Abstract
Blending processing based on seamlines in image mosaicking is a procedure designed to obtain a smooth transition between images along seamlines and make seams invisible in the final mosaic. However, for high-resolution aerial orthoimages in urban areas, factors such as projection differences, moving objects, and radiometric differences in overlapping areas may result in ghosting and artifacts or visible shifts in the final mosaic. Such a mosaic is not a true reflection of the earth’s surface and may have a negative impact on image interpretation. Therefore, this paper presents a multi-resolution blending method considering changed regions to improve mosaic image quality. The method utilizes the region change rate (RCR) to distinguish changed regions from unchanged regions in overlapping areas. The RCR of each region is computed using image segmentation and change detection methods. Then, a mask image is generated considering changed regions, and Gaussian and Laplacian pyramids are constructed. Finally, a multi-resolution reconstruction is performed to obtain the final mosaic. Experimental results from digital aerial orthoimages in urban areas are provided to verify this method for blending processing based on seamlines in mosaicking. Comparisons with other methods further demonstrate the potential of the presented method, as shown in a detailed comparison in three typical cases of the seamline passing by buildings, the seamline passing through buildings, and the seamline passing through areas with large radiometric differences.
Highlights
Orthoimage mosaicking is the process of combining multiple orthorectrified images into a single seamless composite image
This paper focuses on the blending processing in mosaicking, i.e., a procedure to obtain a smooth transition between images along seamlines
The Edge Detection and Image SegmentatiON (EDISON) library is used for image segmentation and the Geospatial Data Abstraction Library (GDAL) is used to read and write image files
Summary
Orthoimage mosaicking is the process of combining multiple orthorectrified images into a single seamless composite image. It is a necessary process for covering a large geographic region in many applications, e.g., environmental monitoring, disaster management, and the construction of digital cities or smart cities [1,2]. The seam-based method is the most popular method. In mosaicking, each pixel in the final result is represented entirely by one orthoimage based on which side of the seamline it lies on. A blending processing, called feathering, based on seamlines is performed to make the seam invisible in the final mosaic. This paper focuses on the blending processing in mosaicking, i.e., a procedure to obtain a smooth transition between images along seamlines
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
