Landsat data are widely used in various earth observations, but the clouds interfere with the applications of the images. This paper proposes a weighted variational gradient-based fusion method (WVGBF) for high-fidelity thin cloud removal of Landsat images, which is an improvement of the variational gradient-based fusion (VGBF) method. The VGBF method integrates the gradient information from the reference band into visible bands of cloudy image to enable spatial details and remove thin clouds. The VGBF method utilizes the same gradient constraints to the entire image, which causes the color distortion in cloudless areas. In our method, a weight coefficient is introduced into the gradient approximation term to ensure the fidelity of image. The distribution of weight coefficient is related to the cloud thickness map. The map is built on Independence Component Analysis (ICA) by using multi-temporal Landsat images. Quantitatively, we use R value to evaluate the fidelity in the cloudless regions and metric Q to evaluate the clarity in the cloud areas. The experimental results indicate that the proposed method has the better ability to remove thin cloud and achieve high fidelity.
Traditional shadow detection methods are usually detected shadow areas by the single threshold in shadow feature map.
This leads to the detection results susceptible to affect by noise, and some special target (high-bright objects and green
vegetation etc.) susceptible to misdetection. In this paper, a shadow detection method is proposed based on pulse coupled
neural network (PCNN). The model can ignore small differences of pixels values in one area, because the network output
is not only associated with the pixel brightness but also associated with pixel spatial location. Firstly, a new shadow
feature map is build. Then PCNN model is applied to get optimal detection result with max entropy. The experimental
results showed that the proposed model performed better than the single threshold models.