André Frank Krause
ABSTRACT
Gradient based dark pupil tracking [Timm and Barth 2011] is a simple and robust algorithm for pupil center estimation. The algorithm's time complexity of O(n4) can be tackled by applying a two-stage process (coarse center estimation followed by a windowed refinement), as well as by optimizing and parallelizing code using cache-friendly data structures, vector-extensions of modern CPU's and GPU acceleration. We could achieve a substantial speed up compared to a non-optimized implementation: 12x using vector extensions and 65x using a GPU. Further, the two-stage process combined with parameter optimization using differential evolution considerably increased the accuracy of the algorithm. We evaluated our implementation using the "Labelled pupils the wild" data set. The percentage of frames with a pixel error below 15px increased from 28% to 72%, surpassing algorithmically more complex algorithms like ExCuse (64%) and catching up with recent algorithms like PuRe (87%).
- ARM. 2008. ARM NEON support in the ARM compiler. https://www.arm.com/files/pdf/NEON_Support_in_the_ARM_Compiler.pdf.Google Scholar
- Joseph Coombs and R Prabhu. 2011. OpenCV on TI's DSP+ ARM® platforms: Mitigating the challenges of porting OpenCV to embedded platforms. Texas Instruments (2011).Google Scholar
- Keith Diefendorff, Pradeep K Dubey, Ron Hochsprung, and HASH Scale. 2000. Altivec extension to PowerPC accelerates media processing. IEEE Micro 20, 2 (2000), 85--95. Google ScholarDigital Library
- Wolfgang Fuhl, David Geisler, Thiago Santini, Tobias Appel, Wolfgang Rosenstiel, and Enkelejda Kasneci. 2018. CBF:Circular binary features for robust and real-time pupil center detection. In ACM Symposium on Eye Tracking Research & Applications. Google ScholarDigital Library
- Wolfgang Fuhl, Thomas Kübler, Katrin Sippel, Wolfgang Rosenstiel, and Enkelejda Kasneci. 2015. Excuse: Robust pupil detection in real-world scenarios. In International Conference on Computer Analysis of Images and Patterns. Springer, 39--51.Google ScholarCross Ref
- Wolfgang Fuhl, Thiago Santini, Gjergji Kasneci, and Enkelejda Kasneci. 2016a. Pupil-net: Convolutional neural networks for robust pupil detection. arXiv preprint arXiv:1601.04902 (2016).Google Scholar
- Wolfgang Fuhl, Thiago C Santini, Thomas Kübler, and Enkelejda Kasneci. 2016b. Else: Ellipse selection for robust pupil detection in real-world environments. In Proceedings of the Ninth Biennial ACM Symposium on Eye Tracking Research & Applications. ACM, 123--130. Google ScholarDigital Library
- Wolfgang Fuhl, Marc Tonsen, Andreas Bulling, and Enkelejda Kasneci. 2016c. Pupil detection for head-mounted eye tracking in the wild: an evaluation of the state of the art. Machine Vision and Applications 27, 8 (2016), 1275--1288. Google ScholarDigital Library
- Tristan Hume. 2012. EyeLike: A webcam based pupil tracking implementation. https://github.com/trishume/eyeLike.Google Scholar
- André Frank Krause. 2019. Boosting Speed- and Accuracy of Gradient based Pupil Tracking, Supplementary Materials & Source Code. http://andre-krause.net/publications/etra2019 | mirror: https://mediablix.de/publications/etra2019.Google Scholar
- Victor W Lee, Changkyu Kim, Jatin Chhugani, Michael Deisher, Daehyun Kim, Anthony D Nguyen, Nadathur Satish, Mikhail Smelyanskiy, Srinivas Chennupaty, Per Hammarlund, et al. 2010. Debunking the 100X GPU vs. CPU myth: an evaluation of throughput computing on CPU and GPU. ACM SIGARCH computer architecture news 38, 3 (2010), 451--460. Google ScholarDigital Library
- Yunsup Lee, Andrew Waterman, Rimas Avizienis, Henry Cook, Chen Sun, Vladimir Stojanović, and Krste Asanović. 2014. A 45nm 1.3 GHz 16.7 double-precision GFLOPS/W RISC-V processor with vector accelerators. In European Solid State Circuits Conference (ESSCIRC), ESSCIRC 2014--40th. IEEE, 199--202.Google ScholarCross Ref
