Search

Localization based on single-line lidar is widely used in various robotics applications, such as warehousing, service, transit, and construction, due to its high accuracy, cost-effectiveness, and minimal computational requirements. However, challenges such as LiDAR degeneration and frequent map changes persist in hindering its broader adoption. To address these challenges, we introduce the Contribution Sampling and Map-Updating Localization (CSMUL) algorithm, which incorporates weighted contribution sampling and dynamic map-updating methods for robustness enhancement. The weighted contribution sampling method assigns weights to each map point based on the constraints within degenerate environments, significantly improving localization robustness under such conditions. Concurrently, the algorithm detects and updates anomalies in the map in real time, addressing issues related to localization drift and failure when the map changes. The experimental results from real-world deployments demonstrate that our CSMUL algorithm achieves enhanced robustness and superior accuracy in both degenerate scenarios and dynamic map conditions. Additionally, it facilitates real-time map adjustments and ensures continuous positioning, catering to the needs of dynamic environments. [ABSTRACT FROM AUTHOR]

Localization based on single-line lidar is widely used in various robotics applications, such as warehousing, service, transit, and construction, due to its high accuracy, cost-effectiveness, and minimal computational requirements. However, challenges such as LiDAR degeneration and frequent map changes persist in hindering its broader adoption. To address these challenges, we introduce the Contribution Sampling and Map-Updating Localization (CSMUL) algorithm, which incorporates weighted contribution sampling and dynamic map-updating methods for robustness enhancement. The weighted contribution sampling method assigns weights to each map point based on the constraints within degenerate environments, significantly improving localization robustness under such conditions. Concurrently, the algorithm detects and updates anomalies in the map in real time, addressing issues related to localization drift and failure when the map changes. The experimental results from real-world deployments demonstrate that our CSMUL algorithm achieves enhanced robustness and superior accuracy in both degenerate scenarios and dynamic map conditions. Additionally, it facilitates real-time map adjustments and ensures continuous positioning, catering to the needs of dynamic environments.

An analysis of the soil cover of Russia as presented on the soil map on a scale of 1 : 2.5 M with the use of a new substantive-genetic soil classification system has been performed at the level of soil orders. The high level of classification-based generalization makes it possible to assess the most general patterns of soil geography and soil resources and to identify changes that have occurred as a result of renaming of each polygon on the map with the use of the new classification. The areas occupied by soil orders have been calculated. In total, there are 24 soil orders on the new map, including 21 orders of natural soils and 3 orders (agrozems, turfzems, stratozems) of anthropogenically transformed soils. Soils of the orders of agro-abrazems, chernozems, and turbozems are not presented on the map. As on most small-scale soil maps of Russia, the zonal regularities of the soil cover in the East European Plain and high lithogenic mosaicity in Central and Eastern Siberia are clearly seen. The new map includes soil orders that were absent on the initial map: cryozems, cryometamorphic and hydrometamorphic soils, lithozems, cryoabrazems, cryoturbozems, urbostratozems, and organo-accumulative soils. Soils characteristic of humid conditions predominate: Al-Fe-humus soils (Podzols) (319.2 M ha, or 19% of the land fund of Russia), gley soils (Gleysols) (223.9 M ha, 13%), texture-differentiated soils (Luvisols and Regosols) (190.8 M ha, 11%), and peat soils (Histosols) (143.5 M ha, 8%) and occupy more than a half of the territory of Russia. The area of humus-accumulative soils most suitable for arable use is 103.6 M ha (6%). Considerable areas are occupied by soils of the orders of cryozems (Turbic Cryosols) (111.4 M ha), iron-metamorphic soils (Chromic Cambisols) (92.7 M ha), structure-metamorphic soils (Cambisols) (47.3 M ha), pale-metamorphic soils (Cambic Cryosols) (12.8 M ha), hydrometamorphic soils (Calcic Gleysols) (4.3 M ha), and cryometamorphic soils (Cambisols Gelic) (3.4 M ha), which corresponds to the vast continental territory of Russia with balanced moisture conditions. Separate place belongs to the soils with strict limitations for use (lithosols (Leptosols), weakly developed soils (Regosols, Nudilithic Leptosols)) but playing important biospheric functions and requiring special protection.

