TY  - JOUR
AU  - Ivan Huerta
AU  - Ariel Amato
AU  - Xavier Roca
AU  - Jordi Gonzalez
PY  - 2013//
TI  - Exploiting Multiple Cues in Motion Segmentation Based on Background Subtraction
T2  - NEUCOM
JO  - Neurocomputing
SP  - 183–196
VL  - 100
PB  - Elsevier
KW  - Motion segmentation
KW  - Shadow suppression
KW  - Colour segmentation
KW  - Edge segmentation
KW  - Ghost detection
KW  - Background subtraction
N2  - This paper presents a novel algorithm for mobile-object segmentation from static background scenes, which is both robust and accurate under most of the common problems found in motionsegmentation. In our first contribution, a case analysis of motionsegmentation errors is presented taking into account the inaccuracies associated with different cues, namely colour, edge and intensity. Our second contribution is an hybrid architecture which copes with the main issues observed in the case analysis by fusing the knowledge from the aforementioned three cues and a temporal difference algorithm. On one hand, we enhance the colour and edge models to solve not only global and local illumination changes (i.e. shadows and highlights) but also the camouflage in intensity. In addition, local information is also exploited to solve the camouflage in chroma. On the other hand, the intensity cue is applied when colour and edge cues are not available because their values are beyond the dynamic range. Additionally, temporal difference scheme is included to segment motion where those three cues cannot be reliably computed, for example in those background regions not visible during the training period. Lastly, our approach is extended for handling ghost detection. The proposed method obtains very accurate and robust motionsegmentation results in multiple indoor and outdoor scenarios, while outperforming the most-referred state-of-art approaches.
L1  - http://refbase.cvc.uab.es/files/HAR2013.pdf
UR  - http://dx.doi.org/10.1016/j.neucom.2011.10.036
N1  - ISE
ID  - Ivan Huerta2013
ER  -