Cooperative Coevolutionary Approximation in HOG-based Human Detection Embedded System

Created by W.Langdon from gp-bibliography.bib Revision:1.8051

@InProceedings{Wiglasz:2018:ieeeCompIntl,

• author = "Michal Wiglasz and Lukas Sekanina",
• booktitle = "2018 IEEE Symposium Series on Computational Intelligence (SSCI)",
• title = "Cooperative Coevolutionary Approximation in {HOG-based} Human Detection Embedded System",
• year = "2018",
• pages = "1313--1320",
• month = "18-21 " # nov,
• address = "Bangalore, India",
• publisher = "IEEE",
• keywords = "genetic algorithms, genetic programming, Cartesian genetic programming, Approximate computing, Cooperative coevolution",
• DOI = "doi:10.1109/SSCI.2018.8628910",
• size = "8 pages",
• abstract = "The histogram of oriented gradients (HOG) feature extraction is a computer vision method widely used in embedded systems for detection of objects such as pedestrians. We used cooperative coevolutionary Cartesian genetic programming (CGP) to exploit the error resilience in the HOG algorithm. We evolved new approximate implementations of the arctan and square root functions, which are typically employed to compute the gradient orientations and magnitudes. When the best evolved approximations are integrated into the software implementation of the HOG algorithm, not only the execution time, but also the classification accuracy was improved in comparison with approximations evolved separately using CGP and also compared to the state-of-the art approximate implementations. As the evolved code does not contain any loops and branches, it is suitable for the follow-up low-power hardware implementation.",
• notes = "Replaces \cite{Wiglasz:2017:GlobalSIP}

  SVM LIBLINEAR

  p1319 'CGP to evolve new approximate implementations of the arctan and square root functions'

  Also known as \cite{8628910}",

}

Genetic Programming entries for Michal Wiglasz Lukas Sekanina

Citations