Student-t background modeling for persons' fall detection through visual cues

This article presents a robust, real-time background subtraction algorithm able to operate properly in complex dynamically changing visual conditions and indoor/outdoor environments, based on a single, cheap monocular camera, like a webcam. This algorithm uses an image grid and models each pixel of the grid as a mixture of adaptive Student-t distributions. This approach makes this algorithm robust and efficient, in terms of computational cost and memory requirements, and thus suitable for large scale implementations. The proposed algorithm is applied in the problem of humans' fall detection that presents high complexity of visual content. Finally, the performances of this scheme and the scheme proposed in [1] by the same authors, are compared.