High-definition digital map is the foundation of autonomous driving technology, which provides precise location information for autonomous vehicles. However, with the change of environment and the passage of time, the fidelity performance of unstructured road map will gradually decline. Therefore, this paper proposes a digital map updating method of open-pit mine based on vehicle-cloud collaboration to effectively improve the efficiency of map updating. Firstly, a three-layer map model structure is constructed to ensure the integrity of map updating of open-pit mine. Then, a track-based map updating method is proposed for many scenarios of open-pit mines. Meanwhile, a map updating framework based on vehicle-cloud collaboration is designed to improve the efficiency of automatic driving map updating in open-pit mines. Experimental results show that this method can effectively reduce the map updating delay. Compared with the single-vehicle mode, the average map updating delay is reduced by 75%. At the same time, the relative error of map updating is reduced, and the overall accuracy is increased by 10%, which meets the requirements of map fidelity.

ABSTRACTThe earth surface changes continuously due to the natural causes and ‎human activities. New generations of satellite sensors, such as WorldView and ‎GeoEye, provide new data to better delineate, track and visualise changes in land ‎cover. A number of classes are used in the satellite images. All artefacts with ‎elevations greater than the ground surface (buildings in particular) may appear in ‎a wrong location. The correction of buildings position is an important task for ‎mapping applications. The main aim of this study is to introduce a change ‎detection approach using very high resolution satellite images (VHR) for map ‎updating. In this approach, an approximated method for building relief ‎displacement correction was developed.‎In this paper, image preprocessing was carried out and information content ‎of the satellite image was evaluated. Then change detection between GeoEye-1 ‎image and Sohag map was carried out using post-classification comparison ‎technique. After that the change map result was divided into two classes: building ‎and non-building. All objects were transformed from raster to vector format. For ‎building objects, the height was estimated. A python code was written to calculate ‎relief displacement using buildings height and shadow length. The vector layer ‎was added to update the reference map. The results showed the ability of very ‎high-resolution satellites images for updating large scale maps in Egypt. Also, the ‎approximated method for building relief displacement correction is a promising ‎method. It has RMSE accuracy of 0.95m.‎

Urban land cover classification using Very High Resolution (VHR) satellite images is a very important source of information for map updating. Egyptian environment has more challenges in feature extraction. The main problem lies in the spectral similarity between different land cover classes. Also, great diversity in sizes, shapes, and materials of each class. The main aim of this work is to represent a new automatic indices-based classification method for map updating using VHR satellite images. The method uses a set of spectral indices with their thresholds in consecutive order, chosen based on WorldView-2 (WV-2) bands, to classify land cover in the Egyptian environment. For this study, WV-2 satellite images with eight spectral bands were used. The proposed method is compared with five traditional classification methods; Minimum distance, Spectral angle mapper, Mahalanobis distance, Spectral correlation mapper, and Maximum likelihood method, which included in ERDAS 2015 software, for validation purpose and checking its stability. The results show that the extracted features with the proposed method can contribute significantly to update Egyptian medium scale maps. The average overall accuracy achieved with the proposed approach (75.31%) is higher than those obtained using Minimum distance (54.0%), Spectral angle mapper (69.50%), and Mahalanobis distance (73.63%). Also, it is near to those obtained by the Spectral correlation mapper (76.50%), and Maximum likelihood method (78.25%).

Robust building detection from satellite images has been a subject of interest for several decades. Very High Resolution (VHR) satellite images support the efficient extraction of manmade objects. The main aim of this paper is to present an approach for building extraction from VHR satellite images for map updating in Egypt. To achieve this aim, a comparison of pixel and object-based classification techniques has been applied. Then, different refinement processes based on shadow, context, shape, and Digital Surface Model (DSM) data are carried out. Two study areas from the VHR satellite images for Assuit and Sohag cities are used. A comparison of the classification techniques shows that the Maximum Likelihood Classifier (MLC) for pixel-based technique and Support Vector Machine (SVM) for object-based technique give the highest overall accuracy results. Refinement based on shadow, context, shape, and DSM information improves the overall accuracy with an average of 18%. Thus, the building extraction results can contribute significantly to update maps in Egypt.

