(Created page with " == Abstract == Deep Learning requires huge amount of data with related labels, that are necessary for proper training. Thanks to modern videogames, which aim at photorealism...") |
|||
| (One intermediate revision by the same user not shown) | |||
| Line 3: | Line 3: | ||
Deep Learning requires huge amount of data with related labels, that are necessary for proper training. Thanks to modern videogames, which aim at photorealism, it is possible to easily obtain synthetic dataset by extracting information directly from the game engine. The intent is to use data extracted from a videogame to obtain a representation of various scenarios and train a deep neural network to infer the information required for a specific task. In this work we focus on computer vision aids for automotive applications and we target to estimate the distance and speed of the surrounding vehicles by using a single dashboard camera. We propose two network models for distance and speed estimation, respectively. We show that training them by using synthetic images generated by a game engine is a viable solution that turns out to be very effective in real settings. | Deep Learning requires huge amount of data with related labels, that are necessary for proper training. Thanks to modern videogames, which aim at photorealism, it is possible to easily obtain synthetic dataset by extracting information directly from the game engine. The intent is to use data extracted from a videogame to obtain a representation of various scenarios and train a deep neural network to infer the information required for a specific task. In this work we focus on computer vision aids for automotive applications and we target to estimate the distance and speed of the surrounding vehicles by using a single dashboard camera. We propose two network models for distance and speed estimation, respectively. We show that training them by using synthetic images generated by a game engine is a viable solution that turns out to be very effective in real settings. | ||
| − | |||
| − | |||
| Line 19: | Line 17: | ||
* [https://iris.unito.it/bitstream/2318/1719738/2/Camera%20Ready%20paper.pdf https://iris.unito.it/bitstream/2318/1719738/2/Camera%20Ready%20paper.pdf] | * [https://iris.unito.it/bitstream/2318/1719738/2/Camera%20Ready%20paper.pdf https://iris.unito.it/bitstream/2318/1719738/2/Camera%20Ready%20paper.pdf] | ||
| − | * [http://link.springer.com/content/pdf/10.1007/978-3-030-30642-7_35 http://link.springer.com/content/pdf/10.1007/978-3-030-30642-7_35],[http://dx.doi.org/10.1007/978-3-030-30642-7_35 http://dx.doi.org/10.1007/978-3-030-30642-7_35] under the license http://www.springer.com/tdm | + | * [http://link.springer.com/content/pdf/10.1007/978-3-030-30642-7_35 http://link.springer.com/content/pdf/10.1007/978-3-030-30642-7_35], |
| + | : [http://dx.doi.org/10.1007/978-3-030-30642-7_35 http://dx.doi.org/10.1007/978-3-030-30642-7_35] under the license http://www.springer.com/tdm | ||
| − | * [https://link.springer.com/chapter/10.1007%2F978-3-030-30642-7_35 https://link.springer.com/chapter/10.1007%2F978-3-030-30642-7_35],[https://academic.microsoft.com/#/detail/2971590130 https://academic.microsoft.com/#/detail/2971590130] | + | * [https://www.scipedia.com/public/Zaffaroni_et_al_2019a https://www.scipedia.com/public/Zaffaroni_et_al_2019a], |
| + | : [https://dblp.uni-trier.de/db/conf/iciap/iciap2019-1.html#ZaffaroniGF19 https://dblp.uni-trier.de/db/conf/iciap/iciap2019-1.html#ZaffaroniGF19], | ||
| + | : [https://link.springer.com/chapter/10.1007%2F978-3-030-30642-7_35 https://link.springer.com/chapter/10.1007%2F978-3-030-30642-7_35], | ||
| + | : [https://rd.springer.com/chapter/10.1007/978-3-030-30642-7_35 https://rd.springer.com/chapter/10.1007/978-3-030-30642-7_35], | ||
| + | : [https://academic.microsoft.com/#/detail/2971590130 https://academic.microsoft.com/#/detail/2971590130] | ||
Latest revision as of 17:12, 21 January 2021
Abstract
Deep Learning requires huge amount of data with related labels, that are necessary for proper training. Thanks to modern videogames, which aim at photorealism, it is possible to easily obtain synthetic dataset by extracting information directly from the game engine. The intent is to use data extracted from a videogame to obtain a representation of various scenarios and train a deep neural network to infer the information required for a specific task. In this work we focus on computer vision aids for automotive applications and we target to estimate the distance and speed of the surrounding vehicles by using a single dashboard camera. We propose two network models for distance and speed estimation, respectively. We show that training them by using synthetic images generated by a game engine is a viable solution that turns out to be very effective in real settings.
Original document
The different versions of the original document can be found in:
- http://dx.doi.org/10.1007/978-3-030-30642-7_35 under the license http://www.springer.com/tdm
Document information
Published on 01/01/2019
Volume 2019, 2019
DOI: 10.1007/978-3-030-30642-7_35
Licence: CC BY-NC-SA license
Share this document
Keywords
claim authorship
Are you one of the authors of this document?