Scipediacontent: Scipediacontent moved page Draft Content 387031582 to Dolereit et al 2018a

2021-02-03T18:16:53Z

Scipediacontent moved page Draft Content 387031582 to Dolereit et al 2018a

Scipediacontent: Created page with " == Abstract == Real-time object recognition on low-power embedded devices is a widely requested task, needed in manifold applications. However, it is still a demanding chall..."

2021-02-03T18:16:50Z

Created page with " == Abstract == Real-time object recognition on low-power embedded devices is a widely requested task, needed in manifold applications. However, it is still a demanding chall..."

New page

== Abstract ==

Real-time object recognition on low-power embedded devices is a widely requested task, needed in manifold applications. However, it is still a demanding challenge to achieve desired performance goals. For example, for advanced driver assistance systems (ADAS) or autonomously driven cars, object recognition and lane detection are indispensable tasks. Another field of application is the continuous retrieval of the construction progress on-site for validation of the construction site status, by detecting installed components using a given CAD model. This paper presents a framework for highly customizable object detection systems implemented on a single heterogeneous computing chip leveraging FPGA logic and standard processors. The FPGA logic is used to implement a custom variation of the Hough Transform and further image processing tasks efficiently. The dedicated logic is supplemented with a software stack, which consists of a Linux operating system, including hardware access drivers, as well as high-level libraries like OpenCV and Robot Operating System (ROS) - all running on the same device. The capabilities of the system are demonstrated for three application scenarios, namely race track recognition, lane recognition and object detection tasks performed within a construction assistance system.

== Original document ==

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

* [http://publica.fraunhofer.de/documents/N-516099.html http://publica.fraunhofer.de/documents/N-516099.html]

* [http://xplorestaging.ieee.org/ielx7/8424123/8445082/08445086.pdf?arnumber=8445086 http://xplorestaging.ieee.org/ielx7/8424123/8445082/08445086.pdf?arnumber=8445086],
: [http://dx.doi.org/10.1109/asap.2018.8445086 http://dx.doi.org/10.1109/asap.2018.8445086]

* [https://dblp.uni-trier.de/db/conf/asap/asap2018.html#SarcherSZDSVK18 https://dblp.uni-trier.de/db/conf/asap/asap2018.html#SarcherSZDSVK18],
: [https://academic.microsoft.com/#/detail/2888797031 https://academic.microsoft.com/#/detail/2888797031]

← Older revision	Revision as of 18:16, 3 February 2021
(No difference)

Dolereit et al 2018a - Revision history

Scipediacontent: Scipediacontent moved page Draft Content 387031582 to Dolereit et al 2018a

Scipediacontent: Created page with " == Abstract == Real-time object recognition on low-power embedded devices is a widely requested task, needed in manifold applications. However, it is still a demanding chall..."