This paper illustrates a land consumption map for Italy (year 2017) at a scale 1:1,300,000, and the assessment of its changes (2012–2017). We define land consumption as the replacement of a non-artificial land cover to an artificial land cover, both permanent and no-permanent. The maps are a 10 m spatial resolution raster, produced by photointerpretation of very high resolution images and semiautomatic classification of high resolution remote sensing images. An overall accuracy of 97.7% for the map of 2012 and of 99.66% for the map of 2017 was obtained. The results suggest that the method proposed is appropriate to detect land consumption, both for the urban densification and for the sprawling phenomena, from national to local level. Furthermore, because of the high spatial resolution and the classification scheme adopted, it is suitable for an effective monitoring system, compared to other existing classification systems or monitoring programs.

The earth surface changes continuously due to natural causes and human activities. New generations of satellite sensors, such as WorldView and GeoEye, provide new data to better delineate, track, and visualize changes in land cover. Several classes are used in the satellite images. All artifacts with elevations greater than the ground surface (buildings in particular) may appear in the wrong location. The correction of buildings position is an important task for mapping applications. The main aim of this study is to introduce a change detection approach using very high-resolution satellite images (VHR) for map updating. In this approach, an approximated method for building relief displacement correction was developed. In this paper, image preprocessing was carried out and the information content of the satellite image was evaluated. Then change detection between GeoEye-1 image and Sohag map was carried out using post-classification comparison technique. After that, the change map result was divided into two classes: building and non-building. All objects were transformed from raster to vector format. For building objects, the height was estimated. A python code was written to calculate relief displacement using buildings' height and shadow length. The vector layer was added to update the reference map. The results showed the ability of very high-resolution satellite images for updating large-scale maps in Egypt. Also, the approximated method for building relief displacement correction is a promising method. It has RMSE accuracy of 0.95m. [ABSTRACT FROM AUTHOR]

Urban areas are changing rapidly. In order to document the urban realities in topographic databases and geographic information systems efficient methods are required. Vector data of buildings are of special importance. A methodology for an automated generation of cartographically enhanced data is presented and applied to two test sites at Vaihingen, Germany. The steps of the workflow are described in detail. The examples use imagery of a large-format aerial camera to map different types of buildings. First, land cover maps are generated by means of supervised classification using two sets of attributes (basic attributes and attribute profile, basic attributes and dispersion). After the enhancement of the extracted buildings their outlines have straight, orthogonal, and parallel line segments created by least squares adjustment. The assessment of the geometric accuracy used 264 well-defined building corners and two types of references (land cover map, ortho-image). The obtained average standard deviation of the coordinates was σx,y = 1.0 m. The additional use of an attribute profile did not improve upon the geometric accuracy that was obtained by means of five attributes (height above ground, normalized difference vegetation index, standard deviation of the elevations in the 5 × 5 pixels window, intensity value of the near-infrared band, and standard deviation of intensities in the 5 × 5 surrounding at a pixel of the near-infrared band). The experiences with the developed software reveal that a graphical output of intermediate results is helpful to obtain complete and reliable results at complex building structures.

Urban land cover classification using Very High Resolution (VHR) satellite images is a very important source of information for map updating. Egyptian environment has more challenges in feature extraction. The main problem lies in the spectral similarity between different land cover classes. Also, great diversity in sizes, shapes, and materials of each class. The main aim of this work is to represent a new automatic indices-based classification method for map updating using VHR satellite images. The method uses a set of spectral indices with their thresholds in consecutive order, chosen based on WorldView-2 (WV-2) bands, to classify land cover in the Egyptian environment. For this study, WV-2 satellite images with eight spectral bands were used. The proposed method is compared with five traditional classification methods; Minimum distance, Spectral angle mapper, Mahalanobis distance, Spectral correlation mapper, and Maximum likelihood method, which included in ERDAS 2015 software, for validation purpose and checking its stability. The results show that the extracted features with the proposed method can contribute significantly to update Egyptian medium scale maps. The average overall accuracy achieved with the proposed approach (75.31%) is higher than those obtained using Minimum distance (54.0%), Spectral angle mapper (69.50%), and Mahalanobis distance (73.63%). Also, it is near to those obtained by the Spectral correlation mapper (76.50%), and Maximum likelihood method (78.25%). [ABSTRACT FROM AUTHOR]

