Road (line) Smoothing by SCMS and Circle Window Methods

Volume: 7    Issue: 2

Year of Publication: 2020

Pages: (65-69)

Authors: Sama Lenin Kumar Reddy, C.V.Rao, P.Rajesh Kumar

Download Full Text (PDF)

Abstract

In the feature extraction methods, the features have noise like spikes or ridges and gaps. These affect the accuracy. This paper aims to remove the connected noise (ridges) and gap filling in between the two points of roads extracted by an index Normalized Difference Asphalt Road Index (NDARI).The extracted roads from the methodology have connected noise like spikes. This connected noise can remove or smooth by a Subspace Constrained Mean Shift (SCMS) algorithm is a non-parametric and Circle Window method. By using these methods, roads (line) features smoothed and shown in the experimental results.

References

1. S. L. K. Reddy, C. V. Rao, P. R. Kumar, R. V. G. Anjaneyulu and V. M. Bothale, \"Automatic Road Feature Extraction using MRF from LANDSAT-8 OLI Images,\" 2019 IEEE Recent Advances in Geoscience and Remote Sensing : Technologies, Standards and Applications (TENGARSS), Kochi, Kerala, India, 2019, pp.15-20, doi: 10.1109/TENGARSS48957.2019. 8976046.

2. W. Shi, Z. Miao, and J. Debayle, “An integrated method for urban main-road centerline extraction from optical remotely sensed imagery,” IEEE Transactions on Geoscience and Remote Sensing, vol. 52, no. 6, pp. 3359–3372, 2014, ISSN: 0196-2892. DOI: 10.1109/TGRS.2013.

3. Z. Miao, W. Shi, H. Zhang, and X. Wang, “Road centerline extraction from high-resolution imagery based on shape features and multivariate adaptive regression splines,” IEEE Geoscience and Remote Sensing Letters, vol. 10, no. 3, pp. 583–587, 2013, ISSN: 1545-598X. DOI: 10.1109/LGRS.2012.2214761

4. Y. A. Ghassabeh, T. Linder, and G. Takahara, “On the convergence and applications of mean shift type algorithms,” in 2012 25th IEEE Canadian Conference on Electrical and Computer Engineering (CCECE), 2012, pp. 1–5. DOI: 10.1109/CCECE.2012.6334859.

5. D. Comaniciu and P. Meer, “Mean shift: A robust approach toward feature space analysis,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 5, pp. 709–713, 2002, ISSN: 0162-8828. DOI: 10 .1109/34.1000236R.

6. U. Ozertem and D. Erdogmus, “Locally defined principal curves and surfaces,” J. Mach. Learn. Res., vol. 12, pp. 1249–1286, Jul. 2011, ISSN: 1532-4435. [Online].Available: http://dl.acm.org/citation.cfm?id= 1953048.

7. K. Fukunaga and L. Hostetler, “The estimation of the gradient of a density function, with applications in pattern recognition,” IEEE Transactions on Information Theory, vol. 21, no. 1, pp. 32–40, 1975, ISSN: 0018-9448. DOI:10.1109/TIT.1975.1055330.

8. Z. Miao, W. Shi, P. Gamba, and Z. Li, “An object based method for road network extraction in vhr satellite images,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 8, no. 10, pp. 4853–4862, 2015, ISSN: 1939-1404. DOI: 10.1109/ JSTARS.2015.2443552

Keywords

Landsat-8, Remote Sensing, Mathematical Morphology, Mean Shift, Kernel Density Estimation, Gap Filling, Sub-space Constrained Mean Shift.