Monitoring device, monitoring system, monitoring method and program

Abstract

A monitoring device (101) includes an acquisition unit (102) and a processing unit (103). The acquisition unit (102) acquires appearance information about the appearance of a mobile object included in images captured by a plurality of image capturing devices (152) installed in the whole town. The processing unit (103) performs statistical processing using the appearance information.

Description

Technical Field

[0003] ,

[0007] , , ,

[0005] , , ,

[0004] , , ,

[0006] ,

[0001] The present invention relates to a monitoring device, a monitoring system, a monitoring method, and program relates to.

Background Art

[0002] Patent Document 1 discloses a passing vehicle monitoring system including a plurality of monitoring cameras connected in a daisy chain and imaging the passing status of vehicles, and a center device connected to the plurality of monitoring cameras. Each monitoring camera includes a plurality of imaging units, at least one spotlight, an irradiation position changing unit, a distance image generation unit, a stationary object detection processing unit, a light lighting processing unit, and a light control unit.

[0003] The irradiation position changing unit changes the irradiation position of the spotlight. The distance image generation unit generates distance image data from a plurality of images obtained by the plurality of imaging units. The stationary object detection processing unit detects stationary objects based on the distance image.

[0004] When the stationary object detection processing unit detects a stationary object, the light lighting processing unit detects the position of the stationary object based on the distance image and outputs a light lighting signal for irradiating the stationary object with the light of the spotlight.

[0005] Based on the light lighting signal, the light control unit controls the irradiation position changing unit to change the irradiation position of the spotlight to the position of the stationary object, and also controls the spotlight to be lit.

[0006] Patent Document 2 discloses a monitoring system that detects the movement of a person photographed by a camera, determines "walking while doing something else", and effectively gives a warning. In Patent Document 2, "walking while doing something else" refers to the act of walking in a state of inattention ahead while looking at a mobile phone, an electronic terminal (including a smartphone), or a book.

[0007] Furthermore, Patent Document 3 describes a technique for calculating the feature quantities of each of several key points of a human body contained in an image, and for searching for images containing human bodies with similar postures or movements based on the calculated feature quantities, or for classifying images that are similar in posture or movement together. Non-Patent Document 1 also describes a technique related to estimating the skeleton of a person. [Prior art documents] [Patent Documents]

[0008] [Patent Document 1] Japanese Patent Publication No. 2012-103921 [Patent Document 2] International Publication No. 2018 / 061616 [Patent Document 3] International Publication No. 2021 / 084677 [Non-patent literature]

[0009] [Non-Patent Document 1] Zhe Cao, Tomas Simon, Shih-En Wei, Yaser Sheikh, [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields];, The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, P. 7291-7299 [Overview of the Initiative] [Problems that the invention aims to solve]

[0010] Even if the technologies described in Patent Documents 1 and 2 can detect stationary objects or actions such as walking while distracted by looking at a mobile phone, it is difficult to improve safety in urban areas from a broader perspective.

[0011] One example of the object of the present invention is to provide a monitoring device, monitoring system, monitoring method, and recording medium that address the above-mentioned problems and aim to improve safety in urban areas. [Means for solving the problem]

[0012] According to one aspect of the present invention, Photography An acquisition means for acquiring appearance information regarding the appearance of a moving object included in an image captured by a shadow device, A processing means that performs statistical processing using the aforementioned appearance information, The system acquires dispatch information from at least one middle device used by a designated organization when the organization is dispatched, generates update information to update event information related to a pre-set event based on the acquired dispatch information, and sends it to a terminal that detects a moving object corresponding to the event based on the results of analyzing the event information and the image. The update information generated above It includes means for transmitting event updates. A monitoring device will be provided.

[0013] According to one aspect of the present invention, Photography A monitoring device comprising an acquisition means for acquiring appearance information relating to the appearance of a moving object included in an image captured by a shadow device, and a processing means for performing statistical processing using the appearance information, The aforementioned multiple imaging devices, At least one terminal connected to the aforementioned plurality of imaging devices, It comprises at least one middleware device used in a designated institution, The aforementioned terminal is The aforementioned appearance information is transmitted to the monitoring device. Based on event information relating to a pre-set event and the results of analyzing the image, a moving object corresponding to the event is detected, and detection information relating to the detected moving object is transmitted to the middle device. The aforementioned monitoring device is When the engine is activated, obtain activation information regarding the activation, and send to the terminal update information for updating the event information based on the obtained activation information The update information generated above The monitoring system further includes an event update unit for transmitting A monitoring system is provided.

[0014] According to one aspect of the present invention, a computer Photography obtains appearance information regarding a moving object included in an image captured by an imaging device, performs statistical processing using the appearance information, obtains activation information regarding activation when the activation occurs from at least one middle device used in a predetermined institution, generates update information for updating event information regarding a preset event based on the obtained activation information, and transmits to a terminal that detects a moving object corresponding to the event based on the event information and a result of analyzing the image The update information generated above A monitoring method is provided.

[0015] According to one aspect of the present invention, a program causes a computer Photography to obtain appearance information regarding a moving object included in an image captured by an imaging device, perform statistical processing using the appearance information, obtain activation information regarding activation when the activation occurs from at least one middle device used in a predetermined institution, generate update information for updating event information regarding a preset event based on the obtained activation information, The update information generated above and transmit to a terminal that detects a moving object corresponding to the event based on the event information and a result of analyzing the image The update information generated above A program is provided.

Advantages of the Invention

[0016] According to this invention, it becomes possible to support the improvement of safety in urban areas. [Brief explanation of the drawing]

[0017] [Figure 1] This diagram shows an overview of the monitoring system according to Embodiment 1. [Figure 2] This is a flowchart outlining the monitoring process according to Embodiment 1. [Figure 3] This figure shows a detailed example of the monitoring system according to Embodiment 1. [Figure 4] This figure shows an example of the configuration of the external information according to Embodiment 1. [Figure 5] This figure shows an example of the functional configuration of the processing unit according to Embodiment 1. [Figure 6] This figure shows an example of event information related to Embodiment 1. [Figure 7] This figure shows an example of the physical configuration of the monitoring device according to Embodiment 1. [Figure 8] This flowchart shows an example of terminal processing according to Embodiment 1. [Figure 9] This flowchart shows an example of the monitoring process according to Embodiment 1. [Figure 10] This flowchart shows a detailed example of the acquisition process according to Embodiment 1. [Figure 11] This flowchart shows a detailed example of the first process according to Embodiment 1. [Figure 12] This figure shows an example of detection information. [Figure 13] This figure shows an example configuration of the monitoring system according to Embodiment 2. [Figure 14] This figure shows an example of the functional configuration of a terminal according to Embodiment 2. [Figure 15] This figure shows an example of the configuration of the appearance information according to Embodiment 2, where (a) shows an example of the first information and (b) shows an example of the second information. [Figure 16] This figure shows an example of the functional configuration of the processing unit according to Embodiment 2. [Figure 17]This flowchart shows an example of terminal processing according to Embodiment 2. [Figure 18] This flowchart shows a detailed example of the detection process according to Embodiment 2. [Figure 19] This flowchart shows an example of the monitoring process according to Embodiment 2. [Figure 20] This flowchart shows a detailed example of the first process according to Embodiment 2. [Figure 21] This figure shows an example configuration of the monitoring system according to Embodiment 3. [Figure 22] This figure shows an example of the functional configuration of the processing unit according to Embodiment 3. [Figure 23] This flowchart shows an example of the event update process according to Embodiment 3. [Modes for carrying out the invention]

[0018] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. In all drawings, similar components are denoted by the same reference numerals, and their descriptions are omitted as appropriate.

[0019] <Embodiment 1> Figure 1 is a diagram showing an overview of the monitoring system 100 according to Embodiment 1. The monitoring system 100 comprises a monitoring device 101, a plurality of imaging devices 152, and at least one terminal 153 connected to the plurality of imaging devices 152.

[0020] The monitoring device 101 comprises an acquisition unit 102 and a processing unit 103. The acquisition unit 102 acquires appearance information regarding the appearance of moving objects included in images captured by multiple camera devices 152 installed in the city. The processing unit 103 performs statistical processing using the appearance information.

[0021] Terminal 153 transmits external information to the monitoring device.

[0022] This monitoring system 100 will help improve safety in urban areas. This monitoring device 101 will help improve safety in urban areas.

[0023] Figure 2 is a flowchart showing an overview of the monitoring process according to Embodiment 1.

[0024] The acquisition unit 102 acquires appearance information regarding the appearance of moving objects included in images captured by multiple imaging devices 152 installed in the city (step S101). The processing unit 103 performs statistical processing using the appearance information (step S102g).

[0025] This monitoring process will help improve safety in urban areas.

[0026] The following describes a detailed example of the monitoring system 100 according to Embodiment 1.

[0027] Figure 3 shows a detailed example of the monitoring system 100 according to Embodiment 1. The monitoring system 100 is a system for monitoring a city. The monitoring system 100 comprises a monitoring device 101 and four terminal systems 151a to 151d.

[0028] The monitoring device 101 and each of the terminal systems 151a to 151d are connected via network N, and they send and receive information from each other via network N. Network N is a communication network constructed using wired, wireless, or a combination thereof.

[0029] (Example configuration of terminal system 151) Each of the terminal systems 151a to 151d is a system for taking pictures of the city and transmitting visual information regarding the appearance of moving objects included in the captured images to the monitoring device 101. Each of the terminal systems 151a to 151d includes multiple imaging devices 152a to 152d and terminals 153a to 153d.

