It is crucial to enhance the lower contrast Remote sensing images to obtain more details information for further remote sensing image processing and application. In this letter here, a self-adaptive remote sensing image contrast enhancement method has been proposed. The method is an improvement, based on gradient and intensity histogram equalization (GIHE) by using the advantage of histogram compaction transform (HCT). Firstly, we obtained two enhanced images by GIHE and HCT, respectively. Then furthermore, the two enhanced images were normalized with a self-adaptive paremeter, which based on standard deviation and mean of the gradient. Finally and then, we modified the normalized image by dual-gamma function for preserving the local details. It’s evidenced that the proposed method have more richer details and better subjective visual quality, compared with the other methods. The experimental results depicted in terms of PSNR, MAE and Q. Comparing with the other methods, the proposed method had richer details and better subjective visual quality.
Reliable cloud detection plays an important role in the manufacture of remote sensing and the alarm of natural calamities. However, it makes the task difficult with high-resolution remote sensing images with complex background and various types of clouds with different concentration, color and shapes. Related works mostly used gray, shape and texture features to detect clouds, which obtain results with poor robustness and efficiency. To detect cloud more automatically and robustly, we propose a novel could detection method based on the fusion of local optimum by adaptive simple linear iterative clustering (ASLIC) and the whole optimum by bilateral filtering with an improved saliency detection method. After this step, we trained a multi-feature fusion model based support vector machine(SVM) used geometric feature: fractal dimension index (FRAC) and independence index (IDD) which is proposed by us to describe the piece of region’s spatial distribution, texture feature: we use four angles to calculate the gray-level co-occurrence matrix (GLXM) about entropy, energy, contrast, homogeneity, spectral feature(SF): after principal component analysis(PCA) we choose the first bond, the second bond and the near infrared bond(NIR). Besides, in view of the disturbance of water, ice, we also use NDVI and HOT index to estimate the model. Compared to the traditional methods of SLIC, our new method for cloud detection is accurate, and robust when dealing with clouds of different types and sizes over various land satellite images.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.