Title :
A VLSI architecture for VGA 30 fps video segmentation with affine motion model estimation
Author :
Miyama, Masayuki ; Yunbe, Yoshiki ; Togo, Kouji ; Matsuda, Yoshio
Author_Institution :
Grad. Sch. of Natural Sci. & Technol., Kanazawa Univ., Ishikawa, Japan
Abstract :
This paper proposes a VLSI architecture for VGA 30 fps video segmentation with affine motion model estimation. The adopted algorithm is formulated as a contextual statistical labeling problem exploiting multiscale Markov random field (MRF) models. The algorithm optimization for VLSI implementation is characterized by image division method, ICM labeling limited to region boundary, and omission of motion models estimation for new regions. The optimization reduces the computational costs by 82%, the amount of memory by 95%, and the amount of data traffic by 99% without accuracy degradation. The VLSI architecture is characterized by pipeline processing of the divided images, concurrent motion models estimation for multiple regions, and a common processing element of update and detection labeling. The architecture enables VGA 30 fps video segmentation with 167 MHz frequency. The estimated core area using 0.18 ¿m technology is 30 mm2. This processor is applicable to the video recognition applications such as vehicle safety, robot, and surveillance systems under the restriction of energy consumption.
Keywords :
Markov processes; VLSI; image segmentation; motion estimation; optimisation; video signal processing; ICM labeling; VGA; VLSI architecture; affine motion model estimation; contextual statistical labeling problem; energy consumption; image division method; multiscale Markov random field models; optimization; robot; surveillance systems; vehicle safety; video recognition; video segmentation; Computational efficiency; Context modeling; Degradation; Image segmentation; Labeling; Markov random fields; Motion estimation; Optimization methods; Traffic control; Very large scale integration; FPGA; VLSI; affine motion model estimation; motion segmentation; real-time processing; video segmentation;
Conference_Titel :
Integrated Circuits, ISIC '09. Proceedings of the 2009 12th International Symposium on
Conference_Location :
Singapore
Print_ISBN :
978-9-8108-2468-6