Map Representation Research Articles

Motion planning in complex urban environments: An industrial application on autonomous last‐mile delivery vehicles

AbstractIn this article, a motion planning framework for autonomous driving is explored to achieve unmanned last‐mile delivery vehicle application in complicated urban scenario. This approach can dramatically improve the intelligence, driving safety, driving robustness, and scalability of autonomous vehicles. In this framework, a specific High‐Definition (HD) map representation was proposed for last‐mile delivery applications, and a Route Planning layer generates a kinematically feasible reference line with smoothness condition based on Routing and HD Map components. Then a Scenario Planning layer considers routing results and both static and dynamic obstacles into account to select a corresponding scenario to execute, such as cruise on‐road scenario, cross intersection scenario, parking scenario, and so forth. Finally, a Trajectory Planning layer which is classified with trajectory generation and optimization modules is described. In the trajectory generation part, a rough path–speed profile and corresponding decisions, such as nudge, stop, yield, and so forth, are generated. Then, the rough path–speed profile is postprocessed by optimization algorithms in the trajectory optimization part. On the basis of the real road test results from thousands of times for JD.com's real autonomous delivery vehicle operations and approximate 115,475 km of fully autonomous driving mode in an urban scenario, the proposed motion planning framework demonstrates the efficiency of autonomous driving, improves the driving quality and reduces the manual intervention.

PHOTOGRAMMETRIC TOPOGRAPHIC BASIS OF ARCHAEOLOGICAL SITE

The publication highlights the use of photogrammetry as one of the methods of fixing the topographic base of a site and the creation of the topographic base using a series of photographs. In archaeological science, a qualitatively prepared topographic plan is the basis for combining the results of previous and subsequent works, reconstruction of a realistic model of the site, its micro-relief, a source of accurate measurements of structures and features of the site, and monitoring its current state. There are a number of methods for creating the topo-bases of archaeological sites, starting with the «classic» one using measuring devices (tape measure), a compass, an optical level or theodolite, and ending with high-tech LiDAR technologies.
 One of the methods of creating a topographic base is photogrammetric recording, both on the ground and with the help of low-altitude aerial photography by drone. With the help of a series of photos and their processing in specialized programs, a 3D-model of the object is created.
 The article gives an example of the creation of topo-bases using photogrammetry at two Old Rus hill-forts. The obtained results are compared with the plans of the middle of the 20th century, which were created by researchers by hand. On the basis of the presented orthophoto plans, detailed maps of the heights of both archaeological monuments were created, which became the basis for creating their topographic foundations. For ease of graphic display and perception, heat maps and isolines with markings according to the Baltic system of heights are superimposed on the height maps. Thus, at this stage, ready-made topographic bases of archaeological monuments were created in the following sequence: 1) photogrammetric recording of the area; 2) creation of a 3D-model; 3) creating a photo plan; 4) creating a height map; 5) convenient graphical representation of the topographic map. Topobase serves as a basis for digital recording of archaeological research — both excavations in general and individual objects and each individual find, which allows for spatial analysis of the planning structure, decomposition of objects and material by context and horizons, spatial analysis of the concentration of material in a separate area objects, etc.

Towards real time transient mGT performance assessment: effective prediction using accurate component modelling techniques

In an energy mix driven by renewables, there is a need for small-scale highly efficient and flexible cogeneration units, such as Micro Gas Turbines (mGTs). These mGTs should perform transient operations and work at part-load to meet the power grid requirements. Therefore, full transient characterisation is necessary. One of the most crucial factors is accurately incorporating each component's dynamic behavior. Compressor and Turbine performance maps, although essential, are usually obtained in costly test rigs or CFD simulations. Also, the accurate modelling of the heat exchanger affects the efficiency of the whole cycle. The aim of this work is the development of real time transient mGT model, where we focus in the first step on accurate component modelling. Hence, an effective performance map representation method for mGT's compressor and turbine was developed. Moreover, a Recuperator 1-D numerical model is developed. Those modelling techniques were tested in a MATLAB/SIMULINK model in transient conditions. The fundamental target of this study is to enhance the fidelity of dynamic simulations for small-scale gas turbines. Key parameters like shaft speed and combustor inlet temperature, show deviation from experiments less than 1% which solidifies our aim to establish a general and efficient performance prediction.

