Coffee Crop Recognition Using Multi-scale Convolutional Neural Networks
Identifying crops from remote sensing images is a fundamental to know and monitor land-use. However, manual identification is expensive and maybe impracticable given the amount data. Automatic methods, although interesting, are highly dependent on the quality of extracted features, since encoding the spatial features in an efficient and robust fashion is the key to generating discriminatory models. Even though many visual descriptors have been proposed or successfully used to encode spatial features, in some cases, more specific description are needed. Deep learning has achieved very good results in some tasks, mainly boosted by the feature learning performed which allows the method to extract specific and adaptable visual features depending on the data In this paper, we propose two multi-scale methods, based on deep learning, to identify coffee crops. Specifically, we propose the Cascade Convolutional Neural Networks, or simply CCNN, that identifies crops considering a hierarchy of networks and, also, propose the Iterative Convolutional Neural Network, called ICNN, which feeds a same network with data several times. We conducted a systematic evaluation of the proposed algorithms using a remote sensing dataset. The experiments show that the proposed methods outperform the baseline consistent of state-of-the-art components by a factor that ranges from 3 to 6%, in terms of average accuracy.
KeywordsDeep learning Coffee crop Remote sensing Feature learning
Unable to display preview. Download preview PDF.
- 2.Benediktsson, J., Chanussot, J., Moon, W.: Advances in very-high-resolution remote sensing [scanning the issue] 566–569Google Scholar
- 4.Stehling, R.O., Nascimento, M.A., Falcao, A.X.: A compact and efficient image retrieval approach based on border/interior pixel classification. In: International Conference on Information and Knowledge Management (2002)Google Scholar
- 5.dos Santos, J.A., Faria, F.A., Calumby, R.T., Torres, R.S., Lamparelli, R.A.C.: A genetic programming approach for coffee crop recognition. In: IEEE International Geoscience & Remote Sensing Symposium (2010)Google Scholar
- 6.dos Santos, J.A., Faria, F.A., Torres, R.S., Rocha, A., Gosselin, P.-H., Philipp-Foliguet, S., Falcao, A.: Descriptor correlation analysis for remote sensing image multi-scale classification. In: International Conference on Pattern Recognition, pp. 3078–3081, November 2012Google Scholar
- 8.Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., and Darrell, T.: Caffe: Convolutional architecture for fast feature embedding. arXiv preprint arXiv:1408.5093 (2014)
- 11.Tuia, D., Flamary, R., Courty, N.: Multiclass feature learning for hyperspectral image classification: Sparse and hierarchical solutions. Journal of Photogrammetry and Remote Sensing 0 (2015)Google Scholar
- 12.Vargas, J.E., Saito, P.T., Falcao, A.X., de Rezende, P.J., dos Santos, J.A.: Superpixel-based interactive classification of very high resolution images. In: SIBGRAPI Conference on Graphics, Patterns and Images (2014)Google Scholar