Automated Detection of People and Vehicles in Natural Environments Using High Temporal Resolution Airborne Remote Sensing

Advances in aerial platforms, imaging sensors, image processing/computing, geo-positioning systems, and wireless communications make near real-time detection and tracking of moving objects on the ground more practical and cost effective. In Coulter et al. (2011), we presented a methodological framework for near real-time monitoring of border areas with active and frequent illegal immigration and/or smuggling. The patent pending methodology is designed to assist law enforcement in locating and monitoring people and/or vehicles traversing the border region. The approach utilizes low cost platforms such as light aircraft (LA) or unmanned aerial systems (UAS) for repeat imaging over short time periods of minutes to hours depending on the border response zone (i.e. urban, rural, and remote). Specialized image collection and preprocessing procedures are utilized to obtain precise spatial co-registration between multitemporal image frame pairs. In addition, specialized change detection techniques are employed in order to automate the detection of people and vehicles moving within the border region. The objective of this paper is to describe the specialized techniques and provide initial results for detecting people and vehicle object changes in the context of U.S. border security. However, detection and tracking of moving objects across wide geographic areas may also be appropriate for such things as search and rescue of missing persons, wildlife tracking, and monitoring military resources or enemy movements on the battlefield. This work is developed by the National Center for Border Security and Immigration: A Department of Homeland Security Science and Technology Center of Excellence.