SEMIAUTOMATIC CLASSIFICATION PROCEDURES FOR FIRE MONITORING USING MULTITEMPORAL SAR IMAGES AND NOAA-AVHRR HOTSPOT DATA
暂无分享,去创建一个
Large scale fire monitoring using remote sensing imagery is an important environmental task. Following the severe wildfires of 1997/98 in Indonesia, the need for an operational monitoring system became obvious. Based on object oriented image analysis techniques an application was implemented to generate fire damage maps out of a combination of ERS SAR images, vegetation maps and NOAA-AVHRR hotspot data. The application uses a modular approach which distinguishes classification rules based on pixel values from spatial ones and thereby allows the user to easily adapt the analysis routine to new input data if necessary. An XML based Wizard guides the analyst through the classification process and allows even an untrained user to handle the software. This way a monitoring application was generated, which allows to quickly produce the needed information.
[1] Florian Siegert,et al. The 1998 Forest Fires in East Kalimantan (Indonesia): A Quantitative Evaluation Using High Resolution, Multitemporal ERS-2 SAR Images and NOAA-AVHRR Hotspot Data , 2000 .
[2] F. Siegert,et al. Use of multitemporal ERS-2 SAR images for identification of burned scars in south-east Asian tropical rainforest , 2000 .
[3] Yunhan Dong,et al. Segmentation and classification of vegetated areas using polarimetric SAR image data , 2001, IEEE Trans. Geosci. Remote. Sens..