WO2014208025A1 - 感度調整装置、感度調整方法および記憶媒体、並びに監視システム - Google Patents
感度調整装置、感度調整方法および記憶媒体、並びに監視システム Download PDFInfo
- Publication number
- WO2014208025A1 WO2014208025A1 PCT/JP2014/003060 JP2014003060W WO2014208025A1 WO 2014208025 A1 WO2014208025 A1 WO 2014208025A1 JP 2014003060 W JP2014003060 W JP 2014003060W WO 2014208025 A1 WO2014208025 A1 WO 2014208025A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- monitoring
- location
- sensitivity
- event
- information
- Prior art date
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 411
- 230000035945 sensitivity Effects 0.000 title claims abstract description 288
- 238000000034 method Methods 0.000 title claims description 17
- 238000000605 extraction Methods 0.000 claims abstract description 69
- 230000002159 abnormal effect Effects 0.000 claims abstract description 60
- 239000000284 extract Substances 0.000 claims abstract description 23
- 230000008569 process Effects 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 4
- 230000005856 abnormality Effects 0.000 claims 2
- 238000001514 detection method Methods 0.000 abstract description 14
- 238000010586 diagram Methods 0.000 description 21
- 230000010365 information processing Effects 0.000 description 9
- 230000006399 behavior Effects 0.000 description 8
- 238000004891 communication Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 238000013459 approach Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000005065 mining Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 230000009118 appropriate response Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B29/00—Checking or monitoring of signalling or alarm systems; Prevention or correction of operating errors, e.g. preventing unauthorised operation
- G08B29/18—Prevention or correction of operating errors
- G08B29/20—Calibration, including self-calibrating arrangements
- G08B29/24—Self-calibration, e.g. compensating for environmental drift or ageing of components
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
- G08B13/19613—Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion
Definitions
- the present invention relates to a sensitivity adjustment device that adjusts sensitivity for detecting occurrence of an abnormal situation in a monitoring system.
- the monitoring system is a system aimed at improving security at stations or airports.
- the monitoring system includes a sensor such as a monitoring camera or a sound collecting microphone.
- the monitoring system detects an abnormal situation using information output from the sensor and a monitoring rule.
- a monitoring rule is a conditional expression that includes information that defines a condition.
- the monitoring rule is, for example, a conditional expression “if (an image in which a person puts a bag appears on the camera and a person does not approach that bag for a certain period of time) then (outputs an alarm)”.
- the conditional clause (if clause) included in such a monitoring rule is satisfied, the monitoring system outputs an alarm to the person in charge of monitoring of the monitoring system.
- the monitoring person who has received the warning knows that an abnormal situation has occurred, saying that the bag has been left behind.
- Non-Patent Document 1 discloses an example of a monitoring system for monitoring that a bag is left behind in a public place.
- the monitoring system In order for the monitoring system to detect an abnormal situation efficiently, it is necessary for the monitoring system to detect the abnormal situation with appropriate sensitivity (Sensitivity). In order for the monitoring system to efficiently detect an abnormal situation, the present inventor has found that the sensitivity for detecting the abnormal situation must be adjusted according to the situation at the monitoring location.
- the main object of the present invention is to provide a sensitivity adjustment device, a sensitivity adjustment method, and a program capable of appropriately adjusting the sensitivity for detecting an abnormal situation according to the situation at the monitoring place.
- Another object of the present invention is to provide a monitoring system capable of appropriately adjusting the sensitivity for detecting an abnormal situation according to the situation at the monitoring location.
- a first aspect of the present invention is a candidate location that is a location in the vicinity of a monitoring location that is monitored by the monitoring system, and a location where an event that affects the degree of congestion of the monitoring target may occur.
- An extraction unit that extracts information about an event that is scheduled to occur at the candidate location from a database that stores text described about the event using the candidate location information that represents the event, and the candidate location information and the event extracted by the extraction unit
- a sensitivity determination unit including a sensitivity determination unit that determines sensitivity when the monitoring system detects an abnormal situation occurring at the monitoring location according to a degree of congestion of the monitoring location expected based on information about is there.
- the second aspect of the present invention is a place in the vicinity of a monitoring place that is monitored by a monitoring system and a place where an event that affects the degree of congestion of a person or a car may occur.
- the candidate location information representing the candidate location as a key
- information related to the event that is scheduled to occur at the candidate location is extracted from the database in which the text describing the event is stored, and the candidate location information and the extraction unit extract
- the third aspect of the present invention is a candidate location that is a location in the vicinity of the monitoring location that is monitored by the monitoring system, and a location where an event that affects the degree of congestion of people or vehicles may occur.
- a process for extracting information related to an event scheduled to occur at the candidate location from a database storing text describing the event using candidate location information representing the event, and the event extracted by the candidate location information and the extraction unit A program for causing a computer to execute a process of determining sensitivity when the monitoring system detects an abnormal situation occurring at the monitoring location according to a degree of congestion of the monitoring location expected based on information on .
- 4th aspect of this invention is a monitoring system which has the said monitoring server and the said sensitivity adjustment apparatus.
- a fifth aspect of the present invention relates to an event scheduled to occur at a monitoring location from a database in which text described with respect to the event is stored using monitoring location information representing the monitoring location that is monitored by the monitoring system as a key.
- An abnormal situation that occurs in the monitoring location by the monitoring system according to the degree of congestion of the monitoring location that is expected based on the extraction portion that extracts information, and the monitoring location information and the information related to the event extracted by the extraction portion
- a sensitivity determination unit that determines sensitivity when detecting.
- information representing a situation at a monitoring location is received from a sensor that measures the situation at a monitoring location that is a location monitored by the monitoring system, and based on the received information,
- a congestion level determination unit that determines the congestion level of a person or a vehicle, and the monitoring system detects an abnormal situation that occurs at the monitoring location according to the congestion level at the monitoring location determined by the congestion level determination unit.
- a sensitivity adjustment device including a sensitivity determination unit that determines sensitivity.
- the object of the present invention is also achieved by a computer-readable storage medium storing the above program.
- a sensitivity adjustment device capable of appropriately adjusting the sensitivity for detecting an abnormal situation according to the situation at the monitoring place.
- the present invention it is possible to provide a monitoring system capable of appropriately adjusting the sensitivity of detecting an abnormal situation according to the situation at the monitoring place.
- FIG. 1 is a diagram for explaining an overview of the monitoring system 1000.
- the monitoring system 1000 includes the monitoring server 100 and one or more sensors 200.
- the sensor 200 measures the situation at the monitoring location that is monitored by the monitoring system.
- the sensor 200 is, for example, a surveillance camera or a sound collection microphone.
- the surveillance camera photographs the surveillance location.
- the monitoring location is, for example, a range reflected on one monitoring camera.
- the monitoring location may be a range monitored by a plurality of monitoring cameras.
- the monitoring location may be, for example, a specific store, a specific park, or a specific area specified by latitude and longitude.
