Application of adaptive level set model in cloud image with weak boundary segmentation
Yang Zhipen · Computer Engineering and Applications Journal · 2013
The automatic segmentation of cloud image can't give consideration to both speed and preciseness with just one model because of the changeable shape and fuzzy boundary. A novel adaptive level set method of cloud segmentation is proposed. Energy function would be set automatically based on the degree of variation of each point which is on the closed curve. The convergence rate of closed curve is faster in the obvious boundary area and lower in the weak boundary area with this method. Experimental results for the real cloud images show desirable performance of cloud segmentation with weak boundary and recognition accuracy of cloud point in interesting region.