Abstract
Time series land cover maps play a key role in monitoring the dynamic change of land use. To obtain classification maps with better spatial-temporal consistency and classification accuracy, this study used an algorithm that incorporated information from spatial and temporal neighboring observations in a hidden Markov model (HMM) to improve the time series land cover maps initially produced by a support vector machine (SVM). To investigate the effects of different initial distributions and transition probability matrices on the classification of the HMM, we designed different experimental schemes with different input elements to verify this algorithm with Landsat and HJ satellite images. In addition, we introduced spatial weights into the HMM to make effective use of spatial information. The experimental results showed that the HMM considered that spatial weights could eliminate the vast majority of illogical land cover transition that may occur in previous pixel-wise classification, and that this model had obvious advantages in spatial-temporal consistency and classification accuracy over some existing classification models.
Highlights
The mapping of regional land cover is of great help to local construction and plan [1,2]
To consider the spatial-temporal consistency in the time series land cover mapping, in this study, we proposed a method to incorporate temporal and spatial information from neighboring observations into a hidden Markov model (HMM) to produce land cover maps from time series satellite images simultaneously
Besides the time information of the remote sensing image that was taken into account in the HMM, we further considered the spatial distribution of land cover of each pixel
Summary
The mapping of regional land cover is of great help to local construction and plan [1,2]. How to adapt a new classification strategy that incorporates the spatial-temporal consistency to the production of time series land cover products is very difficult at present. Studies on land cover mapping that consider spatial-temporal land cover change consistency are still limited. Cai & Wang et al, considered “illogical land cover transition” into Maximum A Posterior-Markov Random Field (MAP-MRF) model which was proposed by Kasetkasem et al [14], and improved the MODIS Collection 5 product with the spatial-temporal context information [15,16]. To consider the spatial-temporal consistency in the time series land cover mapping, in this study, we proposed a method to incorporate temporal and spatial information from neighboring observations into a hidden Markov model (HMM) to produce land cover maps from time series satellite images simultaneously. We concluded that the HMM that considered spatial weight had obvious advantages in spatial-temporal consistency and classification accuracy
Sign-in/Register to view highlights & summary 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.
