Learning Efficient Sensing for Active Vision (Esensing)

• Applicant: Professor Dr. Thomas Martinetz
• Subject Area: Image and Language Processing, Computer Graphics and Visualisation, Human Computer Interaction, Ubiquitous and Wearable Computing
• Term: from 2011 to 2016
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 200335461

• Final Report Year: 2015

Final Report Abstract

The different sensing frameworks developed during Esensing are novel approaches to the problem of how to adaptively sense the environment, i.e., how to extract relevant information from a particular environment that is previously unknown. Since they are based on learning and can be embedded in an action-perception loop, the novel methods have a great potential in the context of autonomously acting agents that must rely on efficient sensing schemes. Our approaches are inspired by Active Vision, motivated by Compressed Sensing, and are based on the principles of Sparse Coding. The scientific contribution we have accomplished during Esensing is twofold: (i) we developed new algorithms (CA, OSC, GF-OSC) to learn representations for an efficient encoding and sensing, and (ii) we developed new performant hierarchical sensing schemes (AHS, HMS), which are adaptive, because sensing operations are not conducted in a random fashion but are more carefully selected depending on both, the environment and the particular scene that is sensed. We developed AHS and HMS in the context of actionperception loops and collaborated with our partners in Leipzig and Berkeley. Our methods are inspired by biological sensing strategies and enable mobile agents to autonomously adapt their representations and their sensing strategies to a particular environment, which can then be sensed more efficiently.

Publications

• Intrinsic dimensionality predicts the saliency of natural dynamic scenes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(6):1080–1091, 2012
  Eleonora Vig, Michael Dorr, Thomas Martinetz, and Erhardt Barth
  (See online at https://doi.org/10.1109/TPAMI.2011.198)
• Sparse coding and selected applications. KI - Künstliche Intelligenz, 26(4):349–355, 2012
  Jens Hocke, Kai Labusch, Erhardt Barth, and Thomas Martinetz
  (See online at https://dx.doi.org/10.1007/s13218-012-0197-0)
• Learning orthogonal bases for k-sparse representations. In Barbara Hammer, Thomas Martinetz, and Thomas Villmann, editors, Workshop New Challenges in Neural Computation 2013, volume 02/2013 of Machine Learning Reports, pages 119–120, 2013
  Henry Schütze, Erhardt Barth, and Thomas Martinetz
  
• An adaptive hierarchical sensing scheme for sparse signals. In Bernice E. Rogowitz, Thrasyvoulos N. Pappas, and Huib de Ridder, editors, Human Vision and Electronic Imaging XIX, volume 9014 of Proc. of SPIE Electronic Imaging, pages 15:1–8, 2014
  Henry Schütze, Erhardt Barth, and Thomas Martinetz
  (See online at https://doi.org/10.1117/12.2043082)
• Visual manifold sensing. In Bernice E. Rogowitz, Thrasyvoulos N. Pappas, and Huib de Ridder, editors, Human Vision and Electronic Imaging XIX, volume 9014 of Proc. of SPIE Electronic Imaging, pages 48:1–8, 2014
  Irina Burciu, Adrian Ion-Margineanu, Thomas Martinetz, and Erhardt Barth
  (See online at https://doi.org/10.1117/12.2043012)