[0030] Each terminal system 151a to 151d may have a different number of imaging devices 152a to 152d, provided that each terminal system includes at least one imaging device 152a to 152d. When terminal systems 151a to 151d are not distinguished, each is also referred to as terminal system 151.

[0031] Multiple imaging devices 152a to 152d are devices for photographing the city. For example, each of imaging devices 152a to 152d is a camera installed in the city. Each of imaging devices 152a to 152d generates image information including the captured image.

[0032] In Figure 3, multiple imaging devices 152a to 152d are arranged to photograph roads within appropriately defined monitoring areas Pa to Pd. Specifically, for example, each imaging area of ​​imaging device 152a is a predetermined area within monitoring area Pa, and at least a portion of each area is different from the others. The same applies to imaging devices 152b to 152d.

[0033] Each of these imaging devices 152a to 152d is an example of the imaging device 152 described above and may be configured similarly. When imaging devices 152a to 152d are not distinguished, each will also be referred to as imaging device 152.

[0034] Furthermore, if monitoring areas Pa to Pd are not distinguished, each will also be referred to as monitoring area P. Note that the multiple imaging devices 152 may not only photograph roads, but also various facilities, structures, buildings, etc.

[0035] Each of the terminals 153a to 153d acquires image information, including images captured by each of the multiple imaging devices 152a to 152d included in the common terminal system 151a to 151d, via a communication line. This communication line may be part of network N or a separate line from network N. Each of the terminals 153a to 153d generates appearance information based on the acquired image information and transmits it to the monitoring device 101 via network N.

[0036] The appearance information is information about the appearance of a moving object included in the images captured by the multiple imaging devices 152. The moving object is an object moving within the monitoring area P and includes at least one of a person or a vehicle. In this embodiment, an example in which the moving object is a person and a vehicle will be used for explanation.

[0037] The appearance of the moving object is included in the images captured by the multiple imaging devices 152. Therefore, as an example of appearance information, information including images captured by the multiple imaging devices 152 can be given. In this embodiment, an example in which appearance information includes images captured by the multiple imaging devices 152 will be used for explanation.

[0038] Figure 4 shows an example of the configuration of the appearance information according to this embodiment. The appearance information shown in the figure associates the image, the time of capture, the device ID (Identifier), and the location of capture.

[0039] The images included in the appearance information are images taken by the imaging device 152. The capture time is the time when the associated image was taken. The device ID is information for identifying the imaging device 152 that took the associated image. The device ID is, for example, the address of the imaging device 152 in the terminal system 151. The capture location indicates the location where the associated image was taken. The capture location is, for example, the address of the area (capture area) that the imaging device 152 captures, and is pre-set in association with the imaging device 152 for each of the terminals 153a to 153d.

[0040] Each of the terminals 153a to 153d acquires image information from multiple imaging devices 152a to 152d, associates the image contained in the image information with the time the image information was acquired and the device ID of the imaging device 152. As a result, each of the terminals 153a to 153d generates appearance information in the configuration illustrated in Figure 4. Each of the terminals 153a to 153d transmits the generated appearance information to the monitoring device 101.

[0041] Each of these terminals 153a to 153d is an example of terminal 153 described above and may be configured similarly. When terminals 153a to 153d are not distinguished, each will also be referred to as terminal 153.

[0042] Furthermore, one of the multiple imaging devices 152 included in the common terminal system 151 may also function as a terminal 153. Alternatively, each of the multiple imaging devices 152 may also function as a terminal 153.

[0043] (Example configuration of monitoring device 101) As shown in Figure 3, the monitoring device 101 is a device for monitoring the city. Functionally, the monitoring device 101 includes an acquisition unit 102, a processing unit 103, a history storage unit 104, an input reception unit 105, and a display unit 106. The history storage unit 104 is a storage unit for storing the history of appearance information. The input reception unit 105 receives input from the user. The display unit 106 displays various types of information.

[0044] The acquisition unit 102 acquires appearance information relating to the appearance of the mobile object from the terminal 153 via the network N. The acquisition unit 102 stores the acquired appearance information in the history storage unit 104.

[0045] As described above, the processing unit 103 performs statistical processing using the appearance information. For example, the processing unit 103 performs statistical processing based on at least one of the following: the attribute of the location where the image was taken, the time of day when the image was taken, and the attribute of the moving object included in the image.

[0046] The processing unit 103 according to this embodiment analyzes the image included in the appearance information to obtain at least one of the appearance features and attributes of the moving object, and performs statistical processing using at least one of the appearance features and attributes of the moving object.

[0047] The processing unit 103 according to this embodiment detects a moving object corresponding to a preset event based on the results of analyzing the image included in the appearance information. Then, the processing unit 103 further performs statistical processing using the detection results of the moving object corresponding to the preset event.

[0048] The details of the functions of this processing unit 103 will be explained below.

[0049] Figure 5 shows an example of the functional configuration of the processing unit 103 according to this embodiment. The processing unit 103 includes an image analysis unit 111, an event storage unit 112, an event detection unit 113, a statistical processing unit 114, and a notification unit 115.

[0050] The image analysis unit 111 analyzes the images captured by the imaging device 152 to determine the external features and attributes of the moving object.

[0051] The image analysis unit 111 then stores the obtained appearance features and attributes of the moving object in the history storage unit 104. At this time, the image analysis unit 111 stores the appearance features and attributes of the moving object in the history storage unit 104 in association with the image from which they were obtained. Alternatively, the image analysis unit 111 may obtain either the appearance features or attributes of the moving object by analyzing the image captured by the imaging device 152.

[0052] (Visual features of a moving object) Appearance features of a moving object are features related to the appearance of the moving object. Appearance features of a moving object are features obtained from an image that includes the moving object.

[0053] The appearance features of a moving object include, for example, features relating to at least one of the object's appearance attributes, its orientation, and its motion.

[0054] Features relating to the appearance attributes of the moving object include, for example, at least one of the appearance attribute features described later, the color and size of the vehicle. Features relating to the attitude of the moving object include, for example, at least one of the attitude features described later, the orientation of the vehicle. Features relating to the movement of the moving object include, for example, at least one of the motion features described later, the movement path of the moving object, the movement speed of the moving object.

[0055] (Attributes of the moving object) If the moving object is a person, its attributes include at least one of the following: age group, gender, person requiring assistance, person walking while distracted, police officer, person alone or acting alone.

[0056] A person requiring assistance is someone who needs help, such as a person in a wheelchair or a person using a cane. The image analysis unit 111 detects persons requiring assistance, for example, by detecting a person in a wheelchair or a person using a cane.

[0057] A person who is walking while distracted is defined as someone who is walking while operating or viewing a mobile device, smartphone, etc., or someone who is walking while smoking a cigarette. The image analysis unit 111 detects a person who is walking while distracted by detecting a person who is walking while holding a mobile device, smartphone, cigarette, etc. When the image analysis unit 111 detects a person who is walking while operating or viewing a mobile device, smartphone, etc., it may further use the fact that the person's face is looking downwards to detect a person who is walking while distracted.

[0058] If the moving object is a vehicle, its attributes include at least one of the following: private car, taxi, truck, emergency vehicle (police car, ambulance, fire truck, etc.), motorcycle, bicycle, etc. The vehicle attributes may also include the type of vehicle. The image analysis unit 111 can determine the vehicle attributes based on, for example, the shape, color, size, etc.

[0059] (Analysis function) The image analysis unit 111 is equipped with an image analysis function to acquire the external features and attributes of a moving object. The image analysis function is a function that analyzes images.

[0060] The analysis functions provided by the image analysis unit 111 include, for example, one or more of the following: (1) object detection function, (2) face analysis function, (3) human figure analysis function, (4) posture analysis function, (5) behavior analysis function, (6) appearance attribute analysis function, (7) gradient feature analysis function, (8) color feature analysis function, and (9) movement path analysis function.

[0061] (1) The object detection function detects objects from an image. The object detection function can also determine the position, size, etc., of objects within an image. One example of a model applied to object detection processing is YOLO (You Only Look Once). Objects include people and things. The object detection function can detect, for example, moving objects, objects left on the street, wheelchairs, canes (including crutches and white canes), mobile devices, smartphones, cigarettes, etc. Also, for example, the object detection function can determine the position of moving objects, objects left on the street, wheelchairs, etc.

[0062] (2) The face analysis function detects human faces from images, extracts the features of the detected faces, and classifies the detected faces. The face analysis function can also determine the position of a face within an image. The face analysis function can also determine the identity of people detected from different images based on the similarity between the facial features of people detected from different images.

[0063] (3) The human figure analysis function extracts human physical characteristics of people contained in an image (for example, values ​​indicating overall characteristics such as body shape, height, and clothing), and classifies (categorizes) the people contained in the image. The human figure analysis function can also identify the position of a person within an image. The human figure analysis function can also determine the identity of people contained in different images based on the human physical characteristics of people contained in those different images.

[0064] (4) The posture analysis function detects the joint points of a person from an image and creates a stick-figure model by connecting the joint points. The posture analysis function then uses the information from the stick-figure model to estimate the person's posture, extracts the estimated posture features (posture features), and classifies the people in the image. The posture analysis function can also determine the identity of people in different images based on the posture features of people in different images.

