Supervised feature-based classification of multi-channel SAR images

Borghys, Dirk; Yvinec, Yann; Perneel, Christiaan; Pižurica, Aleksandra; Philips, Wilfried

doi:10.1016/j.patrec.2005.08.006

Cited by 42 publications

(23 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 4 summarizes the input of the fusion module. A logistic regression classification was developed on SAR data at RMA (Borghys et al, 2004). The results consist of confidence images for each class, except for class 4, which is not detected by this approach.…”

Section: Data and Their Specificities In Smartmentioning

confidence: 99%

Multi-sensor Data Fusion Based on Belief Functions and Possibility Theory: Close Range Antipersonnel Mine Detection and Remote Sensing Mined Area Reduction

Bloch¹,

Acheroy²

2008

Humanitarian Demining

View full text Add to dashboard Cite

Section: Data and Their Specificities In Smartmentioning

confidence: 99%

Multi-sensor Data Fusion Based on Belief Functions and Possibility Theory: Close Range Antipersonnel Mine Detection and Remote Sensing Mined Area Reduction

Bloch¹,

Acheroy²

2008

Humanitarian Demining

View full text Add to dashboard Cite

“…6, despite its advantage in a previous report [11]. It also suggests that feature-based classification [12,21] should be assessed carefully; substantial achievements might not be obtained in different landscapes or applications. In general, a thematic map produced by combining the coherence matrix and polarimetric features was the most reliable information.…”

Section: Classificationmentioning

confidence: 98%

“…The first was a coherence matrix dataset, which has been a common practice in polarimetric SAR classification (for recent assessment, see [20]). A second experiment employed a polarimetric feature set derived from the Cloude-Pottier decomposition theorem as suggested by Borghys et al [21]. The third dataset exploited an original coherence matrix coupled with polarimetric features.…”

Section: Classificationmentioning

confidence: 99%

The Use of Polarimetric SAR Data for Forest Disturbance Monitoring

Trisasongko

2010

Sens Imaging

View full text Add to dashboard Cite

Tropical forest degradation has been a major area of interest for the remote sensing community. Various sensors have been dedicated to monitor its changes; however, due to widespread cloud cover, limited information could be retrieved through optical datasets. Synthetic Aperture Radar (SAR) sensors provide an alternative for such purpose. This paper discusses an application of SAR polarimetry data coupled with the Cloude-Pottier decomposition theorem as a noninvasive method for the assessment of degraded forests in Indonesia. It was found that Cloude-Pottier feature space provides a convenient way to describe degradation levels, especially using P-band datasets. Both L-and P-band data provided appreciable classification accuracy through Support Vector Machine methods. Results suggest that fully polarimetric SAR data, combined with polarimetric parameters, can be useful for operational monitoring.

show abstract

“…Classifiers built specifically for this application include a minimum-distance discounted classifier, a classifier of multi-spectral data based on belief functions and SARspecific classifiers [3][2] [1].…”

Section: Classificationmentioning

confidence: 99%