While deep learning-based methods have gained considerable improvements in remote sensing (RS) image change detection (CD), scale variations and pseudochanges hinder most supervised methods' performance. The CD networks derived from other fields can be fronted with false alarms and miss detections in high-resolution RS images due to the weak feature representation ability. In this article, an attention-guided end-to-end change detection network (AGCDetNet) is proposed based on the fully convolutional network and attention mechanism. AGCDetNet learns to enhance the feature representation of change information and achieve accuracy improvements using spatial attention and channel attention. A spatial attention module (SPAM) promotes the discrimination between the changed objects and the background by adding the learned spatial attention to the deep features. Channelwise attention-guided interference filtering unit (CIFU)/atrous spatial pyramid pooling (CG-ASPP) module enhances the representation of multilevel features and multiscale context, respectively. Extensive experiments have been conducted on several public datasets for performance evaluation, including LEVIR-CD, WHU, Season-Varying, WV2, and ZY3. Experiment results demonstrate that AGCDetNet outperforms several state-of-the-art methods of accuracy and robustness. Specifically, AGCDetNet achieves the best F1-score on two datasets, i.e., LEVIR-CD (0.9076) and Season-Varying (0.9654).

Under dynamic conditions, star spots move across the image plane of a star tracker and form a smeared star image. This smearing effect increases errors in star position estimation and degrades attitude accuracy. First, an analytical energy distribution model of a smeared star spot is established based on a line segment spread function because the dynamic imaging process of a star tracker is equivalent to the static imaging process of linear light sources. The proposed model, which has a clear physical meaning, explicitly reflects the key parameters of the imaging process, including incident flux, exposure time, velocity of a star spot in an image plane, and Gaussian radius. Furthermore, an analytical expression of the centroiding error of the smeared star spot is derived using the proposed model. An accurate and comprehensive evaluation of centroiding accuracy is obtained based on the expression. Moreover, analytical solutions of the optimal parameters are derived to achieve the best performance in centroid estimation. Finally, we perform numerical simulations and a night sky experiment to validate the correctness of the dynamic imaging model, the centroiding error expression, and the optimal parameters.

The detection and identification of impact craters on a planetary surface are crucially important for planetary studies and autonomous navigation. Crater detection refers to finding craters in a given image, whereas identification means to actually mapping them to particular reference craters. However, no method is available for simultaneously detecting and identifying craters with sufficient accuracy and robustness. Thus, this study proposes a novel end-to-end fully convolutional neural network (CNN), namely, CraterIDNet, which takes remotely sensed planetary images of any size as input and outputs detected crater positions, apparent diameters, and identification results. CraterIDNet comprises two pipelines, namely, crater detection pipeline (CDP) and crater identification pipeline (CIP). First, we propose a pre-trained model with high generalization performance for transfer learning. Then, anchor scale optimization and anchor density adjustment are proposed for CDP. In addition, multi-scale impact craters are detected simultaneously by using different feature maps with multi-scale receptive fields. These strategies considerably improve the detection performance of small craters. Furthermore, a grid pattern layer is proposed to generate grid patterns with rotation and scale invariance for CIP. The grid pattern integrates the distribution and scale information of nearby craters, which will remarkably improve identification robustness when combined with the CNN framework. We comprehensively evaluate CraterIDNet and present state-of-the-art crater detection and identification performance with a small network architecture (4 MB).

Counting people or objects with significantly varying scales and densities has attracted much interest from the research community and yet it remains an open problem. In this paper, we propose a simple but efficient and effective network, named DENet, which is composed of two components, i.e. , a detection network (DNet) and an encoder-decoder estimation network (ENet). We first run the DNet on the input image to detect and count individuals who can be segmented clearly. Then, the ENet is utilized to estimate the density maps of the remaining areas, typically with low resolution and high densities where individuals cannot be detected. For this purpose, we propose a modified Xception network as the encoder for feature extraction and a combination of dilated convolution and transposed convolution as the decoder. When evaluated on the ShanghaiTech Part A, UCF and WorldExpo’10 datasets, our DENet has achieved lower Mean Absolute Error (MAE) than those of the state-of-the-art methods.

The accuracy of star centroid extraction and identified star number is both crucial features for star sensor precision. Motion blur and fracture are introduced when star sensor works under high dynamic conditions, which affect the accuracy of star centroid extraction and further reduce the precision of the star sensor. To improve the precision of star sensor, this paper proposes a star image restoration algorithm, including blur kernel estimation as well as an accelerated Richardson-Lucy (RL) reconstruction for motion blur star image under high dynamic conditions. First, an improved Radon transform method is presented by introducing a combination of Z-function and double threshold mask that have considerable anti-noise performance. Based on this improved method, the blur kernel of the degraded star image can be obtained by only utilizing a single blurred star image. Furthermore, as the traditional RL is time-consuming, to overcome this shortcoming, an accelerated algorithm based on the second-order vector extrapolation is proposed, offering speedup of 20 times over the original RL and five times over the existing acceleration algorithms. Finally, experiments on simulated as well as real star images demonstrate that the proposed algorithm is effective in improving the dynamic performance of star sensor even under low signal-to-noise ratio conditions, which is of great importance for the further applications of star sensor.

Remote sensing (RS) image change detection (CD) is a critical technique of detecting land surface changes in earth observation. Deep learning (DL)-based approaches have gained popularity and have made remarkable progress in change detection. The recent advances in DL-based methods mainly focus on enhancing the feature representation ability for performance improvement. However, deeper networks incorporated with attention-based or multiscale context-based modules involve a large number of network parameters and require more inference time. In this paper, we first proposed an effective network called 3M-CDNet that requires about 3.12 M parameters for accuracy improvement. Furthermore, a lightweight variant called 1M-CDNet, which only requires about 1.26 M parameters, was proposed for computation efficiency with the limitation of computing power. 3M-CDNet and 1M-CDNet have the same backbone network architecture but different classifiers. Specifically, the application of deformable convolutions (DConv) in the lightweight backbone made the model gain a good geometric transformation modeling capacity for change detection. The two-level feature fusion strategy was applied to improve the feature representation. In addition, the classifier that has a plain design to facilitate the inference speed applied dropout regularization to improve generalization ability. Online data augmentation (DA) was also applied to alleviate overfitting during model training. Extensive experiments have been conducted on several public datasets for performance evaluation. Ablation studies have proved the effectiveness of the core components. Experiment results demonstrate that the proposed networks achieved performance improvements compared with the state-of-the-art methods. Specifically, 3M-CDNet achieved the best F1-score on two datasets, i.e., LEVIR-CD (0.9161) and Season-Varying (0.9749). Compared with existing methods, 1M-CDNet achieved a higher F1-score, i.e., LEVIR-CD (0.9118) and Season-Varying (0.9680). In addition, the runtime of 1M-CDNet is superior to most, which exhibits a better trade-off between accuracy and efficiency.