Hermann et al 2009a - Revision history

Scipediacontent at 14:03, 21 January 2021

2021-01-21T14:03:40Z

Scipediacontent: Scipediacontent moved page Draft Content 944446931 to Hermann et al 2009a

2020-10-14T13:28:59Z

Scipediacontent moved page Draft Content 944446931 to Hermann et al 2009a

Scipediacontent: Created page with " == Abstract == Today's stereo vision algorithms and computing technology allow real-time 3D data analysis, for example for driver assistance systems. A recently developed Se..."

2020-10-14T13:28:56Z

Created page with " == Abstract == Today's stereo vision algorithms and computing technology allow real-time 3D data analysis, for example for driver assistance systems. A recently developed Se..."

New page

== Abstract ==

Today's stereo vision algorithms and computing technology allow real-time 3D data analysis, for example for driver assistance systems. A recently developed Semi-Global Matching (SGM) approach by H. Hirschmuller became a popular choice due to performance and robustness. This paper evaluates different parameter settings for SGM, and its main contribution consists in suggesting to include a second order prior into the smoothness term of the energy function. It also proposes and tests a new cost function for SGM. Furthermore, some preprocessing (edge images) proved to be of great value for improving SGM stereo results on real-world sequences, as previously already shown by S. Guan and R. Klette for belief propagation. There is also a performance gain for engineered stereo data (e.g.) as currently used on the Middlebury stereo website. However, the fact that results are not as impressive as on the .enpeda.. sequences indicates that optimizing for engineered data does not neccessarily improve real world stereo data analysis.

Document type: Part of book or chapter of book

== Full document ==
<pdf>Media:Draft_Content_944446931-beopen793-8709-document.pdf</pdf>

== Original document ==

The different versions of the original document can be found in:

* [http://dx.doi.org/10.1007/978-3-540-92957-4_55 http://dx.doi.org/10.1007/978-3-540-92957-4_55]

* [https://link.springer.com/content/pdf/10.1007%2F978-3-540-92957-4_55.pdf https://link.springer.com/content/pdf/10.1007%2F978-3-540-92957-4_55.pdf]

← Older revision		Revision as of 14:03, 21 January 2021
Line 3:		Line 3:

	Today's stereo vision algorithms and computing technology allow real-time 3D data analysis, for example for driver assistance systems. A recently developed Semi-Global Matching (SGM) approach by H. Hirschmuller became a popular choice due to performance and robustness. This paper evaluates different parameter settings for SGM, and its main contribution consists in suggesting to include a second order prior into the smoothness term of the energy function. It also proposes and tests a new cost function for SGM. Furthermore, some preprocessing (edge images) proved to be of great value for improving SGM stereo results on real-world sequences, as previously already shown by S. Guan and R. Klette for belief propagation. There is also a performance gain for engineered stereo data (e.g.) as currently used on the Middlebury stereo website. However, the fact that results are not as impressive as on the .enpeda.. sequences indicates that optimizing for engineered data does not neccessarily improve real world stereo data analysis.		Today's stereo vision algorithms and computing technology allow real-time 3D data analysis, for example for driver assistance systems. A recently developed Semi-Global Matching (SGM) approach by H. Hirschmuller became a popular choice due to performance and robustness. This paper evaluates different parameter settings for SGM, and its main contribution consists in suggesting to include a second order prior into the smoothness term of the energy function. It also proposes and tests a new cost function for SGM. Furthermore, some preprocessing (edge images) proved to be of great value for improving SGM stereo results on real-world sequences, as previously already shown by S. Guan and R. Klette for belief propagation. There is also a performance gain for engineered stereo data (e.g.) as currently used on the Middlebury stereo website. However, the fact that results are not as impressive as on the .enpeda.. sequences indicates that optimizing for engineered data does not neccessarily improve real world stereo data analysis.
−
−	~~Document type: Part of book or chapter of book~~
−
−	~~== Full document ==~~
−	~~<pdf>Media:Draft_Content_944446931-beopen793-8709-document.pdf</pdf>~~


Line 17:		Line 12:

	* [https://link.springer.com/content/pdf/10.1007%2F978-3-540-92957-4_55.pdf https://link.springer.com/content/pdf/10.1007%2F978-3-540-92957-4_55.pdf]		* [https://link.springer.com/content/pdf/10.1007%2F978-3-540-92957-4_55.pdf https://link.springer.com/content/pdf/10.1007%2F978-3-540-92957-4_55.pdf]
		+
		+	* [http://link.springer.com/content/pdf/10.1007/978-3-540-92957-4_55 http://link.springer.com/content/pdf/10.1007/978-3-540-92957-4_55],
		+	: [http://dx.doi.org/10.1007/978-3-540-92957-4_55 http://dx.doi.org/10.1007/978-3-540-92957-4_55] under the license http://www.springer.com/tdm
		+
		+	* [https://researchspace.auckland.ac.nz/handle/2292/3258 https://researchspace.auckland.ac.nz/handle/2292/3258],
		+	: [https://core.ac.uk/display/102650455 https://core.ac.uk/display/102650455],
		+	: [http://dblp.uni-trier.de/db/conf/psivt/psivt2009.html#HermannKD09 http://dblp.uni-trier.de/db/conf/psivt/psivt2009.html#HermannKD09],
		+	: [https://dl.acm.org/citation.cfm?id=1505942.1506008 https://dl.acm.org/citation.cfm?id=1505942.1506008],
		+	: [https://link.springer.com/chapter/10.1007/978-3-540-92957-4_55 https://link.springer.com/chapter/10.1007/978-3-540-92957-4_55],
		+	: [https://researchspace.auckland.ac.nz/bitstream/2292/3258/2/MItech-TR-16.pdf https://researchspace.auckland.ac.nz/bitstream/2292/3258/2/MItech-TR-16.pdf],
		+	: [https://academic.microsoft.com/#/detail/1559052834 https://academic.microsoft.com/#/detail/1559052834]

← Older revision	Revision as of 13:28, 14 October 2020
(No difference)