Superpixel segmentation integrated feature subset selection for wetland classification over Yellow River Delta

Wetlands are one of the world's most significant and vulnerable ecosystems. The wetlands of the Yellow River Delta are subject to multiple influences of ocean tidal action and the massive sediment deposits of the Yellow River, resulting in a more complex and unstable composition of land cover types. To better distinguish the wetlands in the region, we conducted the classification using an object-oriented combined with feature preference machine learning approach. To alleviate the pretzel phenomenon in pixel-based classification, a superpixel segmentation method using the watershed algorithm with H-minima labeling was used to segment the images at the optimal scale. The best feature subset for classification was filtered using the recursive feature elimination cross-validation approach, which extracts multiple spectral indices from the images. A random forest classifier combining superpixel segmentation and feature selection methods was proposed for the wetland classification. The model improves the classification accuracy of wetlands compared to three classical pixel-based machine learning classification methods. And the overall accuracy was 91.74% and the kappa coefficient was 0.9078, both of which were improved by about 4.53% and 0.0506, respectively, compared with the best-performing random forest classifier in pixel-oriented. The results showed that this method can effectively improve the classification accuracy of the Yellow River Delta wetlands compared with the previous studies.

Automated summary

Wetlands in the Yellow River Delta are important and vulnerable due to tidal action and sediment deposits. A object-oriented approach with feature preference machine learning was used to classify the wetlands. A superpixel segmentation method using the watershed algorithm improved the classification accuracy. The random forest classifier combining superpixel segmentation and feature selection methods outperformed other pixel-based machine learning methods with a 91.74% overall accuracy and a kappa coefficient of 0.9078.