Automatic Map Generation Research Articles

Tactile Simultaneous Localization and Mapping Using Low-Cost, Wearable LiDAR

Tactile maps are widely recognized as useful tools for mobility training and the rehabilitation of visually impaired individuals. However, current tactile maps lack real-time versatility and are limited because of high manufacturing and design costs. In this study, we introduce a device (i.e., ClaySight) that enhances the creation of automatic tactile map generation, as well as a model for wearable devices that use low-cost laser imaging, detection, and ranging (LiDAR,) used to improve the immediate spatial knowledge of visually impaired individuals. Our system uses LiDAR sensors to (1) produce affordable, low-latency tactile maps, (2) function as a day-to-day wayfinding aid, and (3) provide interactivity using a wearable device. The system comprises a dynamic mapping and scanning algorithm and an interactive handheld 3D-printed device that houses the hardware. Our algorithm accommodates user specifications to dynamically interact with objects in the surrounding area and create map models that can be represented with haptic feedback or alternative tactile systems. Using economical components and open-source software, the ClaySight system has significant potential to enhance independence and quality of life for the visually impaired.

Automatic smooth map generation of internal combustion engines via local-global model based calibration technique

The addition of new sensors and actuators to the engine, to reduce fuel consumption and emissions besides improving the engine operation, complicates the control commands stored in the engine control unit (ECU). Substitution of mechanical actuators with electronic ones increases the engine’s degrees of freedom and the number of control parameters, which results in the increased engine calibration time and cost. The aim of this paper is to take advantage of optimization techniques to achieve optimal values of control parameters in a fast and automated way. In this regard, it requires replacing the real engine with the virtual model and implementing the model-based calibration by coupling the virtual engine model with optimization algorithms. In this study, deep neural network (DNN) modeling and genetic algorithm (GA, NSGA-II) optimization are used for model-based calibration. The effect of all input control parameters, including ignition angle, continuously variable valve timing, etc., on all output control parameters including, brake-specific fuel consumption, emissions level, knock limit, combustion stability, etc., are investigated simultaneously by a valid global model, which is a remarkable achievement in the model-based calibration. Dynamic lag of some actuators delays the execution of control commands sent from ECU. To avoid abrupt variations in the actuators values, smoothness of the engine maps is considered in the calibration process. To reduce fuel consumption, decrease emission levels and attain smooth maps, the calibration of control parameters is performed by local-multi-objective optimization and global-single-objective optimization. Local-global model-based calibration presented in this study reduces 3.7% of the brake-specific fuel consumption and 7%–10% of emissions level at breakpoints of the engine map compared to manual calibration. In addition, the calibration time and costs while producing better engine performance can be reduced by automating the calibration process. Finally, calibrated maps are stored as a lookup table (LUT) in ECU. Generating an optimal lookup table involves the pre-calculation of several points that cover the calculation domain and allow the interpolation for other points. Selecting the optimal points for exact calculation is of great importance in the size and accuracy of LUT. In this study, an optimization tool is also presented to generate accurate and efficient LUT.

Weakly Supervised Concept Map Generation through Task-Guided Graph Translation.

Recent years have witnessed the rapid development of concept map generation techniques due to their advantages in providing well-structured summarization of knowledge from free texts. Traditional unsupervised methods do not generate task-oriented concept maps, whereas deep generative models require large amounts of training data. In this work, we present GT-D2G (Graph Translation-based Document To Graph), an automatic concept map generation framework that leverages generalized NLP pipelines to derive semantic-rich initial graphs, and translates them into more concise structures under the weak supervision of downstream task labels. The concept maps generated by GT-D2G can provide interpretable summarization of structured knowledge for the input texts, which are demonstrated through human evaluation and case studies on three real-world corpora. Further experiments on the downstream task of document classification show that GT-D2G beats other concept map generation methods. Moreover, we specifically validate the labeling efficiency of GT-D2G in the label-efficient learning setting and the flexibility of generated graph sizes in controlled hyper-parameter studies.