- the monitoring system 1000 detects an abnormal situation by monitoring the behavior of the monitoring target at the monitoring location.
- the monitoring target is, for example, a person, a car, a bicycle, an object (for example, a bag) or an animal present at the monitoring place.
- the description will be continued assuming that the monitoring target is a person.
- the sensor 200 transmits information (images and the like) obtained by measuring the situation at the monitoring location to the monitoring server 100.
- the monitoring server 100 receives information obtained by measuring the situation at the monitoring location from the sensor 200.
- the monitoring server 100 detects whether or not an abnormal situation has occurred at the monitoring location.
- a monitoring rule for detecting an abnormal situation is set in the monitoring server 100.
- a monitoring rule is a conditional expression that includes information that defines a specific condition.
- the monitoring rule is, for example, a conditional expression “if (an image on which a person puts a bag appears on the camera, and a person does not approach that bag for a certain period of time) then (outputs an alarm to the monitoring person 900)”.
- the monitoring server 100 When the monitoring server 100 receives the information obtained by measuring the situation at the monitoring location from the sensor 200 (monitoring camera), the monitoring server 100 analyzes the received information and extracts the behavior or attribute of the monitoring target (such as a person) at the monitoring location.
- the monitoring server extracts the behavior of the monitoring target (for example, walking, talking, etc.) by using, for example, behavior estimation technology.
- the monitoring server extracts an attribute (for example, age or sex) to be monitored by using, for example, face recognition technology.
- the behavior or attribute of the monitoring target extracted by the monitoring server 100 satisfies the conditional clause (if clause) included in the monitoring rule, the monitoring server 100 executes the then clause included in the monitoring rule.
- conditional clause of the monitoring rule is referred to as “conditional clause of the monitoring rule”.
- then clause included in the monitoring rule is referred to as “then clause of the monitoring rule”.
- the sensitivity with which the monitoring system 1000 detects an abnormal situation depends on, for example, a variable included in a conditional clause of the monitoring rule.
- a specific description will be given by taking the above-described monitoring rule as an example.
- monitoring rule 1 a monitoring rule including a conditional clause “if (an image on which a person puts a bag appears on the camera and the person does not approach the package for 30 minutes)”
- surveillance rule 2 A surveillance rule including a conditional clause “if (the image on which the person puts the bag appears on the camera and the person does not approach the baggage for 1 hour)”.
- the monitoring system 1000 in which the monitoring rule 1 is set has a higher sensitivity for detecting an abnormal situation such as “the cocoon has been left behind” than the monitoring system 1000 in which the monitoring rule 2 is set.
- the monitoring system 1000 In order for the monitoring system 1000 to efficiently detect an abnormal situation, it is necessary for the monitoring system 1000 to detect the occurrence of the abnormal situation with an appropriate sensitivity.
- the inventor In order for the monitoring system 1000 to efficiently detect an abnormal situation, the inventor has found that the sensitivity for detecting the abnormal situation must be adjusted according to the degree of congestion of the monitoring target at the monitoring location. It was.
- the degree of congestion is the number of people per unit area.
- the situation where the degree of congestion is high represents, for example, a situation where there are many people at the monitoring location.
- the congestion degree is the number of cars per unit area or unit length.
- the situation where the degree of congestion is high represents, for example, a situation where many cars are parked in a parking lot or a situation where cars are congested.
- the first reason is derived from the characteristics of the abnormal situation to be detected.
- monitoring system 1000 detects a criminal act of “stalking”.
- An example shown below is a monitoring rule for detecting a misbehavior.
- Monitoring rule “if (There is a person who keeps a distance within a certain distance (X meters) with respect to a specific person and follows the specific person for more than 5 minutes) then (stores the video in the database And set a flag indicating the behavior that is associated with the video).
- the congestion level of the monitoring place When the congestion level of the monitoring place is low, it is appropriate to set the variable (X meter) included in the condition clause of the monitoring rule to high sensitivity (ie, long distance). This is because, when the degree of congestion in the monitoring place is low, a criminal who performs a criminal act can accompany the victim without losing sight of the victim even if they are some distance away from the victim.
- variable (X meter) included in the condition clause of the monitoring rule When the monitoring place is highly congested, it is appropriate to set the variable (X meter) included in the condition clause of the monitoring rule to a low sensitivity (ie, a short distance). This is because, when the monitoring place is highly congested, ordinary people who are not related to obscene acts also walk at a close distance from those who walk in front. In such a case, if a relatively short distance is set for the variable X, erroneous detection of obscuring actions increases.
- the sensitivity for detecting the abnormal situation must be adjusted according to the degree of congestion of the monitoring target at the monitoring location.
- the second reason is derived from the monitoring cost of the monitoring person 900 who receives an alarm from the monitoring server 100.
- the monitoring system 1000 detects whether or not a person who has been arranged is shown in an image taken by a monitoring camera.
- An example shown below is a monitoring rule for detecting a person who has been requested. Monitoring rule: “if (the face of the person shown in the image and the face of the person who has been “They match with a confidence level greater than or equal to the value (Y%)” then (output an alarm to the supervisor 900).
- variable (Y%) included in the conditional clause of the monitoring rule is set to a high sensitivity (that is, a low value). This is because the higher the sensitivity is set, the lower the risk of missing a wanted crime.
- the congestion degree of the monitoring place is high, it is appropriate to set the variable (Y%) included in the condition clause of the monitoring rule to a low sensitivity (that is, a high value). This is because, when the degree of congestion at the monitoring location is high, many people's faces appear in the video of the monitoring camera, and accordingly, the number of times the alarm is output to the monitoring person 900 increases. The number of monitoring personnel 900 who can confirm alarms in real time is limited. In such a case, it is appropriate to set the variable (Y%) included in the conditional clause of the monitoring rule to a high sensitivity so as not to notify an alarm with a high possibility of erroneous detection.
- the sensitivity for detecting an abnormal situation must be adjusted according to the degree of congestion of the monitoring target at the monitoring location.
- FIG. 2 is a block diagram illustrating a configuration of the monitoring system 1000 according to the first embodiment.
- the monitoring system 1000 includes a sensor 200, a monitoring server 100, and a sensitivity adjustment device 300.
- the monitoring server 100 and the sensitivity adjustment device 300 may be the same device.
- the monitoring server 100 includes a rule determination unit 110 and a rule storage unit 120.
- the rule determination unit 110 receives information obtained by measuring the situation at the monitoring location from the sensor 200.
- the rule determination unit 110 analyzes the received information and extracts the behavior or attribute of the monitoring target at the monitoring location.
- the rule determination unit 110 refers to the rule storage unit 120 and searches for a monitoring rule including a conditional clause (if clause) that matches the behavior or attribute of the monitoring target. When the monitoring rule is searched, the rule determination unit 110 executes an operation specified by the then clause included in the monitoring rule.
- the rule storage unit 120 stores monitoring rules.
- the monitoring rule is stored in association with the monitoring location, for example.
