Retrieving Urban Objects Using a Wavelet Transform Approach

This paper studies the use of the wavelet transform in retrieving discrete objects from urban images. The multi-scale framework of the wavelet transform method is used to represent the edge information for the retrieval of industrial complexes from digital aerial photographs. The edge information for the target objects is extracted and enhanced using a set of retrieval parameters that include summary statistical indices for the detail sub-images of the wavelet transform, an edge-pixel index, weighting schemes for these indices, the level of the wavelet transform and the search window size. Results show that all of these retrieval parameters, except for the weighting schemes, are effective in retrieving the target objects, with the majority of retrieval rates reaching 60-90 percent. Although this study focuses on industrial complexes, other types of urban objects could also be retrieved using similar retrieval framework, parameters and strategies.