Ship detection in remote sensing imagery serves as a cornerstone of modern maritime surveillance. Existing visible light detectors suffer from severe performance degradation in adverse environmental conditions (e.g., fog, low light) due to domain gaps. Traditional global enhancement methods often lack adaptability, leading to “negative transfer”—where artifacts are introduced into clean images or mismatched with degradation types. To address these challenges, we propose CLEAR (Cognitive Large Language Model (LLM)-Empowered Adaptive Restoration) framework. Inspired by the dual-process theory of cognition, we introduce a dynamic switching mechanism between fast perception and deep reasoning. Rather than processing all images indiscriminately, it utilizes a hybrid gating mechanism to efficiently filter nominal samples, triggering Vision–Language Model (VLM) only when necessary to diagnose degradation and dispatch targeted restoration operators. Extensive experiments on the constructed HRSC-Robust dataset demonstrate that CLEAR achieves an overall mean Average Precision (mAP) at 0.5 Intersection-over-Union (IoU) of 86.92%, outperforming the baseline by 7.74%. Notably, it establishes a “fail-safe” mechanism for optical degradations. By adaptively resolving fog and low-light, it effectively mitigates detector blindness—exemplified by a doubled Recall rate (52.52%) in dark scenarios. Furthermore, a confidence-based sparse triggering strategy ensures operational efficiency, maintaining a throughput of ~11.8 FPS in nominal conditions. This work validates the potential of VLMs for interpretable and robust remote sensing tasks.

Automatic Dependent Surveillance-Broadcast (ADS-B) systems provide continuous aircraft position reports for aviation surveillance and short-term trajectory prediction. However, many data-driven predictors directly model the longitude, latitude, and altitude contained in ADS-B messages as generic multivariate time-series variables, which can weaken latitude-dependent displacement, bearing, and local motion relationships during multi-step forecasting. This paper proposes Geometry-Informed Adaptive Time-Series Fusion (GeoATF), a forecasting framework for short-term aircraft trajectory prediction from ADS-B position reports. For multi-route learning, each input window is mapped from global absolute coordinates to a local geodesic chart anchored at the last observation. The predicted local offsets are subsequently decoded into World Geodetic System 1984 (WGS-84) coordinates through great-circle forward navigation. GeoATF combines a patch-based time-series Transformer (PatchTST) temporal branch for modeling historical ADS-B position sequences with a geometric–kinematic branch that constructs great-circle distance, bearing, velocity component, and trajectory change rate features from the same sequence. An adaptive branch weight fusion module then learns horizon-dependent geometric–kinematic branch weights for residual correction. Experiments on 945 ADS-B flights from ten routes demonstrate that GeoATF delivers more accurate multi-horizon trajectory forecasts than the evaluated baselines, with more pronounced advantages at longer forecast horizons. Flight-level statistical analysis supports the robustness of these improvements, while resource evaluation indicates a moderate computational footprint under the common inference protocol. These results suggest that explicitly representing geometric–kinematic information and adaptively fusing it with temporal features can improve short-term aircraft trajectory prediction using only historical ADS-B position data.

Aerial–ground visual tracking facilitates dynamic remote sensing and scene monitoring by integrating complementary observations from unmanned aerial vehicle (UAV) and ground cameras, allowing one view to compensate when the target is poorly observed or temporarily invisible in the other. However, substantial cross-view variations in target appearance, scale, and geometry make it difficult to establish reliable target correspondences and effectively fuse complementary cues. To address these challenges, we propose CVAC-Net, a Cross-View Alignment and Adaptive Collaboration Network for aerial–ground visual tracking. Specifically, CVAC-Net uses cross-view contrastive learning to reduce semantic differences and a learned spatial offset to adjust the relative positions of aerial- and ground-view target features within their normalized search crops. Next, it uses the similarity between the main-view template and the aligned auxiliary-view search features to generate an importance map that reweights redundant and target-irrelevant regions, thereby improving the reliability of feature aggregation. Finally, its view-specific branches select and weight the top-K encoder outputs to integrate complementary cross-view features. Extensive experiments on the UAV–ground visual tracking (UGVT) benchmark show that CVAC-Net improves the baseline by 3.2, 3.1, and 1.7 percentage points in success rate (SR), normalized precision rate (NPR), and precision rate (PR), respectively. We further evaluate CVAC-Net using a two-dimensional (2D) single-object tracking protocol derived from Griffin using its predefined training and validation splits, providing supplementary validation on a simulated aerial–ground distribution.