This letter presents a novel local feature descriptor, entitled “Scale-Orientation Robust Infrared Features” (SORIF), specifically designed to be robust to geometric variations, particularly to rotations, while dealing with the non-monotonic intensity variations between images from the visible (VIS) and infrared (IR) spectrum. The method calculates the keypoint’s orientation using phase congruency, rotates the window for alignment, and then extracts texture and edge features using Log-Gabor filters. These features are compiled into a single vector, forming a descriptor that effectively handles texture and maintains consistency across different orientations of the image, showcasing its robustness in addressing geometric issues in remote-sensing images. We evaluated the proposed descriptor using four different data sets, extensively used in previous works and composed of images taken from the visible and infrared spectrum. The experimental results revealed that the proposed descriptor is robust to VIS/IR images’ non-monotonic intensity variations and geometric changes. Moreover, it had a superior matching performance, outperforming some state-of-the-art algorithms.

This letter presents a new local feature descriptor for problems related to multispectral images. Most previous approaches are typically based on descriptors designed to work with images uniquely captured in the visible light spectrum. In contrast, this letter proposes a descriptor termed a multispectral feature descriptor (MFD) that is especially developed, such that it can be employed with image data acquired at different frequencies across the electromagnetic spectrum. The performance of the MFD is evaluated by using three data sets composed of images obtained in visible light and infrared spectra, and its performance is compared with those of state-of-the-art algorithms, such as edge-oriented histogram (EOH) and log-Gabor histogram descriptor (LGHD). The experimental results indicate that the computational efficiency of MFD exceeds those of EOH and LGHD, and that the precision and recall values of MFD are statistically comparable to the corresponding values of the forementioned algorithms.

In this paper, we consider the problem of estimating the spatiotemporal alignment between N unsynchronized video sequences of the same dynamic 3D scene, captured from distinct viewpoints. Unlike most existing methods, which work for N = 2 and rely on a computationally intensive search in the space of temporal alignments, we present a novel approach that reduces the problem for general N to the robust estimation of a single line in IR(N). This line captures all temporal relations between the sequences and can be computed without any prior knowledge of these relations. Considering that the spatial alignment is captured by the parameters of fundamental matrices, an iterative algorithm is used to refine simultaneously the parameters representing the temporal and spatial relations between the sequences. Experimental results with real-world and synthetic sequences show that our method can accurately align the videos even when they have large misalignments (e.g., hundreds of frames), when the problem is seemingly ambiguous (e.g., scenes with roughly periodic motion), and when accurate manual alignment is difficult (e.g., due to slow-moving objects).