The real time detection of moving objects in video sequences has many important applications . This paper proposes the FPGA hardware implementation of segmentation and denoising units. The segmentation is conducted using the Gaussian Mixture Model (GMM), a probabilistic method for the moving objects identification. The implemented algorithm is the OpenCV (Open source Computer Vision library) version of the GMM. The denoising is conducted implementing the morphological operators of erosion, dilation, opening and closing. The proposed HW design achieves real time processing of HD (High Definition, frame size 1920x1080) video sequences.
FPGA architecture for real time video segmentation and denoising / Genovese, Mariangela; Petra, Nicola; DE CARO, Davide; Napoli, Ettore; Strollo, ANTONIO GIUSEPPE MARIA. - STAMPA. - (2012), pp. 7-8. (Intervento presentato al convegno GE2012, 44th Conference tenutosi a Marina di Carrara, (I) nel June 20-22, 2012).
FPGA architecture for real time video segmentation and denoising
GENOVESE, MARIANGELA;PETRA, NICOLA;DE CARO, Davide;NAPOLI, ETTORE;STROLLO, ANTONIO GIUSEPPE MARIA
2012
Abstract
The real time detection of moving objects in video sequences has many important applications . This paper proposes the FPGA hardware implementation of segmentation and denoising units. The segmentation is conducted using the Gaussian Mixture Model (GMM), a probabilistic method for the moving objects identification. The implemented algorithm is the OpenCV (Open source Computer Vision library) version of the GMM. The denoising is conducted implementing the morphological operators of erosion, dilation, opening and closing. The proposed HW design achieves real time processing of HD (High Definition, frame size 1920x1080) video sequences.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