Dense Oil Tank Detection and Classification via YOLOX-TR Network in Large-Scale SAR Images

Oil storage tank detection and classification in synthetic aperture radar (SAR) images play a vital role in monitoring energy distribution and consumption. Due to the SAR side-looking imaging geometry and multibouncing scattering mechanism, dense oil tank detection and classification tasks have faced more challenges, such as overlapping, blurred contours, and geometric distortion, especially for small-sized tanks. To address the above issues, this paper proposes YOLOX-TR, an improved YOLOX based on the Transformer encoder and structural reparameterized VGG-like (RepVGG) blocks, to achieve end-to-end oil tank detection and classification in densely arranged areas of large-scale SAR images. Based on YOLOX, the Transformer encoder, a self-attention-based architecture, is integrated to enhance the representation of feature maps and capture the region of interest of oil tanks in densely distributed scenarios. Furthermore, RepVGG blocks are employed to reparameterize the backbone with multibranch typologies to strengthen the distinguishable feature extraction of multi-scale oil tanks without increasing computation in inference time. Eventually, comprehensive experiments based on a Gaofen-3 1 m oil tank dataset (OTD) demonstrated the effectiveness of the Transformer encoder and RepVGG blocks, as well as the performance superiority of YOLOX-TR with a mAP and mAP0.5 of 60.8% and 94.8%, respectively.

SeqPolar: Sequence Matching of Polarized LiDAR Map With HMM for Intelligent Vehicle Localization

3D LiDAR maps are playing a more and more important role in intelligent vehicle localization. In this paper, the proposed SeqPolar localization method consists of two parts. The first part is a novel node-based LiDAR map representation method, termed polarized LiDAR map (PLM), and the second is a map matching algorithm based on a second-order hidden Markov model (HMM2) for vehicle localization. Unlike existing 3D LiDAR map, which is usually constructed by accumulating 3D LiDAR clouds collected at different times, the proposed polarized LiDAR map is generated from a set of nodes. Each node consists of three elements: a polarized LiDAR image, scene features extracted from the polarized LiDAR image, and sensor pose. The polarized LiDAR image encodes 3D coordinates and reflectivities of the 3D LiDAR cloud using a multi-channel image format, a more concise, straightforward, and structured representation of the 3D LiDAR cloud. In the localization step, we propose an HMM2-based method to match a sequence of input polarized images within the map nodes and find the nearest node from the PLM. Afterward, the vehicle is readily localized from the matched map node with 3D registration. The proposed SeqPolar localization method has been validated with the actual field dataset and the public KITTI database. Experimental results demonstrate that the proposed HMM2-based matching method can achieve up to 98% accuracy to find the nearest node from PLM. Moreover, the SeqPolar localization method based on the pre-built PLM can achieve 30-centimeter localization accuracy in average on both test datasets.

Adaptive-Resolution Field Mapping Using Gaussian Process Fusion With Integral Kernels

Unmanned aerial vehicles are rapidly gaining popularity in many environmental monitoring tasks. A prerequisite for their autonomous operation is the ability to perform efficient and accurate mapping online, given limited on-board resources constraining operation time and computational capacity. To address this, we present an online adaptive-resolution approach for field mapping based on Gaussian Process fusion, a strategy in which Bayesian fusion is applied to update a Gaussian Process prior map. A key aspect of our approach is an integral kernel encoding spatial correlation over the areas of grid cells. This enables efficient information compression in uninteresting areas to achieve a compact map representation while maintaining spatial correlations in a theoretically sound fashion. We evaluate the performance of our approach on both synthetic and real-world data. Results show that our method is more efficient in terms of mapping time and memory consumption without compromising on map quality. Further, we integrate our mapping strategy into an adaptive path planning framework to show that it facilitates information gathering efficiency in online settings.

DCPCR: Deep Compressed Point Cloud Registration in Large-Scale Outdoor Environments

Reliable and accurate registration of point clouds is a challenging problem in robotics as well as in the domain of autonomous driving. In this article, we address the task of aligning point clouds with low overlap, containing moving objects, and without prior information about the initial guess. We enhance classical ICP-based registration with neural feature-based matching to reliably find point correspondences. Our novel 3D convolutional and attention-based network is trained in an end-to-end fashion to learn features, which are well suited for matching and for rating the quality of the point correspondences. By utilizing a compression encoder, we can directly operate on a compressed map representation, making our approach well suited for operation under memory constraints. We evaluate our approach on point clouds obtained at completely different points in time, showing that our approach is able to register point clouds even under those challenging conditions reliably.

