Michael Albright

Michael Albright

Senior R&D Engineer

Michael Albright is a Senior R&D Engineer on Kitware’s Computer Vision Team. He has an academic background in theoretical physics, with a Ph.D. from the University of Minnesota. In his physics research, he developed mathematical models and supercomputer simulations of physics phenomena ranging from the behavior of magnetic materials in computer hard drives to the strong force (QCD) that holds atomic nuclei together. While at the U of M, Michael grew increasingly interested in applying his math and computing skills to industry problems, so he interned as a software engineer at the supercomputer company, Cray. He was also heavily involved with the student chapter of the Society for Industrial and Applied Mathematics and the university’s Institute for Mathematics and its Applications.

In 2015, Michael joined Honeywell’s R&D labs in Golden Valley, MN, where he spent the next two years applying his quantitative and software skills as a data scientist. As a data scientist, Michael worked with multiple business units on machine learning projects related to the internet of things (IoT). 

In 2017, Michael was recruited into a Honeywell R&D team focused on computer vision and artificial intelligence. In this new group, he worked on a mixture of commercial projects and externally-funded R&D. For example, Michael developed new 3D computer vision technologies for Honeywell’s Autocube 3D scanning product, with his day-to-day tasks ranging from algorithm development to software engineering. With his Honeywell colleagues, Michael wrote deep learning-powered software that won IARPA’s UG2 contest for automated enhancement of UAV imagery. Michael also worked on DARPA’s Media Forensics (MediFor) project. While working on MediFor, he developed new algorithms to detect and attribute manipulated imagery, which resulted in several papers and patents. He also took over as the acting PI of the Honeywell MediFor team near the end of the project.  

Most recently, Michael has worked with Honeywell Aerospace to develop new computer vision technologies for autonomous aircraft. 

  1. W. Scheirer, R. VidalMata, S. Banerjee, B. RichardWebster, M. Albright, P. Davalos, S. McCloskey, B. Miller, A. Tambo, S. Ghosh, S. Nagesh, Y. Yuan, Y. Hu, J. Wu, W. Yang, X. Zhang, J. Liu, Z. Wang, H. Chen, T. Huang, W. Chin, Y. Li, M. Lababidi, and C. Otto, "Bridging the Gap Between Computational Photography and Visual Recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 1-1, 2020. [URL]
  2. S. McCloskey and M. Albright, "Detecting GAN-Generated Imagery Using Saturation Cues," in 2019 IEEE International Conference on Image Processing, 2019.
  3. M. Albright and S. McCloskey, "Source generator attribution via inversion," CVPR Workshop on Media Forensics, pp. 96-103, May 2019.
  4. A. Tambo, M. Albright, and S. Mccloskey, "Low-and semantic-level cues for forensic splice detection," in 2019 IEEE Winter Conference on Applications of Computer Vision, 2019.
  5. S. McCloskey and M. Albright, "Detecting gan-generated imagery using color cues," arXiv preprint arXiv:1812.08247, Dec. 2018.
  6. M. Albright and J. Kapusta, "Quasiparticle theory of transport coefficients for hadronic matter at finite temperature and baryon density," Physical Review C, vol. 93, no. 1, pp. 014903, Jan. 2016. [URL]
  7. J. Kapusta, M. Albright, and C. Young, "Net baryon fluctuations from a crossover equation of state," The European Physical Journal A, vol. 52, no. 8, pp. 250, Aug. 2016. [URL]
  8. M. Albright, J. Kapusta, and C. Young, "Baryon number fluctuations from a crossover equation of state compared to heavy-ion collision measurements in the beam energy range s NN = 7.7 to 200 GeV," Physical Review C, vol. 92, no. 4, pp. 044904, Oct. 2015. [URL]
  9. M. Albright, J. Kapusta, and C. Young, "Matching excluded-volume hadron-resonance gas models and perturbative QCD to lattice calculations," Physical Review C, vol. 90, no. 2, pp. 024915, Aug. 2014. [URL]

Bibliography generated 2021-01-30-04:03:05 (4453)