Robust building detection from satellite images has been a subject of interest for several decades. Very High Resolution (VHR) satellite images support the efficient extraction of manmade objects. The main aim of this paper is to present an approach for building extraction from VHR satellite images for map updating in Egypt. To achieve this aim, a comparison of pixel and object-based classification techniques has been applied. Then, different refinement processes based on shadow, context, shape, and Digital Surface Model (DSM) data are carried out. Two study areas from the VHR satellite images for Assuit and Sohag cities are used. A comparison of the classification techniques shows that the Maximum Likelihood Classifier (MLC) for pixel-based technique and Support Vector Machine (SVM) for object-based technique give the highest overall accuracy results. Refinement based on shadow, context, shape, and DSM information improves the overall accuracy with an average of 18%. Thus, the building extraction results can contribute significantly to update maps in Egypt. [ABSTRACT FROM AUTHOR]

This paper illustrates a land consumption map for Italy (year 2017) at a scale 1:1,300,000, and the assessment of its changes (2012–2017). We define land consumption as the replacement of a non-artificial land cover to an artificial land cover, both permanent and no-permanent. The maps are a 10 m spatial resolution raster, produced by photointerpretation of very high resolution images and semiautomatic classification of high resolution remote sensing images. An overall accuracy of 97.7% for the map of 2012 and of 99.66% for the map of 2017 was obtained. The results suggest that the method proposed is appropriate to detect land consumption, both for the urban densification and for the sprawling phenomena, from national to local level. Furthermore, because of the high spatial resolution and the classification scheme adopted, it is suitable for an effective monitoring system, compared to other existing classification systems or monitoring programs. [ABSTRACT FROM AUTHOR]

Vegetation and water bodies are a fundamental element of urban ecosystems, and water mapping is critical for urban and landscape planning and management. A methodology of automated recognition of vegetation and water bodies on the territory of megacities in satellite images of sub-meter spatial resolution of the visible and IR bands is proposed. By processing multispectral images from the satellite SuperView-1A, vector layers of recognized plant and water objects were obtained. Analysis of the results of image processing showed a sufficiently high accuracy of the delineation of the boundaries of recognized objects and a good separation of classes. The developed methodology provides a significant increase of the efficiency and reliability of updating maps of large cities while reducing financial costs. Due to the high degree of automation, the proposed methodology can be implemented in the form of a geo-information web service functioning in the interests of a wide range of public services and commercial institutions. [ABSTRACT FROM AUTHOR]

Supervised classification of remotely sensed images is a classical method for change detection. The task requires training data in the form of image data with known class labels, whose manually generation is time-consuming. If the labels are acquired from the outdated map, the classifier must cope with errors in the training data. These errors, referred to as label noise, typically occur in clusters in object space, because they are caused by land cover changes over time. In this paper we adapt a label noise tolerant training technique for classification, so that the fact that changes affect larger clusters of pixels is considered. We also integrate the existing map into an iterative classification procedure to act as a prior in regions which are likely to contain changes. Our experiments are based on three test areas, using real images with simulated existing databases. Our results show that this method helps to distinguish between real changes over time and false detections caused by misclassification and thus improves the accuracy of the classification results. [ABSTRACT FROM AUTHOR]

To overcome the weakness of modelling the relationships between map objects that represent the same geographic entities or phenomena at different times and scales, an agent-based approach is presented to modelling of the spatial evolution of map objects for better understanding of the evolutional process of different maps. Map agents are used to establish and manage the many-to-many corresponding relationships between map objects, and they render map objects active rather than traditionally passive. The evolutions of map objects are modelled by map agents using association and generation relationships to model the connectivity between map objects. This effort reduces the workload of multi-scale map updating by avoiding update of the entire map; instead, it simply allows map agents to detect, perceive and choose suitable behaviours on which to operate and update a spatially evolving object. Experiments of specific examples are presented to demonstrate the feasibility and the effectiveness of our approach. [ABSTRACT FROM PUBLISHER]

Spatial data of cartographic bases are often used for nautical and aeronautical charts, reference maps, or other thematic maps. Traditionally, such spatial data sets of different scales are created apart from each other, are stored in different databases, and, in many cases, have no relations. This makes the update of the spatial data a complex and costly task. Meanwhile, automatic detection of changes in spatial data, when older versions of data are compared to more recent version of data, saves time in this process. To model such a process, two major tasks are solved, namely, detection of a change in spatial data and identification of its significance to answer whether the change detected is significant enough that an update of the data will be effective. The model also takes into account the requirements for spatial data, the scale of the data, and update methods.

