Abstract
As an intermediate step between raw remote sensing data and digital maps, remote sensing data classification has been a challenging and long-standing problem in the remote sensing research community. In this work, an automated and effective supervised classification framework is presented for classifying high-resolution remote sensing data. Specifically, the presented method proceeds in three main stages: feature extraction, classification, and classified result refinement. In the feature extraction stage, both multispectral images and 3D geometry data are used, which utilizes the complementary information from multisource data. In the classification stage, to tackle the problems associated with too many training samples and take full advantage of the information in the large-scale dataset, a random forest (RF) ensemble learning strategy is proposed by combining several RF classifiers together. Finally, an improved fully connected conditional random field (FCCRF) graph model is employed to derive the contextual information to refine the classification results. Experiments on the ISPRS Semantic Labeling Contest dataset show that the presented 3-stage method achieves 86.9% overall accuracy, which is a new state-of-the-art non-CNN (convolutional neural networks)-based classification method.
Highlights
As one of the most challenging and important problems in the remote sensing community, high-resolution remote sensing data classification is very useful for many applications such as geographical database construction, digital map updating, 3D building reconstruction, land cover mapping and change detection
conditional random field (CRF) can potentially improve the results, we found that some thin-structures may be smoothed out in practice, which is harmful to the classification
In terms of the fully connected conditional random field (FCCRF)-based refinement, as described by Krahenbuhl [57], we found that the kernel parameters w(2) and σγ do not significantly affect the classification accuracy but yield a small visual improvement
Summary
As one of the most challenging and important problems in the remote sensing community, high-resolution remote sensing data classification is very useful for many applications such as geographical database construction, digital map updating, 3D building reconstruction, land cover mapping and change detection. The RF and AdaBoost classifiers can theoretically handle a large-scale dataset, the large memory storage and computational load still hamper their applications to big training datasets To tackle this problem and take full advantage of the information in the large-scale dataset, an RF-based ensemble learning strategy is proposed by combining several RF classifiers together in the present study. Vergara et al [36] derived the optimum fusion rule of N non-independent detectors in terms of the individual probabilities of detection and false alarms and defined the dependence factors This could be a future line of research in the remote sensing community.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