[0065] For example, the posture analysis function estimates postures such as standing, squatting, and crouching from an image and extracts posture features that represent each posture. Alternatively, the posture analysis function can estimate the posture of an object detected using an object detection function from an image and extract posture features that represent that posture.

[0066] For example, the techniques disclosed in Patent Document 3 and Non-Patent Document 1 can be applied to the posture analysis function.

[0067] (5) The behavioral analysis process can estimate human movement using information from a stick figure model, changes in posture, etc., extract characteristic features of human movement (motion features), and classify people included in an image. The behavioral analysis process can also estimate a person's height or identify a person's position in an image using information from a stick figure model. For example, the behavioral analysis process can estimate actions such as changes or transitions in posture or movement (changes or transitions in position) from an image and extract motion features of those actions.

[0068] (6) The appearance attribute analysis function can recognize appearance attributes associated with a person. The appearance attribute analysis function extracts features related to the recognized appearance attributes (appearance attribute features) and classifies (categorizes) people included in the image. Appearance attributes are attributes of appearance and include one or more, for example, the color of clothing, the color of shoes, hairstyle, wearing or not wearing a hat or tie, glasses, etc. Appearance attributes may also include, for example, a police officer's uniform.

[0069] (7) The gradient feature analysis function extracts gradient features (gradient features) from an image. Techniques such as SIFT, SURF, RIFF, ORB, BRISK, CARD, and HOG can be applied to the gradient feature detection process.

[0070] (8) The color feature analysis function can detect objects from an image, extract color features from the detected objects, and classify the detected objects. Color features include, for example, a color histogram.

[0071] (9) The motion analysis function can determine the motion path (trajectory of movement) of moving objects contained in an image, for example, by using the results of identity determination or classification in any of the analysis functions (2) to (8) described above. More specifically, for example, the motion path of a moving object can be determined by connecting moving objects that have been determined to be the same across images that are different in time series. The motion analysis function can also determine motion paths that span across multiple images taken from different shooting areas, for example, when video footage has been acquired from multiple shooting devices 152 that are shooting from different shooting areas.

[0072] The analysis functions provided by the image analysis unit 111 are preferably configured to allow each other to use the analysis results. The image analysis unit 111 may also be equipped with a function (analysis function) that uses the above-mentioned analysis functions to analyze an image and determine age group, gender, speed of movement of people, posture (direction) of vehicles, speed of movement of vehicles, etc.

[0073] The analysis function described here is just one example of a method for determining the external features and attributes of a moving object, and the method for determining the external features and attributes of a moving object is not limited to this.

[0074] The event storage unit 112 is a storage unit for storing event information related to events that are set in advance.

[0075] (Example of event information) Figure 6 shows an example of event information according to this embodiment. The event information associates an event, detection conditions, a notification event flag, and a notification destination. The detection conditions are the conditions for detecting the associated event from the image.

[0076] An event is predefined in relation to, for example, the posture, movement, or at least one of the attributes of a moving object. Movement may include at least one of the following: position, speed, trajectory, etc., and may also include being stationary. Specific examples of events, as shown in Figure 6, include falling, feeling unwell, abandoned objects, traffic accidents, traffic jams, driving the wrong way, speeding, needing assistance, incidents / suspicious persons, getting lost, walking alone at night, etc.

[0077] For example, a fall is associated with the detection condition that a person is lying down or has fallen. For example, poor health is associated with the detection condition that a person is crouching for a specified period of time or longer. Such falls and poor health are examples of events related to a person's posture, movement, etc.

[0078] For example, if there are objects left on the street, people, vehicles, and other moving objects may change their direction of movement to avoid them. Therefore, the detection condition for abandoned objects is associated with a predetermined number of moving objects changing their direction of movement in a direction different from the predicted position. The predicted position is the position obtained by extrapolating the previous movement path in the direction of travel with a straight or curved line. Such abandoned objects are examples of events related to the movement (movement path) of moving objects. Note that the detection condition for abandoned objects may also be that an object has been on the street for a predetermined amount of time or longer.

[0079] For example, traffic accidents are associated with detection conditions such as contact between vehicles or between a vehicle and a person. Contact can be detected based on one or more factors, such as a sudden change in position or orientation. Such traffic accidents are examples of events related to the movement and orientation of moving objects.

[0080] For example, traffic congestion is associated with the detection conditions that the driving speed is below a predetermined value and that general vehicles are lined up in the direction of travel for a predetermined length or longer. General vehicles are, for example, vehicles other than taxis, trucks, emergency vehicles, motorcycles, and bicycles. For example, driving against traffic is associated with the detection conditions that a vehicle is traveling in a direction different from the direction of travel on the road. For example, speeding is associated with the detection conditions that a vehicle's speed exceeds the legal speed limit on the road. Traffic congestion, driving against traffic, and speeding are examples of events related to the movement and attributes of vehicles.

[0081] For example, "assistance required" indicates an event where assistance is needed. As can be seen by referring to the detection conditions in Figure 6, "assistance required" is associated with conditions for detecting a person in need of assistance. "Assistance required" is an example of an event related to a person's attributes. Note that the detection conditions for "assistance required" may be, for example, a person in a wheelchair heading towards a step or stairs.

[0082] For example, areas where police officers are present or patrol cars are parked may be near where an incident has occurred or where a suspicious person is present. Furthermore, suspicious individuals may move within a certain range for a specified period of time. Therefore, detection conditions such as the presence of police officers, the presence of parked patrol cars, or movement within a certain range for a specified period of time are associated with incidents and suspicious individuals. Such incidents and suspicious individuals are examples of events related to human attributes (e.g., police officers).

[0083] For example, a lost child is associated with the detection condition that a child under a certain age is alone for a specified period of time or longer. The specified age is, for example, 10 years old. Such lost child detection is an example of an event related to a person's attributes (age group, being alone, etc.).

[0084] For example, walking alone at night is associated with the detection condition that the person is alone during a specific time period. This specific time period is, for example, from 11 PM to 4 AM. Such walking alone at night is an example of an event related to a person's movement, attributes (being alone), etc.

[0085] The notification event flag is an example of notification event information that indicates whether or not the associated event is a notification event. A notification event flag of "1" indicates that the associated event is a notification event. A notification event flag of "0" indicates that the associated event is not a notification event.

[0086] A notification event is an event that, when detected, triggers notification to a designated recipient. Notification events can be predetermined from a selection of events; for example, they may be events that require prompt action.

[0087] The recipient of the notification is associated with the event being reported. The recipient of the notification is an organization or other entity that reports on the associated event.

[0088] When the reported event is a fall, abandoned object, traffic accident, driving the wrong way, incident / suspicious person, or lost child, the police are generally the ones who will handle these events. Therefore, in the example of the reported information shown in Figure 6, the recipient of these reports is the police. Also, when the reported event is illness or need for assistance, the facility staff, such as station staff, are generally the ones who will handle these events. Therefore, in the example of the reported information shown in Figure 6, the recipient of these reports is the facility.

[0089] Refer to Figure 5 again. The event detection unit 113 detects moving objects from among the moving objects contained in the image that correspond to a pre-set event, based on the results of the image analysis unit 111's analysis of the image and the event information.

[0090] The results of the image analysis performed by the image analysis unit 111 are the results of analysis using the analysis functions of the image analysis unit 111. Specifically, for example, the results of the image analysis performed by the image analysis unit 111 include at least one of the external features and attributes of the moving object.

[0091] The event detection unit 113 generates detection information when it detects a moving object that corresponds to a pre-set event. The detection information is information indicating the detection result of a moving object that corresponds to a pre-set event. The event detection unit 113 stores the generated detection information in the history storage unit 104.

[0092] The statistical processing unit 114 performs statistical processing using at least one of the results of the image analysis unit 111's analysis of the image and the moving objects detected by the event detection unit 113. The statistical processing unit 114 performs statistical processing based on at least one of the attributes of the location where the image was taken, the time period when the image was taken, and the attributes of the vehicles included in the image. The statistical processing unit 114 displays the results of the statistical processing on the display unit 106.

[0093] (Examples of place affiliations) The attributes of a place include at least one of the characteristics of a place related to the passage of a moving object, such as a region.

[0094] The characteristics of a place related to vehicle traffic include at least one of the following: an intersection, an intersection with a predetermined number of intersecting roads or lanes, a curve, or a road with a straight section of a predetermined length or longer. The characteristics of a place related to pedestrian traffic include at least one of the following: a step or stairs.

[0095] Areas may be indicated using facilities such as train stations, bus stops, entertainment facilities, parks, sports centers, convenience stores, supermarkets, shops, and parking lots. Areas may also be indicated using addresses such as Chiyoda-ku, Tokyo, or Kasumigaseki 1-chome, Chiyoda-ku, Tokyo.

[0096] When the notification unit 115 detects a moving object corresponding to a notification event, it notifies a predetermined notification destination associated with the notification event that the notification event has been detected.

[0097] In detail, for example, when a moving object corresponding to a notification event is detected, the notification unit 115 identifies a notification destination associated with the notification event based on the event information. The notification unit 115 transmits the detection information to a device (not shown) installed at the identified notification destination.

[0098] The device installed at the specified notification destination is, for example, the device installed at the notification destination closest to the notification event. The notification unit 115 may pre-store information associating the location and device (address in network N) of the notification destination, or it may obtain the device (address in network N) of the notification destination from an external device (not shown) via network N.