Convolutional block attention module U-Net: a method to improve attention mechanism and U-Net for remote sensing images

Building extraction from high-resolution remote sensing images is the foundation of many fields, but the existing algorithms cannot extract building details from remote sensing images well because of complex background conditions and the occlusion of interfering objects. To solve the problems of low accuracy and incomplete boundary of traditional building extraction methods, ProCBAM, a parallel attention mechanism based on U-Net network, is adopted and added to the feature transmission step of U-Net. Through the representation of spatial dimension image feature map and channel dimension optimized feature map, we can learn more detailed image information and reduce the error of image recognition. Experiments are carried out on the Massachusetts building dataset, Wuhan University dataset, and IND.v2 dataset, and the experimental results show the effectiveness of this method in building extraction from remote sensing images.

Virtual McKenzie extension exercises for low back and leg pain: a prospective pilot exploratory case series

ABSTRACT Introduction Current evidence supports the inclusion of directional preference exercises for a subgroup of patients with low back (LBP) and leg pain. Recent pain neuroscience strategies have suggested that cortical restructuring associated with movement activating the body map representation in the brain might account for the observed improvement with the directional preference approach. Objectives To explore whether or not a motor imagery directional preference approach would result in any changes in patients with LBP and leg pain. Methods A consecutive convenience sample of patients with LBP and leg pain were recruited at two outpatient physical therapy clinics. Measurements of LBP, leg pain, fear-avoidance beliefs (FABQ), pain catastrophizing (PCS), active lumbar flexion, and straight leg raise (SLR) were compared before and immediately after a virtual (motor imagery) directional preference exercise. Results Statistically significant differences for LBP, FABQ, PCS, active lumbar flexion, and SLR were observed, but only SLR changes met or exceeded the minimally clinically important difference (MCID). Conclusions A brief virtual motor imagery extension treatment yielded some immediate positive shifts in patients presenting to physical therapy with LBP and leg pain. Our results indicate that randomized comparison trials are needed to determine the effect of this intervention on the short- and longer-term outcomes in patients with LBP and leg pain.

Identifying locations susceptible to micro-anatomical reentry using a spatial network representation of atrial fibre maps.

Micro-anatomical reentry has been identified as a potential driver of atrial fibrillation (AF). In this paper, we introduce a novel computational method which aims to identify which atrial regions are most susceptible to micro-reentry. The approach, which considers the structural basis for micro-reentry only, is based on the premise that the accumulation of electrically insulating interstitial fibrosis can be modelled by simulating percolation-like phenomena on spatial networks. Our results suggest that at high coupling, where micro-reentry is rare, the micro-reentrant substrate is highly clustered in areas where the atrial walls are thin and have convex wall morphology, likely facilitating localised treatment via ablation. However, as transverse connections between fibres are removed, mimicking the accumulation of interstitial fibrosis, the substrate becomes less spatially clustered, and the bias to forming in thin, convex regions of the atria is reduced, possibly restricting the efficacy of localised ablation. Comparing our algorithm on image-based models with and without atrial fibre structure, we find that strong longitudinal fibre coupling can suppress the micro-reentrant substrate, whereas regions with disordered fibre orientations have an enhanced risk of micro-reentry. With further development, these methods may be useful for modelling the temporal development of the fibrotic substrate on an individualised basis.

Characteristics and stability of sensorimotor activity driven by isolated-muscle group activation in a human with tetraplegia

Understanding the cortical representations of movements and their stability can shed light on improved brain-machine interface (BMI) approaches to decode these representations without frequent recalibration. Here, we characterize the spatial organization (somatotopy) and stability of the bilateral sensorimotor map of forearm muscles in an incomplete-high spinal-cord injury study participant implanted bilaterally in the primary motor and sensory cortices with Utah microelectrode arrays (MEAs). We built representation maps by recording bilateral multiunit activity (MUA) and surface electromyography (EMG) as the participant executed voluntary contractions of the extensor carpi radialis (ECR), and attempted motions in the flexor carpi radialis (FCR), which was paralytic. To assess stability, we repeatedly mapped and compared left- and right-wrist-extensor-related activity throughout several sessions, comparing somatotopy of active electrodes, as well as neural signals both at the within-electrode (multiunit) and cross-electrode (network) levels. Wrist motions showed significant activation in motor and sensory cortical electrodes. Within electrodes, firing strength stability diminished as the time increased between consecutive measurements (hours within a session, or days across sessions), with higher stability observed in sensory cortex than in motor, and in the contralateral hemisphere than in the ipsilateral. However, we observed no differences at network level, and no evidence of decoding instabilities for wrist EMG, either across timespans of hours or days, or across recording area. While map stability differs between brain area and hemisphere at multiunit/electrode level, these differences are nullified at ensemble level.

