Improved Partition Trees for Multi-Class Segmentation of Remote Sensing Images

Emmanuel Maggiori (1, 2) , Yuliya Tarabalka (1, 2) , Guillaume Charpiat (3, 4)

1 AYIN - Models of spatio-temporal structure for high-resolution image processing
2 TITANE - Geometric Modeling of 3D Environments
3 STARS - Spatio-Temporal Activity Recognition Systems
4 TAO - Machine Learning and Optimisation

We propose a new binary partition tree (BPT)-based framework for multi-class segmentation of remote sensing images. In the literature, BPTs are typically computed in a bottom-up manner based on spectral similarities, then analyzed to extract image objects. When image objects exhibit a considerable internal spectral variability, it often happens that such objects are composed of several disjoint regions in the BPT, yielding errors in object extraction. We pose the multi-class segmentation problem as an energy minimization task and solve it by using BPTs. Our main contribution consists in introducing a new dissimilarity function for the tree construction , which combines both spectral discrepancies and supervised class-specific information to take into account the within-class spectral variability. The experimental validation proved that the proposed method constitutes a competitive alternative for object-based image classification.

Mots clés: Binary partition tree; Segmentation; Object-based classification; Energy minimization

Domaines: Traitement des images [eess.IV]

Emmanuel Maggiori, Yuliya Tarabalka, Guillaume Charpiat. Improved Partition Trees for Multi-Class Segmentation of Remote Sensing Images. 2015 IEEE International Geoscience and Remote Sensing Symposium - IGARSS 2015, IEEE, Jul 2015, Milan, Italy. ⟨hal-01182772⟩