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]

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 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]

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]

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]

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]