Model-Based OpenMP Implementation of a 3D Facial Pose Tracking System

Saha, Subhajit; Shen, Chung-Ching; Hsu, Chia-Jui; Aggarwal, Gaurav; Veeraraghavan, Ashok; Sussman, Alan; Bhattacharyya, Shuvra S.

doi:10.1109/icppw.2006.55

Cited by 8 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A high number of image processing applications involved processes that are computation-intensive where memory consumption and performance requirements are high [8]. Hence, implementation solutions to image processing applications on shared-memory systems based on a parallel basis is an attractive option.…”

Section: Related Workmentioning

confidence: 99%

Investigation of Threading Building Blocks Framework on Real Time Visual Object Tracking Algorithm

Ang¹,

Sundararajan

et al. 2014

AMM

View full text Add to dashboard Cite

Object tracking plays important roles in various applications such as surveillance, search and rescue, augmented reality and robotics. This paper presents an investigation on multi-threading framework capability for color-based object tracking applications. A multi-threading framework based on Threading Building Blocks (TBB) was implemented on a multi-core system to enhance the image processing performance on a real-time visual object tracking algorithm. Intel Parallel Studio was used to implement this parallel framework. The performance between sequential and multi-threading framework was evaluated and compared. We demonstrated the multi-threading framework was approximately two times faster when compared to the sequential framework in our experiments.

show abstract

Section: Related Workmentioning

confidence: 99%

Investigation of Threading Building Blocks Framework on Real Time Visual Object Tracking Algorithm

Ang¹,

Sundararajan

et al. 2014

AMM

View full text Add to dashboard Cite

show abstract

“…However, this work mainly concentrates at the algorithmic level. In [67], a shared memory multiprocessor implementation of a particle-filter-based 3D facial pose tracking algorithm was developed. This implementation was shown to provide significant performance gains.…”

Section: Parameterized Design Framework For Particle Filter Systemsmentioning

confidence: 99%

Design Methodology for Embedded Computer Vision Systems

Bhattacharyya

Saha

2009

Embedded Computer Vision

View full text Add to dashboard Cite

Computer vision has emerged as one of the most popular domains of embedded applications. Though various new powerful embedded platforms to support such applications have emerged in recent years, there is a distinct lack of efficient domain-specific synthesis techniques for optimized implementation of such systems. In this thesis, four different aspects that contribute to efficient design and synthesis of such systems are explored:(1) Graph Transformations: Dataflow modeling is widely used in digital signal processing (DSP) systems. However, support for dynamic behavior in such systems exists mainly at the modeling level and there is a lack of optimized synthesis techniques for these models. New transformation techniques for efficient system-on-chip (SoC) design methods are proposed and implemented for cyclo-static dataflow and its parameterized version (parameterized cyclo-static dataflow) -two powerful models that allow dynamic reconfigurability and phased behavior in DSP systems.

show abstract

“…Given the current configuration, the grids can be projected onto the image frame and the mean can be computed for each of them; a perspective projection of the cylinder and the grids is used. For further details please refer to [14]. Fig.…”

Section: Application Overviewmentioning

confidence: 99%

“…In such mixed-mode approaches, the analog components are used for the non-linear computations that are involved in particle filtering [19]. In design efforts towards computer vision applications, in [14] a shared memory multiprocessor implementation of a particle-filter-based 3D facial pose tracking algorithm was developed which was shown to provide significant performance gains. However, the implementation domain was not embedded platforms.…”

Section: Related Workmentioning

confidence: 99%

“…A possible solution for real-time implementation of such systems is parallelization and the use of multiprocessor systems; but this is also restricted because of the presence of an unavoidable computing step (resampling), which is serial in nature, and therefore difficult to parallelize. Nonetheless, parallel software implementation of particle filter based tracking applications have been explored such as the one demonstrated in [14] where a high-speed multiprocessor cluster comprising of 24 SUN UltraSparcIII machines running at 750 MHz was used as the target platform. Such tracking applications are of great significance to various embedded systems such as smart cameras that do not feature such powerful computing platforms.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Design and implementation of embedded computer vision systems based on particle filters

Saha

Bambha

Bhattacharyya

2010

Computer Vision and Image Understanding

View full text Add to dashboard Cite

a b s t r a c tParticle filtering methods are gradually attaining significant importance in a variety of embedded computer vision applications. For example, in smart camera systems, object tracking is a very important application and particle filter based tracking algorithms have shown promising results with robust tracking performance. However, most particle filters involve vast amount of computational complexity, thereby intensifying the challenges faced in their real-time, embedded implementation. Many of these applications share common characteristics, and the same system design can be reused by identifying and varying key system parameters and varying them appropriately. In this paper, we present a System-on-Chip (SoC) architecture involving both hardware and software components for a class of particle filters. The framework uses parameterization to enable fast and efficient reuse of the architecture with minimal re-design effort for a wide range of particle filtering applications as well as implementation platforms.Using this framework, we explore different design options for implementing three different particle filtering applications on field-programmable gate arrays (FPGAs). The first two applications involve particle filters with one-dimensional state transition models, and are used to demonstrate the key features of the framework. The main focus of this paper is on design methodology for hardware/software implementation of multi-dimensional particle filter application and we explore this in the third application which is a 3D facial pose tracking system for videos. In this multi-dimensional particle filtering application, we extend our proposed architecture with models for hardware/software co-design so that limited hardware resources can be utilized most effectively. Our experiments demonstrate that the framework is easy and intuitive to use, while providing for efficient design and implementation. We present different memory management schemes along with results on trade-offs between area (FPGA resource requirement) and execution speed.

show abstract

Model-Based OpenMP Implementation of a 3D Facial Pose Tracking System

Cited by 8 publications

References 13 publications

Investigation of Threading Building Blocks Framework on Real Time Visual Object Tracking Algorithm

Investigation of Threading Building Blocks Framework on Real Time Visual Object Tracking Algorithm

Design Methodology for Embedded Computer Vision Systems

Design and implementation of embedded computer vision systems based on particle filters

Contact Info

Product

Resources

About