Automatic road extraction using high resolution satellite images based on level set and mean shift methods

Revathi, M.; Sharmila, M.

doi:10.1109/icccnt.2013.6726766

Cited by 10 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The empirical results demonstrated that the suggested technique can efficiently extract road parts. Revathi and Sharmila (2013) applied pre-processing approach to increase the quality of images by removing noises first. They then implemented SVM and mean shift approach to extract road portions from IKONOS images.…”

Section: Related Workmentioning

confidence: 99%

Integrated technique of segmentation and classification methods with connected components analysis for road extraction from orthophoto images

Abdollahi

Pradhan

2021

Expert Systems with Applications

View full text Add to dashboard Cite

Road networks are one of the main urban features. Therefore, road parts extraction from high-resolution remotely sensed imagery and updated road database are beneficial for many GIS applications. However, owing to the presence of various types of obstacles in the images, such as shadows, cars, and trees, with similar transparency and spectral values as road class, achieving accurate road extraction using different classification and segmentation methods is still difficult. This paper proposes an integrated method combining segmentation and classification methods with connected components analysis to extract road class from orthophoto images. The proposed technique is threefold. First, multiresolution segmentation method was applied to segment images. Then, the main classification methods, namely, decision trees (DT), k-nearest neighbors (KNN), and support vector machines (SVM), were implemented based on spectral, geometric, and textural information to classify the obtained results into two classes: road and non-road. Three main accuracy evaluation measures, such as recall, precision, and F1-score, were evaluated to determine the performance of the proposed method, with respective average values of 87.62%, 89.71%, and 88.61%, respectively, for DT; 86.61%, 88.17%, and 87.30%, respectively, for KNN; and 89.83%, 89.52%, and 89.67%, respectively, for SVM. Finally, connected components labelling was used to extract road component parts, and morphological operation was employed to delete non-road parts and noises and improve the performance. These results were also compared with other prior works, which confirmed that the integrated method is an effective road extraction technique.

show abstract

Section: Related Workmentioning

confidence: 99%

Integrated technique of segmentation and classification methods with connected components analysis for road extraction from orthophoto images

Abdollahi

Pradhan

2021

Expert Systems with Applications

View full text Add to dashboard Cite

show abstract

“…In recent years, many automatic road networks extraction methods from high-resolution multispectral satellite image are proposed. Revathi et al preprocessed the highresolution satellite images to improve the tolerance and reduce the noise at the same time, such as the buildings, parking lots and other open spaces, then used level set and mean shift to extract road regions [4] . A strategy for road extraction based on wavelet filter and the fuzzy inference algorithm was proposed [5] .…”

Section: Introductionmentioning

confidence: 99%

Multiple Saliency Features Based Automatic Road Extraction from High‐Resolution Multispectral Satellite Images

Zhang

Wang

2018

Chin. j. electron.

View full text Add to dashboard Cite

“…For example, Trinder and Wang presented a knowledge-based method for automatic extraction of road from aerial photographs and highresolution remotely sensed imagery [1]. Other methods, level set search algorithm and mean shift clustering technique [2], reference circle and central pixel technology [3], have been applied to extract geometrical characteristics of roads with a great performance. Song and Daniel used support vector machine to classify image into two groups [4]: a road group and a non-road group.…”

Section: Introductionmentioning

confidence: 99%

Extracting Logical Connectivity of Intersection from Floating Car Data Using Support Vector Machine Method

Huang¹,

Zhang²,

Pan³

et al. 2018

Proceedings of the 2018 International Conference on Network, Communication, Computer Engineering (NCCE 2018)

View full text Add to dashboard Cite

This paper aims to extract traffic rule at intersection from floating car data, traffic rule is the logical connectivity data in road network. Firstly, based on intersection data model, the geometric characteristics of intersection are presented, and the angle of arcs is calculated to get the traffic diversion. Secondly, routes are extracted from floating car data, which represent the number of turning car at intersection. Thirdly, a classification model based on support vector machine is used to classify the connected state of arcs, and the classification feature includes the number of car and traffic diversion. Finally, this method is applied in some intersections of Guangzhou Province using six days' floating car data. The experiment results reveal the accuracy is about 90 percent.

show abstract

Automatic road extraction using high resolution satellite images based on level set and mean shift methods

Cited by 10 publications

References 10 publications

Integrated technique of segmentation and classification methods with connected components analysis for road extraction from orthophoto images

Integrated technique of segmentation and classification methods with connected components analysis for road extraction from orthophoto images

Multiple Saliency Features Based Automatic Road Extraction from High‐Resolution Multispectral Satellite Images

Extracting Logical Connectivity of Intersection from Floating Car Data Using Support Vector Machine Method

Contact Info

Product

Resources

About