Comparison of map metrics as fitness input for assisted seismic history matching

Abstract Assisted seismic history matching (ASHM) is an optimisation problem that incorporates 4D seismic data as a constraint upon a reservoir simulation update. The observed and simulated three-dimensional seismic data is typically reduced to a Cartesian map representation and the misfit between the two is calculated using the mean squared error (MSE). The MSE metric is simple to implement and understand, but it is incapable of capturing the nuances and patterns required to match seismic maps effectively. We test alternative measures of the misfit (metrics) that borrow from image processing and meteorological history matching so that more robust misfit information can be used during optimisation. In this two-part study we first test our metrics on realistic but synthetic one-dimensional problems to understand the metric characteristics, and their sensitivity to noise, better. The introduced metrics are then tested in a realistic ASHM optimisation task. We find that two of our proposed alternatives to MSE are more stable and provide superior results when used for ASHM optimisation.

A Multi-Scale Residential Areas Matching Method Considering Spatial Neighborhood Features

Residential areas is one of the basic geographical elements on the map and an important content of the map representation. Multi-scale residential areas matching refers to the process of identifying and associating entities with the same name in different data sources, which can be widely used in map compilation, data fusion, change detection and update. A matching method considering spatial neighborhood features is proposed to solve the complex matching problem of multi-scale residential areas. The method uses Delaunay triangulation to divide complex matching entities in different scales into closed domains through spatial neighborhood clusters, which can obtain many-to-many matching candidate feature sets. At the same time, the geometric features and topological features of the residential areas are fully considered, and the Relief-F algorithm is used to determine the weight values of different similarity features. Then the similarity and spatial neighborhood similarity of the polygon residential areas are calculated, after which the final matching results are obtained. The experimental results show that the accuracy rate, recall rate and F value of the matching method are all above 90%, which has a high matching accuracy. It can identify a variety of matching relationships and overcome the influence of certain positional deviations on matching results. The proposed method can not only take account of the spatial neighborhood characteristics of residential areas, but also identify complex matching relationships in multi-scale residential areas accurately with a good matching effect.

Functionally specific and sparse domain-based micro-networks in monkey V1 and V2

The cerebral cortices of human and nonhuman primate brains are characterized by submillimeter functional domains. However, little is known about the connections of single functional domains. Here, in macaque monkey visual cortex, we have developed a targeted focal electrical stimulation method, coupled with functional optical imaging, to map cortical networks with submillimeter precision invivo. We find that single functional domains are a part of highly specific and sparse intra-areal and inter-areal micro-networks. Across color-related and orientation-related functionalities, these micro-networks exhibit parallel connection patterns, suggesting a common domain-based architecture. Moreover, these micro-networks shift topographically at a submillimeter scale, suggesting that they serve as a fundamental unit for cortical information processing. Our findings establish a domain-based connectional architecture in the primate brain and present new constraints for cortical map representation.

A Novel Fault Diagnosis Method of Rolling Bearing Based on Integrated Vision Transformer Model.

In order to improve the diagnosis accuracy and generalization of bearing faults, an integrated vision transformer (ViT) model based on wavelet transform and the soft voting method is proposed in this paper. Firstly, the discrete wavelet transform (DWT) was utilized to decompose the vibration signal into the subsignals in the different frequency bands, and then these different subsignals were transformed into a time–frequency representation (TFR) map by the continuous wavelet transform (CWT) method. Secondly, the TFR maps were input with respective to the multiple individual ViT models for preliminary diagnosis analysis. Finally, the final diagnosis decision was obtained by using the soft voting method to fuse all the preliminary diagnosis results. Through multifaceted diagnosis tests of rolling bearings on different datasets, the diagnosis results demonstrate that the proposed integrated ViT model based on the soft voting method can diagnose the different fault categories and fault severities of bearings accurately, and has a higher diagnostic accuracy and generalization ability by comparison analysis with integrated CNN and individual ViT.

The ornithological collection of the Zoological Museum of Babeș-Bolyai University, Cluj-Napoca, Romania - Part 1: the catalogue of bird skin specimens.

