Imaging with different spectrums often leads to significant nonlinear differences in the intensity. Consequently, automatic matching of the multispectral images is a challenging task. Considering the limitations of using intensity information alone, this paper studies multispectral image matching based on the structure consistency (MMSC). Firstly, the Log-Gabor filter is extended to construct the phase congruency maps, which embody the structural properties of images and provide rich meaningful features. Then, a new algorithm is developed for salient feature point detection by performing nonlinear diffusion on the phase congruency. Those feature points reflect the characteristics of image structure which are illumination and contrast invariant. Finally, structural descriptors are built according to the orientation of the maximum Log-Gabor filter responses, and the matching can be performed by computing the correspondent descriptors. To evaluate the effectiveness of the proposed method, extensive experiments are carried out on three multispectral image datasets. The experimental results show that, the proposed method is not sensitive to the nonlinear intensity variance across spectrums, and outperforms the comparison methods in terms of the number of correct matches and the matching precision.

Frequency domain analysis reveals fundamental image patterns difficult to observe in raw pixel values, while avoiding redundant information in original image processing. Although recent remote sensing foundation models (FMs) have made progress in leveraging spatial and spectral information, they have limitations in fully utilizing frequency characteristics that capture hidden features. Existing FMs that incorporate frequency properties often struggle to maintain connections with the original image content, creating a semantic gap that affects downstream performance. To address these challenges, we propose the All-in-One Spectral-Spatial-Frequency Awareness Foundation Model (Alliance), a framework that effectively integrates information across all three domains. Alliance introduces several key innovations: (1) a progressive frequency decoding mechanism inspired by human visual cognition that minimizes multi-domain information gaps while preserving connections between general image information and frequency characteristics, progressively reconstructing from low to mid to high frequencies to extract patterns difficult to observe in raw pixel values; (2) a triple-domain fusion attention module that separately processes amplitude, phase, and spectral-spatial relationships for comprehensive feature integration; and (3) frequency embedding with frequency-aware Cls token initialization and frequency-specific mask token initialization that achieves fine-grained modeling of different frequency band information. Additionally, to evaluate FMs generalizability, we construct the Yellow River dataset, a large-scale multi-temporal collection that introduces challenging cross-domain tasks and establishes more rigorous standards for FMs assessment. Extensive experiments across six downstream tasks demonstrate Alliance’s superior performance.

Flight line planning is the first step in an aerial photography campaign. Its two key parameters, ground sampling distance (GSD), and overlap should be designed carefully as they will impact subsequent flying workload and even the final mapping accuracy. For a flat terrain region, flight line planning is easy using a traditional method with fixed baseline, flight spacing, and flight altitude. But for a steep terrain region, photo overlap and GSD will change greatly with topography, and thus a flight line planning using the traditional method is not sufficient. This article presents a novel adaptable flight line planning method for frame camera with four application modes. The flight line planning procedure is implemented through rigorous imaging geometry model using digital elevation data, where actual overlap and GSD can be calculated precisely. Using the desired overlap and GSD as constraint conditions, the flight spacing, baseline, and flight altitude can be adjusted adaptively according to ground topography. To assess the effect, a hypothetical test in a rugged terrain region was conducted to compare the project workload, GSD, and overlap of the four modes. The results show that Mode 2, Mode 3, and Mode 4 can realize better overlap with lower workload than the traditional method Mode 1. Mode 3 and Mode 4 have better GSD distribution than Mode 1 and Mode 2. The Mode 3 method was also validated in an actual project, showing a favorable performance in final reality 3D model result.

Aerial optical cameras are the primary method for capturing high-resolution images to produce large-scale mapping products. To improve aerial photography efficiency, multiple cameras are often used in combination to generate large-format virtual central projection images. This paper presents a high-precision method for directly transforming raw images obtained from a dual-camera system mounted at an oblique angle into virtual central projection images, thereby enabling the construction of low-cost, large-format aerial camera systems. The method commences with an adaptive sub-block in the overlapping regions of the raw images to extract evenly distributed feature points, followed by iterative relative orientation to improve accuracy and reliability. A global projection transformation matrix is constructed, and the sigmoid function is employed as a weighted distance function for image stitching. The results demonstrate that the proposed method produces more evenly distributed feature points, higher relative orientation accuracy, and greater reliability. Simulation analysis of image overlap indicates that when the overlap exceeds 7%, stitching accuracy can be better than 1.25 μm. The aerial triangulation results demonstrate that the virtual central projection images satisfy the criteria for the production of 1:1000 scale mapping products.

Small object detection in airborne remote sensing imagery is challenged by tiny target scales, complex backgrounds, and heavy computational demands, thereby limiting real-time deployment on edge devices. To address these issues, we propose ALF-Net, a lightweight and efficient detection network specifically designed for small object detection in airborne remote sensing images. ALF-Net incorporates three key innovations: (1) an Optimized Base Structure (OBS) that preserves high-resolution features to enhance small-object representation; (2) the DualConv-enhanced Cross Stage Partial bottleneck (DC-CSP) that strengthens fine-grained feature extraction without increasing parameter complexity; (3) a plug-and-play Background Separation Enhancement Module (BSEM) with the Bidirectional Gating Attention Module (BGAM) that adaptively suppresses background interference and highlights target features. Experiments on three benchmark datasets—AI-TOD, USOD, and VEDAI—demonstrate the effectiveness of ALF-Net for small object detection under resource constraints. On AI-TOD, ALF-Net achieves a $\bf {mAP}_{0.5}$ of 0.484 and a $\bf {mAP}_{0.5{:}0.95}$ of 0.207, while obtaining small-object $\bf {mAP}_{s}$ of 0.270 (USOD) and 0.462 (VEDAI), respectively. With only 3.07 M parameters and 21.8 GFLOPs, ALF-Net attains a latency of 57.9 ms on an embedded hardware platform (NVIDIA Jetson Xavier NX), significantly outperforming advanced methods such as FFCA-YOLO in efficiency. In addition, evaluations on RS-STOD further corroborate robustness to super-tiny objects; however, on size-balanced scenes (STAR) it may trail heavier DETR/conv detectors, reflecting an explicit accuracy–efficiency trade-off. Overall, ALF-Net achieves a favorable balance between detection accuracy and efficiency, highlighting its strong potential for real-time airborne applications.