Classification of remote sensing images from urban areas using Laplacian image and Bayesian theory

Yousefi, Bardia; Mirhassani, Seyed Mostafa; Marvi, Hossein

doi:10.1117/12.754563

Cited by 9 publications

(6 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Eventually, final result of algorithm is calculated by adding the results of each direction of flowchart. The presented method was compared to the methods [1] and [13]. The result of experiments showed promising results.…”

Section: Discussionmentioning

confidence: 73%

“…250 pixels are considered as minimum size of large buildings. The experiments of the proposed approach shows promising results compared with the reviewed methods [13].In Table 1 we compare the results of classification using the proposed approach with two reviewed methods [1] and [13]. We depicted the correct classification rate for pixels in the remote sensing image as the criterion for comparing these methods.…”

Section: Resultsmentioning

confidence: 87%

“…As the next step, the MUSM filter is applied on the original image. The laplacian of original and filtered image is then fed to the classifier [13]. Finally the results of original and filtered image after classification determine the extracted objects.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Motion based unsharp masking [MUSM] for extracting building from urban images

Mirhassani

Yousefi

Ahmadyfard

et al. 2008

2008 IEEE International Conference on Systems, Man and Cybernetics

View full text Add to dashboard Cite

In recent decades, classification of remote sensing images from urban area as a means to achieve necessitated information for some applications such as automatic map updating and GIS, planning and emergency response has become one of the challenging subjects for image processing researches. In this paper, a method for classification of remote sensing image from urban area is addressed. First, motion based unsharp masking [MUSM] is applied to the input image to enhance its high frequency components. Then, laplacian of image as input feature for the Bayesian classifier is utilized. After that, size filter is used for large and small building discrimination. The classification of small and large building using unsharp mask and Bayesian discrimination function has increased in aspect of accuracy in comparison with original Bayesian method for classification of urban area. Experiments justify the efficiency of the proposed approach.

show abstract

Section: Discussionmentioning

confidence: 73%

Section: Resultsmentioning

confidence: 87%

See 1 more Smart Citation

Motion based unsharp masking [MUSM] for extracting building from urban images

Mirhassani

Yousefi

Ahmadyfard

et al. 2008

2008 IEEE International Conference on Systems, Man and Cybernetics

View full text Add to dashboard Cite

show abstract

“…The principle of the classifier is to calculate the posterior probability of an object using its prior probability and the Bayesian theorem, that is, the object belongs to a certain class with the largest posterior probability. In the paper [57], the buildings were detected by Bayesian decision theory in regard to Laplacian probability density function followed by the discerning of roads by a special intensity threshold. Storvik [58] described a Bayesian framework for classification based on the multiscale features, which was realized by the iterative conditional modes (ICM) algorithm.…”

Section: Methods Based On Segmentationmentioning

confidence: 99%

Road Extraction Methods in High-Resolution Remote Sensing Images: A Comprehensive Review

Lian

Wang

Mustafa

et al. 2020

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

105

View full text Add to dashboard Cite

Road extraction from high-resolution remote sensing images (HRSI) is a challenging but hot research topic in the past decades. A large number of methods are invented to deal with this problem. This article provides a comprehensive review of these existing approaches. We classified the methods into heuristic and data-driven. The heuristic methods are the mainstream in the early years, and the data-driven methods based on deep learning have been quickly developed recently. With regard to the heuristic methods, the road feature model is firstly introduced, then, the classic extraction methods are reviewed in two sub-categories: semi-automatic and automatic. The principles, inspirations, advantages and disadvantages of these methods are described. In terms of the data-driven methods, the road extraction methods based on deep neural network, particularly those based on patched convolutional neural network, fully convolutional network and generative adversarial network are reviewed. We perform subjective comparisons between the methods inner each type. Furthermore, the quantity performances achieved on the same dataset are compared between the heuristic and data-driven methods to show the strengthening of the data-driven methods. Finally, the conclusion and prospects are summarized.

show abstract

“…The input video is grayscale with a bit-depth of 8 and has a resolution of 40 by 40 pixels. The Laplacian operator, widely used in applications such as artifact rejection [8] and scene classification [9], is realised and given by (1). The hardware architecture is a two dimensional mesh array consisting of interconnecting primitive pixel processors, whereby each processor processes a single pixel.…”

Section: A Specificationsmentioning

confidence: 99%

High Speed Video Processing Using Fine-Grained Processing on FPGA Platform

Ang

Kumar

2013

2013 IEEE 21st Annual International Symposium on Field-Programmable Custom Computing Machines

View full text Add to dashboard Cite

This summary paper 1 proposes an FPGA-based array processor which performs Laplacian filtering on a 40 by 40 pixel grayscale video. The architecture comprises of bitserial pixel processors interconnected to give a two-dimensional mesh array. This architecture features the novel use of partial reconfiguration which transfers data to and fro the array. Each processor occupies a configurable logic block and achieves a target frame rate of 10000 frames per second, at an operating frequency of 0.31 MHz on the Virtex-6 ML605 Evaluation Kit. The detailed correspondence between the contents of slice lookup tables and the Virtex-6 bitstream format is also documented.

show abstract

Classification of remote sensing images from urban areas using Laplacian image and Bayesian theory

Cited by 9 publications

References 0 publications

Motion based unsharp masking [MUSM] for extracting building from urban images

Motion based unsharp masking [MUSM] for extracting building from urban images

Road Extraction Methods in High-Resolution Remote Sensing Images: A Comprehensive Review

High Speed Video Processing Using Fine-Grained Processing on FPGA Platform

Contact Info

Product

Resources

About