Home People Lucas Beyer

Lucas Beyer

Lucas Beyer

UMIC Research Centre (Room 129)

Phone: +49 241 80 20 773

Fax: +49 241 80 22731

Email: emantsal AT ed.nehcaa-htwr.noisiv

Note for HiWi applicants: Due to my busy schedule, I cannot currently supervise any HiWi/Master students which have no hands-on experience with DeepLearning and solid Python and C or C++ coding skills. Sorry.

Busy doing too many cool things. See my homepage for more. Mostly working on these things:

Wordcloud, wow.



Research in progress :)

While head pose estimation has been studied for some time, continuous head pose estimation is still an open problem. Most approaches either cannot deal with the periodicity of angular data or require very fine-grained regression labels. We introduce biternion nets, a CNN-based approach that can be trained on very coarse regression labels and still estimate fully continuous 360° head poses. We show state-of-the-art results on several publicly available datasets. Finally, we demonstrate how easy it is to record and annotate a new dataset with coarse orientation labels in order to obtain continuous head pose estimates using our biternion nets.
  author    = {Lucas Beyer and Alexander Hermans and Bastian Leibe},
  title     = {Biternion Nets: Continuous Head Pose Regression from Discrete Training Labels},
  booktitle = {Pattern Recognition},
  publisher = {Springer},
  series    = {Lecture Notes in Computer Science},
  volume    = {9358},
  pages     = {157-168},
  year      = {2015},
  isbn      = {978-3-319-24946-9},
  doi       = {10.1007/978-3-319-24947-6_13},
  ee        = {http://lucasb.eyer.be/academic/biternions/biternions_gcpr15.pdf},
We present an ample description of a socially compliant mobile robotic platform, which is developed in the EU-funded project SPENCER. The purpose of this robot is to assist, inform and guide passengers in large and busy airports. One particular aim is to bring travellers of connecting flights conveniently and efficiently from their arrival gate to the passport control. The uniqueness of the project stems from the strong demand of service robots for this application with a large potential impact for the aviation industry on one side, and on the other side from the scientific advancements in social robotics, brought forward and achieved in SPENCER. The main contributions of SPENCER are novel methods to perceive, learn, and model human social behavior and to use this knowledge to plan appropriate actions in real-time for mobile platforms. In this paper, we describe how the project advances the fields of detection and tracking of individuals and groups, recognition of human social relations and activities, normative human behavior learning, socially-aware task and motion planning, learning socially annotated maps, and conducting empirical experiments to assess socio-psychological effects of normative robot behaviors.
  author    = {Rudolph Triebel and Kai Arras and Rachid Alami and Lucas Beyer and Stefan Breuers and Raja Chatila and Mohamed Chetouani and Daniel Cremers and Vanessa Evers and Michelangelo Fiore and Hayley Hung and Omar A. Islas Ram\'{i}rez and Michiel Joosse and Harmish Khambhaita and Tomasz Kucner and Bastian Leibe and Achim J. Lilienthal and Timm Linder and Manja Lohse and Martin Magnusson and Billy Okal and Luigi Palmieri and Umer Rafi and Marieke van Rooij and Lu Zhang},
  title     = {SPENCER: A Socially Aware Service Robot for Passenger Guidance and Help in Busy Airports},
  booktitle = {Proc. Field and Service Robotics (FSR)},
  publisher = {TBD},
  series    = {TBD},
  volume    = {TBD},
  pages     = {TBD},
  year      = {2015},
  isbn      = {TBD},
  ee        = {http://www.spencer.eu/papers/spencer.pdf},


A sad year.


In the context of the genome-wide association studies (GWAS), one has to solve long sequences of generalized least-squares problems; such a task has two limiting factors: execution time --often in the range of days or weeks-- and data management --data sets in the order of Terabytes. We present an algorithm that obviates both issues. By pipelining the computation, and thanks to a sophisticated transfer strategy, we stream data from hard disk to main memory to GPUs and achieve sustained peak performance; with respect to a highly-optimized CPU implementation, our algorithm shows a speedup of 2.6x. Moreover, the approach lends itself to multiple GPUs and attains almost perfect scalability. When using 4 GPUs, we observe speedups of 9x over the aforementioned implementation, and 488x over a widespread biology library.
  author    = {Lucas Beyer and Paolo Bientinesi},
  title     = {Streaming Data from HDD to GPUs for Sustained Peak Performance},
  booktitle = {Euro-Par},
  publisher = {Springer},
  series    = {Lecture Notes in Computer Science},
  volume    = {8097},
  pages     = {788-799},
  year      = {2013},
  isbn      = {3642400477},
  ee        = {http://arxiv.org/abs/1302.4332},


Accelerate Genome-Wide Association Studies (GWAS) by performing the most demanding computation on the GPU in a streamed fashion. Involves huge data size, streaming, asynchronicity parallel computation and some more buzzwords.
  author = {Lucas Beyer},
  title = {{Exploiting Graphics Adapters for Computational Biology}},
  school = {RWTH Aachen (AICES)},
  address = {Aachen, Germany},
  year = {2012},

Document Actions