Land-cover classification is perhaps one of the most important applications of remote-sensing data. There are limitations with conventional (hard) classification methods because mixed pixels are often abundant in remote-sensing images, and they cannot be appropriately or accurately classified by these methods. This paper presents a new approach in improving the classification performance of remote-sensing applications based on mixed-label analysis (MLA). This MLA model can determine class proportions within a pixel in producing soft classification from remote-sensing data. Simulated images and real data sets are used to illustrate the simplicity and effectiveness of this proposed approach. Classification accuracy achieved by MLA is compared with other conventional methods such as linear spectral mixture models, maximum likelihood, minimum distance, and artificial neural networks. Experiments have demonstrated that this new method can generate more accurate land-cover maps, even in the presence of uncertainties in the form of mixed pixels.
展开▼