This paper reviews the bird skin collection housed in the Zoological Museum of Babeș-Bolyai University, Cluj-Napoca, Romania. The collection includes 925 specimens, belonging to 193 species from 53 families and 20 orders, collected between 1859 and 2021. Due to its historical background and the presence of rare species, it is considered to be one of most important ornithological collections in Eastern Europe. Such a collection can serve as a basis for valuable ornithological studies. Furthermore, a map representation with new distribution data for bird species is provided, which represents a source of information for the status of the avifauna of the Carpathian basin in the 19th and 20th centuries.

Map representation: all the land and sea which is written

Space cannot exist only as a given place where social relations and social processes operate, which would imprison the spatial imagination of literary geography. The absence of the spatial dimension in social theory largely reduces the imagination of geography and the creativity of literature. Literary painting has become a key way of understanding our world, and literature creates a much grander world. Every time we open a nautical chart, we find the lost imperial sailors on the edge of the world, winding up on the voyage. Spatial cognition is an important area of research in cognitive science, and the problem of space is first and foremost a problem of geography, but also an important problem that is being studied in psychology, cartography, information science, computer science, and artificial intelligence, among other disciplines. A map is a planar representation of land territorial possession and maritime territorial possession, and at the same time, a map embodies a transcendent knowledge or a symbol of absolute power. Along with the exploration of new worlds and the reorganization of old societies, we can see that maps are at the same time an expression of language and an expression of emotion while reading the space they bring us.

Görüntüden Görüntüye Dönüşüm Modeli Kullanılarak Derinlik Haritası Girdisiyle Sahne Görseli Üretimi

In recent years, deep learning approach to solve the image and video processing problems have become very popular. Generative Adversarial Networks (GANs) are one of the most popular deep learning-based models. GANs form a generative model utilizing two sub-models, namely, generator and discriminator. The generator tries to generate indistinguishably realistic outputs where the discriminator tires to classify the outputs of the generator as real or fake. These two models work together to achieve a successful generation of realistic outputs. This study aims to reconstruct daytime image of a given depth map data recorded with a camera or a sensor which can capture the depth map data during night time or in a lightless environment. Our model was used for reconstructing the 2D images for a given depth map representation of a known scene. The model was trained with the chess scene from 7-scenes dataset and realistic 2D images were successfully generated for the given input maps.

Neural evidence for age-related deficits in the representation of state spaces.

Under high cognitive demands, older adults tend to resort to simpler, habitual, or model-free decision strategies. This age-related shift in decision behavior has been attributed to deficits in the representation of the cognitive maps, or state spaces, necessary for more complex model-based decision-making. Yet, the neural mechanisms behind this shift remain unclear. In this study, we used a modified 2-stage Markov task in combination with computational modeling and single-trial EEG analyses to establish neural markers of age-related changes in goal-directed decision-making under different demands on the representation of state spaces. Our results reveal that the shift to simpler decision strategies in older adults is due to (i) impairments in the representation of the transition structure of the task and (ii) a diminished signaling of the reward value associated with decision options. In line with the diminished state space hypothesis of human aging, our findings suggest that deficits in goal-directed, model-based behavior in older adults result from impairments in the representation of state spaces of cognitive tasks.

Implementación de mapas coropléticos y algoritmos bioquímicos desde el laboratorio clínico en la valoración del riesgo cardiovascular

Introduction and objectivesTo quantify in selected health areas the prevalence of patients with severe dyslipidemia and their geolocation in order to implement cardiovascular prevention strategies in primary care. MethodsA retrospective cohort study was performed with laboratory data for triglyceride, low-density lipoprotein cholesterol and lipoprotein (a) levels following the incorporation of biochemical algorithms during 2019 and 2020. The existence of geographic clustering clusters by zip codes was studied for each parameter along with choropleth map representation. ResultsThe analytical data included in the study were triglycerides (n = 301069), low density lipoproteins (n = 91316) and lipoprotein to lipoprotein (a) (n = 667). Areas with the highest and lowest percentage of cases were identified for each parameter. Two grouping clusters with statistical significance were detected, one for patients with triglyceride levels > 150 mg/dL of 16.47 km radius and another for patients with low-density lipoprotein-bound cholesterol > 190 mg/dL of 6.23 km, with a relative risk of 1.08 and 1.23 respectively. ConclusionsStudies using geolocation have been widely used in infectious diseases because of the need to know the epidemiology of diseases with a rapid capacity to spread. However, they have not been used as much in other pathologies that occur silently, such as those related to cardiovascular risk. These new tools can help to control severe dyslipidemia and improve cardiovascular prevention in primary care.