- the monitoring rule is stored in association with the monitoring period, for example.
- FIG. 3 is a block diagram showing the configuration of the sensitivity adjustment apparatus 300 shown in FIG. As shown in FIG. 3, the sensitivity adjustment device 300 includes a congestion degree determination unit 310 and a sensitivity determination unit 320.
- the congestion degree determination unit 310 receives information representing the situation at the monitoring place from the sensor 200.
- the congestion degree determination unit 310 determines the degree of congestion of the monitoring target at the monitoring location based on the received information.
- the congestion degree determination unit 310 determines the degree of congestion of the monitoring target at the monitoring location using, for example, face recognition technology or voice recognition technology.
- the sensitivity determination unit 320 determines the sensitivity when the monitoring system 1000 detects an abnormal situation that occurs at the monitoring location based on the congestion level determined by the congestion level determination unit.
- the sensitivity determination unit 320 may determine the sensitivity by referring to, for example, a table that stores information that associates the degree of congestion with the sensitivity.
- the sensitivity determination unit 320 may update the monitoring rule stored in the rule storage unit 120 based on the determined sensitivity.
- the sensitivity determination unit 320 may transmit the determined sensitivity to the monitoring server 100.
- the monitoring server 100 may include a monitoring rule update unit (not shown) that updates the monitoring rule stored in the rule storage unit 120 based on the received sensitivity.
- the sensitivity for detecting the occurrence of an abnormal situation can be appropriately adjusted according to the situation at the monitoring location.
- the monitoring system 1000 monitors the movement of a crowd at a ticket gate of a station.
- the surveillance camera shows a video of a large number of people moving from the same direction in a short time. Therefore, compared with the normal time that is not immediately after arrival of the train, the monitoring system 100 has detected that the crowd is getting out of the train and passing through the ticket gate. There is a risk of false detection.
- the sensitivity adjustment apparatus 300 according to the first embodiment, the sensitivity of the monitoring rule can be appropriately adjusted in such a case.
- the monitoring system 1000 detects whether crowd disturbance has occurred at a ticket gate of a station.
- the monitoring system 1000 mistakenly detects the ordinary situation that the crowd is heading to the store where the half price sale is being held by using the train as an abnormal situation “the crowd is evacuating”. There is a risk that.
- it is necessary to adjust the sensitivity for detecting an abnormal situation at the time of congestion.
- the sensitivity adjustment apparatus 300 according to the first embodiment, the sensitivity of the monitoring rule can be appropriately adjusted in such a case.
- ⁇ Second Embodiment> an outline of the sensitivity adjustment apparatus 400 according to the second embodiment will be described.
- the monitoring server 100 determines the degree of congestion at the monitoring location in real time.
- the performance of the monitoring server 100 is low, it is difficult to perform image processing on the image received from the sensor in real time and determine the degree of congestion at the monitoring location in real time.
- the performance of the sensor 200 that is a monitoring camera is low, it is difficult to perform face recognition processing or the like on a captured image with low image quality by the sensor 200 in real time and determine the degree of congestion at the monitoring location in real time.
- the process for determining the degree of congestion based on such an image is generally a process that requires a high level of information processing capability.
- the sensitivity adjustment device 400 according to the second embodiment can solve such a problem.
- the sensitivity adjustment apparatus 400 according to the second embodiment grasps in advance events scheduled to occur in the vicinity of the monitoring place. Thereby, the sensitivity adjustment apparatus 400 concerning 2nd Embodiment can estimate the congestion degree of a monitoring place before monitoring is performed.
- the sensitivity adjustment apparatus 400 according to the second embodiment determines the sensitivity when the monitoring system detects an abnormal situation based on the degree of congestion of the monitoring location predicted from events scheduled to occur in the vicinity of the monitoring location. To do.
- the sensitivity adjustment apparatus 400 according to the second embodiment will be described in detail with reference to the drawings.
- FIG. 4 is a block diagram showing a configuration of the monitoring system 2000 having the sensitivity adjustment device 400 according to the second embodiment.
- the monitoring system 2000 includes a monitoring server 100, a sensor 200, and a sensitivity adjustment device 400. Components that are substantially the same as those shown in FIG.
- FIG. 5 is a block diagram showing the configuration of the sensitivity adjustment apparatus 400 shown in FIG.
- the sensitivity adjustment device 400 includes a monitoring location acquisition unit 410, a candidate location extraction unit 420, an event extraction unit 430, a sensitivity determination unit 440, a sensitivity table 450, a sensitivity adjustment unit 460, Is provided.
- the monitoring location acquisition unit 410 acquires monitoring location information representing the monitoring location.
- the monitoring location may be a surveillance camera identifier, for example.
- the sensitivity adjustment apparatus 400 may store a correspondence relationship between the identifier of the monitoring camera and the installation location of the monitoring camera.
- the monitoring location may be, for example, a specific store, a specific park, a specific station, or a specific area specified by latitude and longitude.
- the candidate location extraction unit 420 is a location in the vicinity of the monitoring location represented by the monitoring location information acquired by the monitoring location acquisition unit 410, and is a location where an event that affects the degree of congestion of people or vehicles may occur. , “Candidate place” is extracted.
- “event” indicates an event in which an increase or decrease in the monitoring target (such as a person) is expected at the monitoring location. For example, when a “sale” that is an example of an event occurs, it is expected that many people will come to the store where the sale occurs during the sale period. For example, when “road construction”, which is an example of an event, starts, a person avoids a place where road construction is performed, so it is expected that there will be fewer people around the place where road construction is performed.
- the candidate place extraction unit 420 is realized by using a database in which places that can be event holding place candidates, that is, event venues, stores, parks, roads, terrain, and the like are recorded together with their location information.
- places that can be event holding place candidates that is, event venues, stores, parks, roads, terrain, and the like are recorded together with their location information.
- An example of such a database is shown in [Reference 1] below.
- the candidate location extraction unit 420 extracts, for example, candidate locations near the monitoring location “A intersection” as follows. For example, let us consider a case where a store or the like exists in the vicinity of the “A intersection” that is a monitoring place at the following distance.
- the candidate place extraction unit 420 extracts the department store A, the bank B, and the clothes shop D as candidate places by using a database as shown in [Reference Document 1], for example.
- the monitoring location information or candidate location information may include location information such as the location name (for example, store name), the location address, and the location latitude and longitude.
- the event extraction unit 430 receives input of candidate location information extracted by the candidate location extraction unit 420.
- the event extraction unit 430 extracts “information about an event” scheduled to occur at the candidate location from a database in which text described about the event is stored using the candidate location information as a key.
- the event extraction unit 430 accesses the Internet, for example, and searches text information described about the event from a database existing on the Internet.
- the event extraction unit 430 extracts “information about the event” scheduled to occur at the candidate location from the searched text information.
- the information related to the event is, for example, information indicating whether or not the event is held, the type of event that occurs, or the event holding period.