- Dongheng Li, David Winfield, and Derrick J Parkhurst. 2005. Starburst: A hybrid algorithm for video-based eye tracking combining feature-based and model-based approaches. In null. IEEE, 79. Google ScholarDigital Library
- Chris Lomont. 2011. Introduction to intel advanced vector extensions. Intel White Paper (2011), 1--21.Google Scholar
- Brad L Miller, David E Goldberg, et al. 1995. Genetic algorithms, tournament selection, and the effects of noise. Complex systems 9, 3 (1995), 193--212.Google Scholar
- Thiago Santini, Wolfgang Fuhl, and Enkelejda Kasneci. 2018. PuRe: Robust Pupil Detection for Real-Time Pervasive Eye Tracking. Elsevier Computer Vision and Image Understanding To Appear (2018). Google ScholarDigital Library
- John E Stone, David Gohara, and Guochun Shi. 2010. OpenCL: A parallel programming standard for heterogeneous computing systems. Computing in science & engineering 12, 3 (2010), 66--73.Google ScholarDigital Library
- Rainer Storn and Kenneth Price. 1997. Differential evolution-a simple and efficient heuristic for global optimization over continuous spaces. Journal of global optimization 11, 4 (1997), 341--359. Google ScholarDigital Library
- Lech Świrski, Andreas Bulling, and Neil Dodgson. 2012. Robust real-time pupil tracking in highly off-axis images. In Proceedings of the Symposium on Eye Tracking Research and Applications. ACM, 173--176. Google ScholarDigital Library
- Jakub Szuppe. 2016. Boost. Compute: A parallel computing library for C++ based on OpenCL. In Proceedings of the 4th International Workshop on OpenCL. ACM, 15. Google ScholarDigital Library
- Fabian Timm and Erhardt Barth. 2011. Accurate Eye Centre Localisation by Means of Gradients. Visapp 11 (2011), 125--130.Google Scholar
- Marc Tonsen, Xucong Zhang, Yusuke Sugano, and Andreas Bulling. 2016. Labelled pupils in the wild: a dataset for studying pupil detection in unconstrained environments. In Proceedings of the Ninth Biennial ACM Symposium on Eye Tracking Research & Applications. ACM, 139--142. Google ScholarDigital Library
- Roberto Valenti and Theo Gevers. 2008. Accurate eye center location and tracking using isophote curvature. In 2008 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 1--8.Google ScholarCross Ref
Index Terms
- Boosting speed- and accuracy of gradient based dark pupil tracking using vectorization and differential evolution
Recommendations
Massively parallel differential evolution--pattern search optimization with graphics hardware acceleration: an investigation on bound constrained optimization problems
This paper presents a novel parallel Differential Evolution (DE) algorithm with local search for solving function optimization problems, utilizing graphics hardware acceleration. As a population-based meta-heuristic, DE was originally designed for ...
On the Efficacy of a Fused CPU+GPU Processor (or APU) for Parallel Computing
SAAHPC '11: Proceedings of the 2011 Symposium on Application Accelerators in High-Performance ComputingThe graphics processing unit (GPU) has made significant strides as an accelerator in parallel computing. However, because the GPU has resided out on PCIe as a discrete device, the performance of GPU applications can be bottlenecked by data transfers ...
Evaluation of GPU Architectures Using Spiking Neural Networks
SAAHPC '11: Proceedings of the 2011 Symposium on Application Accelerators in High-Performance ComputingDuring recent years General-Purpose Graphical Processing Units (GP-GPUs) have entered the field of High-Performance Computing (HPC) as one of the primary architectural focuses for many research groups working with complex scientific applications. Nvidia'...
Comments