Development of a Large-Scale Roadside Facility Detection Model Based on the Mapillary Dataset [PDF]
Sensors, 2022 The detection of road facilities or roadside structures is essential for high-definition (HD) maps and intelligent transportation systems (ITSs). With the rapid development of deep-learning algorithms in recent years, deep-learning-based object detection
Chenbo Zhao, Hiroya Maeda
exaly +6 more sources
Crowdsourcing Street View Imagery: A Comparison of Mapillary and OpenStreetCam [PDF]
ISPRS International Journal of Geo-Information, 2020 Over the last decade, Volunteered Geographic Information (VGI) has emerged as a viable source of information on cities. During this time, the nature of VGI has been evolving, with new types and sources of data continually being added.
Ron Mahabir +2 more
exaly +4 more sources
ANALYSIS OF THE SPATIOTEMPORAL ACCUMULATION PROCESS OF MAPILLARY DATA AND ITS RELATIONSHIP WITH OSM ROAD DATA: A CASE STUDY IN JAPAN [PDF]
International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, 2022 This paper presents a geospatial analysis of a FlatGeobuf database composed of six years of geographic data on approximately 41.7 million Mapillary photo shooting locations throughout Japan and geospatial data including road data from OpenStreetMap (OSM).
T. Seto, Y. Nishimura
exaly +4 more sources
GEO-TAGGED IMAGE RETRIEVAL FROM MAPILLARY STREET IMAGES FOR A TARGET BUILDING [PDF]
International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, 2020 This study aims to investigate the possibility to automate the image selection process for the target building from Mapillary images through a web application where the user only initiates one image of the target building as a query.
N. Çelik, E. Sümer
exaly +4 more sources
Mapillary Street-Level Sequences: A Dataset for Lifelong Place Recognition [PDF]
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020 Lifelong place recognition is an essential and challenging task in computer vision with vast applications in robust localization and efficient large-scale 3D reconstruction. Progress is currently hindered by a lack of large, diverse, publicly available datasets.
Pau Gargallo +2 more
exaly +5 more sources
A Large Crowdsourced Street View Dataset for Mapping Road Surface Types in Africa [PDF]
Scientific DataIdentifying road surface types is crucial for road maintenance and socio-economic development. Crowdsourced street view data, with global coverage and free access, is a valuable source for this task. However, deep learning models typically require large,
Qi Zhou +4 more
doaj +2 more sources
USE-SVI: A reproducible pipeline for sampling, acquiring, and stitching Street View imagery to support urban analyticsI have shared my data/code at [PDF]
MethodsXStreet-level imagery (SLI) is increasingly used in urban analytics for tasks like estimating greenery, conducting transport audits, and assessing facades.
Iuria Betco +2 more
doaj +2 more sources
Hierarchical Novelty Detection for Traffic Sign Recognition [PDF]
Sensors, 2022 Recent works have made significant progress in novelty detection, i.e., the problem of detecting samples of novel classes, never seen during training, while classifying those that belong to known classes.
Idoia Ruiz, Joan Serrat
doaj +2 more sources
The Mapillary Traffic Sign Dataset for Detection and Classification on a Global Scale [PDF]
Lecture Notes in Computer Science, 2020 Traffic signs are essential map features globally in the era of autonomous driving and smart cities. To develop accurate and robust algorithms for traffic sign detection and classification, a large-scale and diverse benchmark dataset is required. In this paper, we introduce a traffic sign benchmark dataset of 100K street-level images around the world ...
Christian Ertler +2 more
exaly +3 more sources
SAM for Road Object Segmentation: Promising but Challenging [PDF]
Journal of ImagingRoad object segmentation is crucial for autonomous driving, as it enables vehicles to perceive their surroundings. While deep learning models show promise, their generalization across diverse road conditions, weather variations, and lighting changes ...
Alaa Atallah Almazroey +2 more
doaj +2 more sources