Hardware implementation of optical flow constraint equation using FPGAs

Martín, José Luis Martín; Zuloaga, Aitzol; Cuadrado, Carlos; Laizaro, Jesus; Bidarte, Unai

doi:10.1016/j.cviu.2004.10.002

Cited by 67 publications

(31 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Initially, the default result is assumed as zero for all optic flow field vectors. In a recent work, Martin et al [13] show a new optical flow computing technique. In this work, the iterations are made between a set of successive images in an image sequence, not only between a pair of two consecutive images.…”

Section: Implementation Considerationsmentioning

confidence: 99%

See 1 more Smart Citation

Change-driven data flow image processing architecture for optical flow computation

Sosa¹,

Boluda

Pardo

et al. 2007

J Real-Time Image Proc

View full text Add to dashboard Cite

Optical flow computation has been extensively used for motion estimation of objects in image sequences. The results obtained by most optical flow techniques are computationally intensive due to the large amount of data involved. A new change-based data flow pipelined architecture has been developed implementing the Horn and Schunk smoothness constraint; pixels of the image sequence that significantly change, fire the execution of the operations related to the image processing algorithm. This strategy reduces the data and, combined with the custom hardware implemented, it achieves a significant optical flow computation speed-up with no loss of accuracy. This paper presents the bases of the change-driven data flow image processing strategy, as well as the implementation of custom hardware developed using an Altera Stratix PCI development board.

show abstract

Section: Implementation Considerationsmentioning

confidence: 99%

“…Moreover, there are few works that pay attention to the computational speed aspects, like achieving faster speed with real-time constraints. Additionally, novel theoretical analysis of motion and optical flow estimation encourage the use of custom-embedded architectures [13].…”

Section: Introductionmentioning

confidence: 99%

Change-driven data flow image processing architecture for optical flow computation

Sosa¹,

Boluda

Pardo

et al. 2007

J Real-Time Image Proc

View full text Add to dashboard Cite

show abstract

“…FPGA implementations of the Lucas and Kanade feature tracker [15], [16] are presented in [17] and [18]. In [12], the Horn and Schunck optical flow algorithm [19] is implemented, while [13] presents a tensorbased optical flow [20] FPGA implementation.…”

Section: Algorithmic Considerations a Optical Flow Estimationmentioning

confidence: 99%

Robust Real-Time Super-Resolution on FPGA and an Application to Video Enhancement

Angelopoulou

Bouganis

Cheung

et al. 2009

ACM Trans. Reconfigurable Technol. Syst.

View full text Add to dashboard Cite

Abstract-The use of Unmanned Aerial Vehicles (UAVs) in commercial and warfare activities has intensified over the last decade. One of the main challenges is to enable UAVs to become as autonomous as possible. A vital component towards this direction is the robust and accurate estimation of the egomotion of the UAV. Egomotion estimation can be enhanced by equipping the UAV with a video camera, which enables a visionbased egomotion estimation. However, the high computational requirements of vision-based egomotion algorithms, combined with the real-time performance and low power consumption requirements that are related to such an application, cannot be met by general-purpose processing units. This work presents a system architecture that employs a Field Programmable Gate Array (FPGA) as the main processing platform connected to a low-power CPU that targets the problem of vision-based egomotion estimation in a UAV. The performance evaluation of the proposed system, using real data captured by a UAV's onboard camera, demonstrates the ability of the system to render accurate estimation of the egomotion parameters, meeting at the same time the real-time requirements imposed by the application.

show abstract

“…Gradientbased methods that can estimate the optical flow by calculating the brightness gradients of images, unlike correlationbased methods [5], [6], are suitable for real-time optical flow estimation, because heavy computation is not required to calculate brightness gradients locally. There have been several reports of hardware implementations for gradient-based methods that can simultaneously estimate optical flow at a frame rate of several dozen frames per second (fps) at VGA resolution or better [7]- [9]. Furthermore, with the rapid progress in processor performance, real-time optical flow estimation for camera inputs with video signals (e.g., NTSC at 30 fps and PAL 25 at fps) has become possible by using only software-based gradient-based methods on a personal computer (PC), and gradient-based methods have been widely used to estimate the motion field in real time for real-world applications.…”

Section: Introductionmentioning

confidence: 99%

Accuracy of Gradient-Based Optical Flow Estimation in High-Frame-Rate Video Analysis

Chen

Takaki

Ishii

2012

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

Lei CHEN†a) , Nonmember, Takeshi TAKAKI †b) , and Idaku ISHII †c) , Members SUMMARYThis study investigates the effect of frame intervals on the accuracy of the Lucas-Kanade optical flow estimates for high-frame-rate (HFR) videos, with a view to realizing accurate HFR-video-based optical flow estimation. For 512 × 512 pixels videos of patterned objects moving at different speeds and captured at 1000 frames per second, the averages and standard deviations of the estimated optical flows were determined as accuracy measures for frame intervals of 1-40 ms. The results showed that the accuracy was highest when the displacement between frames was around 0.6 pixel/frame. This common property indicates that accurate optical flow estimation for HFR videos can be realized by varying frame intervals according to the motion field: a small frame interval for high-speed objects and a large frame interval for low-speed objects. key words: gradient-based optical flow, accuracy, high-frame-rate videos

show abstract

Hardware implementation of optical flow constraint equation using FPGAs

Cited by 67 publications

References 36 publications

Change-driven data flow image processing architecture for optical flow computation

Change-driven data flow image processing architecture for optical flow computation

Robust Real-Time Super-Resolution on FPGA and an Application to Video Enhancement

Accuracy of Gradient-Based Optical Flow Estimation in High-Frame-Rate Video Analysis

Contact Info

Product

Resources

About