Analysis of IRS imagery for detecting man-made objects with a multivalued recognition system

Mandal, Deba Prasad; Murthy, C. A.; Pal, Sankar K.

doi:10.1109/3468.485750

Cited by 21 publications

(16 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have applied the method proposed by Mandal et al [15] and have summarized the results of this method and the method proposed in this paper for detection of bridges in both images. For the scene shown in Fig.…”

Section: Resultsmentioning

confidence: 99%

“…Hence, there is no additional registration step. The method proposed by Mandal et al [15] uses a contour tracing method. Misclassification results in many nonbridge segments to be detected as bridges.…”

Section: Introductionmentioning

confidence: 99%

“…For bridge detection, they first segment water in the SPOT image to spatially constrain the location of bridges in the SAR image. Mandal et al [15] use a method of analyzing the IRS satellite imagery for detecting various man-made objects including bridges. Initially, a multivalued recognition system is used to classify the image pixels into six land-cover types.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An Automatic Bridge Detection Technique for Multispectral Images

Chaudhuri

Samal

2008

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Abstract-Extraction of features from images has been a goal of researchers since the early days of remote sensing. While significant progress has been made in several applications, much remains to be done in the area of accurate identification of high-level features such as buildings and roads. This paper presents an approach for detecting bridges over water bodies from multispectral imagery. The multispectral image is first classified into eight land-cover types using a majority-must-be-granted logic based on the multiseed supervised classification technique. The classified image is then categorized into a trilevel image: water, concrete, and background. Bridges are then recognized in this trilevel image by using a knowledge-based approach that exploits the spatial arrangement of bridges and their surroundings using a five-step approach. A river extraction module identifies the rivers using a recursive scanning technique and geometric constraints. Using a neighborhood operator and the knowledge of the spatial dimensions of a typical bridge, we identify the possible bridge pixels. These potential bridge pixels are then grouped into possible bridge segments based on their connectivity and geometric properties.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Automatic Bridge Detection Technique for Multispectral Images

Chaudhuri

Samal

2008

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

show abstract

“…In fact, the maximum number of clusters for image data is usually smaller than 50 (e.g. SPOT image has seven clusters [8]; IRS image has five clusters [31]). Therefore, as a rule of thumb, we set c max = 50.…”

Section: The Proposed Validity Index and A Validation Algorithmmentioning

confidence: 99%

A cluster validity index for fuzzy clustering

Zhang

Wang

Zhang

et al. 2008

Information Sciences

114

View full text Add to dashboard Cite

“…In particular, special attention has to be paid to the detection of man-made objects, like roads. Some solutions have been proposed for the detection of man-made structures from remote sensing imagery in the case of SPOT or IRS data [7], [17] (optical), which imply the use of some a priori knowledge, specific strategies, or heuristic rules. However, these methods are unfeasible when one is obliged to use SAR data.…”

Section: Introductionmentioning

confidence: 99%

Synthetic aperture radar image segmentation by a detail preserving Markov random field approach

Smits

Dellepiane

1997

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

A multichannel image segmentation method is proposed that utilizes Markov random fields (MRF's) with adaptive neighborhood (AN) systems. Bayesian inference is applied to realize the combination of evidence from different knowledge sources. In such a way, optimization of the shape of a neighborhood system is achieved by following a criterion that makes use of the Markovian property exploiting the local image content. The MRF segmentation approach with AN systems (MRF-AN) makes it possible to better preserve small features and border areas. The purpose of the paper is to show the usefulness of the concept of MRF-AN for SAR image segmentation.

show abstract

Analysis of IRS imagery for detecting man-made objects with a multivalued recognition system

Cited by 21 publications

References 9 publications

An Automatic Bridge Detection Technique for Multispectral Images

An Automatic Bridge Detection Technique for Multispectral Images

A cluster validity index for fuzzy clustering

Synthetic aperture radar image segmentation by a detail preserving Markov random field approach

Contact Info

Product

Resources

About