Automatic threat recognition for HD AIT
Inventors
Conley, Melissa • Fortune, John • Chandarlis, Michael • GARRETT, WILLIAM • Lewis, Brian
Assignees
Government Of United States, Represented By Secretary Of Homeland Security • US Department of Homeland Security
Publication Number
US-11940558-B2
Publication Date
2024-03-26
Expiration Date
2041-06-17
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Abstract
Described herein are examples of evaluating electromagnetic energy reflection data of security scans. In embodiments, a method to evaluate electromagnetic energy reflection data determines whether electronic information of a security scan contains an anomaly, and identifies an anomaly location in the electronic information corresponding to the anomaly. The method determines a subset of the electronic information corresponding to the anomaly location, determines anomaly attributes using the subset of the electronic information, and evaluates the anomaly attributes using a database of reference items by comparing anomaly attributes to respective reference characteristics of reference items or identity information. When a comparison meets the respective match criterion for the given reference item, the method assigns to the anomaly the respective identifier as an anomaly identifier.
Core Innovation
Described herein are methods and apparatuses for evaluating electromagnetic energy reflection data obtained from security scans of human subjects to detect anomalies and classify them automatically. The invention determines whether electronic information from a security scan contains an anomaly, identifies the anomaly location, determines a subset of electronic information for that location, determines anomaly attributes from that subset, and evaluates those attributes by comparing them to a database of reference items, each having identifiers, reference characteristics, and matching criteria. If the anomaly attributes meet the match criterion for a reference item, an anomaly identifier is assigned accordingly.
The invention solves the problem of inefficiencies and privacy concerns related to manual screening at security checkpoints, such as airports and other controlled access venues. Existing automatic threat recognition (ATR) technology merely identifies the location of anomalies but does not categorize or depict them, requiring manual investigation by agents that is time-consuming, space-intensive, and inefficient. The embodiments leverage high-definition Advanced Imaging Technology (HD-AIT) and anomaly identification computational approaches to automatically categorize anomalies as prohibited, permitted, or unidentifiable, and adjust anomaly depiction based on subject privacy information to respect subject privacy while facilitating more efficient security operations.
Claims Coverage
The patent includes multiple independent claims covering both a method and an apparatus with core inventive features.
Method for identity-based anomaly evaluation
The method determines whether electronic information of a security scan contains an anomaly, identifies the anomaly location, determines a subset of electronic information corresponding to that location, evaluates anomaly attributes against a database of reference items with identifiers, reference characteristics, and match criteria, assigns anomaly identifiers when matches occur, obtains identity information of the subject from remote databases containing pre-stored personal information provided by the subject, determines if the anomaly matches a permitted device for that subject, and assigns a pass status if consistent.
Apparatus including identity-aware anomaly evaluation logic
An apparatus comprising a computer system with a processing system and memory, storing anomaly identifying logic to detect anomalies and their locations from electronic security scan information, anomaly analyzer logic to determine anomaly attributes from subsets of data and evaluate those attributes against a reference database with identifiers and match criteria, assign anomaly identifiers when matches occur, user interface capabilities to output identifiers, and identity logic to obtain identity information from remote databases with pre-stored subject information, determine consistency with permitted devices, and assign pass status accordingly.
The independent claims cover a comprehensive system and method for automatic threat recognition in security scans by combining anomaly detection, classification via a reference database, and subject-specific identity information to assign identifiers and pass statuses, increasing accuracy and respecting privacy.
Stated Advantages
Reduces the need for manual screening, thereby increasing efficiency and reducing staffing and space requirements at security checkpoints.
Enables automatic identification and categorization of anomalies, distinguishing prohibited threats from permitted items and unidentifiable anomalies.
Respects subject privacy by limiting depiction of personal scan data and adjusting visualization based on individual privacy preferences.
Improves agent effectiveness by providing detailed anomaly identifiers and tailored information for specialized response.
Enables silent clearance of known permitted items, enhancing throughput and user experience without requiring manual intervention.
Documented Applications
Security screening at airports and other travel departure/arrival venues.
Mass transit security screening.
Border security.
Correctional facilities.
Department of motor vehicles.
Sporting events.
Testing centers.
Interested in licensing this patent?