Lane-Level Map Generation and Management Framework Using Connected Car Data

This study proposes a lane-level map generation and management framework using connected sensor data to reduce the manpower and time required for producing and updating high-definition (HD) maps. Unlike previous studies that relied on the onboard processing capabilities of vehicles to collect map-constructing elements, this study offloads computing for map generation to the cloud, assigning vehicles solely the role of transmitting sensor data. For efficient data collection, we divide the space into a grid format to define it as a partial map and establish the state of each map and its transition conditions. Lastly, tailored to the characteristics of the road elements composing the map, we propose an automated map generation technique and method for selectively collecting data. The map generation method was tested using data collected from actual vehicles. By transmitting images with an average size of 350 KB, implementation was feasible even with the current 5G upload bandwidth. By utilizing 12,545 elements, we were able to achieve a position accuracy and regression RMSE of less than 0.25 m, obtaining 651 map elements to construct the map. We anticipate that this study will help reduce the manpower and time needed for deploying and updating HD maps.

Towards the Monitoring of Violent Events in Social Media through Visual Information

Violence is a latent threat for individuals, this is an even more concerning issue in Latin American cities. The detection and monitoring of events reported in social media could help to build maps of zones with incident of violent events. This could eventually lead to the automatic generation of risk maps which could be of great help to users and even authorities. This paper aims to detect violent incidents reported in social media using visual information only. While most of the related work focuses on the text modality, the goal of this paper is to assess the feasibility of detection when only visual information is available. CNN based feature extraction and standard classification models are implemented and evaluated in a recently released corpus. Experimental results show that distinguishing images depicting violent events is feasible, but the fine grain recognition of categories is still an open problem.

Fully automatic DOM generation method based on optical flow field dense image matching

ABSTRACT Automatic Digital Orthophoto Map (DOM) generation plays an important role in many downstream works such as land use and cover detection, urban planning, and disaster assessment. Existing DOM generation methods can generate promising results but always need ground object filtered DEM generation before otho-rectification; this can consume much time and produce building facade contained results. To address this problem, a pixel-by-pixel digital differential rectification-based automatic DOM generation method is proposed in this paper. Firstly, 3D point clouds with texture are generated by dense image matching based on an optical flow field for a stereo pair of images, respectively. Then, the grayscale of the digital differential rectification image is extracted directly from the point clouds element by element according to the nearest neighbor method for matched points. Subsequently, the elevation is repaired grid-by-grid using the multi-layer Locally Refined B-spline (LR-B) interpolation method with triangular mesh constraint for the point clouds void area, and the grayscale is obtained by the indirect scheme of digital differential rectification to generate the pixel-by-pixel digital differentially rectified image of a single image slice. Finally, a seamline network is automatically searched using a disparity map optimization algorithm, and DOM is smartly mosaicked. The qualitative and quantitative experimental results on three datasets were produced and evaluated, which confirmed the feasibility of the proposed method, and the DOM accuracy can reach 1 Ground Sample Distance (GSD) level. The comparison experiment with the state-of-the-art commercial softwares showed that the proposed method generated DOM has a better visual effect on building boundaries and roof completeness with comparable accuracy and computational efficiency.

Vision Navigation Based PID Control for Line Tracking Robot

In a controlled indoor environment, line tracking has become the most practical and reliable navigation strategy for autonomous mobile robots. A line tracking robot is a self-mobile machine that can recognize and track a painted line on the floor. In general, the path is set and can be visible, such as a black line on a white surface with high contrasting colors. The robot’s path is marked by a distinct line or track, which the robot follows to move. Several scientific contributions from the disciplines of vision and control have been made to mobile robot vision-based navigation. Localization, automated map generation, autonomous navigation and path tracking is all becoming more frequent in vision applications. A visual navigation line tracking robot should detect the line with a camera using an image processing technique. The paper focuses on combining computer vision techniques with a proportional-integral-derivative (PID) controller for automatic steering and speed control. A prototype line tracking robot is used to evaluate the proposed control strategy.