High and accelerating rate of the urban changes and extensions, in developing countries such as Egypt, calls for an efficient and fast technique for mapping. The availability of the new generation commercial one-meter resolution satellite images has opened a new era for producing and updating large-scale digital maps. The main objective of this study is to evaluate the potential of VHR satellite images for large scale mapping in Egypt. Data used in this study are IKONOS-2 images (Panchromatic (1m) and Multispectral (4m)) acquired on 2006 and topographic map dated 2002 at scale 1:5000 of Assiut area. In this paper, an investigation is carried out for the potential of the information content in pan- sharpened IKONOS image. Then, the classification process is carried out with object-based method . The classified image has been converted to vector format. After that, an investigation is carried out for these vectors through overlaid it to the available old map. The result showed that the information content of IKONOS images has the capability of updating of 1: 5000 maps for good planned area , while, that ability will be decreases with decreasing the degree of planning. [ABSTRACT FROM AUTHOR]

The aim of this study is to develop a cost-effective approach for soil sealing change detection integrating radiometric analysis, multi-resolution segmentation and object-based classifiers in two study areas in Italy: Campania region and Veneto region. The integrated approach uses multi-temporal satellite images and CORINE Land Cover (CLC) maps. A good overall accuracy was obtained for the soil sealing maps produced. The results show an improvement in terms of size of the minimum mapping unit and of the changed object (1,44 ha in both cases) in respect to the CLC. The approach proves to be cost-effective given the data which are provided at low or no cost and as well as the level of automation achievable. [ABSTRACT FROM AUTHOR]

Spatial data of cartographic bases are often used for nautical and aeronautical charts, reference maps, or other thematic maps. Traditionally, such spatial data sets of different scales are created apart from each other, are stored in different databases, and, in many cases, have no relations. This makes the update of the spatial data a complex and costly task. Meanwhile, automatic detection of changes in spatial data, when older versions of data are compared to more recent version of data, saves time in this process. To model such a process, two major tasks are solved, namely, detection of a change in spatial data and identification of its significance to answer whether the change detected is significant enough that an update of the data will be effective. The model also takes into account the requirements for spatial data, the scale of the data, and update methods. [ABSTRACT FROM AUTHOR]

Road network detection from very high resolution satellite and aerial images has diverse and important usage areas such as map generation and updating. Although an expert can label road pixels in a given image, this operation is prone to errors and quite time consuming. Therefore, an automated system is needed to detect the road network in a given satellite or aerial image in a robust manner. In this paper, we propose such a novel system. Our system has three main modules: probabilistic road center detection, road shape extraction, and graph-theory-based road network formation. These modules may be used sequentially or interchangeably depending on the application at hand. To show the strengths and weaknesses of our system, we tested it on several very high resolution satellite (Geoeye, Ikonos, and QuickBird) and aerial image sets. We compared our system with the ones existing in the literature. We also tested the sensitivity of our system to different parameter values. Obtained results indicate that our system can be used in detecting the road network on such images in a reliable and fast manner. [ABSTRACT FROM AUTHOR]

Abstract: Automated approaches to building detection in multi-source aerial data are important in many applications, including map updating, city modeling, urban growth analysis and monitoring of informal settlements. This paper presents a comparative analysis of different methods for automated building detection in aerial images and laser data at different spatial resolutions. Five methods are tested in two study areas using features extracted at both pixel level and object level, but with the strong prerequisite of using the same training set for all methods. The evaluation of the methods is based on error measures obtained by superimposing the results on a manually generated reference map of each area. The results in both study areas show a better performance of the Dempster-Shafer and the AdaBoost methods, although these two methods also yield a number of unclassified pixels. The method of thresholding a normalized DSM performs well in terms of the detection rate and reliability in the less vegetated Mannheim study area, but also yields a high rate of false positive errors. The Bayesian methods perform better in the Memmingen study area where buildings have more or less the same heights. [Copyright &y& Elsevier]