[0099] Up to this point, the functional configuration of the monitoring system 100 according to Embodiment 1 has been mainly described. From here, the physical configuration of the monitoring system 100 according to this embodiment will be described.

[0100] (Physical configuration of monitoring system 100) The monitoring system 100 consists of a monitoring device 101 and at least one terminal system 151, which are physically connected via a network N. The terminal system 151 consists of a plurality of imaging devices 152 and terminals 153, which are physically connected via a communication line. Each of the monitoring device 101, the plurality of imaging devices 152, and the terminal 153 consists of a single, physically distinct device.

[0101] Furthermore, one of the multiple imaging devices 152 may be physically integrated with the terminal 153. Either or both of the monitoring device 101 and the terminal 153 may be composed of multiple devices physically connected via an appropriate communication line such as a network N.

[0102] The monitoring device 101 is, physically, for example, a general-purpose computer. Figure 7 shows an example of the physical configuration of the monitoring device 101 according to Embodiment 1.

[0103] The monitoring device 101 includes, for example, a bus 1010, a processor 1020, a memory 1030, a storage device 1040, a network interface 1050, an input interface 1060, and an output interface 1070.

[0104] Bus 1010 is a data transmission path for the processor 1020, memory 1030, storage device 1040, network interface 1050, input interface 1060, and output interface 1070 to send and receive data to and from each other. However, the method of connecting the processor 1020 and other components to each other is not limited to bus connection.

[0105] The 1020 processor is a processor implemented in components such as the CPU (Central Processing Unit) and GPU (Graphics Processing Unit).

[0106] Memory 1030 is a main memory device implemented using RAM (Random Access Memory), etc.

[0107] The storage device 1040 is an auxiliary storage device implemented as an HDD (Hard Disk Drive), SSD (Solid State Drive), memory card, or ROM (Read Only Memory). The storage device 1040 stores program modules for realizing the functions of the monitoring device 101. The processor 1020 loads each of these program modules into memory 1030 and executes them, thereby realizing the functions corresponding to those program modules.

[0108] The network interface 1050 is an interface for connecting the monitoring device 101 to the network N.

[0109] The input interface 1060 is an interface for the user to input information. The input interface 1060 consists of, for example, a touch panel, a keyboard, a mouse, and so on.

[0110] The output interface 1070 is an interface for presenting information to the user. The output interface 1070 is composed of, for example, a liquid crystal panel, an organic EL (Electro-Luminescence) panel, etc.

[0111] The terminal 153 physically has, for example, a bus 1010, a processor 1020, memory 1030, a storage device 1040, and a network interface 1050, similar to those of the monitoring system 100.

[0112] The storage device 1040 of terminal 153 stores program modules for realizing the functions of terminal 153. The network interface 1050 of terminal 153 is an interface for connecting terminal 153 to network N. Aside from these points, terminal 153 may be physically configured in the same way as the monitoring system 100.

[0113] So far, the physical configuration of the monitoring system 100 according to Embodiment 1 has been mainly described. From here, the operation of the terminal system 151 according to this embodiment will be described.

[0114] Figure 8 is a flowchart showing an example of terminal processing according to Embodiment 1. Terminal processing is a process performed by the terminal system 151 to capture a monitoring area P and transmit appearance information regarding the appearance of a moving object included in the captured image. The terminal system 151 repeatedly performs terminal processing, for example, while in operation.

[0115] Each of the imaging devices 152 captures an image of the area to be photographed and generates image information including the captured image (step S151). Each of the imaging devices 152 transmits the image information generated in step S151 to the terminal 153 (step S152).

[0116] Terminal 153 acquires the image information transmitted in step S152 (step S153). Terminal 153 generates appearance information based on the image information acquired in step S153 (step S154). Terminal 153 transmits the appearance information generated in step S154 to the monitoring device 101 (step S155).

[0117] By performing this terminal processing, the terminal system 151 can generate appearance information regarding the appearance of the mobile object and transmit it to the monitoring device 101 in near real time.

[0118] In step S155, terminal 153 may generate appearance information for all image information generated by each of the imaging devices 152 and transmit it to monitoring device 101.

[0119] Furthermore, in step S155, terminal 153 may generate appearance information from, for example, image information at predetermined time intervals from all the image information generated by each of the imaging devices 152, and transmit it to the monitoring device 101. In this way, by decimating a portion of the image information generated by each of the imaging devices 152 and generating and transmitting appearance information, the amount of data transmitted to the monitoring device 101 can be reduced. This makes it possible to reduce the communication load on the network N.

[0120] Figure 9 is a flowchart showing an example of the monitoring process according to Embodiment 1. The monitoring process is performed by the monitoring device 101 to monitor the city. The monitoring device 101 repeatedly performs the monitoring process, for example, while in operation.

[0121] The acquisition unit 102 acquires appearance information regarding the appearance of a moving object included in images captured by multiple imaging devices 152, as described above with reference to Figure 2 (step S101). The processing unit 103 performs a first process, including statistical processing using the appearance information described above (step S102g), as described above with reference to Figure 2 (step S102).

[0122] Steps S101 and S102 will be explained in detail with reference to the diagram.

[0123] Figure 10 is a flowchart showing a detailed example of the acquisition process (step S101) according to Embodiment 1.

[0124] The acquisition unit 102 acquires appearance information relating to the appearance of the mobile object from the terminal 153 (step S101a). The acquisition unit 102 stores the appearance information acquired in step S101a in the history storage unit 104 (step S101b), and returns to the monitoring process (see Figure 2).

[0125] Figure 11 is a flowchart showing a detailed example of the first process (step S102) according to Embodiment 1.

[0126] The image analysis unit 111 analyzes the image acquired in step S101a to determine the appearance features of the moving object (step S102a). The image analysis unit 111 analyzes the image acquired in step S101a to determine the attributes of the moving object (step S102b). The image analysis unit 111 stores the appearance features and attributes of the moving object obtained in steps S102a and S102b in the history storage unit 104, associating them with the corresponding images.

[0127] The event detection unit 113 determines whether or not a moving object corresponding to a pre-set event has been detected among the moving objects included in the image acquired in step S101a (step S102c).

[0128] More specifically, for example, the event detection unit 113 detects a moving object that corresponds to a preset event based on the appearance features and attributes of the moving object obtained in steps S102a and S102b and the event information stored in the event storage unit 112. More specifically, for example, the event detection unit 113 detects a moving object that corresponds to a detection condition included in the event information based on the appearance features and attributes of the moving object.

[0129] If a moving object corresponding to the event is detected (step S102c; Yes), the event detection unit 113 generates detection information regarding the detected moving object (step S102d).

[0130] The event detection unit 113 generates detection information, including an image with a label indicating the event corresponding to the detected moving object. The event detection unit 113 stores the generated detection information in the history storage unit 104.

[0131] Figure 12 shows an example of detection information. This figure shows an example of an image included in the detection information when the event "fall" is detected. A person is lying on the sidewalk R2 next to the roadway R1, and this person is marked with a dotted rectangle frame. The label "fall" is also attached in association with this frame. Furthermore, information indicating the location and date and time of detection is attached. The location of detection is the place where the image was taken. The date and time of detection is the date and time the image was taken.

[0132] Refer to Figure 11 again. The notification unit 115 transmits detection information to the appropriate agency based on the notification information (step S102e).

[0133] For example, if the notification unit 115 detects a moving object that falls under categories such as "fallen," "lost," or "abandoned object," it transmits the detection information generated in step S102d to the police equipment, which is associated with the organization that falls under categories such as "fallen," "lost," or "abandoned object," for example, via the network N.

[0134] For example, if the notification unit 115 detects a moving object that falls under the category of "requiring assistance," it identifies the nearest railway or facility from the location where the "requiring assistance" was detected, among the railways or facilities associated with the "requiring assistance." The notification unit 115 transmits the detection information generated in step S102d to the device of the identified facility, for example, via the network N.

[0135] By providing this kind of information, it becomes possible to respond quickly to each incident. Therefore, it becomes possible to support improvements in safety in urban areas.

[0136] If no moving object corresponding to the event is detected (step S102c; No), or following step S102e, the statistical processing unit 114 determines whether or not there has been an instruction from the user for statistical processing (step S102f). The instruction from the user is received, for example, by the input receiving unit 105.

[0137] If the user does not instruct the statistical processing to proceed (step S102f; No), the statistical processing unit 114 terminates the first processing (step S102) and ends the monitoring process (see Figure 2).

[0138] If the user requests statistical processing (step S102f; Yes), the statistical processing unit 114 performs the statistical processing (step S102g) and terminates the monitoring process (see Figure 2).

[0139] In step S102g, the statistical processing unit 114 performs statistical processing using the appearance features and attributes of the moving objects obtained in steps S102a to S102b and the detection results of the moving objects corresponding to the event in step S102c. In other words, the statistical processing unit 114 performs statistical processing using the appearance features and attributes of the moving objects and the detection results of the moving objects corresponding to the event.

[0140] At this time, the statistical processing unit 114 may perform statistical processing using the appearance features and attributes of moving objects for an appropriate period from among the appearance features and attributes of moving objects in the present and past. Alternatively, the statistical processing unit 114 may perform statistical processing using the detection results of moving objects corresponding to present and past events for an appropriate period. The statistical processing unit 114 can obtain the appearance features and attributes of past moving objects and past detection results from the history storage unit 104.

