Recently, remote sensing image forgery detection has received widespread attention. To improve the detection accuracy, we build a novel scheme based on Transformer and model fusion. Specifically, we model this task as a binary classification task that focuses on global information. First, we explore the performance of various excellent feature extraction networks in this task under the constructed unified classification framework. On this basis, we select three high-performance Transformer-based networks that focus on global information, namely, Swin Transformer V1, Swin Transformer V2, and Twins, as the backbone networks and fuse them. Secondly, considering the small number of samples, we use the public ImageNet-1K dataset to pre-train the network to learn more stable feature expressions. At the same time, a circular data divide strategy is proposed, which can fully utilize all the samples to improve the accuracy in the competition. Finally, to promote network optimization, on the one hand, we explore multiple loss functions and select label smooth loss, which can reduce the model’s excessive dependence on training data. On the other hand, we construct a combined learning rate optimization strategy that first uses step degeneration and then cosine annealing, which reduces the risk of the network falling into local optima. Extensive experiments show that the proposed scheme has excellent performance. This scheme won seventh place in the “Forgery Detection in Multi-scenario Remote Sensing Images of Typical Objects” track of the 2024 ISPRS TC I contest on Intelligent Interpretation for Multi-modal Remote Sensing Application.

Modeling videos and image sets by linear subspaces has achieved great success in various visual recognition tasks. However, subspaces constructed from visual data are always notoriously embedded in a high-dimensional ambient space, which limits the applicability of existing techniques. This letter explores the possibility of proposing a geometry-aware framework for constructing lower-dimensional subspaces with maximum discriminative power from high-dimensional subspaces in the supervised scenario. In particular, we make use of Riemannian geometry and optimization techniques on matrix manifolds to learn an orthogonal projection, which shows that the learning process can be formulated as an unconstrained optimization problem on a Grassmann manifold. With this natural geometry, any metric on the Grassmann manifold can theoretically be used in our model. Experimental evaluations on several data sets show that our approach results in significantly higher accuracy than other state-of-the-art algorithms.

Geometric transformations of images are the predominant factor, which influences the effectiveness of visual tracking and detection tasks in computer vision. Naturally, although it makes significant sense to grasp the process of image geometric transformations, the numerical relationship of geometric transformations cannot be revealed directly from images themselves. Even if the geometric transformation matrices form the three-dimensional special linear group, Sl(3, ℝ) group, it is difficult to comprehend the manifold of this invisible visual motion, which resides in the high-dimensional space. Furthermore, the main challenge is the deficiency of analytic expressions of the Riemannian logarithmic map to compute the geodesic distance on the Sl(3, ℝ) manifold. Facing these issues, this paper comes up with a novel approach to visualize the geometric transformation in images by presenting a new metric, and then, computes a set of coordinate-vectors in the three-dimensional state transition space for visualization using the Riemannian stress majorization. The superiority of the presented framework for visualization, in terms of accuracy and efficiency, is demonstrated through abundant experiments on aerial images and moving objects.

Passive polarimetric imaging has gained substantial attention over the past three decades in various applications in defense. The complexity of polarimetry modeling and measurement in the thermal infrared exceeds that of the visible and near-infrared due to the complementary polarization orientation of reflected and emitted radiance. This paper presents a comprehensive polarimetric radiance model and a degree of linear polarization (DOLP) model, both of which are specifically tailored for the infrared spectrum, accounting for both reflected and emitted radiance. Building on this foundation, we conduct an analysis and simulation of the DOLP’s variation as the object temperature changes. This analysis enables the observation of relationships that can be strategically utilized in subsequent experiments focused on measuring polarized model parameters. To mitigate the influence of reflected radiance components, the samples are subjected to high temperatures. The observed Stokes images from the sample surfaces are normalized to eliminate the dependence of each Stokes image on temperature. This parameters acquisition measurement method is particularly well-suited for refractories. Finally, the efficacy of the polarized model parameters acquisition technique is demonstrated through experiments involving three distinct refractory materials in the MWIR.