Event detection system, event detection method, and non-transitory computer readable medium
An event detection system ( 10 ) includes: a calculation unit ( 16 ) that calculates a degree of similarity between at least a part of skeletal information extracted from a captured image in which a user who is visiting an ATM is captured and at least a part of registration skeletal information, the registration skeletal information being extracted from a registration image showing a phone call action of a person and being registered in an action database; and a determination unit ( 17 ) that determines that an event related to the ATM has been detected when the degree of similarity is equal to or greater than a predetermined threshold. Thus, a problematic event at an ATM can be easily detected while protecting privacy.
1 . An event detection system comprising:
at least one memory storing instructions; and
at least one processor configured to execute the instructions to:
in response to detection of a predetermined operation signal sent to an Automatic Teller Machine (ATM), extract skeletal information from a captured image in which a user who is visiting the ATM is captured;
calculate a plurality of degrees of similarity between at least a part of the skeletal information and at least a part of registration skeletal information, the registration skeletal information being extracted from a registration image showing a phone call action of a person visiting and operating the ATM and being registered in an action database; and
determine that an event related to the ATM has been detected in case that at least one of the calculated similarities is equal to or greater than a predetermined threshold.
2 . The event detection system according to claim 1 , wherein the at least one processor configured to execute the instructions to:
acquire the captured image; and
extract the skeletal information about at least a part of a body of the user based on the captured image.
3 . The event detection system according to claim 1 , wherein the registration image shows an action of the person talking on a phone and performing an input operation in the ATM.
4 . The event detection system according to claim 1 , wherein in case that at least one of the calculated similarities is equal to or greater than a predetermined threshold and it is determined that the user has a predetermined attribute, the at least one processor configured to execute the instructions to determine that the event has been detected.
5 . The event detection system according to claim 4 , wherein the at least one processor configured to execute the instructions to acquire an attribute of the user based on information read by the ATM.
6 . The event detection system according to claim 1 , wherein in case that at least one of the calculated similarities is equal to or greater than a predetermined threshold and a predetermined operation signal sent to the ATM has been detected, the at least one processor configured to execute the instructions to determine that the event has been detected.
7 . The event detection system according to claim 1 , wherein the at least one processor configured to execute the instructions to learn a plurality of degrees of similarity calculation parameter by using the skeletal information and a result of the determination of the event,
wherein the at least one processor configured to execute the instructions to calculate the plurality of degrees of similarity by using the plurality of degrees of similarity calculation parameter.
8 . The event detection system according to claim 1 , the at least one processor configured to execute the instructions to register skeletal information extracted from the registration image in the action database as registration skeletal information.
9 . The event detection system according to claim 8 , wherein when it is determined that the user has a predetermined attribute, the at least one processor configured to execute the instructions to ask a management apparatus whether to register the skeletal information extracted from the captured image in the action database.
10 . The event detection system according to claim 1 , wherein the skeletal information includes a plurality of key points detected from a body.
11 . The event detection system according to claim 10 , wherein the skeletal information includes a plurality of bones indicating links between the key points, at least one of the plurality of bones being detected from the body.
12 . The event detection system according to claim 1 , wherein the skeletal informationskeleton-information is extracted from an upper body.
13 . An event detection method comprising:
in response to detection of a predetermined operation signal sent to an Automatic Teller Machine (ATM), extracting skeletal information from a captured image in which a user who is visiting the ATM is captured;
calculating a plurality of degrees of similarity between at least a part of the skeletal information is captured and at least a part of registration skeletal information, the registration skeletal information being extracted from a registration image showing a phone call action of a person visiting an operating the ATM and being registered in an action database; and
determining that an event related to the ATM has been detected in case that at least one of the calculated similarities is equal to or greater than a predetermined threshold.
14 . A non-transitory computer readable medium storing a program for causing a computer to execute:
extracting processing for, in response to detection of a predetermined operation signal sent to an Automatic Teller Machine (ATM), extracting skeletal information from a captured image in which a user who is visiting the ATM is captured;
calculation processing for calculating a plurality of degrees of similarity between at least a part of the skeletal information and at least a part of registration skeletal information, the registration skeletal information being extracted from a registration image showing a phone call action of a person visiting and operating the ATM and being registered in an action database; and
determination processing for determining that an event related to the ATM has been detected in case that at least one of the calculated similarities is equal to or greater than a predetermined threshold.