Zobrazeno 1 - 10
of 28
pro vyhledávání: '"Markus Thom"'
Publikováno v:
Intelligent Vehicles Symposium
This paper proposes a learning-based behavior generation approach for automated vehicles which is adapted sequentially. Instead of engineering behavioral policies for a variety of individual traffic situations by hand, our approach concentrates on a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::aca91765722e5802a3d16e6bfb3648cf
https://doi.org/10.1109/ivs.2016.7535422
https://doi.org/10.1109/ivs.2016.7535422
Learning dictionaries suitable for sparse coding instead of using engineered bases has proven effective in a variety of image processing tasks. This paper studies the optimization of dictionaries on image data where the representation is enforced to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5ff3d01ae619d596ed3c9ad506b9dcbe
http://arxiv.org/abs/1604.04767
http://arxiv.org/abs/1604.04767
Autor:
Gunther Krehl, Markus Thom, Dominik Nuss, Stephan Reuter, Klaus Dietmayer, Ting Yuan, Michael Maile, Axel Gern
Grid mapping is a well-established approach for environment perception in robotic and automotive applications. Early work suggests estimating the occupancy state of each grid cell in a robot’s environment using a Bayesian filter to recursively comb
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7eabff876da47b655476e64c70d47070
Autor:
Markus Thom, Franz Gritschneder
A rigorous formulation of the dynamics of a signal processing scheme aimed at dense signal scanning without any loss in accuracy is introduced and analyzed. Related methods proposed in the recent past lack a satisfactory analysis of whether they actu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::be5a5b60d893d2b9a4afa2992ce179e6
Publikováno v:
2015 IEEE 18th International Conference on Intelligent Transportation Systems; 2015, p423-429, 7p
Autor:
Michael Gabb, Roland Schweiger, Markus Thom, Christian Feller, Albrecht Rothermel, Raimar Wagner
Publikováno v:
ICCE-Berlin
Common image compression algorithms like JPEG or JPEG2000 transform the individual pixel values into a domain that favors a compact representation. In contrast to the fixed DCT or Wavelet domains, recent efforts were made on image coding with learned
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4188b363f65e6bce42e293d4d364d26b
https://doi.org/10.1109/icce-berlin.2013.6698022
https://doi.org/10.1109/icce-berlin.2013.6698022
Publikováno v:
IJCNN
Learning Convolutional Neural Networks (CNN) is commonly carried out by plain supervised gradient descent. With sufficient training data, this leads to very competitive results for visual recognition tasks when starting from a random initialization.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2542978a6502398d07eb58c92bb14231
https://doi.org/10.1109/ijcnn.2013.6706969
https://doi.org/10.1109/ijcnn.2013.6706969
Autor:
Albrecht Rothermel, Roland Schweiger, Markus Thom, Matthias Limmer, Michael Gabb, Raimar Wagner
Publikováno v:
Intelligent Vehicles Symposium
In rural areas, wildlife animal road crossings are a threat to both the driver and the wildlife population. Since most accidents take place at night, recent night vision driver assistance systems are supporting the driver by automatically detecting a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2c19c04ba6e50e0c7fbb4b0957f42c4d
https://doi.org/10.1109/ivs.2013.6629488
https://doi.org/10.1109/ivs.2013.6629488
Publikováno v:
SISY
Bandwidth restrictions and increasing data volumes in the transmission path of automotive driver assistance systems make video compression unavoidable for future applications. Conventional image compression algorithms are solely tuned for optimal hum
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::039b45479e366e1b6ec8d19d41fdf853
https://doi.org/10.1109/sisy.2012.6339546
https://doi.org/10.1109/sisy.2012.6339546
Publikováno v:
IJCNN
Non-negative Matrix Factorization is a technique for decomposing large data sets into bases and code words, where all entries of the occurring matrices are non-negative. A recently proposed technique also incorporates sparseness constraints, in such
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::91d005da31c5c7d76d77533b22972c2e
https://doi.org/10.1109/ijcnn.2011.6033328
https://doi.org/10.1109/ijcnn.2011.6033328