Processor core for real time background identification of HD video based on OpenCV Gaussian mixture model algorithm

The identification of moving objects is a fundamental step in computer vision processing chains. The development of low cost and lightweight smart cameras steadily increases the request of efficient and high performance circuits able to process high definition video in real time. The paper proposes two processor cores aimed to perform the real time background identification on High Definition (HD, 1920 1080 pixel) video streams. The implemented algorithm is the OpenCV version of the Gaussian Mixture Model (GMM), an high performance probabilistic algorithm for the segmentation of the background that is however computationally intensive and impossible to implement on general purpose CPU with the constraint of real time processing. In the proposed paper, the equations of the OpenCV GMM algorithm are optimized in such a way that a lightweight and low power implementation of the algorithm is obtained. The reported performances are also the result of the use of state of the art truncated binary multipliers and ROM compression techniques for the implementation of the non-linear functions. The first circuit has commercial FPGA devices as a target and provides speed and logic resource occupation that overcome previously proposed implementations. The second circuit is oriented to an ASIC (UMC-90nm) standard cell implementation. Both implementations are able to process more than 60 frames per second in 1080p format, a frame rate compatible with HD television.

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

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

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

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

[5]  Davide De Caro,et al.  A novel truncated squarer with linear compensation function , 2010, Proceedings of 2010 IEEE International Symposium on Circuits and Systems.

[6]  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.

[7]  Ettore Napoli,et al.  An FPGA-based Real-time Background Identification Circuit for 1080p Video , 2012, 2012 Eighth International Conference on Signal Image Technology and Internet Based Systems.

[8]  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).

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

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

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

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

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

[14]  Davide De Caro,et al.  Fixed-Width Multipliers and Multipliers-Accumulators With Min-Max Approximation Error , 2013, IEEE Transactions on Circuits and Systems I: Regular Papers.

[15]  Ettore Napoli,et al.  ASIC and FPGA Implementation of the Gaussian Mixture Model Algorithm for Real-Time Segmentation of High Definition Video , 2014, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[16]  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.

[17]  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).

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

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

[20]  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.

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

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

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

[24]  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..

[25]  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.

[26]  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.

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

[28]  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.

[29]  Davide De Caro,et al.  A novel high-speed sense-amplifier-based flip-flop , 2005, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[30]  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.

[31]  Davide De Caro,et al.  FPGA Implementation of Gaussian Mixture Model Algorithm for 47 fps Segmentation of 1080p Video , 2013, J. Electr. Comput. Eng..