Automatic generation of land use maps using aerial orthoimages and building floor data with a Conv-Depth Block (CDB) ResU-Net architecture

Unlike land classification maps, it is difficult to automate the generation of land use (LU) maps. The deep learning approach is a state-of-the-art methodology that can expedite the creation of LU maps. However, as the deep learning output depends on the training input, it is critical to decide upon the input that should be selected. In this study, a method for securing accurate LU information is established and used for ground truthing, using data on the number of building floors extracted from a digital topographic map and a 51 cm resolution aerial orthoimages as inputs. To this end, we developed a Conv-Depth Block (CDB) ResU-Net architecture. To verify the versatility of the proposed network, our neural network was applied to three complex metropolitan areas with different LU characteristics in Korea. The accuracy of LU maps for these cities was improved by combining convolution layers and depth-wise separable convolution as well as by including numerical building floor data. The proposed CDB ResU-Net achieved an overall accuracy of 83.7 % for the test samples. Our network exhibited an improved performance compared to Deeplab v3+, ResUnet, ResASPP-Unet, and context-based ResU-Net in classifying residential classes, which is crucial for estimating the degree of exposure in urban risk analyses.

An Approach to Test Program Generation for Memory Coherence Verification of “Elbrus” Microprocessors

One of the key aspects of the correctness of the memory subsystem of a microprocessor is its functioning in accordance with the memory coherence protocol. This article presents an approach to test program generation for memory coherence verification of “Elbrus” microprocessors. Requirements for memory coherence tests are considered. The memory map structure allowing to describe the memory areas used in tests and the types of accesses to these areas in a flexible way is presented. The method of test program generation based on the memory map structure is described. The method of automatic memory map generation is proposed. Generated tests have been used for verification of RTL models and FPGA-based prototypes.

Development of the Tactile Map Creator (TMC) Application

There are multiple studies demonstrating that 3D printed maps are important to people with blindness. When designed properly, they help users by improving safety and mobility and allow people with blindness to efficiently learn spatial information from the map and plan their travel prior to navigation. However, tactile maps are still not widely among people with blindness, as they are not readily available to them. Creating maps for each person needing a map of a certain location currently requires help from an individual with advanced technical training. They need to use specialized software for 3D models that personnel from disability services and family members of people with blindness usually have no experience with. The goal of this research is to design and implement software that can be used for the automatic generation of maps and be accessible to the general public. Our hypothesis is that by automating all the challenging steps (generation of the 3D model and drawing of optimally designed symbols), this will lead to increased usability and acceptance. Here, we demonstrated an early prototype and evaluated our hypothesis in a user study. To assess the success of this approach, participants answered questions about the process, usability, and social impacts of the software. Overall, participants liked the application because it was easy to use and allowed them to create custom maps with appropriate tactile-encoding features that provide meaningful information to the end user.

Automatic wall slant angle map generation using 3D point clouds

Recently, quantitative and repetitive inspections of the old urban area were conducted because many structures exceed their designed lifetime. The health of a building can be validated from the condition of the outer wall, while the slant angle of the wall widely serves as an indicator of urban regeneration projects. Mostly, the inspector directly measures the inclination of the wall or partially uses 3D point measurements using a static light detection and ranging (LiDAR). These approaches are costly, time-consuming, and only limited space can be measured. Therefore, we propose a mobile mapping system and automatic slant map generation algorithm, configured to capture urban environments online. Additionally, we use the LiDAR-inertial mapping algorithm to construct raw point clouds with gravity information. The proposed method extracts walls from raw point clouds and measures the slant angle of walls accurately. The generated slant angle map is evaluated in indoor and outdoor environments, and the accuracy is compared with real tiltmeter measurements.

STATE-WIDE CALCULATION OF TERRAIN-VISUALISATIONS AND AUTOMATIC MAP GENERATION FOR ARCHAEOLOGICAL OBJECTS

Abstract. Airborne laser scanning (ALS) became very popular in the last two decades for archaeological prospection. With the state-wide availability of ALS-data in Lower Saxony, Germany, about 48,000 km², we needed flexible and scalable approaches to process the data. First, we produced a state-wide digital terrain model (DTM) and some visualisations of it to use it in standard GIS software. Some of these visualisations are available as web maps and used for prospection also by volunteers. In a second approach, we automatically generate maps for all known archaeological objects. This is mainly used for the documentation of the 130,000 known objects in Lower Saxony, but also for object-by-object revision of the database. These Maps will also be presented in the web portal “Denkmalatlas Niedersachsen”, an open data imitative of the state Lower Saxony.In the first part of this paper, we show how the state-wide DTM and its visualisations can be calculated using tiles. In the second part, we describe the automatic map generation process. All implementations were done with ArcGIS and its scripting interface ArcPy.