[0141] In detail, for example, the statistical processing unit 114 performs statistical processing using the appearance features and attributes of moving objects and the moving objects corresponding to the events, based on the attributes of the location where the image was taken, the time of day when the image was taken, and the attributes of the vehicles included in the image. The statistical processing unit 114 displays the results of the statistical processing on the display unit 106.

[0142] Specifically, for example, the statistical processing unit 114 aggregates the number of times each event, such as "falls," "getting lost," "traffic jams," and "walking while distracted," for example, by location attribute, time of day, and displays an image showing the aggregated results on the display unit 106. By referring to this, it is possible to consider, for example, the causes of each event, measures to prevent each event from occurring, and measures to respond quickly to each event, based on the locations and time of day when each event, such as "falls," "getting lost," "traffic jams," and "walking while distracted," occurs frequently.

[0143] For example, if traffic congestion is frequent around a station due to an increase in temporarily stopped vehicles during a certain time in the evening, patrols during that time could be strengthened. For example, if there are many lost children near a certain facility on holidays, patrols at that facility on holidays could be strengthened. For example, if there are more than a certain number of people who need assistance to use a certain step or staircase, it could be considered to install a ramp or elevator there. For example, if there are many people walking while distracted at a certain time of day at a certain facility, measures such as broadcasting warnings during the times when people are most likely to walk while distracted could be considered.

[0144] Specifically, for example, the statistical processing unit 114 aggregates the traffic volume of vehicles, pedestrians, or both, by location attributes, time of day, vehicle type, etc., and displays an image showing the aggregated results on the display unit 106. By referring to these results together with the results of statistical processing related to "traffic congestion," "traffic accidents," etc., it is possible to consider the causes of traffic congestion or traffic accidents, and measures to prevent traffic congestion or traffic accidents, based on the location attributes and vehicle attributes of the time of day when traffic volume or traffic accidents are high.

[0145] Furthermore, specifically, for example, the statistical processing unit 114 aggregates the amount of pedestrian traffic at a particular intersection by age group and displays an image showing the aggregated results on the display unit 106. Since walking speeds differ among age groups, by referring to these aggregated results, measures can be taken to ensure safe passage through the intersection, such as appropriately setting the green light duration for pedestrians at that intersection.

[0146] As illustrated by the examples above, by considering countermeasures based on the results of statistical processing, it becomes possible to support improvements in urban safety.

[0147] Furthermore, specifically, for example, the statistical processing unit 114 aggregates data on clothing, clothing colors, etc., by location attributes, time of day, and age group, and displays an image showing the aggregated results on the display unit 106. By comparing this with, for example, similar aggregated results from the previous year, it is possible to understand the clothing trends of the year, seasonal changes, and changes in perceived temperature. This makes it possible to provide information on fashion trends, climate, and other related information.

[0148] (Effects / Actions) As described above, according to this embodiment, the monitoring device 101 comprises an acquisition unit 102 and a processing unit 103. The acquisition unit 102 acquires appearance information regarding the appearance of moving objects included in images captured by multiple imaging devices 152 installed in the city. The processing unit 103 performs statistical processing using the appearance information.

[0149] This allows for the implementation of safety measures in urban areas from a broad perspective, based on the results of statistical analysis. Therefore, it becomes possible to support improvements in urban safety.

[0150] According to this embodiment, the moving body includes at least one of a person and a vehicle.

[0151] This allows for the implementation of safety measures in urban areas related to at least one of people and vehicles, based on the results of statistical processing, from a broad perspective. Therefore, it becomes possible to support improvements in urban safety.

[0152] According to this embodiment, the appearance information includes an image. The processing unit 103 analyzes the image included in the appearance information to obtain appearance features of the moving object, and performs statistical processing using the obtained appearance features.

[0153] This allows for the implementation of safety measures in urban areas from a broad perspective, based on the results of statistical processing using visual features. Therefore, it becomes possible to support improvements in urban safety.

[0154] According to this embodiment, the processing unit 103 analyzes the image included in the appearance information to further determine the attributes of the moving object, and then performs statistical processing using the attributes of the moving object.

[0155] This allows for the implementation of safety measures in urban areas from a broader perspective, based on statistical processing results that further utilize the attributes of moving objects. Therefore, it becomes possible to support improvements in urban safety.

[0156] According to this embodiment, the appearance feature quantity includes a feature quantity relating to at least one of the appearance attributes, posture, and motion of the moving object.

[0157] This allows for the implementation of safety measures in urban areas from a broad perspective, based on the results of statistical processing using features related to at least one of the appearance attributes, posture, and movement of moving objects. Therefore, it becomes possible to support improvements in urban safety.

[0158] According to this embodiment, the characteristic quantities relating to the movement of the moving object include at least one of the movement path and the movement speed.

[0159] This allows for the implementation of safety measures in urban areas from a broad perspective, based on the results of statistical processing using features related to the movement of moving objects, including at least one of the movement path and movement speed. Therefore, it becomes possible to support improvements in urban safety.

[0160] According to this embodiment, the processing unit 103 performs statistical processing based on at least one of the attributes of the location where the image was taken, the time period when the image was taken, and the attributes of the moving object included in the image.

[0161] This allows for the implementation of safety measures in urban areas from a broad perspective, based on the results of statistical processing performed on the attributes of the location where the image was taken, the time of day the image was taken, and the attributes of the moving objects contained in the image. Therefore, it becomes possible to support improvements in urban safety.

[0162] According to this embodiment, the attributes of a place include at least one of the characteristics of the passage of a moving object and a region.

[0163] This allows for the implementation of safety measures in urban areas from a broad perspective, based on the characteristics of movement and the results of statistical processing performed on the attributes of locations, including at least one region. Therefore, it becomes possible to support improvements in urban safety.

[0164] According to this embodiment, the processing unit 103 detects a moving object that corresponds to a preset event based on the results of analyzing the image included in the appearance information.

[0165] This allows for statistical analysis of events, and based on the results of that analysis, measures for urban safety can be taken from a broad perspective. Furthermore, events can be detected and addressed quickly. Therefore, it becomes possible to support improvements in urban safety.

[0166] According to this embodiment, when the processing unit 103 detects a moving object that corresponds to a predetermined notification event from among the events, it notifies a predetermined notification destination associated with the notification event that the notification event has been detected.

[0167] This allows for a quicker response to detected notification events, thereby contributing to improved safety in urban areas.

[0168] According to this embodiment, the processing unit 103 further performs statistical processing using the detection results of moving objects corresponding to pre-set events.

[0169] This allows for the implementation of safety measures in urban areas from a broad perspective, based on the results of statistical analysis of events. Therefore, it becomes possible to support improvements in urban safety.

[0170] According to this embodiment, the event is related to at least one of the attitude, movement, or attribute of the moving object.

[0171] This allows for the implementation of safety measures in urban areas from a broad perspective, based on the results of statistical processing of events related to at least one of the attitude, movement, or attributes of moving objects. Alternatively, it enables the early detection of events related to at least one of the attitude, movement, or attributes of moving objects, and allows for responses to those events. Therefore, it becomes possible to support improvements in urban safety.

[0172] <Embodiment 2> Embodiment 1 describes an example in which the monitoring device 101 obtains the appearance features and attributes of a moving object, detects an event, and provides notification when a notification event is detected. The terminal 153 may perform some or all of the following: obtaining the appearance features of the moving object, obtaining the attributes of the moving object, detecting an event, and providing notification when a notification event is detected. In this embodiment, an example is described in which the terminal 153 performs all of the following: obtaining the appearance features of the moving object, obtaining the attributes of the moving object, detecting an event, and providing notification when a notification event is detected.

[0173] In this embodiment, in order to keep the explanation concise, we will mainly describe the differences from Embodiment 1, and redundant explanations will be omitted as appropriate.

[0174] Figure 13 shows an example configuration of the monitoring system 200 according to Embodiment 2. The monitoring system 200 comprises a monitoring device 201 and four terminal systems 251a to 251d, replacing the monitoring device 101 and four terminal systems 151a to 151d according to Embodiment 1.

[0175] (Example configuration of terminal system 251) Each terminal system 251a to 251d includes a plurality of imaging devices 152a to 152d similar to those in Embodiment 1, and terminals 253a to 253d that replace the terminals 153a to 153d according to Embodiment 1. When terminal systems 251a to 251d are not distinguished, each is also referred to as terminal system 251.

[0176] Each of the terminals 253a to 253d acquires image information, including images captured by each of the multiple imaging devices 152a to 152d included in the common terminal system 251a to 251d, via a communication line. Based on the acquired image information, each of the terminals 253a to 253d generates appearance information and transmits it to the monitoring device 201 via the network N.

[0177] Each of terminals 253a to 253d may be configured similarly. If terminals 253a to 253d are not distinguished, each will also be referred to as terminal 253.

[0178] Figure 14 shows an example of the functional configuration of terminal 253 according to this embodiment.

[0179] Terminal 253 includes an image acquisition unit 254, an image analysis unit 111, an event storage unit 112, an event detection unit 113, and a notification unit 115, similar to those in Embodiment 1, as well as an image acquisition unit 254, an event acquisition unit 255, and an information transmission unit 256.

[0180] The image acquisition unit 254 acquires image information from multiple imaging devices 152 included in the common terminal system 251, including images captured by each of the imaging devices 152a to 152d. The image acquisition unit 254 retains images for at least a predetermined time T1 (for example, 5 minutes). That is, it retains images captured at a predetermined time T1 prior to the present.

