干旱区生态环境知识资源中心(Arid): Identifying Low-Profile Objects from Low-Light UAS Imagery Using Cascading Deep Learning

Arid

DOI	10.1117/12.2518259
	Identifying Low-Profile Objects from Low-Light UAS Imagery Using Cascading Deep Learning
	Overbey, Lucas A.; Pan, Jean; Lyle, Jamie R.; Campbell, Georgianna; Jaegar, Alan; Jaegar, Ryan; Van Epps, Todd; Ruane, Martin
通讯作者	Overbey, LA (corresponding author), Naval Informat Warfare Ctr Atlantic, POB 190022, N Charleston, SC USA.
会议名称	30th Conference on Infrared Imaging Systems - Design, Analysis, Modeling, and Testing
会议日期	APR 16-18, 2019
会议地点	Baltimore, MD
英文摘要	Unmanned aircraft systems (UAS) have gained utility in the Navy for many purposes, including facilities needs, security, and intelligence, surveillance, and reconnaissance (ISR). UAS surveys can be employed in place of personnel to reduce safety risks, but they generate significant quantities of data that often require manual review. Research and development of automated methods to identify targets of interest in this type of imagery data can provide multiple benefits, including increasing efficiency, decreasing cost, and potentially saving lives through identification of hazards or threats. This paper presents a methodology to efficiently and effectively identify cryptic target objects from UAS imagery. The approach involves flight and processing of airborne imagery in low-light conditions to find low-profile objects (i.e., birds) in beach and desert-like environments. The object classification algorithms combat the low-light conditions and low-profile nature of the objects of interest using cascading models and a tailored deep convolutional neural network (CNN) architecture. Models were able to identify and count endangered birds (California least terns) and nesting sites on beaches from UAS survey data, achieving negative/positive classification accuracies from candidate images upwards of 97% and an f(1) score for detection of 0:837.
英文关键词	deep learning unmanned aircraft systems object detection target identification aerial imagery field monitoring computer vision machine learning
来源出版物	INFRARED IMAGING SYSTEMS: DESIGN, ANALYSIS, MODELING, AND TESTING XXX
ISSN	0277-786X
EISSN	1996-756X
出版年	2019
卷号	11001
ISBN	978-1-5106-2668-3
出版者	SPIE-INT SOC OPTICAL ENGINEERING
类型	Proceedings Paper
语种	英语
收录类别	CPCI-S
WOS记录号	WOS:000502049700034
WOS类目	Optics
WOS研究方向	Optics
资源类型	会议论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/370163
作者单位	[Overbey, Lucas A.; Lyle, Jamie R.; Campbell, Georgianna] Naval Informat Warfare Ctr Atlantic, POB 190022, N Charleston, SC USA; [Pan, Jean] Naval Facil Engn & Expeditionary Warfare Ctr, 1100 23rd Ave, Port Hueneme, CA USA; [Jaegar, Alan] Naval Surface Warfare Ctr, Port Hueneme Div, 4363 Missile Way, Port Hueneme, CA USA; [Jaegar, Ryan; Van Epps, Todd] Ventura Cty Educ, 5189 Verdugo Way, Camarillo, CA USA; [Ruane, Martin] Naval Base Ventura Cty, 311 Main Rd 355, Nas Point Mugu, CA USA
推荐引用方式 GB/T 7714	Overbey, Lucas A.,Pan, Jean,Lyle, Jamie R.,et al. Identifying Low-Profile Objects from Low-Light UAS Imagery Using Cascading Deep Learning[C]:SPIE-INT SOC OPTICAL ENGINEERING,2019.