result improvement can be obtained from deep residual networks over a baseline image processing model -- even in the case where data collection is highly expensive and pre-trained networks cannot be easily built upon. Our work also constitutes a useful contribution to understanding the benefit of applying deep image multi-spectral processing techniques to the agri-food domain.
O’Byrne, P., Jackman, P., Berry, D., Franco-Penya, H.-H., French, M., and Ross, R. J. (2019). Multi-spectral visual crop assessment under limited data constraints. Irish Machine Vision and Image Processing Conference 2019, Grangegorman Campus, TU Dublin, 28 - 30 August .