- the event extraction unit 430 extracts that the event “half-price sale” is scheduled for the holding period “July to August”. For example, for the bank B, the event extraction unit 430 extracts that there is no event that occurs. For example, for the clothes shop D, the event extraction unit 430 extracts that the event “Summer sale sale” is scheduled for the holding period “August to September”.
- the event extraction unit 430 may store a keyword related to the event, for example.
- the keywords related to the event are, for example, nouns representing the name of the event (for example, “sale”, “road construction”, etc.), or verbs indicating that the event will occur (for example, “wake up”, “held”, “open”) Etc.).
- the event extraction unit 430 searches, for example, a text document that includes both a keyword related to an event and candidate place information, and performs an extraction process using a known text mining technique.
- the event extraction unit 430 is realized by applying the technology disclosed in [Reference 2], for example.
- the sensitivity determination unit 440 detects an abnormal situation that occurs at the monitoring location based on the monitoring location information, candidate location information, or information related to the event, according to the expected degree of congestion at the monitoring location. Determine the sensitivity. Specifically, the sensitivity determination unit 440 determines a sensitivity adjustment parameter.
- the sensitivity adjustment parameter is a parameter for adjusting the value of a variable included in the conditional clause of the monitoring rule. For example, the following monitoring rule is assumed.
- “x” is a symbol indicating multiplication.
- the operation executed between the value of the variable included in the monitoring rule and the value of the sensitivity adjustment parameter is not limited to multiplication, but may be another operation.
- the description will be continued on the assumption that the greater the value of the sensitivity adjustment parameter, the lower the sensitivity of the monitoring rule when the value of the sensitivity adjustment parameter is calculated as a variable value.
- the relationship between the sensitivity adjustment parameter value and the monitoring rule sensitivity is not limited to the above-described relationship.
- the sensitivity determination unit 440 determines the sensitivity adjustment parameter.
- the various variations will be described.
- the sensitivity determination unit 440 refers to the sensitivity table 450 based on the position information included in the monitoring location, the position information included in the candidate location information, and the information related to the event extracted by the event extraction unit 430, thereby detecting the sensitivity. Determine adjustment parameters.
- FIG. 6 is information indicating an example of information stored in the sensitivity table 450.
- the sensitivity table 450 illustrated in FIG. 6 stores information in which the value of the sensitivity adjustment parameter is associated with the distance from the monitoring location to the candidate location.
- sensitivity adjustment parameters are set such that the closer the distance from the monitoring location to the candidate location is, the greater the influence of the sensitivity of the monitoring rule is (the sensitivity is greatly reduced). Is done. This is because the closer the distance from the monitoring location to the event venue, the stronger the congestion level at the monitoring location is likely to be affected by the congestion level at the event location.
- the distance from the monitoring location to the candidate location is calculated based on the location information of the monitoring location and the location information of the candidate location.
- the distance may be a linear distance between the monitoring place and the candidate place, or may be a route distance along the road. It may be a weighted distance in consideration of the scenery from the monitoring location to the candidate location, ease of walking, and the like.
- the sensitivity determination unit 440 acquires the sensitivity adjustment parameter 1.5 because the distance from the monitoring location is 150 meters. For example, for the clothes shop D, the sensitivity determination unit 440 acquires the sensitivity adjustment parameter 1.25 because the distance from the monitoring place is 350 meters.
- the “half-price sale” occurring at department store A is held from July to August, and the “summer bargain sale” occurring at clothing store D is from August to September. Therefore, the sensitivity determination unit 440 determines that the sensitivity adjustment parameter is 1.5 since only the department store A needs to be considered as the sensitivity adjustment parameter for July.
- Sensitivity determination unit 440 determines the sensitivity adjustment parameter as 1.25 because the sensitivity adjustment parameter for September only needs to consider clothing store D.
- the sensitivity determination unit 440 needs to consider both the department store A and the clothing store D as the sensitivity adjustment parameter for August.
- the sensitivity determination unit 440 may set the maximum value of the sensitivity adjustment parameter determined based on the department store A and the clothing store D as the sensitivity adjustment parameter for August.
- the sensitivity determination unit 440 may set other statistical values such as a sum value or an average value as the sensitivity adjustment parameter, not limited to the maximum value.
- the sensitivity determination unit 440 outputs, for example, the sensitivity adjustment parameter and the effective period of the sensitivity adjustment parameter in association with each other.
- FIG. 7 is a diagram illustrating an example of information output by the sensitivity determination unit 440.
- the sensitivity determination unit 440 sets 1.5 as the sensitivity adjustment parameter for July, 1.5 as the sensitivity adjustment parameter for August, and 1.25 as the sensitivity adjustment parameter for September. Is output.
- the sensitivity adjustment unit 460 updates the rules stored in the rule storage unit 120 included in the monitoring server 100 based on the sensitivity adjustment parameter determined by the sensitivity determination unit 440.
- the sensitivity adjustment unit 460 may be provided as a function of the monitoring server 100 instead of the function of the sensitivity adjustment device 400.
- FIG. 8 is a flowchart for explaining the operation of the sensitivity adjustment apparatus 400.
- the monitoring location acquisition unit 410 acquires monitoring location information indicating a monitoring location that is monitored by the monitoring system 2000 (step S101).
- the candidate place extraction unit 420 extracts candidate place information that represents a candidate place that is in the vicinity of the monitoring place and that may cause an event that affects the degree of congestion of people or vehicles (step S102).
- the event extraction unit 430 uses the candidate location information as a key to extract information related to an event scheduled to occur at the candidate location from a database storing text related to the event (step S103).
- the sensitivity determination unit 440 detects an abnormal situation that the monitoring system 2000 generates at the monitoring location according to the degree of congestion of the monitoring location that is expected based on the candidate location information and the information related to the event extracted by the event extraction unit 430. Sensitivity for detection is determined (step S104).
- the sensitivity adjustment unit 460 updates the rule stored in the rule storage unit 120 included in the monitoring server 100 based on the sensitivity adjustment parameter determined by the sensitivity determination unit 440 (step S105).
- the operation indicated by step S105 may be an operation executed by the monitoring server 100, not an operation executed by the sensitivity adjustment device 400.
- the “information about the event” extracted by the event extraction unit 430 may be information indicating the number of participants expected for the event scheduled to be held, for example. For example, when a similar event has been held in the same place in the past, the event extraction unit 430 obtains such information by searching for a text that describes the number of participants in the event that has been held in the past. To do. Specifically, for example, when a text describing an event includes a description of the past number of participants directly, the event extraction unit 430 obtains information indicating the expected number of participants in the event. .
- the case where the description of the event directly includes the description of the past number of participants is, for example, the case where the description includes, for example, “The previous number of participants was 1000” It is. In the above case, the expected number of participants is 1000.
- FIG. 9 is a diagram illustrating an example of information stored in the sensitivity table 450.
