Background subtraction is a widely used technique for detecting moving objects in image sequences.Very often background subtraction approaches assume the availability of one or more clear (i.e., withoutforeground objects) frames at the beginning of the sequence in input. However, this assumption isnot always true, especially when dealing with dynamic background or crowded scenes. In this paper,we present the results of a multi-modal background modeling method that is able to generate a reliableinitial background model even if no clear frames are available. The proposed algorithm runs in real–time on HD images. Quantitative experiments have been conducted taking into account six dierentquality metrics on a set of 14 publicly available image sequences. The obtained results demonstrate ahigh-accuracy in generating the background model in comparison with several other methods.
Parallel multi-modal background modeling
BLOISI, Domenico Daniele;
2017-01-01
Abstract
Background subtraction is a widely used technique for detecting moving objects in image sequences.Very often background subtraction approaches assume the availability of one or more clear (i.e., withoutforeground objects) frames at the beginning of the sequence in input. However, this assumption isnot always true, especially when dealing with dynamic background or crowded scenes. In this paper,we present the results of a multi-modal background modeling method that is able to generate a reliableinitial background model even if no clear frames are available. The proposed algorithm runs in real–time on HD images. Quantitative experiments have been conducted taking into account six dierentquality metrics on a set of 14 publicly available image sequences. The obtained results demonstrate ahigh-accuracy in generating the background model in comparison with several other methods.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
