FPGA Implementation of Gaussian Mixture Model Algorithm for 47 fps Segmentation of 1080p Video

Circuits and systems able to process high quality video in real time are fundamental in nowadays imaging systems. The circuit proposed in the paper, aimed at the robust identification of the background in video streams, implements the improved formulation of the Gaussian Mixture Model (GMM) algorithm that is included in the OpenCV library. An innovative, hardware oriented, formulation of the GMM equations, the use of truncated binary multipliers, and ROM compression techniques allow reduced hardware complexity and increased processing capability. The proposed circuit has been designed having commercial FPGA devices as target and provides speed and logic resources occupation that overcome previously proposed implementations. The circuit, when implemented on Virtex6 or StratixIV, processes more than 45 frame per second in 1080p format and uses few percent of FPGA logic resources.

[1]  Viktor Öwall,et al.  Hardware accelerator design for video segmentation with multi-modal background modelling , 2005, 2005 IEEE International Symposium on Circuits and Systems.

[2]  Zhihe Zhou,et al.  High performance direct digital frequency synthesizers , 2003, Proceedings of the 15th Biennial University/Government/ Industry Microelectronics Symposium (Cat. No.03CH37488).

[3]  Davide De Caro,et al.  Direct digital frequency synthesizers with polynomial hyperfolding technique , 2004, IEEE Transactions on Circuits and Systems II: Express Briefs.

[4]  P. KaewTrakulPong,et al.  An Improved Adaptive Background Mixture Model for Real-time Tracking with Shadow Detection , 2002 .

[5]  Larry S. Davis,et al.  A fast background scene modeling and maintenance for outdoor surveillance , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[6]  Viktor Öwall,et al.  An Embedded Real-Time Surveillance System: Implementation and Evaluation , 2008, J. Signal Process. Syst..

[7]  Davide De Caro,et al.  High-Performance Special Function Unit for Programmable 3-D Graphics Processors , 2009, IEEE Transactions on Circuits and Systems I: Regular Papers.

[8]  Davide De Caro,et al.  Elementary Functions Hardware Implementation Using Constrained Piecewise-Polynomial Approximations , 2011, IEEE Transactions on Computers.

[9]  Andreas Antoniou,et al.  Area-efficient multipliers for digital signal processing applications , 1996 .

[10]  Davide De Caro,et al.  Dual-tree error compensation for high performance fixed-width multipliers , 2005, IEEE Transactions on Circuits and Systems II: Express Briefs.

[11]  Hamid Aghajan,et al.  Video-based freeway-monitoring system using recursive vehicle tracking , 1995, Electronic Imaging.

[12]  K. P. Karmann,et al.  Moving object recognition using an adaptive background memory , 1990 .

[13]  Sun Han,et al.  A Practical Method for Moving Target Detection Under Complex Background , 2005 .

[14]  Hugo Jiménez-Hernández,et al.  Temporal Templates for Detecting the Trajectories of Moving Vehicles , 2009, ACIVS.

[15]  Olaf Munkelt,et al.  Adaptive Background Estimation and Foreground Detection using Kalman-Filtering , 1995 .

[16]  Chung-Cheng Chiu,et al.  A Robust Object Segmentation System Using a Probability-Based Background Extraction Algorithm , 2010, IEEE Transactions on Circuits and Systems for Video Technology.

[17]  Ettore Napoli,et al.  FPGA implementation of OpenCV compatible background identification circuit , 2012, CompIMAGE.

[18]  Alex Pentland,et al.  Pfinder: real-time tracking of the human body , 1996, Proceedings of the Second International Conference on Automatic Face and Gesture Recognition.

[19]  W. Eric L. Grimson,et al.  Adaptive background mixture models for real-time tracking , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[20]  Kentaro Toyama,et al.  Wallflower: principles and practice of background maintenance , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[21]  Davide De Caro,et al.  Low error truncated multipliers for DSP applications , 2008, 2008 15th IEEE International Conference on Electronics, Circuits and Systems.

[22]  Soraia Raupp Musse,et al.  Background Subtraction and Shadow Detection in Grayscale Video Sequences , 2005, XVIII Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI'05).

[23]  Liang-Gee Chen,et al.  Efficient moving object segmentation algorithm using background registration technique , 2002, IEEE Trans. Circuits Syst. Video Technol..

[24]  D. De Caro,et al.  Direct digital frequency synthesizers using high-order polynomial approximation , 2002, 2002 IEEE International Solid-State Circuits Conference. Digest of Technical Papers (Cat. No.02CH37315).

[25]  Richard Bowden,et al.  A real time adaptive visual surveillance system for tracking low-resolution colour targets in dynamically changing scenes , 2003, Image Vis. Comput..

[26]  Davide De Caro,et al.  Truncated Binary Multipliers With Variable Correction and Minimum Mean Square Error , 2010, IEEE Transactions on Circuits and Systems I: Regular Papers.

[27]  Song Zheng,et al.  An Improved Moving Object Detection Algorithm Based on Frame Difference and Edge Detection , 2007, Fourth International Conference on Image and Graphics (ICIG 2007).

[28]  E. Napoli,et al.  OpenCV compatible real time processor for background foreground identification , 2010, 2010 International Conference on Microelectronics.

[29]  Ettore Napoli,et al.  FPGA-based architecture for real time segmentation and denoising of HD video , 2013, Journal of Real-Time Image Processing.

[30]  Lu Cheng,et al.  Moving object detection and recognition based on the frame difference algorithm and moment invariant features , 2008, 2008 27th Chinese Control Conference.

[31]  Davide De Caro,et al.  Design of Fixed-Width Multipliers With Linear Compensation Function , 2011, IEEE Transactions on Circuits and Systems I: Regular Papers.

[32]  Valeria Garofalo.  Fixed-width multipliers for the implementation of efficient digital FIR filters , 2008, Microelectron. J..

[33]  Viktor Öwall,et al.  A Hardware Architecture for Real-Time Video Segmentation Utilizing Memory Reduction Techniques , 2009, IEEE Transactions on Circuits and Systems for Video Technology.

[34]  Ettore Napoli,et al.  Analytical Calculation of the Maximum Error for a Family of Truncated Multipliers Providing Minimum Mean Square Error , 2011, IEEE Transactions on Computers.