- the sensitivity table 450 illustrated in FIG. 9 includes information in which the number of participants expected to participate in the event and the sensitivity adjustment parameter are associated with each other.
- the sensitivity determination unit 440 may determine the sensitivity adjustment parameter with reference to the sensitivity table 450 based on “information indicating the number of participants expected to participate in the event” extracted by the event extraction unit 430.
- the sensitivity determination unit 440 outputs the determined sensitivity adjustment parameter.
- the event extraction unit 430 may extract a type of an event scheduled to occur in the candidate place information with reference to an event type dictionary 470 (not shown).
- FIG. 10 is a diagram illustrating an example of information stored in the event type dictionary 470.
- the event type dictionary 470 stores a word indicating an event type, a word indicating the type of the event, and an expression that easily occurs together.
- the event type dictionary 470 stores “sale”, “bargain”, and “discount” as keywords that are likely to co-occur with the event “sale”. For example, the event type dictionary 470 searches a document including an event name, and registers a high-frequency expression that appears in the searched document and is likely to co-occur with the event name as a keyword in the event type keyword storage unit. create.
- the event extraction unit 430 extracts the appearance frequency of the keyword stored in the event type dictionary 470 from the text information described about the event searched using the candidate location information as a key. For example, the event extraction unit 430 determines the event type including the keyword with the highest appearance frequency as the event type.
- FIG. 11 is a diagram illustrating an example of information stored in the sensitivity table 450.
- the sensitivity table 450 stores information that associates sensitivity adjustment parameters, distances from the monitoring locations to the candidate locations, and event types.
- the sensitivity determination unit 440 refers to the sensitivity table 450 and determines a sensitivity adjustment parameter based on the distance between the monitoring location and the candidate location and the event type extracted by the event extraction unit.
- the sensitivity determination unit 440 outputs the determined sensitivity adjustment parameter.
- the sensitivity adjustment device 400 can appropriately adjust the sensitivity for detecting the occurrence of an abnormal situation according to the degree of congestion at the monitoring location.
- the monitoring server 100 may be difficult for the monitoring server 100 to determine the degree of congestion of the monitoring location in real time due to low performance of the monitoring server 100 or low quality of information received from the sensor 200. .
- the sensitivity adjustment device 400 even in such a case, the sensitivity for detecting the occurrence of an abnormal situation can be appropriately adjusted according to the degree of congestion at the monitoring location.
- the sensitivity adjustment device 400 uses the text mining technology to grasp an event scheduled to occur in the vicinity of the monitoring location prior to the monitoring being executed. The reason is that the sensitivity adjustment device 400 determines the sensitivity when the monitoring system 2000 detects an abnormal situation based on the congestion degree of the monitoring place predicted from an event scheduled to occur in the vicinity of the monitoring place. Because.
- An event occurring in the vicinity of the monitoring location cannot be controlled by the monitoring person 900 of the monitoring system 2000.
- the sensitivity adjustment device 400 even for such an event that the monitoring person 900 of the monitoring system 2000 cannot control whether or not the event is held, an appropriate response according to the change in the degree of congestion at the monitoring location caused by the event. Sensitivity can be determined.
- FIG. 12 is a block diagram illustrating a configuration of a sensitivity adjustment apparatus 500 according to the third embodiment.
- the third sensitivity adjustment apparatus 500 includes an extraction unit 520 and a sensitivity determination unit 530.
- the extraction unit 520 extracts information related to an event scheduled to occur at the monitoring location from a database in which text described regarding the event is stored, using monitoring location information representing a monitoring location that is monitored by the monitoring system as a key. .
- the sensitivity determination unit 530 is a sensitivity when the monitoring system detects an abnormal situation that occurs in the monitoring location according to the monitoring location information and the degree of congestion of the monitoring location expected based on the information related to the event extracted by the extraction unit 520. To decide.
- the sensitivity adjustment device 500 it is possible to appropriately adjust the sensitivity for detecting the occurrence of an abnormal situation according to the degree of congestion at the monitoring location.
- the monitoring server 100 may be difficult for the monitoring server 100 to determine the congestion degree of the monitoring place in real time due to low performance of the monitoring server 100 or low quality of information received from the sensor 200. .
- the sensitivity adjustment device 500 even in such a case, the sensitivity for detecting the occurrence of an abnormal situation can be appropriately adjusted according to the degree of congestion at the monitoring location.
- the reason is that the sensitivity adjustment device 500 uses the text mining technique to grasp an event scheduled to occur at the monitoring location prior to the monitoring being executed. The reason is that the sensitivity adjustment device 500 determines the sensitivity when the monitoring system detects an abnormal situation based on the congestion degree of the monitoring place predicted from the event scheduled to occur at the monitoring place. .
- FIG. 13 is a block diagram illustrating a configuration of a sensitivity adjustment apparatus 600 according to the fourth embodiment.
- the fourth sensitivity adjustment device 600 includes an extraction unit 620 and a sensitivity determination unit 630.
- the extraction unit 620 extracts information on an event scheduled to occur at the candidate location from a database in which text described about the event is stored using the candidate location information as a key.
- Candidate location information is information representing a candidate location.
- the candidate location is a location in the vicinity of the monitoring location that is monitored by the monitoring system, and a location where an event that affects the degree of congestion of the monitoring target may occur.
- Sensitivity determination unit 630 determines whether the monitoring system detects an abnormal situation occurring at the monitoring location according to the degree of congestion of the monitoring location expected based on the candidate location information and information about the event extracted by extraction unit 620. Determine the sensitivity.
- the sensitivity adjustment device 600 it is possible to appropriately adjust the sensitivity for detecting the occurrence of an abnormal situation according to the degree of congestion at the monitoring location.
- the monitoring person in charge of the monitoring system 900 may set an arbitrary value for the threshold of the distance determined in the candidate place extraction unit 420.
- the monitoring person 900 in the monitoring system may want to adjust only the sensitivity of some monitoring rules among the plurality of monitoring rules.
- the sensitivity adjustment unit 460 may output the sensitivity adjustment parameter together with the designation of the monitoring rule for calculating the sensitivity adjustment parameter.
- the event holding period extracted by the event extraction unit 430 may include not only the date on which the event occurs but also information on the time at which the event occurs.
- the sensitivity determination unit 440 does not always output the event holding period itself extracted by the event extraction unit 430 when outputting the determined sensitivity in association with the event holding time. For example, the sensitivity determination unit 440 estimates the time required for a person to move from the candidate location to the monitoring location in consideration of the distance from the monitoring location to the candidate location, and from the event holding time by the estimated time. The shifted time may be output in association with the sensitivity adjustment parameter.
- sensitivity adjustment parameters may be set such that the closer the distance from the monitoring location to the candidate location, the less affected the sensitivity of the monitoring rule.
- a sensitivity adjustment parameter may be set such that the sensitivity of the monitoring rule increases as the distance from the monitoring location to the candidate location is shorter.
