150 likes | 300 Views
VISION for Security. Monique THONNAT ORION INRIA Sophia Antipolis. Introduction. Which Security Problems? Safety and security of goods and human beings How? Data captured by video surveillance cameras Original video understanding approach mixing:
E N D
VISION for Security Monique THONNAT ORION INRIA Sophia Antipolis
Introduction Which Security Problems? • Safety and security of goods and human beings How? • Data captured by video surveillance cameras • Original video understanding approach mixing: • computer vision:4D analysis (3D + temporal analysis) • artificial intelligence:a priori knowledge (scenario, environment) • software engineering: reusable VSIP platform M. Thonnat
Video Understanding for Security Definition: • real time and automated analysis of video sequences • video understanding= from people detectionandtracking tobehavior recognition Recognition of complex behaviors: of individuals(fraud, graffiti, vandalism, bank attack) of small groups(fighting) of crowds(overcrowding) interactions of people and vehicles(aircraft refueling) M. Thonnat
Alarms Video Understanding Interpretation of the videos from pixels to alarms • A PRIORI KNOWLEDGE: • 3d models of the environment • Camera calibration • Scenario Models People detection and tracking 4 D analysis: multi-cameras tracking Scenario recognition People detection and tracking Video understanding M. Thonnat
Video Understanding Impact: • Visual surveillance of metro stations, bank agencies, trains, buildings and airports • 5 European projects (PASSWORDS, AVS-PV, AVS-RTPW, ADVISOR, AVITRACK) • 4 contracts with End-users companies (metro, bank, trains) • 2 transfer activities with Bull (Paris) and Vigitec (Brussels) • Cooperation over more than 11 years with partners • Creation of a start-up (spring 2005) M. Thonnat
Typical problems Metro station surveillance Surveillance inside trains Building access control Airport monitoring M. Thonnat
Video Understanding • Behavior recognition: • approach based on a priori knowledge • model of the empty scene (3D geometry and semantics) • models of predefined scenarios • a language for representing scenarios based on combination of states and events • more than 20 states and 20 events can be used • a reasoning mechanism for real time detection of states, events and scenarios (e.g. temporal reasoning, constraints solving techniques) M. Thonnat
zone derrière le guichet armoire guichet zone de jour commode zone d’accès au bureau du directeur zone de jour/nuit zone d’entrée de l’agence porte salle automates zone devant le guichet salle automates porte d’entrée objet du contexte zone des distributeurs zone d’accès rue mur et porte salle du coffre rue Video Understanding: 3D Scene Model 3d Model of 2 bank agencies Les Hauts de Lagny Villeparisis M. Thonnat
Video Understanding • States, Events and Scenarios : • State: a spatio-temporal property involving one or several actors on a time interval Ex : « close», « walking», « seated» • Event: asignificant change of states Ex : « enters», « stands up», « leaves » • Scenario: a long term symbolic application dependent activity Ex : « fighting», « vandalism» M. Thonnat
Results for Bank Monitoring • Bank attack scenario description: • scenarioBank_attack_one_robber_one_employee • physical_objects: • ((employee : Person), (robber : Person), z1: Back_Counter, • z2: Entrance_Zone, z3: Front_Counter, z4: Safe, d: Safe_door) • components: • (State c1 : Inside_zone(employee, z1)) • (Event c2 : Changes_zone(robber, z2,z3)) • (State c3 : Inside_zone(employee, z4)) • (State c4 : Inside_zone(robber, z4))) • constraints: • ((c2 during c1) (c2 before c3) • (c1 before c3) (c2 before c4) • (c4 during c3) • (d is open)) M. Thonnat
Video Understanding for bank surveillance M. Thonnat
Results in Metro Surveillance • Examples : Brussels and Barcelona Metros Group behavior Group behavior Blocking Fighting Exit zone Individual behavior Crowd behavior Jumping over barrier Overcrowding 12
Video Understanding: Conclusion • Hypotheses: • fixed cameras • 3D model of the empty scene • predefined behavior models • Results: + Behavior understanding for Individuals, Groups of people, Crowd or Vehicles + an operational language for video understanding (more than 20 states and events) + a real-time platform (5 to 25 frames/s) M. Thonnat
Conclusion: Where we go Knowledge Acquisition • Design of ontology driven knowledge acquisition: • video event ontology (T. Van Vu PhD) • Design of learning techniques to complement a priori knowledge: • visual concept learning(Nicolas Maillot PhD) • scenario model learning (A. Toshev) Reusability is still an issue for vision programs • Use of program supervision techniques: dynamic configuration of programs and parameters (B Georis PhD) Video event detection • Finer human shape description:3D posture models (B. Boulay PhD) • Video analysis robustness: Uncertainty management (M. Zuniga PhD) M. Thonnat
State of the Art Computer Vision • Mobile object detection (Wei Yun I2R Singapore) • Tracking of people using geometric approaches (T. Ellis et al. Kingston University UK) Event Recognition • Probalistic approaches HMM, DBN (A Bobick Georgia Tech USA, H Buxton Univ Sussex UK) Reusable platform • Realtime video surveillance platform (Multitel, Be) M. Thonnat