Institutional Repository [SANDBOX]
Technical University of Crete
EN  |  EL

Search

Browse

My Space

Self adaptive background modeling for identifying persons' falls

Doulamis Anastasios, Kalisperakis, I, Stentoumis, C, Matsatsinis Nikolaos

Full record


URI: http://purl.tuc.gr/dl/dias/E04E8031-70F3-4335-811B-B60749E26125
Year 2010
Type of Item Conference Full Paper
License
Details
Bibliographic Citation A. Doulamis, I. Kalisperakis, C. Stentoumis, N. Matsatsinis, "Self Adaptive background modeling for identifying persons' falls," in 2010 Semantic Media Adaptation and Personalization , 5th International Workshop on(SMAP), pp. 57 - 63, doi: 10.1109/SMAP.2010.5706861 https://doi.org/10.1109/SMAP.2010.5706861
Appears in Collections

Summary

This paper presents a new scheme for detecting humans' falls in highly dynamic house environments. The scheme distinguishes falls from other humans' activities, like sitting, walking, lying, under (a) sudden and abrupt illumination changes (b) non-periodic/significant motions in the background (chairs, curtains, tables), (c) humans' movements towards all possible directions across camera. In particular, we combine adaptive background models - able to capture slight modifications of the background patterns with motion-based algorithms that define with high confidence parts of an image that should be considered as foreground/background after a significant visual change. We adopt Gaussian Mixtures for the adaptive background modeling, while we propose hierarchical motion estimation algorithms implemented on selective descriptors. The algorithms are of real time and require single low cost cameras.

Services

Statistics