Combining Feature Correspondence with Parametric Chamfer Alignment: Hybrid Two-Stage Registration for Ultra-Widefield Retinal Images

<div>We propose a novel hybrid framework for registering retinal images in the presence of extreme geometric distortions that are commonly encountered in ultra-widefield (UWF) fluorescein angiography. Our approach consists of two stages: a feature-based global registration and a vessel-based local refinement. For the global registration, we introduce a modified RANSAC algorithm that jointly identifies robust matches between feature keypoints in reference and target images and estimates a polynomial geometric transformation consistent with the identified correspondences. Our RANSAC modification particularly improves feature point matching and the registration in peripheral regions that are most severely impacted by the geometric distortions. The second local refinement stage is formulated in our framework as a parametric chamfer alignment for vessel maps obtained using a deep neural network. Because the complete vessel maps contribute to the chamfer alignment, this approach not only improves registration accuracy but also aligns with clinical practice, where vessels are typically a key focus of examinations. We validate the effectiveness of the proposed framework on a new UWF fluorescein angiography (FA) dataset and on the existing narrow-field FIRE (fundus image registration) dataset and demonstrate that it significantly outperforms prior retinal image registration methods. The proposed approach enhances the utility of large sets of longitudinal UWF images by enabling: (a) automatic computation of vessel change metrics and (b) standardized and co-registered examination that can better highlight changes of clinical interest to physicians.</div>

Combining Feature Correspondence with Parametric Chamfer Alignment: Hybrid Two-Stage Registration for Ultra-Widefield Retinal Images

<div>We propose a novel hybrid framework for registering retinal images in the presence of extreme geometric distortions that are commonly encountered in ultra-widefield (UWF) fluorescein angiography. Our approach consists of two stages: a feature-based global registration and a vessel-based local refinement. For the global registration, we introduce a modified RANSAC algorithm that jointly identifies robust matches between feature keypoints in reference and target images and estimates a polynomial geometric transformation consistent with the identified correspondences. Our RANSAC modification particularly improves feature point matching and the registration in peripheral regions that are most severely impacted by the geometric distortions. The second local refinement stage is formulated in our framework as a parametric chamfer alignment for vessel maps obtained using a deep neural network. Because the complete vessel maps contribute to the chamfer alignment, this approach not only improves registration accuracy but also aligns with clinical practice, where vessels are typically a key focus of examinations. We validate the effectiveness of the proposed framework on a new UWF fluorescein angiography (FA) dataset and on the existing narrow-field FIRE (fundus image registration) dataset and demonstrate that it significantly outperforms prior retinal image registration methods. The proposed approach enhances the utility of large sets of longitudinal UWF images by enabling: (a) automatic computation of vessel change metrics and (b) standardized and co-registered examination that can better highlight changes of clinical interest to physicians.</div>

Self-Localization of Mobile Robots Using a Single Catadioptric Camera with Line Feature Extraction

This paper presents a novel self-localization technique for mobile robots using a central catadioptric camera. A unified sphere model for the image projection is derived by the catadioptric camera calibration. The geometric property of the camera projection model is utilized to obtain the intersections of the vertical lines and ground plane in the scene. Different from the conventional stereo vision techniques, the feature points are projected onto a known planar surface, and the plane equation is used for depth computation. The 3D coordinates of the base points on the ground are calculated using the consecutive image frames. The derivation of motion trajectory is then carried out based on the computation of rotation and translation between the robot positions. We develop an algorithm for feature correspondence matching based on the invariability of the structure in the 3D space. The experimental results obtained using the real scene images have demonstrated the feasibility of the proposed method for mobile robot localization applications.

Marker-Less UAV-LiDAR Strip Alignment in Plantation Forests Based on Topological Persistence Analysis of Clustered Canopy Cover

A holistic strategy is established for automated UAV-LiDAR strip adjustment for plantation forests, based on hierarchical density-based clustering analysis of the canopy cover. The method involves three key stages: keypoint extraction, feature similarity and correspondence, and rigid transformation estimation. Initially, the HDBSCAN algorithm is used to cluster the scanned canopy cover, and the keypoints are marked using topological persistence analysis of the individual clusters. Afterward, the feature similarity is calculated by considering the linear and angular relationships between each point and the pointset centroid. The one-to-one feature correspondence is retrieved by solving the assignment problem on the similarity score function using the Kuhn–Munkres algorithm, generating a set of matching pairs. Finally, 3D rigid transformation parameters are determined by permutations over all conceivable pair combinations within the correspondences, whereas the best pair combination is that which yields the maximum count of matched points achieving distance residuals within the specified tolerance. Experimental data covering eighteen subtropical forest plots acquired from the GreenValley and Riegl UAV-LiDAR platforms in two scan modes are used to validate the method. The results are extremely promising for redwood and poplar tree species from both the Velodyne and Riegl UAV-LiDAR datasets. The minimal mean distance residuals of 31 cm and 36 cm are achieved for the coniferous and deciduous plots of the Velodyne data, respectively, whereas their corresponding values are 32 cm and 38 cm for the Riegl plots. Moreover, the method achieves both higher matching percentages and lower mean distance residuals by up to 28% and 14 cm, respectively, compared to the baseline method, except in the case of plots with extremely low tree height. Nevertheless, the mean planimetric distance residual achieved by the proposed method is lower by 13 cm.

Robust Outlier-Adaptive Filtering for Vision-Aided Inertial Navigation

With the advent of unmanned aerial vehicles (UAVs), a major area of interest in the research field of UAVs has been vision-aided inertial navigation systems (V-INS). In the front-end of V-INS, image processing extracts information about the surrounding environment and determines features or points of interest. With the extracted vision data and inertial measurement unit (IMU) dead reckoning, the most widely used algorithm for estimating vehicle and feature states in the back-end of V-INS is an extended Kalman filter (EKF). An important assumption of the EKF is Gaussian white noise. In fact, measurement outliers that arise in various realistic conditions are often non-Gaussian. A lack of compensation for unknown noise parameters often leads to a serious impact on the reliability and robustness of these navigation systems. To compensate for uncertainties of the outliers, we require modified versions of the estimator or the incorporation of other techniques into the filter. The main purpose of this paper is to develop accurate and robust V-INS for UAVs, in particular, those for situations pertaining to such unknown outliers. Feature correspondence in image processing front-end rejects vision outliers, and then a statistic test in filtering back-end detects the remaining outliers of the vision data. For frequent outliers occurrence, variational approximation for Bayesian inference derives a way to compute the optimal noise precision matrices of the measurement outliers. The overall process of outlier removal and adaptation is referred to here as “outlier-adaptive filtering”. Even though almost all approaches of V-INS remove outliers by some method, few researchers have treated outlier adaptation in V-INS in much detail. Here, results from flight datasets validate the improved accuracy of V-INS employing the proposed outlier-adaptive filtering framework.