Autonomous Robotic Exploration and Navigation System using Tri-layered Mapping and Geometrical Path Planning Techniques

In the recent decade, robotic exploration is emerging as a vast research platform as it prolongs to be a challenging task, especially in unknown dynamic environments. Exploration plays a vital role in collecting data from the areas inaccessible to the human. The operation of manual exploration systems in complex environments is cumbersome due to ineffective noise filtering, poor visibility and shuffling of map characteristics. In order to overcome such drawbacks, our approach focuses on the development of autonomous robotic exploration by designing a robust SLAM-based system, incorporating tri-layered mapping technique for automatic map generation and a new geometrical boundary-based path-planning technique to improve the mobility of the robot during navigation. The proposed path-planning algorithm yields better trajectory planning and obstacle avoidance using the pose, odometry and orientation parameters of the robot. The performance of the developed robot is evaluated through real-time experimentation, and it is evident from the results that, the proposed approach is preferable for autonomous exploration applications.

AN AUTOMATIC SEMANTIC MAP GENERATION METHOD USING TRAJECTORY DATA

Abstract. It’s easily to obtain the geometric information of terrain features in a timely manner using advanced surveying and mapping methods, but it is impossible to obtain their semantic information with low latency due to the rapid development of cities. The popularity of GPS-enabled devices and technologies provide us a large number of personal location information. Moreover, it is possible to extract the personal or group behavior pattern due to the regularity of human behavior. Those conditions make it possible to extract and identify human behavior patterns from their trajectory data. In this paper, we present an automatic semantic map generation method that extract semantic patterns and take advantage of them to tagging spatial objects in an unknown region based on known semantic patterns. We study the regularity of trajectory data and build the semantic pattern based on the regularity of human behavior. Most importantly, we use known semantic patterns to identify the semantics of the stay points in the unknown region, and use this method to realize the semantic recognition of the stay points. Results of the experiments show the effectiveness of our proposed method.

TAILORED FEATURES FOR SEMANTIC SEGMENTATION WITH A DGCNN USING FREE TRAINING SAMPLES OF A COLORED AIRBORNE POINT CLOUD

Abstract. Automation of 3D LiDAR point cloud processing is expected to increase the production rate of many applications including automatic map generation. Fast development on high-end hardware has boosted the expansion of deep learning research for 3D classification and segmentation. However, deep learning requires large amount of high quality training samples. The generation of training samples for accurate classification results, especially for airborne point cloud data, is still problematic. Moreover, which customized features should be used best for segmenting airborne point cloud data is still unclear. This paper proposes semi-automatic point cloud labelling and examines the potential of combining different tailor-made features for pointwise semantic segmentation of an airborne point cloud. We implement a Dynamic Graph CNN (DGCNN) approach to classify airborne point cloud data into four land cover classes: bare-land, trees, buildings and roads. The DGCNN architecture is chosen as this network relates two approaches, PointNet and graph CNNs, to exploit the geometric relationships between points. For experiments, we train an airborne point cloud and co-aligned orthophoto of the Surabaya city area of Indonesia to DGCNN using three different tailor-made feature combinations: points with RGB (Red, Green, Blue) color, points with original LiDAR features (Intensity, Return number, Number of returns) so-called IRN, and points with two spectral colors and Intensity (Red, Green, Intensity) so-called RGI. The overall accuracy of the testing area indicates that using RGB information gives the best segmentation results of 81.05% while IRN and RGI gives accuracy values of 76.13%, and 79.81%, respectively.

Trialstreamer: Mapping and Browsing Medical Evidence in Real-Time.

We introduce Trialstreamer, a living database of clinical trial reports. Here we mainly describe the evidence extraction component; this extracts from biomedical abstracts key pieces of information that clinicians need when appraising the literature, and also the relations between these. Specifically, the system extracts descriptions of trial participants, the treatments compared in each arm (the interventions), and which outcomes were measured. The system then attempts to infer which interventions were reported to work best by determining their relationship with identified trial outcome measures. In addition to summarizing individual trials, these extracted data elements allow automatic synthesis of results across many trials on the same topic. We apply the system at scale to all reports of randomized controlled trials indexed in MEDLINE, powering the automatic generation of evidence maps, which provide a global view of the efficacy of different interventions combining data from all relevant clinical trials on a topic. We make all code and models freely available alongside a demonstration of the web interface.