[0181] The image analysis unit 111 analyzes the image captured by the imaging device 152, similar to Embodiment 1, and determines the external features and attributes of the moving object, similar to Embodiment 1. In other words, in this embodiment, the image analysis unit 111 analyzes the image acquired by the image acquisition unit 254 and determines the external features and attributes of the moving object, similar to Embodiment 1.

[0182] The event acquisition unit 255 acquires event information from the monitoring device 201 via the network N and stores the acquired event information in the event storage unit 112.

[0183] In this embodiment, the event detection unit 113, similar to Embodiment 1, detects a moving object corresponding to a pre-set event from among the moving objects included in the image, based on the results of the image analysis unit 111's analysis of the image and the event information.

[0184] The information transmission unit 256 generates appearance information and transmits it to the monitoring device 201 via the network N. The information transmission unit 256 also transmits detection information generated by the event detection unit 113 to the monitoring device 201 via the network N.

[0185] In detail, the information transmission unit 256 generates and transmits first information, which is appearance information including the image captured by the imaging device 152. Furthermore, the information transmission unit 256 generates and transmits second information, which is appearance information that does not include the image captured by the imaging device 152.

[0186] The first information includes an image and at least one of the appearance features and attributes of a moving object obtained from that image. The second information includes at least one of the appearance features and attributes of a moving object obtained from a common image.

[0187] Figure 15 shows an example of the configuration of appearance information according to this embodiment. Figure 15(a) shows an example of the first information. Figure 15(b) shows an example of the second information.

[0188] The first piece of information associates the image with its visual features, attributes, time of capture, device ID (Identifier), and location of capture.

[0189] Each element associated in the first information is information about a common image captured by the imaging device 152. That is, the images included in the first information are images captured by the imaging device 152. The appearance features and attributes are appearance features and attributes obtained from the associated images. The capture time is the time when the associated image was captured. The device ID is information for identifying the imaging device 152 that captured the associated image. The capture location indicates the location where the associated image was captured.

[0190] The second set of information associates external features, attributes, time of capture, device ID (Identifier), and location of capture.

[0191] Each element associated in the second information is information about a common image captured by the imaging device 152. That is, the appearance features and attributes included in the second information are appearance features and attributes obtained from the common image. The capture time is the time when the common image was captured. The device ID is information for identifying the imaging device 152 that captured the common image. The capture location indicates the location where the common image was captured.

[0192] The information transmission unit 256 switches the first transmission rate between a high rate and a low rate depending on whether or not a moving object corresponding to the event has been detected.

[0193] The transmission rate is the number of times the information transmission unit 256 transmits information per unit time. The first transmission rate is the transmission rate of the first information, that is, the number of times the information transmission unit 256 transmits the first information per unit time. A high rate is a transmission rate that is higher than a low rate, that is, a transmission rate that transmits information more times per unit time.

[0194] The information transmission unit 256 normally transmits the first information at a low rate, and transmits the first information at a high rate when a moving object corresponding to the event is detected. More specifically, the information transmission unit 256 transmits the first information at a high rate during a predetermined time T1 before the detection of a moving object corresponding to the event and a predetermined time T2 after the detection of the moving object corresponding to the event. Except for the predetermined time periods T1 and T2 before and after the detection of a moving object corresponding to the event, the information transmission unit 256 transmits the first information at a low rate.

[0195] The information transmission unit 256 transmits the second information at the second transmission rate.

[0196] The second transmission rate is the transmission rate of the second information, that is, the number of times the information transmission unit 256 transmits the second information per unit time. The second transmission rate is a higher transmission rate than the low rate. In this embodiment, an example in which the second transmission rate is the same as the high rate will be described.

[0197] In this manner, the information transmission unit 256 normally transmits the second information at a high rate and the first information at a low rate. When a moving object corresponding to an event is detected, the information transmission unit 256 transmits the detection information generated by the event detection unit 113. For predetermined time periods T1 and T2 before and after the detection of the moving object corresponding to the event, the information transmission unit 256 transmits the first and second information at a high rate.

[0198] (Example configuration of monitoring device 201) As shown in Figure 13, the monitoring device 201 functionally includes an acquisition unit 202 and a processing unit 203 that replace the acquisition unit 102 and processing unit 103 according to Embodiment 1, as well as a history storage unit 104, an input reception unit 105, and a display unit 106 similar to those in Embodiment 1.

[0199] The acquisition unit 202 acquires information transmitted from the information transmission unit 256 from the terminal 253 via the network N and stores the acquired information in the history storage unit 104.

[0200] In detail, the acquisition unit 202 in this embodiment acquires appearance information (first information and second information) transmitted from the information transmission unit 256 and stores the acquired appearance information (first information and second information) in the history storage unit 104. The acquisition unit 202 also acquires detection information transmitted from the information transmission unit 256.

[0201] The processing unit 203 performs statistical processing using appearance information, similar to Embodiment 1. The processing unit 203 also performs statistical processing based on, for example, at least one of the attributes of the location where the image was taken, the time period when the image was taken, and the attributes of the moving objects included in the image.

[0202] The processing unit 203 according to this embodiment performs statistical processing using at least one of the appearance features and attributes of the moving object included in the appearance information. The processing unit 203 further performs statistical processing using the detection results of the moving object corresponding to the event.

[0203] The processing unit 203 performs statistical processing based on at least one of the attributes of the location where the image was taken, the time period when the image was taken, and the attributes of the moving objects included in the image.

[0204] When the processing unit 203 acquires event information, for example according to user input, it transmits the acquired event information to the terminal 253 via the network N.

[0205] Figure 16 shows an example of the functional configuration of the processing unit 103 according to this embodiment. The processing unit 203 includes a statistical processing unit 114 similar to that in Embodiment 1 and an event setting unit 216.

[0206] The event setting unit 216 acquires event information, for example, according to user input. The event setting unit 216 stores the acquired event information and transmits it to the terminal 253 via the network N.

[0207] So far, the functional configuration of the monitoring system 200 according to Embodiment 2 has been mainly described. The monitoring system 200 according to this embodiment may be physically configured in the same way as the monitoring system 100 according to Embodiment 1. That is, for example, the monitoring device 201 and terminal 253 according to this embodiment may be physically configured in the same way as the monitoring device 101 and terminal 153, respectively, according to Embodiment 1.

[0208] The operation of the terminal system 251 according to this embodiment will now be described.

[0209] The imaging device 152 repeatedly performs steps S151 and S152, similar to the first embodiment (see Figure 8).

[0210] Figure 17 is a flowchart showing an example of terminal processing according to this embodiment. Terminal processing is the process performed by terminal 253 to monitor the city. For example, it is started in response to instructions from a user. The initial value of the first transmission rate is, for example, a low rate and is held in the information transmission unit 256.

[0211] The image acquisition unit 254 performs the same step S153 as in Embodiment 1.

[0212] The image analysis unit 111 performs the same steps S102a to S102b as in Embodiment 1. The event detection unit 113 determines whether or not a moving object corresponding to the event has been detected, as in Embodiment 1 (step S102c).

[0213] If no moving object corresponding to the event is detected (step S102c; No), the information transmission unit 256 determines whether a predetermined time T2 has elapsed since the last detection (step S256).

[0214] In detail, for example, the information transmission unit 256 determines whether a predetermined time T2 has elapsed based on the time elapsed since the event detection unit 113 last detected a moving object corresponding to the event. If the predetermined time T2 has not elapsed, this includes cases where the event detection unit 113 has not detected a moving object corresponding to the event even once.

[0215] If a predetermined time T2 has elapsed (step S256; Yes), the information transmission unit 256 generates either the first information or the second information (step S257). The information transmission unit 256 transmits the first information or the second information generated in step S257 to the monitoring device 201 via the network N (step S258).

[0216] The first and second pieces of information generated in step S257 include the appearance features and attributes of the moving object obtained in steps S102a to S102b. The first piece of information generated in step S257 further includes the image used to determine the appearance features and attributes of the moving object.

[0217] In step S257, the information transmission unit 256 generates either the first information or the second information depending on whether it is a transmission time at a high rate (the second transmission rate in this embodiment). Specifically, if it is a transmission time at a low rate, the information transmission unit 256 generates the first information. Otherwise (i.e., it is a transmission time at a high rate and not at a low rate), the information transmission unit 256 generates the second information.

[0218] As a result, the information transmission unit 256 can generate and transmit the first information at a low rate. Furthermore, the information transmission unit 256 can generate and transmit the second information at a high rate.

[0219] The information transmission unit 256 sets the first transmission rate to a low rate (step S259) and returns to step S153.

[0220] If a moving object corresponding to the event is detected (step S102c; Yes), the event detection unit 113 executes the detection processing (step S260).

[0221] Figure 18 is a flowchart showing a detailed example of the detection process (step S260) according to this embodiment.

[0222] The event detection unit 113 performs the same step S102d as in Embodiment 1. The notification unit 115 performs the same step S102e as in Embodiment 1.

[0223] The information transmission unit 256 transmits the image information before detection (step S260a).

[0224] In detail, the information transmission unit 256 acquires image information from the image acquisition unit 254, including images taken at a predetermined time T1 in the past, which is held by the image acquisition unit 254. The information transmission unit 256 then transmits the acquired image information to the monitoring device 201 via the network N.

