KFU. Card publication. A multithreaded algorithm of UAV visual localization based on a 3D model of environment: implementation with CUDA technology and CNN filtering of minor importance objects

- RUS
- 中文
- ES

A MULTITHREADED ALGORITHM OF UAV VISUAL LOCALIZATION BASED ON A 3D MODEL OF ENVIRONMENT: IMPLEMENTATION WITH CUDA TECHNOLOGY AND CNN FILTERING OF MINOR IMPORTANCE OBJECTS

Form of presentation

Articles in Russian journals and collections

Year of publication

2017

��

��

Authors, employees of KFU

Magid Evgeniy Arkadevich, author

Other authors

Buyval Aleksandr , author

Gavrilenkov Mikhail , author

Bibliographic description in the original language

Buyval A., Gavrilenkov M., Magid E. A multithreaded algorithm of UAV visual localization based on a 3D model of environment: implementation with CUDA technology and CNN filtering of minor importance objects // ICAROB 2017: International Conference on Artificial Life and Robotics (Miyazaki, Japan; 19-22 January 2017) - p. 356-359.

Annotation

Visual based navigation plays an important role in localization and path planning, especially in GPS-denied environments. This paper presents a visual based localization algorithm for a UAV within an indoor environment. The algorithm uses multithreaded computing CUDA technology and CNN-preprocessing filtering, which is responsible for filtering out dynamic objects. The algorithm is simulated in ROS/Gazebo environment with two different approaches – one uses CPU only and the other uses CPU and GPU - and their performance is compared.

Keywords

UAV, visual localization, CNN filtering, CUDA technology

The name of the journal

International Conference on Artificial Life and Robotics

URL

https://www.semanticscholar.org/paper/A-multithreaded-algorithm-of-UAV-visual-based-on-a-Buyval-Gavrilenkov/471a3ad39d90071038cb364931aa31c2fdc5128a

Please use this ID to quote from or refer to the card

https://repository.kpfu.ru/eng/?p_id=154355&p_lang=2

Resource files

File name	Size (MB)	Format
F_2017_A_multithreaded_algorithm_of_UAV_visual_localization_based_on_a_3D_model_of_environment.pdf	0,65	pdf	show / download

Full metadata record

Field DC	Value	Language
dc.contributor.author	Magid Evgeniy Arkadevich	ru_RU
dc.contributor.author	Buyval Aleksandr	ru_RU
dc.contributor.author	Gavrilenkov Mikhail	ru_RU
dc.date.accessioned	2017-01-01T00:00:00Z	ru_RU
dc.date.available	2017-01-01T00:00:00Z	ru_RU
dc.date.issued	2017	ru_RU
dc.identifier.citation	Buyval A., Gavrilenkov M., Magid E. A multithreaded algorithm of UAV visual localization based on a 3D model of environment: implementation with CUDA technology and CNN filtering of minor importance objects // ICAROB 2017: International Conference on Artificial Life and Robotics (Miyazaki, Japan; 19-22 January 2017) - p. 356-359.	ru_RU
dc.identifier.uri	https://repository.kpfu.ru/eng/?p_id=154355&p_lang=2	ru_RU
dc.description.abstract	International Conference on Artificial Life and Robotics	ru_RU
dc.description.abstract	Visual based navigation plays an important role in localization and path planning, especially in GPS-denied environments. This paper presents a visual based localization algorithm for a UAV within an indoor environment. The algorithm uses multithreaded computing CUDA technology and CNN-preprocessing filtering, which is responsible for filtering out dynamic objects. The algorithm is simulated in ROS/Gazebo environment with two different approaches – one uses CPU only and the other uses CPU and GPU - and their performance is compared.	ru_RU
dc.language.iso	ru	ru_RU
dc.subject	UAV	ru_RU
dc.subject	visual localization	ru_RU
dc.subject	CNN filtering	ru_RU
dc.subject	CUDA technology	ru_RU
dc.title	A multithreaded algorithm of UAV visual localization based on a 3D model of environment: implementation with CUDA technology and CNN filtering of minor importance objects	ru_RU
dc.type	Articles in Russian journals and collections	ru_RU