To improve the laser cleaning efficiency of Q235 carbon steel, an imaging analysis-based intelligent technique is proposed. Both offline and online computations are designed. Regarding the offline procedure, first, the corrosion images are accumulated to compute the gray-level co-occurrence matrix (GLCM) and the concave-convex region features. Second, different laser cleanings are performed to obtain various cleaned images. Third, a new cleaning performance evaluation method is developed: a metal color difference feature and a dynamic weight dispatch (DWD) corrosion texture are computed. Finally, a particle swarm optimization (PSO)-support vector machine (SVM) is utilized to forecast the laser process parameters. The corresponding laser parameters include power, linear velocity, and line spacing. For the online computation, after the GLCM and the concave-convex region features are computed, an iterative computation is used to tune the process parameters: the random laser parameters are generated constantly, and the iteration is performed and terminated only if the PSO-SVM output is positive. The experimental results have shown that the cleaning efficiency of this method can be improved, and the qualified rate is 92.5%.

Grain security is a fundamental guarantee for social stability and sustainable development. Accurate monitoring and prediction of overall granary temperature are essential for reducing storage losses and improving warehouse management efficiency. As an integrated system, the temperature evolution of the grain pile is deeply affected by its inherent physical structure and heat transfer pathways. Therefore, a multi-level warehouse–surface–line–point (WSLP) structural modeling approach driven by the physical properties of the grain pile is proposed to extract the joint environmental and spatial characteristics. Building upon the WSLP framework, a dual-channel time-series prediction architecture integrating both long short-term memory (LSTM) and iTransformer through a mutual verification fusion mechanism is developed to enable synchronized temperature forecasting across different regions of the grain piles. Experiments are conducted using real granary data from Shandong, China. The results demonstrate that the proposed model achieves more than 30% improvement over baseline methods in terms of MAE and RMSE. Moreover, the WSLP-LSTM–iTransformer framework significantly improves prediction accuracy in complex warehouse environments and enhances the interpretability and applicability of deep learning models for grain condition forecasting by incorporating real environmental characteristics.

Multimodal remote sensing image registration faces severe challenges due to geometric and radiometric differences, particularly between optical and synthetic aperture radar (SAR) images. These inherent disparities make extracting highly repeatable cross-modal feature points difficult. Current methods typically rely on image intensity extreme responses or network regression without keypoint supervision for feature point detection. Moreover, they not only lack explicit keypoint annotations as supervision signals but also fail to establish a clear and consistent definition of what constitutes a reliable feature point in cross-modal scenarios. To overcome this limitation, we propose PLISA—a novel heterogeneous image registration method. PLISA integrates two core components: an automated pseudo-labeling module (APLM) and a pseudo-twin interaction network (PTIF). The APLM introduces an innovative labeling strategy that explicitly defines keypoints as corner points, thereby generating consistent pseudo-labels for dual-modality images and effectively mitigating the instability caused by the absence of supervised keypoint annotations. These pseudo-labels subsequently train the PTIF, which adopts a pseudo-twin architecture incorporating a cross-modal interactive attention (CIA) module to effectively reconcile cross-modal commonalities and distinctive characteristics. Evaluations on the SEN1-2 dataset and OSdataset demonstrate PLISA’s state-of-the-art cross-modal feature point repeatability while maintaining robust registration accuracy across a range of challenging conditions, including rotations, scale variations, and SAR-specific speckle noise.

Sparse point correspondence is a recurring signal-processing problem in sensing systems that reduce measurements to compact point observations, including image-control points, detected landmarks, star centroids, and target candidates. Many pipelines first estimate a global transform and only then infer point identities, an order that can be fragile when observations are sparse, partially overlapping, and contaminated by false or missing detections. This paper proposes Anchor Relative Topology (ART), a correspondence-first method that treats anchor-centered relative point layouts as the primary geometric signal. For each candidate anchor pair, ART removes translation by local centering, searches over a bounded rotation variable, evaluates a kernelized topology-consistency score, and recovers a partial one-to-one assignment with explicit unmatched-point handling. Two practical variants are reported: ART-RH increases the anchor-hypothesis budget to improve anchor recall, whereas ART-AD adapts the kernel width and angular grid from local structure. On a 1944-case synthetic benchmark, ART-RH achieves a mean F1 score of 0.7907, compared with 0.6965 for rigid CPD correspondence. Real sensor-derived protocols further show that ART remains effective on retinal image control points and provides useful identity recovery on telemetry-derived star-point cases under strong partial overlap. In the reported synthetic and real sparse-coordinate protocols, the ART variants achieve higher correspondence F1 than the evaluated classical coordinate-only baselines, while retaining an explicit runtime–accuracy trade-off. These results indicate that anchor-relative topology is useful when exact sparse correspondence identities are more important than a single global transform.