- the monitoring location acquisition unit 410 may receive monitoring location information from an external device of the sensitivity adjustment device 400.
- the monitoring location acquisition unit 410 may accept input of monitoring location information from the monitoring person 900 of the monitoring system 2000.
- the monitoring location acquisition unit 410 may read monitoring location information from a storage unit (not shown) provided in the sensitivity adjustment device 400.
- the extraction unit 520 may receive monitoring location information from an external device of the sensitivity adjustment device 500.
- the extraction unit 520 may accept input of monitoring location information from the monitoring staff 900.
- the extraction unit 520 may read monitoring location information from a storage unit (not shown) provided in the sensitivity adjustment device 500.
- the database storing the text described about the event accessed by the extraction unit 520 may be provided in the sensitivity adjustment device 500 or in an external device connected to the sensitivity adjustment device 500 via a communication network. It may be done.
- the extraction unit 620 may receive monitoring location information or candidate location information from an external device of the sensitivity adjustment device 600.
- the extraction unit 620 may accept input of monitoring location information or candidate location information from the monitoring staff 900.
- the extraction unit 620 may read monitoring location information or candidate location information from a storage unit (not shown) provided in the sensitivity adjustment device 600.
- the database storing the text described about the event accessed by the extraction unit 620 may be provided in the sensitivity adjustment device 600 or in an external device connected to the sensitivity adjustment device 600 via a communication network. It may be done.
- the variable included in the monitoring rule is not limited to one.
- a surveillance rule that focuses a surveillance camera on a person who is likely to be a victim of snatching is assumed.
- Such a monitoring rule is, for example, the following rule.
- the sensitivity adjustment parameter may adjust all of a plurality of variables (A and B in the above example) included in the monitoring rule as described above, or may adjust a part of the plurality of variables.
- the method for adjusting the sensitivity of the monitoring rule by the sensitivity adjustment parameter is not limited to the method of adjusting the value of the variable included in the monitoring rule.
- the condition clause of the monitoring rule includes a condition obtained by combining a plurality of conditions with “and”.
- the sensitivity adjustment unit 460 may adjust the sensitivity of the monitoring rule by changing “and” included in the conditional clause of the monitoring rule to “or” according to the sensitivity adjustment parameter.
- the sensitivity adjustment unit 460 may adjust the sensitivity of the monitoring rule by ignoring a part of the conditions combined with “and” according to the sensitivity adjustment parameter.
- the sensitivity may be adjusted as follows according to the sensitivity adjustment parameter.
- Surveillance rule “if (a person in the image is female with a reliability of A% or higher) or (the person is 60% or older with a reliability of B% or higher) then (focus the surveillance camera on the person)” .
- the sensitivity may be adjusted as follows according to the sensitivity adjustment parameter.
- FIG. 14 is a diagram illustrating an example of a hardware configuration of an information processing apparatus (computer) that can realize the sensitivity adjustment apparatus according to each embodiment.
- the hardware configuring the information processing device 3000 includes a CPU (Central Processing Unit) 1, a memory 2, a storage device 3, and a communication interface (I / F) 4.
- the information processing device 3000 may include the input device 5 or the output device 6.
- the functions of the information processing apparatus 3000 are realized by, for example, the CPU 1 executing a computer program (software program, hereinafter simply referred to as “program”) read into the memory 2. In execution, the CPU 1 appropriately controls the communication interface 4, the input device 5, and the output device 6.
- program software program
- the present invention which will be described by taking this embodiment and each embodiment described later as an example, is also configured by a non-volatile storage medium 8 such as a compact disk in which such a program is stored.
- the program stored in the storage medium 8 is read by the drive device 7, for example.
- the communication executed by the information processing apparatus 3000 is realized by the application program controlling the communication interface 4 using a function provided by an OS (Operating System), for example.
- the input device 5 is, for example, a keyboard, a mouse, or a touch panel.
- the output device 6 is a display, for example.
- the information processing device 3000 may be configured by connecting two or more physically separated devices in a wired or wireless manner.
- the hardware configuration of the information sensitivity adjusting device and each functional block thereof is not limited to the above-described configuration.
