Recent deep learning methods have achieved promising performance in infrared small target detection (IRSTD) but with high computational cost, limiting deployment or operation on resource-limited scenarios. There is an urgent need to develop both lightweight and high-precision model compression methods. In this paper, we propose a Multi-Directional Contrast Spatial Attention-driven Feature Distillation (DSAD) method for achieving quick and high-performance IRSTD. Specifically, we first extract feature maps from teacher and student networks. Then, a standard Gaussian transformation is adopted to eliminate magnitude effects. After that, a Multi-Directional Contrast Spatial Attention (DSA) is designed to capture multi-directional spatial information from teacher features, which can make student networks pay more attention to small target areas while suppressing background. Finally, we propose a Perceptual Weighted Mean Square Error (PWMSE) distillation loss by combining the DSA with feature discrepancies, guiding student networks to learn more effective information from small target features. Experimental results on the two benchmark datasets (e.g., NUDT-SIRST and NUAA-SIRST) demonstrate that our distillation method can achieve remarkable detection performance compared with the teacher counterparts on several benchmark IRSTD networks (e.g., DNANet, AMFU-Net, and DMFNet) and introduce consistent gains in inference speed (i.e., 2× more) on edge devices (NVIDIA AGX and HUAWEI Ascend-310B).

The rational function model (RFM) is widely used in the most advanced Earth observation satellites, replacing the rigorous imaging model. The RFM method achieves the desired calibration performance when image distortion is caused by long-period errors. However, the calibration performance of the RFM method deteriorates when short-period errors—such as attitude jitter error—are present, and the insufficient and uneven ground control points (GCPs) can also lower the calibration precision of the RFM method. Hence, this paper proposes a geometric calibration method using sparse recovery to remove the linear array push-broom sensor bias. The most important issue regarding this method is that the errors related to the imaging process are approximated to the equivalent bias angles. By using the sparse recovery method, the number and distribution of GCPs needed are greatly reduced. Meanwhile, the proposed method effectively removes short-period errors by recognizing periodic wavy patterns in the first step of the process. The image data from Earth Observing 1 (EO-1) and the Advanced Land Observing Satellite (ALOS) are used as experimental data for the verification of the calibration performance of the proposed method. The experimental results indicate that the proposed method is effective for the sensor calibration of both satellites.

The horizontal alignment design is the result of the designer’s comprehensive consideration of smooth alignment and satisfying multiple design goals such as safety, environmental protection and economy.Through analyzing a large number of highway horizontal design cases,the statistical laws of intersection spacing, declination angle and the relationship between them are introduced. Based on this and the machine learning algorithms, a horizontal basic curve indicator recommendation model suitable for the single intersection design and the double intersection design process is built. Finally, the reliability of the model is verified and evaluated by using the calculation accuracy, test set error and average difference.

Optical satellites with infrared, visible light, multi-spectral and hyper-spectral cameras, are effective means to achieve multi-targets surveillance. In the scenarios of ultra-high data rate and high temporal sensitivity, it is difficult to transmit high-volume data from the satellite to the ground due to the limited satellite-to-ground data transmission link. Therefore, on-orbit computing becomes a superior choice. In this paper, an intelligent heterogeneous system is proposed for on-orbit computing of optical images. Key technologies, including lightweight intelligent processing algorithms, intelligent heterogeneous platforms and distributed computing, are researched aiming at achieving high performance on-orbit computing. Compared with conventional computing, the proposed on-orbit computing system has advantages of low cost, low power consumption, high timeliness and high integration, providing support for the construction of an efficient intelligent space-based optical surveillance system.