Automatic Map Generation for Action Policy Learning of Mobile Robot from Existing Electronic Map

Automatic Map Generation for Action Policy Learning of Mobile Robot from Existing Electronic Map

Automatic Generation of Diagrammatic Subway Maps for Any Date with Maple

The second author was one of the authors of a computer package written in Maple that could automatically generate railway maps of a network for any date. This package was presented at ACA’2008 and its design and implementation is described in a previous article. Each section of the network was colored accordingly to its characteristics. The position of the nodes (stations, junctions, $$\ldots $$) was obtained from a list of geographical coordinates. The work presented here deals with a similar although not identical case: now subway networks are treated as graphs with the help of a computer algebra system in order to obtain the diagrammatic map for any date. Most subway network maps follow more or less closely the ideas introduced by Harry Beck in his diagrammatic design of London subway map (the distances between stations and geographic orientation of the lines don’t have to be respected, as the clarity and the number of stations between two stations is the key information to be visualized). Therefore allocating nodes is far simpler, and we have decided to manually allocate the stations on a predefined grid and to automatize the drawing of the network. The situation is also simpler because all lines are double track and electrified. For instance in Madrid subway there are minor differences between lines, such as the kind of catenary (classic or rigid), the loading gauge (narrow/broad), $$\ldots $$ that will not be considered here. Each node and edge of the graph has dates associated: inauguration date/closure date–the latter if applies. The package takes advantage of the simplifications w.r.t. the previous article mentioned above and the features of Maple’sGraphTheory package. This way the approach, although general, can be implemented in relatively few lines of code. We know of no other similar works. The work is illustrated with the case of Madrid subway network, one of the biggest ones in the world.

Extraction of snow cover from high-resolution remote sensing imagery using deep learning on a small dataset

ABSTRACTSnow cover is of great significance for many applications. However, automatic extraction of snow cover from high spatial resolution remote sensing (HSRRS) imagery remains challenging, owing to its multiscale characteristics, similarities to clouds, and occlusion by the shadows of mountains and clouds. Deep convolutional neural networks for semantic segmentation are the most popular approach to automatic map generation, but they require huge computing time and resources, as well as a large dataset of pixel-wise annotated HSRRS images, which precludes the application of many superior models. In this study, these limitations are overcome by using a sequence of transfer learning steps. The method starts with a modified aligned ‘Xception’ model pre-trained for object classification on ImageNet. Subsequently, a ‘DeepLab version three plus’ (DeepLabv3+) model is trained using a large dataset of Landsat images and corresponding snow cover products. Finally, a second transfer learning step is employed to fine-tune the model on the small dataset of GaoFen-2, the highest resolution HSRRS satellite in China. Experiments demonstrate the feasibility and effectiveness of this framework for automatic snow cover extraction.

APPLICATION OF OFF-NADIR SATELLITE IMAGERY IN EARTHQUAKE DAMAGE ASSESSMENT USING OBJECT-BASED HOG FEATURE DESCRIPTOR

Abstract. One of the most crutial applications of very-high-resolution (VHR) satellite images is disaster management. In disaster management, time is of great importance. Therefore, it is vital to acquire satellite images as quickly as possible and benefit from automatic change detection to speed up the process. Automatic damage map generation is performed by overlaying the co-registered before and after images of the area of interest and, compring them to highlight the affected infrastructures. For speeding up image capture, satellites tilt their imaging sensor and take images from oblique angles. However, this kind of image acquisition causes severe geometric distortion in the images, which hinders image co-registration in automatic change detection. In this study, a Patch-Wise Co-Registration (PWCR) solution is used. In this algorithm, the before and after images are co-registered in a segment-by-segment manner. From the literature, this algorithm is followed by a spectral comparison to detect changes. However, due to the complicated structure of debris in damage detection applications, spectral comparison methods cannot perform well. In this work, we developed an object-based method using Histogram of Oriented Gradient descriptor to detect damges and compared our results to different existing spectral and textural change detection methods. The algorithm is tested on images from the 2010-Heidi earthquake, captured by DigitalGlobe. The achieved highly accurate results demonstrate the potential of using off-nadir remote sensing images for automatic urban damage detection possibly in early response systems as it speeds up the damage map generation by providing flexibility to utilize images taken from different anlges.