Optical aerial image partitioning using level sets based on modified Chan–Vese model

We propose an optical aerial image partitioning method using level set evolution for an arbitrary number of regions and embark on the concept of using one level set function for each region in this paper. The proposed method can be viewed as an extension of the Chan–Vese 2-phase segmentation model. Texture features derived from wavelet transform are utilized to characterize each class in the proposed method. Unlike most of the previous works, the curve evolution partial differential equations for different level set equations are decoupled. Each region of class evolves according to its features and interacts with the neighbor regions in order to obtain a partition with regular contours. Generally, the proposed algorithm is easy to implement and appears to converge in fewer iterations. Results are shown on both synthetic and real images.