Deliberate Motion Analytics Fused Radar and Video Test Results Deployed Beyond the Perimeter Fence in a High Noise Environment
- Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
- Sandia National Laboratories (SNL), Albuquerque, NM, and Livermore, CA (United States)
Security systems that protect the nation’s critical facilities must be capable of detecting physical intrusions in all weather conditions. Intrusion detection sensors in a perimeter with a high nuisance alarm rate (NAR) significantly undermine detection performance and degrade security system effectiveness. This research demonstrated a fused sensor system that can differentiate foliage and weather-induced nuisance alarms from those caused by intruders, providing reliable detection within a two-fence perimeter or beyond the fence. A key element of this work is the creation and application of a “deliberate motion algorithm” that fuses alarm data from radar and video analytics to create video motion detection fused radar system. The two-layer architecture of the algorithm uses machine learning, multi-hypothesis tracking, and Dynamic Bayes Nets to differentiate intruder alarms from weather induced alarms.
- Research Organization:
- Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
- Sponsoring Organization:
- USDOE Office of Nuclear Energy (NE)
- DOE Contract Number:
- NA0003525
- OSTI ID:
- 1855028
- Report Number(s):
- SAND2021-5413; 700646
- Country of Publication:
- United States
- Language:
- English
Similar Records
Nuclear-power-plant perimeter-intrusion alarm systems
Design and evaluation of the ReKon : an integrated detection and assessment perimeter system.