Retrival of Remotely sensed images using multimodal approach

Abstract

With advances in space-borne imaging sensor technology, the potential for building geospatial databases has increased immensely; yet extracting target information from the high resolution remotely sensed images still poses a challenging problem. Many satellites have been launched to analyse different terrain regions such as deserts, coastal areas, metro s, vegetation, to carry out geological surveys for environmental monitoring, disaster forecasting etc. These satellites acquire a large number of images everyday leading to an exponential increase in the database containing unstructured and unorganized satellite images. newlineHence there is imminent need to develop a robust system to retrieve a set of images from this unstructured database that will meet the user s requirement. Conventional query processing systems are based on matching keywords such as time of acquisition, geographic locations, sensor types, etc. The proposed work in this thesis identifies and overcomes the gaps related to this traditional query processing system with the objective to simultaneously improve retrieval performance and to reduce the execution time. newlineLooking at the expected technical improvements in the spatial and spectral resolution of the sensors, satellite imagery could provide a basis for complex information systems to recognize and extract even small-scale and structural features of interest. The analysis of large volumes of multi-sensor satellite data will then definitely require a high degree of automation for processing, analysis and interpretation in order to extract the features of interest. Appropriate selection of features, correct image segmentation and classification techniques are the deciding factors to analyse and retrieve high resolution remotely sensed imagery. Features that can be extracted from this imagery include facilities (e.g. buildings foot prints), transportation features, land use/land cover, vegetation types (e.g. agriculture, forest types), water bodies, desert regions, soil types, coastal regions and many mo