Proceedings ArticleDOI
FPGA/soft-processor based real-time object tracking system
Usman Ali,Mohammad Bilal Malik,Khalid Munawar +2 more
- pp 33-37
TLDR
A low cost FPGA based solution for a real-time moving object tracking system based on a soft RISC processor capable of running kernel based mean shift tracking algorithm within the required time constraint is presented.Abstract:
This paper presents a low cost FPGA based solution for a real-time moving object tracking system. A specialized architecture is presented based on a soft RISC processor capable of running kernel based mean shift tracking algorithm. The system includes a frame grabber unit that stores the video frame in DDR RAM using direct memory access, a video display unit to monitor the tracking statistics and a soft processor capable of running mean shift tracking algorithm within the required time constraint.read more
Citations
More filters
Journal ArticleDOI
A systematic literature review on hardware implementation of artificial intelligence algorithms
TL;DR: This work presents a systematic literature review that focuses on exploring the available hardware accelerators for the AI and ML tools, using FPGAs, GPUs and ASICs to accelerate computationally intensive tasks.
Journal ArticleDOI
A self-adaptive heterogeneous multi-core architecture for embedded real-time video object tracking
TL;DR: This article presents a video tracking application modeled on top of a framework for implementing SMC methods on CPU/FPGA-based systems such as modern platform FPGAs and demonstrates the application and the framework on a real-life video tracking case study and shows that partial reconfiguration can be effectively and transparently used for realizing adaptive real-time HW/SW systems.
Proceedings ArticleDOI
Real-Time Object Tracking System on FPGAs
TL;DR: This paper proposes a dual object region search technique to further boost the performance of the system under complex tracking conditions and compares the proposed FPGA-based implementation with the software implementation running on a 2.2 GHz processor.
Journal ArticleDOI
A real-time, power-efficient architecture for mean-shift image segmentation
TL;DR: A novel hardware architecture is proposed that exploits the customizable computing power of FPGAs and reduces the execution time by clustering pixels in parallel while meeting the low-power demands of embedded applications.
Journal ArticleDOI
Hardware/software co-design of a real-time kernel based tracking system
Usman Ali,Mohammad Bilal Malik +1 more
TL;DR: A hardware/software co-design architecture for implementation of the well-known kernel based mean shift tracking algorithm based on gradient based iterative search instead of exhaustive search which makes the system capable of achieving frame rate up to hundreds of frames per second while tracking multiple targets.
References
More filters
Proceedings Article
An iterative image registration technique with an application to stereo vision
Bruce D. Lucas,Takeo Kanade +1 more
TL;DR: In this paper, the spatial intensity gradient of the images is used to find a good match using a type of Newton-Raphson iteration, which can be generalized to handle rotation, scaling and shearing.
Proceedings ArticleDOI
Real-time tracking of non-rigid objects using mean shift
TL;DR: The theoretical analysis of the approach shows that it relates to the Bayesian framework while providing a practical, fast and efficient solution for real time tracking of non-rigid objects seen from a moving camera.
Journal ArticleDOI
The estimation of the gradient of a density function, with applications in pattern recognition
K. Fukunaga,L. Hostetler +1 more
TL;DR: Applications of gradient estimation to pattern recognition are presented using clustering and intrinsic dimensionality problems, with the ultimate goal of providing further understanding of these problems in terms of density gradients.
Journal ArticleDOI
The Divergence and Bhattacharyya Distance Measures in Signal Selection
TL;DR: This partly tutorial paper compares the properties of an often used measure, the divergence, with a new measure that is often easier to evaluate, called the Bhattacharyya distance, which gives results that are at least as good and often better than those given by the divergence.
Journal ArticleDOI
FPGA-based real-time optical-flow system
TL;DR: To the best of the knowledge, this is the first study that presents a fully stand-alone optical-flow processing system to include measurements of the platform performance in terms of accuracy and speed.
Related Papers (5)
The estimation of the gradient of a density function, with applications in pattern recognition
K. Fukunaga,L. Hostetler +1 more