Facility surveillance systems and methods
Systems and methods for surveillance of a facility including facility elements. The system includes a central computing unit providing a digital model of the facility providing topological or logical or functional relationships of the facility elements, surveillance sensors adapted for surveillance of a plurality of the facility elements and for generation of surveillance data, communication means for transmitting data from the surveillance sensors to the central computing unit, and state derivation means configured to analyse the surveillance data and derive a state of a respective facility element. The central computing unit is configured to record a state pattern by combining states of at least one facility element based on at least one relationship of the facility element provided by the facility model, provide a state pattern critical-noncritical classification model which considers relationships provided by the facility model, and perform a criticality-classification based on the relationship.
1. A surveillance system for surveillance of a facility, the surveillance system comprising:
a mobile surveillance robot having a body, a drive system for moving of the body, and an action controller for controlling actions of the robot, the actions comprising the moving of the body or acquisition of surveillance data by the mobile surveillance robot,
the surveillance system further comprising:
at least a first surveillance sensor designed to acquire first surveillance data of at least one object of the facility,
a state detector configured to detect at least one state associated with the object based on the first surveillance data,
wherein the state detector is configured to:
notice a state ambiguity of the state which indicates an uncertainty of a state detection,
trigger an action of the mobile surveillance robot by the action controller in case a state ambiguity is noticed, the triggered action adapted to generate state verification information about the object, the state verification information being suitable to verify or falsify the detected state and therewith resolve the state ambiguity, and
resolve the state ambiguity considering the state verification information.
2. The surveillance system according to claim 1 , wherein the state detector is further configured to plan the action to be triggered such that the action is optimized with respect to the generation of verification information.
3. The surveillance system according to claim 2 , wherein the triggered action comprises acquisition of second surveillance data of the object by the surveillance robot.
4. The surveillance system according to claim 1 , wherein the triggered action comprises acquisition of second surveillance data of the object by the surveillance robot.
5. The surveillance system according to claim 4 , wherein the triggered action comprises change of acquisition position or direction such that the acquisition of the second surveillance data is performed with at least a second acquisition position or direction different to a first acquisition position or direction of acquisition of surveillance data.
6. The surveillance system according to claim 5 , wherein the state detector provides a correlation map correlating state ambiguity with acquisition position or direction, wherein:
the correlation map is based on a defined criterion representing the state or
the correlation map is established by machine learning or the
correlation map comprises best acquisition positions or directions for a plurality of detectable states.
7. The surveillance system according to claim 6 , wherein the surveillance system comprises at least a second surveillance sensor and:
the state detector is configured to determine with which surveillance sensor the second surveillance data is to be acquired such that the second surveillance is optimised with respect to generation of state verification information or
the first and the second surveillance sensors are sensors of different sort.
8. The surveillance system according to claim 4 , wherein the surveillance system comprises at least a second surveillance sensor and:
the state detector is configured to determine with which surveillance sensor the second surveillance data is to be acquired such that the second surveillance is optimised with respect to generation of state verification information or
the first and the second surveillance sensors are sensors of different sort.
9. The surveillance system according to claim 8 , wherein the triggered action comprises interaction of the surveillance robot with the object.
10. The surveillance system according to claim 1 , wherein the triggered action comprises interaction of the surveillance robot with the object.
11. The surveillance system according to claim 10 , wherein the interaction with the object comprises at least one of:
tactile contact,
application of material onto the object,
output of an acoustic or optic signal directed at the object.
12. The surveillance system according to claim 11 , wherein the state detector provides a correlation map correlating state ambiguity with interaction position or direction, wherein:
the correlation map is based on a defined criterion representing the state or
the correlation map is established by machine learning or the
correlation map comprises best interaction positions or directions for a plurality of detectable states.
13. The surveillance system according to claim 10 , wherein the state detector provides a correlation map correlating state ambiguity with interaction position or direction, wherein:
the correlation map is based on a defined criterion representing the state or
the correlation map is established by machine learning or the
correlation map comprises best interaction positions or directions for a plurality of detectable states.
14. The surveillance system according to claim 13 , wherein the interaction is based on a Markov model of states.
15. The surveillance system according to claim 10 , wherein the interaction is based on a Markov model of states.
16. The surveillance system according to claim 1 , wherein the triggered action is retrieval of data about the object, wherein the data is:
third surveillance data of a third surveillance sensor of the surveillance system, the third surveillance sensor not being part of the surveillance robot, or
stored in a database of the surveillance system.
17. The surveillance system according to claim 1 , wherein the surveillance robot is an unmanned ground vehicle (UGV).
18. The surveillance system according to claim 1 , wherein the first surveillance sensor comprises at least one of:
camera,
microphone,
RIM-camera,
laser scanner,
LIDAR,
RADAR,
motion detector, or
radiometer.
19. A surveillance method adapted for a facility surveillance system comprising at least a first surveillance sensor and a mobile surveillance robot, the method comprising the steps of:
acquiring of first survey data with the first surveillance sensor of an object of the facility,
detecting at least one state associated with the object based on the surveillance data,
noticing a state ambiguity of the state which indicates an uncertainty of a state detection,
triggering an action of the surveillance robot in case a state ambiguity is noticed, wherein the action comprises moving of the mobile surveillance robot or acquisition of surveillance data by the mobile surveillance robot and is adapted to generate state verification information about the object, the state verification information being suitable to verify or falsify the detected state and therewith resolve the state ambiguity, and
resolving the state ambiguity based on the state verification information.
20. A computer programme product comprising programme code which is stored on a non-transient machine-readable medium, comprising a programme code segment, and having computer-executable instructions for performing, when run on a central computing unit of a surveillance system, the steps of the method according to claim 19 .