Existing unsupervised image alignment methods exhibit limited accuracy and high computational complexity. To address these challenges, we propose a dense cross-scale image alignment model. It takes into account the correlations between cross-scale features to decrease the alignment difficulty. Our model supports flexible trade-offs between accuracy and efficiency by adjusting the number of scales utilized. Additionally, we introduce a fully spatial correlation module to further improve accuracy while maintaining low computational costs. We incorporate the just noticeable difference to encourage our model to focus on image regions more sensitive to distortions, eliminating noticeable alignment errors. Extensive quantitative and qualitative experiments demonstrate that our method surpasses state-of-the-art approaches.

Drones have been widely used for remote sensing applications. To perform high-quality drone image stitching, this article first proposes a local and global structure-preserving alignment (LGSPA) method that aligns drone images from local dual feature-based and global pixel-based alignment perspectives, while maintaining local linear and global collinear image structures. To enable an optimal image stitching performance, we then propose a seam-adaptive weighting (SAW) scheme to enhance the local alignment accuracy under the guidance of a seam prior. On the ground of LGSPA and SAW, we further develop a seam-adaptive structure-preserving (SASP) image stitching framework to generate the final stitched drone images. Both qualitative and quantitative experimental results demonstrate that LGSPA and SASP are capable of generating higher quality alignment and stitching results than several state-of-the-art methods over multiple challenging aerial scenarios, including low textures, repetitive textures, large parallax, wide baseline, and occlusions.

In automatic parking scenarios, obstacles on both sides of a target parking space (TPS) will degrade the feasibility and comfort of passengers boarding and alighting (CPBA) when the target vehicle maintains a standard final parking state (FPS). Additionally, the presence of dynamic obstacle vehicles (DOV) in the parking lot severely challenges the adaptability of path - planning algorithms. To tackle these issues, this paper presents a method for FPS optimization and two-stage path planning in dynamic scenarios while considering CPBA. First, a CPBA characterization variable is established using the allowed opening angle of the vehicle door (OAVD) restricted by adjacent obstacles. Then, to enhance path quality, the basic motion curve (BMC) of the vehicle is formulated for the design of queuing, parking, and transition paths. A two-stage path planning framework that integrates the parking lot system and the automatic parking system (APS) of the target vehicle is proposed. It includes a Dijkstra algorithm with embedded occupancy dynamic time windows of corridor nodes (DDTW) for queuing path planning and a parking path planning method based on the multi-objective particle swarm optimization (MOPSO) algorithm, aiming to improve CPBA and parking efficiency. Simulation experiments using real-world parking lot and vehicle parameters show that the proposed method can effectively reduce queuing time and enhance comfort, validating its effectiveness. A comparison with other parking path planning methods further demonstrates the superiority of the path performance achieved by the proposed approach.

In image stitching, artifacts caused by misalignment affect the visual quality and the performance of subsequent tasks such as segmentation and detection. This paper proposes SMPR, a reconstruction-based aligned image composition method to minimize artifacts. SMPR fuses images in part of the overlapping areas and reconstructs other portions from single images. Specifically, we propose a seam mask generation method to obtain optimal seam masks that pass through minimal misalignment. During training, we use the seam masks to guide the model in detecting optimal fusion areas. In testing, the model can detect fusion areas without seam masks and reconstruct stitching results. We propose a quantum-inspired local aggregation (QILA) module to improve feature reconstruction performance. We develop an encoder-decoder network with QILA and experiment on a real-world dataset. The experiments show that our method outperforms state-of-the-art methods in both qualitative and quantitative aspects.

Taking advantages of the quaternion representation of the color image, this paper proposes a quaternion perceptual seamline detection model to generate the seamline in the quaternion domain. It considers seamline detection as a quaternion-domain color image labeling problem and minimizes the local-area quaternion perceptual difference cost to obtain the optimal seamline. To assess seamline quality effectively, we develop a quaternion perceptual seamline quality measure. Based on the proposed quaternion perceptual seamline detection model and quality measure, we further propose a general framework for automatic quaternion-domain color image stitching (AQCIS). To the best of our knowledge, this is the first attempt to perform color image stitching completely in the quaternion domain. Meanwhile, AQCIS introduces the joint optimization strategy of local alignment and seamline in an iterative fashion. Extensive experiments on challenging datasets demonstrate that our AQCIS achieves superior performance for color image stitching in comparison with state-of-the-art methods.

The incredible potentiality of reconfigurable intelligent surface (RIS) in addressing power supply and obstacle environment of Internet of Medical Things (IoMT) has been capturing our interest. Considering the nettlesome "double-fading" effect introduced by passive RIS, we investigate an active RIS-enhanced IoMT system in this article, where the wireless power transfer (WPT) from power station (PS) to IoMT devices and the wireless information transfer (WIT) from IoMT devices to the access point (AP) are both implemented with the assistance of active RIS. Aiming to maximize the sum throughput of the considered IoMT system, a joint design of time schedules and reflecting coefficient matrices of the active RIS is proposed. Trapped by the non-convex and obstinate optimization problem, we explore the semi-definite programming (SDP) relaxation and successive convex approximation (SCA) techniques based on alternating optimization (AO) algorithm. Simulation results verify our solution approach to the intractable optimization problem and showcase the boosted spectrum and energy efficiency of the active RIS-enhanced IoMT system.

Color image stitching is a challenging task in real-world applications. This paper first proposes a quaternion rank-1 alignment (QR1A) model for high-precision color image alignment. To solve the optimization problem of QR1A, we develop a nested iterative algorithm under the framework of complex-valued alternating direction method of multipliers. To quantitatively evaluate image stitching performance, we propose a perceptual seam quality (PSQ) measure to calculate misalignments of local regions along the seamline. Using QR1A and PSQ, we further propose an automatic color image stitching (ACIS-QR1A) framework. In this frame-work, the automatic strategy and iterative learning strategy are developed to simultaneously learn the optimal seamline and local alignment. Extensive experiments on challenging datasets demonstrate that the proposed ACIS-QR1A is able to obtain high-quality stitched images under several difficult scenarios including large parallax, low textures, moving objects, large occlusions or/and their combinations.

Face detection and recognition is an important topic in security. Currently, ubiquitous monitoring has received a large amount of attention. This paper proposes a cloud-based ubiquitous monitoring system via face recognition. It consists of a monitoring client module for face detection and recognition and a cloud storage module for data visualization. In the monitoring client module, the center-symmetric local Gabor binary pattern feature extraction method is proposed for face recognition, which combines improved multi-scale Gabor and center-symmetric local binary pattern (CS-LBP) features. This method maintains crucial local features, reduces the Gabor filter complexity, and adds rotational invariance and more precise texture information. A large number of experiments on the ORL, Yale-B, and Yale databases show that the proposed method obtains significantly better recognition rates than the LBP, CS-LBP, and Scale Gabor methods. Furthermore, we propose a Web browser-based data visualization that renders the geographic locations of the face detection and recognition results.