Object-based crop classification using multi-temporal SPOT-5 imagery and textural features with a Random Forest classifier

Citation

Zhang, H., Li, Q., Liu, J., Du, X., Dong, T., McNairn, H., Champagne, C., Liu, M., Shang, J. (2018). Object-based crop classification using multi-temporal SPOT-5 imagery and textural features with a Random Forest classifier. Geocarto International, [online] 33(10), 1017-1035. http://dx.doi.org/10.1080/10106049.2017.1333533

Plain language summary

Many methods to classify satellite data for crop type, use a pixel based approach. In this research, pixels were grouped into objects for the purpose of classifying optical satellite data for crop type. As well, the researchers explored a Random Forest classifier in order to identify which optical bands, vegetation indices and textural features from the satellite data, provided the highest accuracies. The results demonstrated that an object-based method, which used spectral reflectance at specific crop growth stages, along with textural features, performed the best.

Abstract

In this study, an object-based image analysis (OBIA) approach was developed to classify field crops using multi-temporal SPOT-5 images with a random forest (RF) classifier. A wide range of features, including the spectral reflectance, vegetation indices (VIs), textural features based on the grey-level co-occurrence matrix (GLCM) and textural features based on geostatistical semivariogram (GST) were extracted for classification, and their performance was evaluated with the RF variable importance measures. Results showed that the best segmentation quality was achieved using the SPOT image acquired in September, with a scale parameter of 40. The spectral reflectance and the GST had a stronger contribution to crop classification than the VIs and GLCM textures. A subset of 60 features was selected using the RF-based feature selection (FS) method, and in this subset, the near-infrared reflectance and the image acquired in August (jointing and heading stages) were found to be the best for crop classification.