Car navigation systems (CNS) have become an interesting research and industrial topic due to their wide deployment. However, updating and distribution of the road map database is a complex and high cost process. In this paper, we propose a real-time map generation and updating algorithm, which fulfills or corrects the unknown road area of the conventional road map database by using global positioning system (GPS) information and wireless communication technologies. To generate the road map of unknown roads, the proposed algorithm uses road images, which can be obtained when a driver travels unknown roads. When a driver travels unknown roads, which do not appear on the map of the car navigation system, the car navigation system extracts GPS and image information of the unknown roads. Then, the car navigation system generates the road map for the unknown roads by extracting location and road information, and updates the road map database in the car. After updating the local road map database, the car navigation system updates the master road map database, which is located at the network and is distributed to other car navigation systems. Thus, the road map database provider can update the road map database of other car navigation systems, which share the same master road map database. The proposed algorithm provides an efficient updating process of the road map database with a simplified process and reduced time for unknown road areas. [ABSTRACT FROM AUTHOR]

In the process of topographic map updating, spatial conflicts (inconsistency) between rivers and contours may be created. This project studies the particularity and complexity of the relationships between rivers and contours, and develops a method for automatic detection of the spatial conflicts between them. This method consists of a refined descriptive spatial model (called a topological chain), an algorithm for the computation of spatial relations, and a set of rules for the determination of spatial conflicts. In the spatial relation model, the topological relationships, order relationships, and metric relationships are integrated to describe the line-line spatial relationships. The rules are derived from the natural relations between rivers and contours in the real world. The effectiveness of this method has been verified by using the national 1:50 000 topographic map databases. An accuracy of 91% has been achieved. [ABSTRACT FROM AUTHOR]

Abstract: This paper presents a practical system for automated 3-D road network reconstruction from aerial images using knowledge-based image analysis. The system integrates processing of color image data and information from digital spatial databases, extracts and fuses multiple object cues, takes into account context information, employs existing knowledge, rules and models, and treats each road subclass accordingly. The key of the system is the use of knowledge as much as possible to increase success rate and reliability of the results, working in 2-D images and 3-D object space, and use of 2-D and 3-D interaction when needed. Another advantage of the developed system is that it can correctly and reliably handle problematic areas caused by shadows and occlusions. This work is part of a project to improve and update the 1:25,000 vector maps of Switzerland. The system was originally developed to processed stereo images. Recently, it has been modified to work also with single orthoimages. The system has been implemented as a stand-alone software package, and has been tested on a large number of images with different landscape. In this paper, various parts of the developed system are discussed, and the results of our system in the tests conducted independently by our project partner in Switzerland, and the test results with orthoimages in a test site in The Netherlands are presented together with the system performance evaluation. [Copyright &y& Elsevier]

The extraction of road networks from aerial images is one of the current challenges in digital photogrammetry and computer vision. In this paper, we present a practical system for 3-D road network reconstruction from aerial images using knowledge-based image analysis. In contrast to other approaches, the developed system integrates processing of color image data and information from digital spatial databases, extracts and fuses multiple object cues, takes into account context information, employs existing knowledge, rules and models, and treats each road subclass accordingly. The key of the system is the use of knowledge as much as possible to increase success rate and reliability of the results, working in 2-D images and 3-D object space, and use of 2-D and 3-D interaction when needed. Another advantage of the developed system is that it can correctly and reliably handle problematic areas caused by shadows and occlusions. This work is part of a project to improve and update the 1:25,000 vector maps of Switzerland. The system has been implemented as a stand-alone software package, and has been tested on a large number of images with different landscape. In this paper, various parts of the developed system are discussed, and the results of our system in recent benchmark tests conducted independently by our project partner in Switzerland, and the test results with black and white images in a test site in Belgium are presented together with the system performance evaluation. [Copyright &y& Elsevier]