- each block diagram is a configuration shown for convenience of explanation.
- the present invention described by taking each embodiment as an example is not limited to the configuration shown in each block diagram in the implementation.
- the present invention can be used for a sensitivity adjustment device for adjusting the sensitivity of a monitoring system, a sensitivity adjustment method and program, and a monitoring system.
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Alarm Systems (AREA)
- Emergency Alarm Devices (AREA)
Abstract
Description
監視ルール1:「if(人が鞄を置く画像がカメラに写りその後30分間その荷物に人が近づかない)」という条件節を含む監視ルール、
監視ルール2:「if(人が鞄を置く画像がカメラに写りその後1時間その荷物に人が近づかない)」という条件節を含む監視ルール。
監視ルール:「if (画像に映っている人物の顔と、指名手配されている人物の顔とが、所定の値(Y%)以上の信頼度で一致する)then(監視担当者900に警報を出力する)」。
図2は、第1の実施形態にかかる監視システム1000の構成を示すブロック図である。図2に示すように、監視システム1000は、センサー200と、監視サーバ100と、感度調整装置300とを有する。監視サーバ100と感度調整装置300とは、同一の装置であってもよい。
まず、第2の実施形態にかかる感度調整装置400の概要を説明する。監視サーバ100の性能、または、センサー200から受信する情報の内容によっては、監視サーバ100が、リアルタイムに監視場所の混雑度を判定することが難しい場合がある。例えば、監視サーバ100の性能が低い場合、センサーから受信した画像に対して画像処理をリアルタイムに行い、監視場所の混雑度をリアルタイムに判定することは難しい。例えば、監視カメラであるセンサー200の性能が低い場合は、係るセンサー200による画質の低い撮影画像に対して、顔認識処理等をリアルタイムに行い、監視場所の混雑度をリアルタイムに判定することは難しい。
グーグルマップ https://maps.***.co.jp/(但し、グーグルは登録商標)。
銀行B :A交差点との距離100メートル、
ガソリンスタンドC :A交差点との距離400メートル、
服屋D :A交差点との距離350メートル。
特開2004-102559、
感度決定部440は、監視場所情報、候補場所情報、または、イベントに関する情報などに基づいて、予想される監視場所の混雑度に応じて、監視システム2000が監視場所で発生する異常事態を検出する際の感度を決定する。具体的には、感度決定部440は、感度調整パラメタを決定する。
イベント抽出部430が抽出する「イベントに関する情報」は、例えば、開催が予定されるイベントに予想される参加人数を示す情報であってもよい。例えば、過去に類似のイベントが同じ場所で開催されていた場合に、イベント抽出部430が、過去に開催されたイベントの参加人数が記載されたテキストを検索することによって、このような情報を入手する。具体的には、例えば、イベントに関して記載されたテキストに、直接的に過去の参加人数の記載が含まれていた場合、イベント抽出部430は、予想されるイベントの参加人数を示す情報を入手する。イベントに関して記載されたテキストに、直接的に過去の参加人数の記載が含まれている場合とは、例えば、「前回の参加人数は1000人でした」等の記載がテキストに含まれている場合である。上述の場合には、予想される参加人数は1000人である。
イベント抽出部430は、図示しないイベント種類辞書470を参照して、候補場所情報で起きる予定のイベントの種類を抽出してもよい。
図12は、第3の実施形態にかかる感度調整装置500の構成を表すブロック図である。
図13は、第4の実施形態にかかる感度調整装置600の構成を表すブロック図である。図13に示すように、第4の感度調整装置600は、抽出部620と、感度決定部630と、を備える。
候補場所抽出部420に定められる距離の閾値は、監視システムの監視担当者900が任意の値を設定してもよい。
例えば、ひったくり(purse-snatching)を監視するために、ひったくりの被害者になりやすい人物に監視カメラをフォーカスさせるような監視ルールを想定する。このような監視ルールは、例えば下記のようなルールになる。
図14は、各実施形態における感度調整装置を実現可能な情報処理装置(コンピュータ)のハードウェア構成の一例を示す図である。情報処理装置3000を構成するハードウェアは、CPU(Central Processing Unit)1、メモリ2、記憶装置3、通信インターフェース(I/F)4を備える。情報処理装置3000は、入力装置5または出力装置6を備えていてもよい。情報処理装置3000の機能は、例えばCPU1が、メモリ2に読み出されたコンピュータプログラム(ソフトウェアプログラム、以下単に「プログラム」と記載する)を実行することにより実現される。実行に際して、CPU1は、通信インターフェース4、入力装置5および出力装置6を適宜制御する。
110 ルール判定部
120 ルール記憶部
200 センサー
300,600 感度調整装置
310 混雑度判定部
320,530 感度決定部
400,500 感度調整装置
410 監視場所取得部
420 候補場所抽出部
430 イベント抽出部
440,630 感度決定部
450 感度テーブル
460 感度調整部
470 イベント種類辞書
520,620 抽出部
900 監視担当者
1000,2000 監視システム
3000 情報処理装置
Claims (10)
- 監視システムが監視する場所である監視場所の近傍の場所であり、かつ、監視対象の混雑度に影響するイベントが起きる可能性がある場所である、候補場所を表す候補場所情報をキーとして、イベントに関して記載されたテキストが格納されたデータベースから、前記候補場所で起きる予定のイベントに関する情報を抽出する抽出手段と、
前記候補場所情報および前記抽出手段が抽出したイベントに関する情報に基づいて予想される前記監視場所の混雑度に応じて、前記監視システムが前記監視場所で発生する異常事態を検出する際の感度を決定する感度決定手段と、
を備える感度調整装置。 - センサーと監視サーバとを有する監視システムにおいて用いられる、請求項1に記載の感度調整装置であって、
前記センサーは、前記監視場所における状況を測定し、
前記監視サーバは、前記センサーが測定した情報、および、前記監視場所に関連付けられてあらかじめ設定された監視ルールに基づいて、前記監視場所に異常が発生したか否かを監視し、
前記監視ルールは特定の条件を定義する情報を含み、前記センサーが測定した情報が前記特定の条件を満たすか否かに基づいて、前記監視場所に異常が発生したか否かを監視するルールであり、
前記特定の条件を定義する情報は少なくとも一つの変数を含み、
前記感度調整装置が備える前記感度決定手段は、前記特定の条件を定義する情報に含まれる変数値の調整に用いる感度調整パラメタを決定する、
請求項1に記載の感度調整装置。 - 前記感度決定手段は、前記監視場所の位置情報および前記候補場所の位置情報に基づいて、前記監視場所と前記候補場所との間の距離を算出し、前記算出した距離に基づいて、前記感度調整パラメタを決定する、
請求項1または2に記載の感度調整装置。 - 前記抽出手段は、前記候補場所で起きる予定のイベントの種類を抽出し、
前記感度決定手段は、前記抽出手段が抽出した前記イベントの種類に基づいて、前記感度調整パラメタを決定する、請求項1から3のいずれかに記載の感度調整装置。 - 前記監視ルールは、前記監視場所および特定の期間に関連付けられて設定されており、
前記抽出手段は、前記候補場所で起きる予定のイベントを、当該イベントの開催が予定される期間と併せて抽出し、
前記感度決定手段は、前記抽出手段が抽出した前記イベントの開催が予定される期間、および、前記イベントに関する情報に基づいて、前記特定の条件を定義する情報に含まれる変数の値を調整するための感度調整パラメタを決定し、前記決定した感度調整パラメタを、前記特定の期間を指定する情報と併せて算出する、
請求項2から4のいずれかに記載の感度調整装置。 - 請求項2から5のいずれかに記載の、監視サーバおよび感度調整装置を有する、
監視システム。 - コンピュータによって、
監視システムが監視する場所である監視場所の近傍の場所であり、かつ、人または車の混雑度に影響するイベントが起きる可能性がある場所である候補場所を表す候補場所情報をキーとして、イベントに関して記載されたテキストが格納されたデータベースから、前記候補場所で起きる予定のイベントに関する情報を抽出し、、
前記候補場所情報および前記抽出手段が抽出したイベントに関する情報に基づいて予想される前記監視場所の混雑度に応じて、前記監視システムが前記監視場所で発生する異常事態を検出する際の感度を決定する、
感度調整方法。 - 監視システムが監視する場所である監視場所の近傍の場所であり、かつ、人または車の混雑度に影響するイベントが起きる可能性がある場所である、候補場所を表す候補場所情報をキーとして、イベントに関して記載されたテキストが格納されたデータベースから、前記候補場所で起きる予定のイベントに関する情報を抽出する処理と、
前記候補場所情報および前記抽出手段が抽出したイベントに関する情報に基づいて予想される前記監視場所の混雑度に応じて、前記監視システムが前記監視場所で発生する異常事態を検出する際の感度を決定する処理と、
をコンピュータに実行させるプログラムが格納されたコンピュータ読み取り可能な記憶媒体。 - 監視システムが監視する場所である監視場所を表す監視場所情報をキーとして、イベントに関して記載されたテキストが格納されたデータベースから、前記監視場所で起きる予定のイベントに関する情報を抽出する抽出手段と、
前記監視場所情報および前記抽出手段が抽出したイベントに関する情報に基づいて予想される前記監視場所の混雑度に応じて、前記監視システムが前記監視場所で発生する異常事態を検出する際の感度を決定する感度決定手段と、
を備える感度調整装置。 - 監視システムが監視する場所である監視場所における状況を測定するセンサーから、監視場所における状況を表す情報を受信し、前記受信した情報に基づいて、前記監視場所における人または車の混雑度を判定する混雑度判定手段と、
前記混雑度判定手段が判定した前記監視場所における混雑度に応じて、前記監視システムが前記監視場所で発生する異常事態を検出する際の感度を決定する感度決定手段と、
を備える感度調整装置。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2015523845A JPWO2014208025A1 (ja) | 2013-06-25 | 2014-06-09 | 感度調整装置、感度調整方法およびコンピュータプログラム、並びに監視システム |
US14/898,543 US20160133122A1 (en) | 2013-06-25 | 2014-06-09 | Sensitivity adjustment device, sensitivity adjustment method, storage medium, and monitoring system |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2013-132738 | 2013-06-25 | ||
JP2013132738 | 2013-06-25 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2014208025A1 true WO2014208025A1 (ja) | 2014-12-31 |
