Multisource classification of remotely sensed data: fusion of Landsat TM and SAR images

Solberg, Anne; Jain, Anil K.; Taxt, Torfinn

doi:10.1109/36.298006

Cited by 224 publications

(84 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Single-sensor applications include monitoring of annual land cover changes [50][51][52][53], soil moisture [54][55][56] and lake dynamics [57]. Fusing multi-temporal Landsat and SAR data for land cover classification was demonstrated by [58,59]. Solberg and Huseby [60] used a Bayesian framework for fusing Landsat and SAR time series to monitor snow cover states.…”

Section: Introductionmentioning

confidence: 99%

A Bayesian Approach to Combine Landsat and ALOS PALSAR Time Series for Near Real-Time Deforestation Detection

et al. 2015

View full text Add to dashboard Cite

Abstract:To address the need for timely information on newly deforested areas at medium resolution scale, we introduce a Bayesian approach to combine SAR and optical time series for near real-time deforestation detection. Once a new image of either of the input time series is available, the conditional probability of deforestation is computed using Bayesian updating, and deforestation events are indicated. Future observations are used to update the conditional probability of deforestation and, thus, to confirm or reject an indicated deforestation event. A proof of concept was demonstrated using Landsat NDVI and ALOS PALSAR time series acquired at an evergreen forest plantation in Fiji. We emulated a near real-time scenario and assessed the deforestation detection accuracies using three-monthly reference data covering the entire study site. Spatial and temporal accuracies for the fused Landsat-PALSAR case (overall accuracy = 87.4%; mean time lag of detected deforestation = 1.3 months) were consistently higher than those of the Landsat-and PALSAR-only cases. The improvement maintained even for increasing missing data in the Landsat time series.

show abstract

Section: Introductionmentioning

confidence: 99%

A Bayesian Approach to Combine Landsat and ALOS PALSAR Time Series for Near Real-Time Deforestation Detection

et al. 2015

View full text Add to dashboard Cite

show abstract

“…Several studies have shown that SAR data may provide information on structural features of the surface complementary to the spectral information in optical data, for instance [3,4,15,17,18]. It has thus been shown, that the discriminating power of SAR images is very much improved when they are used in combination with optical data.…”

Section: Introductionmentioning

confidence: 95%

“…It has thus been shown, that the discriminating power of SAR images is very much improved when they are used in combination with optical data. [17] Have compiled a brief but useful review of multi-source classification. Image fusion is a popular method to integrate different sensors data for obtaining a more suitable image for a variety of applications, such as visual interpretation, image classification, etc.…”

Section: Introductionmentioning

confidence: 99%

Jute and Tea Discrimination Through Fusion of Sar and Optical Data

Haldar¹,

Patnaik²,

Mohan³

et al. 2012

PIER B

View full text Add to dashboard Cite

Abstract-Remote sensing approaches based on both optical and microwave region of EM spectra have been widely adapted for large scale crop monitoring and condition assessment. Visible, infrared and microwave wavelengths are sensitive to different crop characteristics, thus data from optical and radar sensors are complementary. Synthetic Aperture Radar (SAR) responds to the large scale crop structure (size, shape and orientation of leaves, stalks, and fruits) and the dielectric properties of the crop canopy. Research is needed to assess the saturation effects of SAR data and to investigate the synergy between the optical and SAR imagery for exploring various dimensions of crop growth which is not possible with any one of them singly with higher degree of accuracy. An attempt has been made to study the potential of SAR and optical data individually and by fusing them to separate various landcover classes. Two-date and three-date SAR data could distinguish jute and tea crop with 70-85% accuracy, while cloud free optical data (green, red and infrared bands) resulted in accuracy 80-85%. On fusing the optical and SAR single date data of May, 29 2010 using Brovey method, an accuracy of 85% was obtained. PCA and HSV with munsell based approaches resulted in similar accuracies but HSV performed the best among these. This emphasizes on the synergistic effect of SAR and optical data. Also the fused data could be used to delineate the crop condition and age by inputs like NDVI from optical and XPR (Cross polarization ratio) from SAR data.The co-and cross polarization ratios along with various indices viz. Biomass Index (BMI), Volume Scattering Index (VSI) and canopy structural index (CSI) were used to discriminate tea from jute. Due to differences in structural component of tea and jute at early season as manifested by the indices, there is clear separability as observed from the mean values. Among the dual polarization combinations, HV/VV performed the best (70%) followed by HV/HH (62%) and lastly HH/VV (42%). Among the single best indices for discrimination BMI performed the best. Combination of Co, Cross-polarization and BMI yields around 80% classification accuracy. BMI and VSI combination yielded the best classification accuracy of 84%. This level of accuracy obtained was much superior to that of multidate HH polarization SAR data.

show abstract

“…Within residential areas, further discrimination is achievable because the low-density areas are generally characterized by lower backscattering, given the wide streets and the presence of trees. This means that SAR sensors provide information that may not be obtained from optical sensors, and therefore, data fusion potentially provides improved results in the classification process compared to the conventional single-source classification results [2].…”

mentioning

confidence: 99%

Urban Mapping Using Coarse SAR and Optical Data: Outcome of the 2007 GRSS Data Fusion Contest

Pacifici

Frate

Emery

et al. 2008

IEEE Geosci. Remote Sensing Lett.

114

View full text Add to dashboard Cite

Multisource classification of remotely sensed data: fusion of Landsat TM and SAR images

Cited by 224 publications

References 22 publications

A Bayesian Approach to Combine Landsat and ALOS PALSAR Time Series for Near Real-Time Deforestation Detection

A Bayesian Approach to Combine Landsat and ALOS PALSAR Time Series for Near Real-Time Deforestation Detection

Jute and Tea Discrimination Through Fusion of Sar and Optical Data

Urban Mapping Using Coarse SAR and Optical Data: Outcome of the 2007 GRSS Data Fusion Contest

Contact Info

Product

Resources

About