Road and Road Intersection Extraction

Henderson, Thomas C.

doi:10.1007/978-1-4419-8167-7_7

Cited by 2 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to Table 1 it can be concluded that the precision of Faster RCNN framework in detecting the intersections is higher than the method of Henderson and Linton (2009) and lower than the one described in Henderson (2014) for the maps with single line symbols of the roads. On the other hand, the recall value of the deep learning method shows the converse analogy.…”

Section: Model Accuracymentioning

confidence: 96%

“…Frequently, such data transformation process is based on computer vision algorithms (Chiang et al 2005, Henderson and Linton 2009, Henderson 2014, however setting optimal parameters in such algorithms requires experience, and, therefore, using them is not an option for users who are non-experts in the field of computer vision (Ball et al 2017, Uhl et al 2018. Moreover, due to low quality of many historical maps and the high rate of overlap of graphical features, the accuracy of the conversion is often low (Chiang et al 2009, Pezeshk andTutwiler 2011).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic extraction of road intersection points from USGS historical map series using deep convolutional neural networks

Saeedimoghaddam

Stepinski

2019

International Journal of Geographical Information Science

View full text Add to dashboard Cite

Road intersections data have been used across different geospatial applications and analysis. The road network datasets dating from pre-GIS years are only available in the form of historical printed maps. Before they can be analyzed by a GIS software, they need to be scanned and transformed into the usable vector-based format. Due to the great bulk of scanned historical maps, automated methods of transforming them into digital datasets need to be employed. Frequently, this process is based on computer vision algorithms. However, low conversion accuracy for low quality and visually complex maps and setting optimal parameters are the two challenges of using those algorithms. In this paper, we employed the standard paradigm of using deep convolutional neural network for object detection task named regionbased CNN for automatically identifying road intersections in scanned historical USGS maps of several US. cities. We have found that the algorithm showed higher conversion accuracy for the double line cartographic representations of the road maps than the single line ones. Also, compared to the majority of traditional computer vision algorithms RCNN provides more accurate extraction. Finally, the results show that the amount of errors in the detection outputs is sensitive to complexity and blurriness of the maps as well as the number of distinct RGB combinations within them.

show abstract

Section: Model Accuracymentioning

confidence: 96%

Section: Introductionmentioning

confidence: 99%

Automatic extraction of road intersection points from USGS historical map series using deep convolutional neural networks

Saeedimoghaddam

Stepinski

2019

International Journal of Geographical Information Science

View full text Add to dashboard Cite

show abstract

“…Later, CIS, especially the histogram technique and K‐means, became more popular for pre‐processing than conventional filters. For example, a set of CIS methods was presented by Henderson and Linton, in which different colored layers are first separated based on the color usage information retrieved from the map legend, and then geometric properties (spatial proximity, continuity, and closure) are used to detect roads and intersections in the separated layers (Henderson, 2014; Linton, 2009). This cluster is colored bright green in Table 1.…”

Section: Discussionmentioning

confidence: 99%

“…Similar approaches are presented by Linton (2009) and Henderson, Linton, Potupchik, and Ostanin (2009). Another similar color histogram-based map image segmentation approach is demonstrated by Henderson (2014). In order to generate an initial feature extraction result, the histogram model of the feature is created as a set of sample histograms representative of the feature class from the map legend.…”

Section: Histogram Techniquementioning

confidence: 99%

A survey of road feature extraction methods from raster maps

Jiao

Heitzler

Hurni

2021

Transactions in GIS

View full text Add to dashboard Cite

Maps contain abundant geospatial information, such as roads, settlements, and river networks, to name a few. The need to access this information to carry out analyses (e.g., in transportation, landscape planning, or ecology), as well as advances in software and hardware technologies, have driven the development of workflows to efficiently extract features from maps. The aim of this article is to provide a comprehensive overview of such methods to extract road features from raster maps. The methods are categorized based on the classes of techniques they employ (e.g., line extraction), as well as their subclasses (e.g., line tracing, Hough transform), the amount of user intervention required (e.g., interactive, automatic), the required data (e.g., scanned maps, contemporary vector data) and the produced results (e.g., raster‐based predictions, vector‐based results, attributes). Additionally, recent road extraction methods from overhead imagery, together with evaluation methods that will possibly benefit road extraction from raster maps, are reviewed. Furthermore, the evolution of this research field is analyzed over the past 35 years and the limitations of the current techniques, as well as possible future directions, are discussed.

show abstract

Road and Road Intersection Extraction

Cited by 2 publications

References 14 publications

Automatic extraction of road intersection points from USGS historical map series using deep convolutional neural networks

Automatic extraction of road intersection points from USGS historical map series using deep convolutional neural networks

A survey of road feature extraction methods from raster maps

Contact Info

Product

Resources

About