Family
ID=52141397
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2014/003060 WO2014208025A1 (ja) | 2013-06-25 | 2014-06-09 | 感度調整装置、感度調整方法および記憶媒体、並びに監視システム |
Country Status (3)
Country | Link |
---|---|
US (1) | US20160133122A1 (ja) |
JP (1) | JPWO2014208025A1 (ja) |
WO (1) | WO2014208025A1 (ja) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2017028561A (ja) * | 2015-07-24 | 2017-02-02 | セコム株式会社 | 画像監視システム |
JP2021064364A (ja) * | 2019-10-16 | 2021-04-22 | 清華大学Tsinghua University | 情報認識システムおよびその方法 |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10650621B1 (en) | 2016-09-13 | 2020-05-12 | Iocurrents, Inc. | Interfacing with a vehicular controller area network |
EP3410413B1 (en) * | 2017-06-02 | 2021-07-21 | Netatmo | Improved generation of alert events based on a detection of objects from camera images |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2000007264A (ja) * | 1998-06-17 | 2000-01-11 | Hitachi Ltd | マンコンベア装置 |
JP2004102559A (ja) * | 2002-09-09 | 2004-04-02 | Toshiba Corp | スケジュール情報抽出編集装置および方法 |
JP2006226977A (ja) * | 2005-02-21 | 2006-08-31 | Alpine Electronics Inc | ナビゲーション装置 |
JP2011081735A (ja) * | 2009-10-09 | 2011-04-21 | Sogo Keibi Hosho Co Ltd | 不審者監視装置および不審者監視方法 |
JP2012069022A (ja) * | 2010-09-27 | 2012-04-05 | Hitachi Ltd | 監視システム |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6028626A (en) * | 1995-01-03 | 2000-02-22 | Arc Incorporated | Abnormality detection and surveillance system |
US9501919B2 (en) * | 2011-03-11 | 2016-11-22 | Elisabeth Laett | Method and system for monitoring the activity of a subject within spatial temporal and/or behavioral parameters |
US9740937B2 (en) * | 2012-01-17 | 2017-08-22 | Avigilon Fortress Corporation | System and method for monitoring a retail environment using video content analysis with depth sensing |
US11397462B2 (en) * | 2012-09-28 | 2022-07-26 | Sri International | Real-time human-machine collaboration using big data driven augmented reality technologies |
US9232178B2 (en) * | 2013-03-15 | 2016-01-05 | Intelmate Llc | Time-based multivariable secure facility alarm system |
-
2014
- 2014-06-09 JP JP2015523845A patent/JPWO2014208025A1/ja active Pending
- 2014-06-09 US US14/898,543 patent/US20160133122A1/en not_active Abandoned
- 2014-06-09 WO PCT/JP2014/003060 patent/WO2014208025A1/ja active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2000007264A (ja) * | 1998-06-17 | 2000-01-11 | Hitachi Ltd | マンコンベア装置 |
JP2004102559A (ja) * | 2002-09-09 | 2004-04-02 | Toshiba Corp | スケジュール情報抽出編集装置および方法 |
JP2006226977A (ja) * | 2005-02-21 | 2006-08-31 | Alpine Electronics Inc | ナビゲーション装置 |
JP2011081735A (ja) * | 2009-10-09 | 2011-04-21 | Sogo Keibi Hosho Co Ltd | 不審者監視装置および不審者監視方法 |
JP2012069022A (ja) * | 2010-09-27 | 2012-04-05 | Hitachi Ltd | 監視システム |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2017028561A (ja) * | 2015-07-24 | 2017-02-02 | セコム株式会社 | 画像監視システム |
JP2021064364A (ja) * | 2019-10-16 | 2021-04-22 | 清華大学Tsinghua University | 情報認識システムおよびその方法 |
JP7075460B2 (ja) | 2019-10-16 | 2022-05-25 | 清華大学 | 情報認識システムおよびその方法 |
Also Published As
Publication number | Publication date |
---|---|
US20160133122A1 (en) | 2016-05-12 |
JPWO2014208025A1 (ja) | 2017-02-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20210191979A1 (en) | Distributed video storage and search with edge computing | |
US10186123B2 (en) | Complex event recognition in a sensor network | |
EP3654285A1 (en) | Object tracking using object attributes | |
WO2019191146A1 (en) | People counting and tracking systems and methods | |
JP2012518846A (ja) | 異常挙動を予測するためのシステムおよび方法 | |
US8971577B2 (en) | Monitoring device, reliability calculation program, and reliability calculation method | |
US11232327B2 (en) | Smart video surveillance system using a neural network engine | |
US9292939B2 (en) | Information processing system, information processing method and program | |
JPWO2018180588A1 (ja) | 顔画像照合システムおよび顔画像検索システム | |
US20150186426A1 (en) | Searching information using smart glasses | |
WO2014208025A1 (ja) | 感度調整装置、感度調整方法および記憶媒体、並びに監視システム | |
US20190051287A1 (en) | Information providing device and information providing system | |
RU2714389C1 (ru) | Система спасения и способ спасения, и сервер, используемый для системы спасения и способа спасения | |
EP3369077B1 (en) | System, method and computer program product for location-based passive payments | |
JP2022008672A (ja) | 情報処理装置、情報処理方法、及びプログラム | |
KR102260123B1 (ko) | 지역내 이벤트감지장치 및 그 장치의 구동방법 | |
Weng et al. | Real-time bus travel speed estimation model based on bus GPS data | |
CN111814510A (zh) | 一种遗留物主体检测方法及装置 | |
JP2004328622A (ja) | 行動パターン識別装置 | |
EP4381472A1 (en) | System and method for audio tagging of an object of interest | |
JP2006048443A (ja) | 物品管理システムおよび物品管理装置 | |
CN113129334A (zh) | 物体追踪方法、装置、存储介质及可穿戴电子设备 | |
JP4601587B2 (ja) | 地図情報表示装置及びその方法 | |
Hardjono et al. | Virtual Detection Zone in smart phone, with CCTV, and Twitter as part of an Integrated ITS | |
JP2018129585A (ja) | 監視システムおよび監視方法 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 14818492 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 14898543 Country of ref document: US |
|
ENP | Entry into the national phase |
Ref document number: 2015523845 Country of ref document: JP Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 14818492 Country of ref document: EP Kind code of ref document: A1 |