[0225] The information transmission unit 256 generates the first information (step S260b).

[0226] The first information generated in step S260b is the same as the first information generated in step S257.

[0227] The information transmission unit 256 transmits the first information and the detection information (step S260c).

[0228] In detail, the information transmission unit 256 transmits the first information generated in step S260b and the detection information generated in step S102d to the monitoring device 201 via the network N.

[0229] The information transmission unit 256 sets a high rate for the first transmission rate (step S258) and returns to step S153 (see Figure 17).

[0230] Refer to Figure 17 again. If the predetermined time T2 has not elapsed (step S256; No), the information transmission unit 256 generates first information (step S261). The first information generated in step S261 is the same as the first information generated in step S258. The information transmission unit 256 transmits the first information generated in step S261 to the monitoring device 201 via the network N (step S262), and returns to step S153.

[0231] Steps S261 and S262 are executed within a predetermined time T2 after the detection of a moving object corresponding to the event, and therefore are executed after step S260d. For this reason, the transmission rate set when executing steps S261 and S262 is a high rate. The information transmission unit 256 executes steps S261 and S262 according to the timing of transmission at the high rate, which is the set first transmission rate. As a result, the information transmission unit 256 can transmit the first information at a high rate until the predetermined time T2 has elapsed after the detection of a moving object corresponding to the event.

[0232] By performing this terminal processing, terminal 253 can normally transmit the first information at a low rate, and when a moving object corresponding to the event is detected, it can transmit the first information at a high rate. Since the first information includes an image, its data size is larger than that of the second information. Therefore, it is possible to reduce the communication load on network N compared to constantly transmitting the first information at a high rate.

[0233] Furthermore, the monitoring device 201 can acquire first information, including images, at a low rate. Therefore, images can be reviewed as needed. When a moving object corresponding to the event is detected, the monitoring device 201 can acquire first information. Therefore, images before and after the detection of the moving object can be managed, and detailed images can be reviewed as needed.

[0234] Furthermore, terminal 253 transmits the second information at a second transmission rate (high rate in this embodiment), which is a higher transmission rate than the low rate. Therefore, the monitoring device 201 can perform statistical processing based on the appearance information and attributes of the moving object acquired at the high transmission rate. This makes it possible to obtain statistical processing results with generally the same accuracy as in Embodiment 1.

[0235] Figure 19 is a flowchart showing an example of the monitoring process according to this embodiment. The acquisition unit 102 performs step S101, which is the same as in Embodiment 1. The processing unit 203 performs step S202, which is a replacement for step S102 in Embodiment 1.

[0236] Figure 20 is a flowchart showing a detailed example of the first process (step S202) according to this embodiment. The statistical processing unit 114 performs steps S102f and S102g, similar to those in Embodiment 1.

[0237] (Effects / Actions) According to this embodiment, the appearance information includes the appearance features of the moving object.

[0238] This allows the monitoring device 201 to perform statistical processing using the visual characteristics of moving objects, enabling it to implement safety measures for the city from a broad perspective based on the results of the statistical processing. Therefore, it becomes possible to support improvements in urban safety.

[0239] Furthermore, since it becomes unnecessary to include images in the appearance information in order to perform statistical processing using the appearance features of a moving object, it becomes possible to reduce the communication load on the network N.

[0240] According to this embodiment, the appearance information further includes the attributes of the moving object.

[0241] This allows the monitoring device 201 to perform statistical processing using the attributes of moving objects, and based on the results of the statistical processing, it can take measures to improve urban safety from a broad perspective. Therefore, it becomes possible to support improvements in urban safety.

[0242] Furthermore, since it becomes unnecessary to include images in the appearance information in order to perform statistical processing using the attributes of the moving object, it becomes possible to reduce the communication load on the network N.

[0243] According to this embodiment, the acquisition unit 202 further acquires detection information indicating the detection result of a moving object corresponding to a preset event.

[0244] This allows the monitoring device 201 to perform statistical processing on events, and based on the results of that statistical processing, it can take measures to improve safety in the city from a broad perspective. Therefore, it becomes possible to support the improvement of safety in the city.

[0245] Furthermore, since it becomes unnecessary to transmit images in order to perform statistical processing on events, it becomes possible to reduce the communication load on network N.

[0246] According to this embodiment, the monitoring device 201 further includes an event setting unit 216 that transmits event information relating to a pre-set event to the terminal 253.

[0247] This allows common event information to be set for all one or more terminals 253 via the monitoring device 201, thus eliminating the need to set event information for each of the one or more terminals 253 individually. Consequently, it becomes easier to support improvements in urban safety.

[0248] <Embodiment 3> Figure 21 shows an example configuration of the monitoring system 300 according to Embodiment 3. The monitoring system 300 includes a monitoring device 301 that replaces the monitoring device 201 according to Embodiment 2, terminal systems 251a to 251d similar to those in Embodiment 2, and two middle devices 361a to 361b. Note that the number of middle devices included in the monitoring system 300 is not limited to two; it may be any number of one or more.

[0249] The middle devices 361a to 361b are connected to the monitoring device 301 and each of the terminals 253a to 253d via network N, and they send and receive information from each other via network N.

[0250] Each of the middle devices 361a to 361b is associated with one or more terminal systems 251. That is, each of the middle devices 361a to 361b is positioned in the network N between the terminals 253a to 253d and the monitoring device 301.

[0251] Each of the middle devices 361a to 361b may be configured in the same manner. When not distinguishing between the middle devices 361a to 361b, each is also referred to as the middle device 361.

[0252] The middle device 361 is a device used in a predetermined institution such as the police. That is, the middle device 361 is an example of a device in which the notification unit 115 transmits detection information.

[0253] When the middle device 361 is activated in an institution, it transmits activation information regarding the activation to the monitoring device 301 via the network N.

[0254] The monitoring device 301 includes a processing unit 303 that replaces the processing unit 203 according to Embodiment 2. Except for this point, the monitoring device 301 may be configured in the same manner as the monitoring device 201 according to Embodiment 2.

[0255] FIG. 22 is a diagram showing a functional configuration example of the processing unit 303 according to this embodiment. The processing unit 303 includes a statistical processing unit 114 and an event setting unit 216 similar to those in Embodiment 2, and an event update unit .

[0256] The event update unit acquires activation information from the middle device 361. The event update unit transmits update information for updating event information to the terminal 253 via the network N based on the acquired activation information.

[0257] So far, the functional configuration of the monitoring system 300 according to Embodiment 3 has been mainly described. Each of the monitoring device 301 and the middle device 361 according to this embodiment may be physically configured in the same manner as the monitoring device 101 according to Embodiment 1.

[0258] It should be noted that in the original text, there is a possible error in the description of the components in . It is guessed that "事象更新部317" should be "事象更新部315" according to the context, but the translation is carried out strictly according to the original text. If there is an error in the original text, it may cause the translation to be a bit difficult to understand accurately. You can check and correct it according to the actual situation.The operation of the monitoring system 300 according to this embodiment will now be described.

[0259] In addition to the same processing as in Embodiment 2, the monitoring system 300 according to this embodiment performs event update processing to update event information.

[0260] Figure 23 is a flowchart showing an example of the event update process according to this embodiment. The event update process is executed repeatedly, for example, while the monitoring system 300 is running.

[0261] The middle unit 361 generates dispatch information related to the dispatch when the organization is dispatched (step S301).

[0262] In detail, for example, the middleware 361 generates dispatch information, including dispatch time, departure point, destination, and incident, based on user input. The dispatch time is the time the dispatch occurred. The departure point is the location of the dispatching agency. The destination is the destination to which the dispatch is going. The incident is the incident that caused the dispatch.

[0263] The middle unit 361 transmits the dispatch information generated in step S301 to the monitoring unit 301 via the network N (step S302).

[0264] The event update unit 317 acquires dispatch information from the middle device 361 (step S303).

[0265] The event update unit 317 generates update information to update the event information based on the dispatch information acquired in step S303 (step S304).

[0266] In more detail, for example, if the event detection unit 113 has not detected an event corresponding to the dispatch information, the event update unit 317 refers to at least one of the destination image, the appearance information of the moving object obtained from the image, and its attributes included in the dispatch information.

[0267] The event update unit 317 creates detection conditions for the event detection unit 113 to detect events included in the dispatch information, based on at least one of the referenced image, the appearance information of the moving object, and its attributes. The detection conditions include, for example, at least one of the referenced image, the appearance information of the moving object, and its attributes. The event update unit 317 generates update information that associates the events corresponding to the dispatch information with the created detection conditions.

[0268] The event update unit 317 transmits the update information generated in step S304 to the terminal 253 via the network N (step S305).

[0269] The event acquisition unit 255 acquires update information (step S306). Based on the update information acquired in step S306, the event acquisition unit 255 updates the event information stored in the event storage unit 112 (step S307).

[0270] This allows the event detection unit 113 to update event information based on at least one of the images, moving object appearance information, and attributes related to the event that actually occurred, if it fails to detect an event.

[0271] (Effects / Actions) According to this embodiment, terminal 253 transmits detection information regarding the detected moving object to middle device 361.

[0272] As a result, the monitoring device 301 can perform statistical processing using the external features of moving objects, and based on the results of the statistical processing, it can take measures for urban safety from a broad perspective. Therefore, it becomes possible to support the improvement of urban safety.

[0273] This allows for a quicker response to detected notification events, thereby contributing to improved safety in urban areas.

