Robust detection of small and dense objects in images from autonomous aerial vehicles

Autor:	Joo Chan Lee, JeongYeop Yoo, Yongwoo Kim, SungTae Moon, Jong Hwan Ko
Jazyk:	angličtina
Rok vydání:	2021
Předmět:	Optical image and video signal processing Aerospace control Mobile robots Computer vision and image processing techniques Electrical engineering. Electronics. Nuclear engineering TK1-9971
Zdroj:	Electronics Letters, Vol 57, Iss 16, Pp 611-613 (2021)
Druh dokumentu:	article
ISSN:	1350-911X 0013-5194
DOI:	10.1049/ell2.12245
Popis:	Abstract Aerial images obtained from autonomous aerial vehicles have lots of small and densely distributed objects because of the capture distance. This paper proposes a deep neural network architecture and training/inference techniques for robust detection of objects in the aerial images. Based on cascade R‐CNN, the proposed model adopts the recursive feature pyramid and switchable atrous convolution for robust detection of dense objects. A patch‐level division and multi‐scale inference techniques are applied to effectively detect small objects. The results show that the proposed approach achieves the highest performance on the VisDrone test‐dev dataset, in the official ECCV VisDrone2020‐DET challenge.
Databáze:	Directory of Open Access Journals
Externí odkaz:	https://doaj.org/article/d16e8e60ca3b47a58ec65d9a3f2d3e73 Zobrazit plný text záznamu Plný text View record in DOAJ