A Comparison of Object-oriented and Pixel-based Classification Approachs Using Quickbird Imagery

Many studies have been carried out to find an appropriate method to classify the remote sensing data.Traditional classification approaches are all pixel-based, and do not utilize the spatial information within an object which is an important source of information to image classification. Instead of pixels, pixel groups and object oriented techniques offer the suitable analysed to classify satellite data. To compare the object-oriented with pixel-based classification approach, a study in a small area using QuickBird data has been accomplished in this paper. In the object-oriented approach, images were segmented to homogenous area by suitable parameters in some level.Classification based on segments was done by a nearest neighbor classifier. In the pixel-based classification, the maxium likelihood classifier was used to classify the images. The result of classification and accuracy assessment show that the object-oriented approach gave more accurate and satisfying results.