Search

The performance of visual SLAM in complex, real-world scenarios is often compromised by unreliable feature extraction and matching when using handcrafted features. Although deep learning-based local features excel at capturing high-level information and perform well on matching benchmarks, they struggle with generalization in continuous motion scenes, adversely affecting loop detection accuracy. Our system employs a Model-Agnostic Meta-Learning (MAML) strategy to optimize the training of keypoint extraction networks, enhancing their adaptability to diverse environments. Additionally, we introduce a coarse-to-fine feature tracking mechanism for learned keypoints. It begins with a direct method to approximate the relative pose between consecutive frames, followed by a feature matching method for refined pose estimation. To mitigate cumulative positioning errors, DK-SLAM incorporates a novel online learning module that utilizes binary features for loop closure detection. This module dynamically identifies loop nodes within a sequence, ensuring accurate and efficient localization. Experimental evaluations on publicly available datasets demonstrate that DK-SLAM outperforms leading traditional and learning based SLAM systems, such as ORB-SLAM3 and LIFT-SLAM. These results underscore the efficacy and robustness of our DK-SLAM in varied and challenging real-world environments., Comment: In submission

Accurately perceiving location and scene is crucial for autonomous driving and mobile robots. Recent advances in deep learning have made it possible to learn egomotion and depth from monocular images in a self-supervised manner, without requiring highly precise labels to train the networks. However, monocular vision methods suffer from a limitation known as scale-ambiguity, which restricts their application when absolute-scale is necessary. To address this, we propose SelfOdom, a self-supervised dual-network framework that can robustly and consistently learn and generate pose and depth estimates in global scale from monocular images. In particular, we introduce a novel coarse-to-fine training strategy that enables the metric scale to be recovered in a two-stage process. Furthermore, SelfOdom is flexible and can incorporate inertial data with images, which improves its robustness in challenging scenarios, using an attention-based fusion module. Our model excels in both normal and challenging lighting conditions, including difficult night scenes. Extensive experiments on public datasets have demonstrated that SelfOdom outperforms representative traditional and learning-based VO and VIO models., Comment: 14 pages, 8 figures, in submission

Time Varying Functional Connectivity (TVFC) investigates how the interactions among brain regions vary over the course of an fMRI experiment. The transitions between different individual connectivity states can be modulated by changes in underlying physiological mechanisms that drive functional network dynamics, e.g., changes in attention or cognitive effort as measured by pupil dilation. In this paper, we develop a multi-subject Bayesian framework for estimating dynamic functional networks as a function of time-varying exogenous physiological covariates that are simultaneously recorded in each subject during the fMRI experiment. More specifically, we consider a dynamic Gaussian graphical model approach, where a non-homogeneous hidden Markov model is employed to classify the fMRI time series into latent neurological states, borrowing strength over the entire time course of the experiment. The state-transition probabilities are assumed to vary over time and across subjects, as a function of the underlying covariates, allowing for the estimation of recurrent connectivity patterns and the sharing of networks among the subjects. Our modeling approach further assumes sparsity in the network structures, via shrinkage priors. We achieve edge selection in the estimated graph structures, by introducing a multi-comparison procedure for shrinkage-based inferences with Bayesian false discovery rate control. We apply our modeling framework on a resting-state experiment where fMRI data have been collected concurrently with pupillometry measurements, leading us to assess the heterogeneity of the effects of changes in pupil dilation, previously linked to changes in norepinephrine-containing locus coeruleus, on the subjects' propensity to change connectivity states.

The pathology of Alzheimer's disease (AD) and mild cognitive impairment (MCI) is characterized by the presence of beta-amyloid extracellular plaques and neurofibrillary tangles containing hyper-phosphorylated tau. Individuals carrying the apolipoprotein E-e4 (APOE-e4) allele are at increased risk of cognitive decline and developing AD pathology. The development of positron emission tomography (PET) radioligands sensitive to tau neurofibrillary tangles, such as 18F-AV1451, has allowed for visualization and assessment of AD pathology in vivo. The radioligand used in 18F-AV1451 binds with iron in addition to tau neurofibrillary tangles. We employ multimodal neuroimaging analyses, combining iron-sensitive measures from MRI with 18F-AV1451 PET, to examine off-target binding effects in cohorts of 20 APOE-e4 negative, 20 APOE-e4 positive MCI, and 29 control participants. Increased tau pathology, after controlling for tissue susceptibility, was found in the temporal lobe and hippocampus of APOE-e4+ MCI participants as compared to APOE-e4 negative MCI and control participants. Tau pathology in the hippocampus was significantly related to memory, but only in APOE-e4+ participants. Correlations between hippocampal 18F-AV1451 PET uptake and cognitive correlations did not significantly differ when correcting for the influence of iron on 18F-AV1451 PET signal. However, controlling for susceptibility was found to influence correlations between tau-PET uptake and diffusion metrics and the change in this interaction may be due to the influence of iron on diffusivity. Taken together, these results suggest that iron does not need to be accounted for in group comparisons of tau-PET uptake or correlations between cognitive measures and tau-PET SUVR. However, iron should be taken into account in correlations between diffusion measures and tau-PET uptake., Comment: 11 pages, 5 figures, 1 table