[0274] According to this embodiment, the middle device 361 is a device used in a predetermined institution. The monitoring device 301 further includes an event update unit 317 that acquires activation information regarding the activation when activated in the institution and transmits update information for updating event information to the terminal 253 based on the acquired activation information.

[0275] Thereby, when the event detection unit 113 fails to detect an event, the event information can be updated, so that the event information can be updated to detect the event more accurately. Therefore, it becomes possible to support the improvement of safety in the city.

[0276] As described above, the embodiments and modifications of the present invention have been described with reference to the drawings, but these are examples of the present invention, and various configurations other than the above can also be adopted.

[0277] In addition, in the plurality of flowcharts used in the above description, a plurality of steps (processes) are described in order, but the execution order of the steps executed in each of the embodiments is not limited to the described order. In each of the embodiments, the order of the illustrated steps can be changed within a range that does not substantially affect the content. Also, the above-described embodiments and modifications can be combined within a range where the contents do not conflict.

[0278] Some or all of the above embodiments can also be described as follows in the appended claims, but are not limited thereto.

[0279] 1. Acquisition means for acquiring appearance information regarding the appearance of a moving object included in an image captured by a plurality of imaging devices installed in the city, Processing means for performing statistical processing using the appearance information. Monitoring device. 2. The moving object includes at least one of a person and a vehicle. The monitoring device according to 1. 3. The appearance information includes the image. The processing means analyzes the image included in the appearance information to obtain appearance features of the moving object, and performs statistical processing using the obtained appearance features. The monitoring device described in 1. or 2. 4. The processing means analyzes the image included in the appearance information to further determine the attributes of the moving object, and further performs statistical processing using the attributes of the moving object. The monitoring device described in 3. 5. The appearance information includes the appearance features of the moving object. The monitoring device described in 1. or 2. 6. The appearance information further includes the attributes of the moving body. The monitoring device described in 5. 7. The appearance feature includes a feature relating to at least one of the appearance attributes, posture, and motion of the moving object. A monitoring device as described in any one of items 3 through 6. 8. The characteristic quantity relating to the movement of the moving body includes at least one of the movement path and movement speed. The monitoring device described in 7. 9. The processing means performs the statistical processing based on at least one of the attributes of the location where the image was taken, the time period when the image was taken, and the attributes of the moving object included in the image. A monitoring device as described in any one of items 1 through 8. 10. The attributes of the place include at least one of the characteristics of the passage of a moving object and a region. The monitoring device described in 9. 11. The processing means detects a moving object corresponding to a preset event based on the results of analyzing the image included in the appearance information. A monitoring device as described in any one of items 1 through 10. 12. When the processing means detects a moving object that corresponds to a predetermined notification event from among the events, it notifies a predetermined notification recipient associated with the notification event that the notification event has been detected. The monitoring device described in 11. 13. The acquisition means further acquires detection information indicating the detection result of a moving object corresponding to a pre-set event. A monitoring device as described in any one of items 1 through 10. 14. Further comprising event setting means for transmitting event information relating to the pre-set events to a terminal. The monitoring device described in 13. 15. The processing means further performs statistical processing using the detection results of moving objects corresponding to the predetermined events. A monitoring device as described in any one of items 11 through 14. 16. The event is related to at least one of the attitude, movement, or attribute of the moving object. A monitoring device as described in any one of items 11 through 15. 17. A monitoring device as described in any one of items 1 through 16, The aforementioned multiple imaging devices, The system comprises at least one terminal connected to the aforementioned plurality of imaging devices, The terminal transmits the appearance information to the monitoring device. Monitoring system. 18. The terminal analyzes the image to obtain the appearance features of the moving object and transmits the appearance information, including the obtained appearance features, to the monitoring device. The monitoring system described in 17. 19. The terminal analyzes the image to further determine the attributes of the moving object, and transmits the appearance information, which further includes the determined attributes of the moving object, to the monitoring device. The monitoring system described in 17. or 18. 20. The aforementioned appearance information includes images captured by the plurality of imaging devices. A monitoring system as described in any one of items 17 through 19. 21. The terminal acquires event information relating to a pre-set event from the monitoring device and detects a moving object corresponding to the event based on the results of analyzing the image. A monitoring system as described in any one of items 17 through 20. 22. The terminal transmits the detection information regarding the detected moving object to the monitoring device. The monitoring system described in 21. 23. Further comprising at least one middle device, The terminal transmits the detection information regarding the detected moving object to the middle device. The monitoring system described in 21. or 22. 24. The aforementioned middle device is a device used in a designated institution, The monitoring device further includes an event update means that acquires dispatch information related to a dispatch when the organization is dispatched, and transmits update information to the terminal for updating the event information based on the acquired dispatch information. The monitoring system described in 23. 25. Computers, We acquire visual information about the appearance of moving objects contained in images taken by multiple cameras installed throughout the city. Statistical processing is performed using the aforementioned appearance information. Monitoring method. 26. To the computer, We acquire visual information about the appearance of moving objects contained in images taken by multiple cameras installed throughout the city. A recording medium containing a program for performing statistical processing using the aforementioned appearance information. 27. To the computer, We acquire visual information about the appearance of moving objects contained in images taken by multiple cameras installed throughout the city. A program for performing statistical processing using the aforementioned appearance information. [Explanation of Symbols]

[0280] 100, 200, 300 monitoring systems 101,201,301 Monitoring equipment 102,202 Acquisition Department 103,203,303 Processing Unit 104 History Storage Unit 105 Input Reception Section 106 Display section 111 Image Analysis Department 112 Event Memory Unit 113 Event detection unit 114 Statistical Processing Section 115 Hochi Department 151, 151a~151d, 251, 251a~251d End System 152, 152a~152d Imaging device Terminals 153, 153a~153d, 253, 253a~253d 216 Event Setting Section 254 Image acquisition unit 255 Event Acquisition Unit 256 Information Transmission Section 317 Event Update Section 361, 361a~361b Middle device

Claims

1. An acquisition means for acquiring appearance information relating to the appearance of a moving object included in an image captured by a camera, A processing means that performs statistical processing using the aforementioned appearance information, The system includes: an event update means that acquires dispatch information related to a dispatch when the organization is dispatched from at least one middle device used by the organization, generates update information for updating event information related to a pre-set event based on the acquired dispatch information, and transmits the generated update information to a terminal that detects a moving object corresponding to the event based on the results of analyzing the event information and the image. monitoring equipment.

2. The aforementioned appearance information includes the aforementioned image, The processing means analyzes the image included in the appearance information to obtain appearance features of the moving object, and performs statistical processing using the obtained appearance features. The monitoring device according to claim 1.

3. The processing means analyzes the image included in the appearance information to further determine the attributes of the moving object, and further performs statistical processing using the attributes of the moving object. The monitoring device according to claim 2.

4. The processing means performs the statistical processing based on at least one of the attributes of the location where the image was taken, the time period when the image was taken, and the attributes of the moving object included in the image. A monitoring device according to any one of claims 1 to 3.

5. The processing means detects a moving object corresponding to a preset event based on the results of analyzing the image included in the appearance information. A monitoring device according to any one of claims 1 to 3.

6. When the processing means detects a moving object that corresponds to a predetermined notification event from among the events, it notifies a predetermined notification recipient associated with the notification event that the notification event has been detected. The monitoring device according to claim 5.

7. The dispatch information includes an image of the destination to which the dispatch is to take place. The aforementioned event information includes the pre-set event and detection conditions for detecting the event from the image. The update information includes an event corresponding to the dispatch information and an update detection condition for detecting the event, The update detection condition includes at least one of the following: an image of the destination, appearance information of a moving object obtained from the image, and attributes. A monitoring device according to any one of claims 1 to 6.

8. A monitoring device comprising acquisition means for acquiring appearance information relating to the appearance of a moving object included in an image captured by a camera, and processing means for performing statistical processing using the appearance information, At least one terminal connected to the aforementioned imaging device, It comprises at least one middleware device used in a designated institution, The aforementioned terminal is The aforementioned appearance information is transmitted to the monitoring device. Based on event information relating to a pre-set event and the results of analyzing the image, a moving object corresponding to the event is detected, and detection information relating to the detected moving object is transmitted to the middle device. The aforementioned monitoring device is The system further comprises event update means for acquiring dispatch information related to a dispatch when the aforementioned organization is dispatched, and transmitting update information to the terminal for updating the event information based on the acquired dispatch information. Monitoring system.

9. Computers The camera acquires visual information regarding the appearance of the moving object contained in the image captured by the camera. Statistical processing is performed using the aforementioned appearance information. At least one middleware device used by a designated organization will acquire dispatch information related to a dispatch when the organization is dispatched. Based on the acquired dispatch information, update information is generated to update the event information related to the pre-set events. The generated update information is transmitted to a terminal that detects a moving object corresponding to the event based on the results of analyzing the event information and the image. Monitoring method.

10. On the computer, The camera acquires visual information regarding the appearance of the moving object contained in the image captured by the camera. Statistical processing is performed using the aforementioned appearance information. At least one middleware device used by a designated organization will acquire dispatch information related to a dispatch when the organization is dispatched. Based on the acquired dispatch information, update information is generated to update the event information related to the pre-set events. A program for transmitting the generated update information to a terminal that detects a moving object corresponding to the event based on the results of analyzing the event information and the image.

Images