22nd International Conference on Field Programmable Logic and Applications (FPL) 2012
DOI: 10.1109/fpl.2012.6339144
|View full text |Cite
|
Sign up to set email alerts
|

Deep-pipelined FPGA implementation of ellipse estimation for eye tracking

Abstract: This paper presents a deep-pipelined FPGA implementation of real-time ellipse estimation for eye tracking. The system is constructed by the Starburst algorithm on a streamoriented architecture and the RANSAC algorithm without any external memories. In particular, the paper presents comparative results between three different hypothesis generators for the RANSAC algorithm based on Cramer's rule, Gauss-Jordan elimination and LU decomposition. The evaluation results showed that the Gauss-Jordan elimination achiev… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
7
0

Year Published

2013
2013
2023
2023

Publication Types

Select...
5
2
2

Relationship

2
7

Authors

Journals

citations
Cited by 13 publications
(7 citation statements)
references
References 8 publications
0
7
0
Order By: Relevance
“…They proposed a multiprocessor system based on the Microblaze processors to provide parallelism. RANSAC implementation on FPGA was also applied in ellipse estimation for eye tracking [6] and road sign detection [14].…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation
“…They proposed a multiprocessor system based on the Microblaze processors to provide parallelism. RANSAC implementation on FPGA was also applied in ellipse estimation for eye tracking [6] and road sign detection [14].…”
Section: Related Workmentioning
confidence: 99%
“…RANSAC is widely used in various computer vision applications such as image stitching [2], [3], motion estimation [4] and object detection and tracking [5], [6]. In most of the applications, RANSAC is utilized for image geometry estimation task [7], [8], [9].…”
Section: Introductionmentioning
confidence: 99%
“…It's one of the best choices for implementing the eye tracking system that can achieve reasonable tradeoff among accuracy, speed, power consumption, flexibility and cost [3]. Currently part of the eye tracking algorithm has been implemented on FPGA, for example, Frank Klefenz [4], Shafer [5], Tomoaki Ando [6], Keisuke Dohi [7] et al had mapped a feature extraction module into FPGA hardware logic, realizing the function of extracting the pupil center. But there is still room for improvement in accuracy, speed and resources consumption.…”
Section: Introductionmentioning
confidence: 99%
“…We have already shown such an approach is of benefit for a variety of image applications in terms of performance and power consumption [5,6,7,8]. In this paper, we propose and implement a streambased architecture of a particle filter based on FO-resampling method.…”
Section: Introductionmentioning
confidence: 99%