The loss of melanized neurons in the substantia nigra pars compacta is a primary feature in Parkinson's disease (PD). Iron deposition occurs in conjunction with this loss. Loss of nigral neurons should remove barriers for diffusion and increase diffusivity of water molecules in regions undergoing this loss. In metrics from single-compartment diffusion tensor imaging models, these changes should manifest as increases in mean diffusivity and the free water compartment as well as and reductions in fractional anisotropy. However, studies examining nigral diffusivity changes from PD with single-compartment models have yielded inconclusive results and emerging evidence in control subjects indicates that iron corrupts diffusivity metrics derived from single-compartment models. Iron-sensitive data and diffusion data were analyzed in two cohorts. The effect of iron on diffusion measures from single- and bi-compartment models was assessed in both cohorts. Measures sensitive to the free water compartment and iron content were found to increase in substantia nigra of the PD group in both cohorts. However, diffusion markers derived from the single-compartment model were not replicated across cohorts. Correlations were seen between single-compartment diffusion measures and iron markers in the discovery cohort and validation cohort but no correlation was observed between a measure from the bi-compartment model related to the free water compartment and iron markers in either cohort. The variability of single-compartment nigral diffusion metrics in PD may be attributed to competing influences of increased iron content, which drives diffusivity down, and increases in the free water compartment, which drives diffusivity up. In contrast to diffusion metrics derived from the single-compartment model, no relationship was seen between iron and the free water compartment in substantia nigra., Comment: Submitted to Brain Communications

Precise geolocalization is crucial for unmanned aerial vehicles (UAVs). However, most current deployed UAVs rely on the global navigation satellite systems (GNSS) or high precision inertial navigation systems (INS) for geolocalization. In this paper, we propose to use a lightweight visual-inertial system with a 2D georeference map to obtain accurate and consecutive geodetic positions for UAVs. The proposed system firstly integrates a micro inertial measurement unit (MIMU) and a monocular camera as odometry to consecutively estimate the navigation states and reconstruct the 3D position of the observed visual features in the local world frame. To obtain the geolocation, the visual features tracked by the odometry are further registered to the 2D georeferenced map. While most conventional methods perform image-level aerial image registration, we propose to align the reconstructed points to the map points in the geodetic frame; this helps to filter out the large portion of outliers and decouples the negative effects from the horizontal angles. The registered points are then used to relocalize the vehicle in the geodetic frame. Finally, a pose graph is deployed to fuse the geolocation from the aerial image registration and the local navigation result from the visual-inertial odometry (VIO) to achieve consecutive and drift-free geolocalization performance. We have validated the proposed method by installing the sensors to a UAV body rigidly and have conducted two flights in different environments with unknown initials. The results show that the proposed method can achieve less than 4m position error in flight at 100m high and less than 9m position error in flight about 300m high.

Introduction: Locus coeruleus (LC) is the primary source of norepinephrine to the brain and its efferent projections innervate many brain regions, including the thalamus. LC degrades with normal aging, but not much is known regarding whether its structural connectivity evolves with age or predicts aspects of cognition. Methods: Here, we use high-resolution diffusion tensor imaging (DTI)-based tractography to examine structural connectivity between LC and the thalamus in younger and older adults. Results: We found LC projections to be bundled in a fiber tract anatomically consistent with the central tegmental tract (CTT) and branch from this tract into the thalamus. The older cohort exhibited a significant reduction in mean and radial diffusivity within CTT as compared to the young cohort. We also observed a significant correlation between CTT mean, axial, and radial diffusivities and memory performance (delayed recall) in the older adult cohort. Discussion: These observations suggest that although LC projections degrade with age, the degree of degradation is associated with cognitive abilities in older adults., Comment: 17 pages, 9 figures, 1 table. Submitted to Brain Connectivity

Background: Approximately forty percent of all dopaminergic neurons in SNpc are located in five dense neuronal clusters, named nigrosomes. T2- or T2*-weighted images are used to delineate the largest nigrosome, named nigrosome-1. In these images, nigrosome-1 is a hyperintense region in the caudal and dorsal portion of the T2- or T2*-weighted substantia nigra. In PD, nigrosome-1 experiences iron accumulation, which leads to a reduction in T2-weighted hyperintensity. Here, we examine neuromelanin-depletion and iron deposition in regions of interest (ROIs) derived from quantitative-voxel based morphometry (qVBM) on neuromelanin-sensitive images and compare the ROIs with nigrosome-1 identified in T2*-weighted images. Methods: Neuromelanin-sensitive and multi-echo gradient echo imaging data were obtained. R2* was calculated from multi-echo gradient echo imaging data. qVBM analysis was performed on neuromelanin-sensitive images and restricted to SNpc. Mean neuromelanin-sensitive contrast and R2* was measured from the resulting qVBM clusters. Nigrosome-1 was segmented in T2*-weighted images of control subjects and its location was compared to the spatial location of the qVBM clusters. Results: Two bilateral clusters emerged from the qVBM analysis. These clusters showed reduced neuromelanin-sensitive contrast and increased mean R2* in PD as compared to controls. Cluster-1 from the qVBM analysis was in a similar spatial location as nigrosome-1, as seen in T2*-weighted images. Conclusion: qVBM cluster-1 shows reduced neuromelanin-sensitive contrast and is in a similar spatial position as nigrosome-1. This region likely corresponds to nigrosome-1 while the second cluster may correspond to nigrosome-2., Comment: 11 pages, 3 figures, 1 table. Submitted to Parkinsonism and Related Disorders