Logo GISdevelopment.net

GISdevelopment > Proceedings > ACRS > 1999


1989 | 1990 | 1991 | 1992 | 1994 | 1995 | 1996 | 1997 | 1998 | 1999 | 2000 | 2002
Sessions

Agriculture/Soil

Water Resources

Disasters

Measurement and Modeling

Land Use

Forest Resources

Mapping from Space

Oceanography/Coastal Zone

Topics Including Education

Hyper Spectral Image Processing

Image Processing

Geology

Environment

GIS

Global Change

Airborne Remote Sensing

Poster Sessions
  • Session 1
  • Session 2
  • Session 3
  • Session 4
  • Session 5
  • Session 6



  • ACRS 1999


    Poster Session 1
    Comparison of jers-1 and radarsat synthetic aperture Radar data for mapping mangrove and its biomass

    Results and Discussion

    Classification of mangrove and species determination
    Unsupervised-supervised approach with maximum likelihood classifier was performed on JERS-1 and Radarsat image (Figure 2). Seven classes can be defined from JERS-1 and five classes from Radarsat. In both images, Rhizophora are still the dominant species where it covers 45.2 % of JERS-1 and 55.4 % of Radarsat data. Accuracy points were carefully selected to avoid error and confusion due to inclusion of mixed, border/edge pixels (Table 2).

    Error matrix were created and figures for User’s Accuracy, Producer’s Accuracy, and Combined Accuracy (kappa statistic) compiled to evaluate the quality of each classification. User’s Accuracy is a ratio statistic compiled by dividing the number of pixels correctly assigned to a category by the total number of pixels to the category. Producer’s Accuracy is calculated by dividing the number of accuracy pixels correctly assigned to a category by the number of accuracy pixels selected for that category. These two measures are useful in defining the type of classifications errors made and provide differents perspectives of accuracy. Results show Radarsat that (5.6 cm wavelength) is less sensitive compare with JERS-1 (23.5 cm). The lower accuracy existence in mangrove classification mapping especially in study area due to the mixed species.

    Table 2: Error matrix of classification statistic for JERS-1 SAR and Radarsat
    Dataset Classes JERS-1 SAR Radarsat
    User’s AccuracyProducer’s AccuracyUser’s AccuracyProducer’s Accuracy
    Muddy plants and Sonneratia sp 100% 67% 100% 50%
    Bareland and small mangroves 50% 44% - -
    Avicennia sp and others small mangroves- - 40% 67%
    Avicennia sp and Ceriops sp 50% 75% - -
    Small mangroves 50% 38% - -
    Rhizophora sp 60% 46% 50% 38%
    Mature Rhizophora 45% 71% 43% 30%
    Bruguiera sp and Xylocarpus sp 43% 50% 45% 45%
    Overall Accuracy 52 46
    KHAT 43 30




    (a)



    (b)

    Figure 2:
    Mangrove species classified from (a) JERS-1 SAR, and (b) Radarsat

    Page 2 of 3
    | Previous | Next |

    Applications | Technology | Policy | History | News | Tenders | Events | Interviews | Career | Companies | Country Pages | Books | Publications | Education | Glossary | Tutorials | Downloads | Site Map | Subscribe | GIS@development Magazine | Updates | Guest Book