Efficient and Effective Hierarchical Feature Propagation

Author(s)

dos Santos, Jefersson A. ; Penatti, Otavio A. B. ; Gosselin, Philippe-Henri ; Falcao, Alexandre X. ; Philipp-Foliguet, Sylvie ; Torres, Ricardo da S.

• Document type: Journal article
• Source: IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING; v. 7, n. 12, p. 12-pg., 2014-12-01.

Abstract

Many methods have been recently proposed to deal with the large amount of data provided by the new remote sensing technologies. Several of those methods rely on the use of segmented regions. However, a common issue in region-based applications is the definition of the appropriate representation scale of the data, a problem usually addressed by exploiting multiple scales of segmentation. The use of multiple scales, however, raises new challenges related to the definition of effective and efficient mechanisms for extracting features. In this paper, we address the problem of extracting features from a hierarchy by proposing two approaches that exploit the existing relationships among regions at different scales. The H-Propagation propagates any histogram-based low-level descriptors. The bag-of-visual-word (BoW)-Propagation approach uses the BoWs model to propagate features along multiple scales. The proposed methods are very efficient, as features need to be extracted only at the base of the hierarchy and yield comparable results to low-level extraction approaches. (AU)

• FAPESP's process: 12/18768-0 - Multiscale Classification By Using Optimum Path-Forest
• Grantee: Jefersson A dos Santos
• Support Opportunities: Scholarships in Brazil - Post-Doctoral
• FAPESP's process: 13/50169-1 - Towards an understanding of tipping points within tropical South American biomes
• Grantee: Ricardo da Silva Torres
• Support Opportunities: Research Grants - Research Partnership for Technological Innovation - PITE
• FAPESP's process: 13/50155-0 - Combining new technologies to monitor phenology from leaves to ecosystems
• Grantee: Leonor Patricia Cerdeira Morellato
• Support Opportunities: Research Program on Global Climate Change - University-Industry Cooperative Research (PITE)
• FAPESP's process: 09/10554-8 - Exploring Visual Dictionaries for Web Image Retrieval
• Grantee: Otávio Augusto Bizetto Penatti
• Support Opportunities: Scholarships in Brazil - Doctorate