Affiliations: [a] INAOE (Coordination of Computer Science), Tonantzintla, Puebla, México | [b] Regional Centre of Space Science and Technology Education for Latin America and the Caribbean, Tonantzintla, Puebla, México
Correspondence:
[*]
Corresponding author: Jorge Morales, INAOE (Coordination of Computer Science), A. P. 72840, Tonantzintla, Puebla, México. Tel.: +52(222)2663106x8303; Fax: +52(222)2663152; E-mail: [email protected].
Abstract: In nature, there exist transition regions between homogeneous land-cover changes. These specific regions cause ambiguity and uncertainty to segmentation and classification algorithms when applied to remote sensed images. Our research, proposes a novel method called TReDet to identify transition regions in the way they are found in nature. They appear in a random way without following a defined geometric pattern. Experimental results with synthetic images show that TReDet clearly outperforms commercial software using some of the quantitative measures used to evaluate our method. Even when in some cases the difference in percentage is not so high (for some of the measures used), TReDet obtains a more realistic segmentation of the transition regions. Furthermore, it does not follow parallel transition bands (or any other geometric pattern) avoiding the errors falling in the borderline of the transition region of other methods.
Keywords: Spatial data analysis, satellite image classification, transition regions identification, land covers, segmentation, uncertainty
