A Novel Framework for Image Matching and Stitching for Moving Car Inspection under Illumination Challenges.

Vehicle exterior inspection is a critical operation for identifying defects and ensuring the overall safety and integrity of vehicles. Visual-based inspection of moving objects, such as vehicles within dynamic environments abounding with reflections, presents significant challenges, especially when time and accuracy are of paramount importance. Conventional exterior inspections of vehicles require substantial labor, which is both costly and prone to errors. Recent advancements in deep learning have reduced labor work by enabling the use of segmentation algorithms for defect detection and description based on simple RGB camera acquisitions. Nonetheless, these processes struggle with issues of image orientation leading to difficulties in accurately differentiating between detected defects. This results in numerous false positives and additional labor effort. Estimating image poses enables precise localization of vehicle damages within a unified 3D reference system, following initial detections in the 2D imagery. A primary challenge in this field is the extraction of distinctive features and the establishment of accurate correspondences between them, a task that typical image matching techniques struggle to address for highly reflective moving objects. In this study, we introduce an innovative end-to-end pipeline tailored for efficient image matching and stitching, specifically addressing the challenges posed by moving objects in static uncalibrated camera setups. Extracting features from moving objects with strong reflections presents significant difficulties, beyond the capabilities of current image matching algorithms. To tackle this, we introduce a novel filtering scheme that can be applied to every image matching process, provided that the input features are sufficient. A critical aspect of this module involves the exclusion of points located in the background, effectively distinguishing them from points that pertain to the vehicle itself. This is essential for accurate feature extraction and subsequent analysis. Finally, we generate a high-quality image mosaic by employing a series of sequential stereo-rectified pairs.

Estimation of Mueller matrices using non-local means filtering.

This article addresses the estimation of polarization signatures in the Mueller imaging framework by non-local means filtering. This is an extension of previous work dealing with Stokes signatures. The extension is not straightforward because of the gap in complexity between the Mueller framework and the Stokes framework. The estimation procedure relies on the Cholesky decomposition of the coherency matrix, thereby ensuring the physical admissibility of the estimate. We propose an original parameterization of the boundary of the set of Mueller matrices, which makes our approach possible. The proposed method is fully unsupervised. It allows noise removal and the preservation of edges. Applications to synthetic as well as real data are presented.

MRI-based volumetry correlates of autobiographical memory in Alzheimer's disease.

The aim of the present volumetric study was to explore the neuro-anatomical correlates of autobiographical memory loss in Alzheimer's patients and healthy elderly, in terms of the delay of retention, with a particular interest in the medial temporal lobe structures. Fifteen patients in early stages of the disease and 11 matched control subjects were included in the study. To assess autobiographical memory and the effect of the retention delay, a modified version of the Crovitz test was used according to five periods of life. Autobiographical memory deficits were correlated to local atrophy via structural MRI using Voxel Based Morphometry. We used a 'lateralized index' to compare the relative contribution of hippocampal sub-regions (anterior vs posterior, left vs right) according to the different periods of life. Our results confirm the involvement of the hippocampus proper in autobiographical memory retrieval for both recent and very remote encoding periods, with larger aspect for the very remote period on the left side. Contrary to the prominent left-sided involvement for the young adulthood period, the implication of the right hippocampus prevails for the more recent periods and decreases with the remoteness of the memories, which might be associated with the visuo-spatial processing of the memories. Finally, we suggest the existence of a rostrocaudal gradient depending on the retention duration, with left anterior aspects specifically related to retrieval deficits of remote memories from the young adulthood period, whereas posterior aspects would result of simultaneous encoding and/or consolidation and retrieval deficit of more recent memories.

Recovery of polarimetric Stokes images by spatial mixture models.

A Bayesian approach for joint restoration and segmentation of polarization encoded images is presented with emphasis on both physical admissibility and smoothness of the solution. Two distinct models for the sought polarized radiances are used: (i) the polarized light at each site of the image is described by its Stokes vector, which directly follows a mixture of truncated Gaussians, explicitly assigning zero probability to inadmissible configurations and (ii) polarization at each site is represented by the coherency matrix, which is parameterized by a set of variables assumed to be generated by a spatially varying mixture of Gaussians. Application on real and synthetic images using the proposed methods assesses the pertinence of the approach.