A star-identification algorithm aimed at identifying imaged stars in a “lost in space” scene, named the global multi-triangle voting algorithm (GMTV), is presented in this paper. There are two core parts included in the proposed algorithm: in the initial match part, triangle feature units are treated as vote units to find the initial match relationship via matching vote units and counting the vote number of each catalog star. During this step, the principal component analysis (PCA) method is implemented to reduce feature dimensions, and a two-dimension lookup table and fuzzy match strategy are utilized to promote database searching efficiency and noise tolerance. After acquiring the initial match results, a verification part is implemented to filter potential errors from initial candidates by the largest cluster method and output the final identification results. The proposed algorithm achieves a 98.6% identification rate with 2.0 pixels position noise and exhibits more robustness to position noise, magnitude noise, and false stars of different levels than the two reference algorithms used in simulations. In addition, our algorithm’s real-time performance is better than reference algorithms, but it requires a larger database.
Remote sensing image classification (RSIC) is designed to assign specific semantic labels to aerial images, which is significant and fundamental in many applications. In recent years, substantial work has been conducted on RSIC with the help of deep learning models. Even though these models have greatly enhanced the performance of RSIC, the issues of diversity in the same class and similarity between different classes in remote sensing images remain huge challenges for RSIC. To solve these problems, a duplex-hierarchy representation learning (DHRL) method is proposed. The proposed DHRL method aims to explore duplex-hierarchy spaces, including a common space and a label space, to learn discriminative representations for RSIC. The proposed DHRL method consists of three main steps: First, paired images are fed to a pretrained ResNet network for extracting the corresponding features. Second, the extracted features are further explored and mapped into a common space for reducing the intra-class scatter and enlarging the inter-class separation. Third, the obtained representations are used to predict the categories of the input images, and the discrimination loss in the label space is minimized to further promote the learning of discriminative representations. Meanwhile, a confusion score is computed and added to the classification loss for guiding the discriminative representation learning via backpropagation. The comprehensive experimental results show that the proposed method is superior to the existing state-of-the-art methods on two challenging remote sensing image scene datasets, demonstrating that the proposed method is significantly effective.
Blind image deblurring tries to recover a sharp version from a blurred image, where blur kernel is usually unknown. Recently, sparse representation has been successfully applied to estimate the blur kernel. However, the sparse representation has not considered the structure relationships among original pixels. In this paper, a blur kernel estimation method is proposed by introducing the locality constraint into sparse representation framework. Both the sparsity regularization and the locality constraint are incorporated to exploit the structure relationships among pixels. The proposed method was evaluated on a real-world benchmark dataset. Experimental results demonstrate that the proposed method achieve comparable performance to the state-of-the-art methods.