Global-Local Feature Fusion for Image Classification of Flood Affected Roads from Social Multimedia

Benjamin Bischke, Patrick Helber, Andreas Dengel

In: Working Notes Proceedings of the MediaEval 2018. MediaEval Benchmark (MediaEval) MediaEval 2018.


This paper presents the solution of the DFKI-team for the Multimedia Satellite Task 2018 at MediaEval. We address the challenge of social multimedia classification with respect to road passability during flooding events. Information about road passability is an important aspect within the context of emergency response and is not well studied in the past. In this paper, we primarily investigate in the visual classification based on global, local and global-local fused image features. We show that local features of objects can be efficiently used for road passability classification and achieve similarly good results with local features as with global features. When we fused global and local visual features, we did not achieve a significant outperformance against global features alone but see a lot of potential for future research in this direction.

MediaEval_18_paper_62.pdf (pdf, 3 MB )

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence