JP7128577B2 - monitoring device - Google Patents

Description

TECHNICAL FIELD The present invention relates to a monitoring apparatus for tracking and photographing an object moving within a monitoring area by changing the photographing direction according to the position of the object.

Conventionally, there has been known a system that detects a moving object by scanning a monitoring area using an area sensor device such as a laser sensor, changes the shooting direction of the camera according to the position of the detected object, and tracks and shoots the object. there is

In this system, when the laser sensor detects multiple objects, there is a method for determining the object to be tracked and photographed. A method of tracking and photographing an object has been proposed (Patent Document 2 below).

JP 2014-175844 A JP 2014-175843 A

The conventional system assumes that the detected object is an object (person or vehicle) to be tracked and photographed. However, the objects detected by the laser sensor are not always the objects to be tracked and photographed. That is, an object that is highly likely to be a person or vehicle, that is, an object that is highly likely to be photographed, can be detected, while an object that is unlikely to be a person or vehicle, that is, an object that is less likely to be a subject to be photographed can also be detected.

Therefore, if the tracking shooting target is determined without considering the difference in shooting target likeliness, there is a risk that an object that is less likely to be an intruder will be tracked and shot even though there are objects that are more likely to be an intruder. On the other hand, when considering the likeness of the shooting target, if the degree of likeness of the shooting target exceeds a threshold is set as a condition for determining the tracking shooting target, the likeliness of the shooting target is evaluated low immediately after the object is detected. There is a risk that the intruder will not be tracked and photographed.

SUMMARY OF THE INVENTION The present invention has been made to solve the above-mentioned problems. The purpose is to provide an apparatus.

(1) A monitoring device according to the present invention is a device that tracks and photographs a moving object in a monitoring area, detects the moving object within the monitoring area, and outputs detection results including the position of the moving object. a detection unit, an imaging unit capable of changing an imaging direction, a control unit that controls the imaging unit based on the detection result, and a predetermined feature amount for each of the detected moving objects that is evaluated for tracking imaging. and an evaluation means for obtaining a degree of tracking and photographing object indicating the degree of object-likeness of the object, and when only one moving object is detected by the object detection unit, the moving object is regarded as a tracking and photographing object regardless of the degree of tracking and photographing object. on the other hand, when a plurality of moving objects are detected, a moving object having a high degree of tracking and photographing is preferentially set as a tracking and photographing object.

(2) In the monitoring apparatus described in (1) above, each time a moving object is newly detected in the monitoring area, the shooting target setting means selects a tracking shooting target for the plurality of detected moving objects. It can be configured to be reset.

(3) In the monitoring apparatus described in (1) and (2) above, the evaluation means increases the tracking imaging target degree as the size of the moving object based on at least the detection result is closer to a predetermined standard. It can be configured to evaluate the moving object as follows.

(4) In the monitoring apparatus described in (1) to (3) above, the photographing object setting means, when the degree of tracking photographing object is the same for a plurality of moving objects, selects the currently selected moving object among the moving objects. A moving object may be set as the tracking imaging target.

(5) In the monitoring apparatus described in (1) to (4) above, the evaluation means determines whether or not the moving object is an intruding object that satisfies a predetermined report condition based on the feature amount. and a tracking imaging target degree of the moving object determined as the intruding object is set higher than the tracking imaging target degree when the moving object is not determined as the intruding object.

According to the present invention, it is possible to preferably set a tracking shooting target for a detected object, particularly in a situation where a plurality of objects are detected, preferably set a tracking shooting target.

BRIEF DESCRIPTION OF THE DRAWINGS It is a schematic diagram which shows the structure of the outline of the monitoring system which concerns on embodiment of this invention. 1 is a block diagram showing a schematic configuration of a monitoring device according to an embodiment of the present invention; FIG. FIG. 4 is a schematic flow diagram of control related to tracking imaging of the monitoring device according to the embodiment of the present invention; FIG. 5 is a schematic diagram for explaining an example of processing by a tracking imaging target setting unit; FIG. 5 is a schematic diagram for explaining an example of processing by a tracking imaging target setting unit;

DESCRIPTION OF THE PREFERRED EMBODIMENTS A monitoring system 1 including a monitoring device according to the present invention will be described below as an embodiment (hereinafter referred to as an embodiment) of the present invention with reference to the drawings.

FIG. 1 is a schematic diagram showing a schematic configuration of a monitoring system 1 according to an embodiment. A monitoring system 1 includes a monitoring device 2 and a monitoring center 3 . The monitoring device 2 and the monitoring center 3 are communicably connected.

The monitoring device 2 is installed in a place, a building, or the like, where a monitoring area 4 to be monitored is set, and tracks and photographs a moving object (person, vehicle, etc.) in the monitoring area 4 . The monitoring device 2 includes an object detection unit 5 , an imaging unit 6 and a control unit 7 , and at least the object detection unit 5 and the imaging unit 6 are installed at positions facing the monitoring area 4 . For example, the monitoring area 4 is set outdoors, and the object detection unit 5 and the imaging unit 6 are installed on an outer wall surface of a building, a pole erected adjacent to the monitoring area 4, or the like. On the other hand, the control unit 7 is installed at a predetermined location within the monitoring area 4 or in the vicinity of the monitoring area 4, and is connected to the object detection unit 5 and the imaging unit 6 via a LAN, for example. The control unit 7 can be installed in a place close to the object detection unit 5 and the imaging unit 6, or the object detection unit 5 and the imaging unit 6 can be installed outdoors, and the control unit 7 can be installed indoors. It can also be placed at a position separated from the object detection unit 5 and the imaging unit 6 . Also, each function of the control unit 7 may be provided in the object detection unit 5 and the imaging unit 6 .

The monitoring area 4 is set, for example, in a semicircular shape with a radius of several tens of meters [m] (for example, 20 m) around the monitoring device 2 . In the monitoring area 4 set in this way, the resolution of an object detected at a position distant from the camera is not so high with a general-purpose camera, and sufficient information about the object cannot be obtained, so it is necessary to perform zoom control appropriately. arise. It should be noted that the monitoring area is not limited to this example, and can be appropriately determined according to security planning.

An object detection unit 5 detects a moving object within the monitoring area 4 and outputs a detection result including the position of the moving object. When the object detection unit 5 detects an abnormal event that has occurred within the monitoring area 4 (for example, a suspicious person or vehicle enters the monitoring area 4), the object detection unit 5 transmits tracking information, which will be described later, to the control unit 7.

The imaging unit 6 performs camera control in accordance with the camera control command from the control unit 7, and photographs the movement of an object that has entered the surveillance area 4 while tracking it.

The control unit 7 generates a camera control command as a control instruction to the imaging unit 6 based on the tracking information of the object.

The monitoring center 3 is a facility operated by a security company or the like, and is usually equipped with a center device composed of one or more computers. Also, the monitoring center 3 is connected to one or more monitoring devices 2 via a network. In the monitoring center 3, for example, various devices are controlled by the center device, abnormal signals received from the monitoring device 2 are recorded, and abnormal information and images captured by the imaging unit 6 are displayed on the display. is monitoring the surveillance area.

FIG. 2 is a block diagram showing a schematic configuration of the monitoring device 2. As shown in FIG. The configuration of the monitoring device 2 shown in FIG. 2 will be described below.

The object detection unit 5 includes an area sensor device, for example, performs spatial scanning of the monitoring area 4 at a predetermined cycle using a beam-shaped search signal, and detects reflected light reflected by an object (person, vehicle, etc.) on the optical path. is received, the position of an object existing within the monitoring area 4 is detected. In addition, the object detection unit 5 can calculate the moving speed and moving direction of the object using the position detection results obtained at a plurality of times.

The object detection unit 5 includes communication means 51 , storage means 52 , detection means 53 , tracking means 54 and control means 55 .

The communication means 51 is connected to the control section 7 , receives a guard start signal and a guard release signal output from the control section 7 , and inputs the signals to the control section 55 . Further, when the presence of a moving object in the monitoring area 4 is determined by the detection means 53 , the communication means 51 transmits a detection signal including its own address information to the control section 7 . For example, tracking information is transmitted to the control unit 7 as a detection signal.

The storage means 52 is a storage device composed of a HDD (Hard Disk Drive), a ROM (Read Only Memory), a RAM (Random Access Memory), etc., and stores various setting information, programs for operating the object detection unit 5, and the like. memorize For example, the storage unit 52 stores address information for specifying the object detection unit 5 itself. In the storage means 52, monitoring area information indicating the monitoring area 4 set as the range to be monitored by the object detection unit 5, reference data generated by the detection means 53, and data obtained by the detection means 53 are stored. Measured data for a predetermined period in the past and tracking information of a moving object (intruding object) are stored.

Here, the reference data is data that is compared with the current measurement data in order to extract a moving object newly appearing in the monitoring area 4 in the object extraction process for detecting moving objects. Specifically, the reference data is generated from the measurement data acquired at any past time from the start of scanning by the detection means 53 to the present. For example, an existing object such as a plant or an outer wall acquired by scanning while there is no moving object in the monitoring area 4 is used as the reference data. The reference data can be stored, for example, in the form of a table that associates angles (directions) with distances.

The tracking information is information used in tracking processing for tracking a moving object newly appearing in the monitoring area 4 over a plurality of cycles, and consists of the detected position, size, shape, and the like of the moving object. The tracking information is also used when the evaluation means 74 obtains the tracking imaging target degree. The tracking information includes an identifier (object ID) for distinguishing moving objects from each other, the position, size, and shape of each moving object (object ID) at which the object first appeared in the monitoring area, the position in each cycle up to the present, The size and shape are associated in chronological order. Further, the tracking information may be associated with the type information of the moving object (vehicle, person, etc.) and the elapsed time after the first detection of the moving object (tracking time).

The detection means 53 is basically means for periodically scanning the monitoring area 4 to detect an object present in the monitoring area 4 and calculating the position of the object. In this embodiment, the detection means 53 is configured using a laser sensor, and emits a laser beam as a search signal. For example, the laser sensor is installed so that the direction of emission of the laser light is horizontal or has a certain depression angle so that the detection target in the monitoring area 4 is irradiated with the laser light.

Specifically, the detection means 53 repeats scanning at a predetermined cycle (for example, 60 milliseconds) in a horizontal angular range facing the monitoring area 4 centering on the laser sensor. Distance measurement by the detection means 53 is performed using the time of flight method (TOF method) at predetermined angular steps (for example, 0.25°) within the scanning angle range. That is, the time required from the emission of the laser pulse to the light reception is measured, and the distance to the object that reflected the laser is calculated from the measured time and the speed of light.

The measurement data obtained by the detection means 53 is represented by a scanning angle (azimuth) and a distance, and the position of the laser light reflection point on the object with the laser sensor as the viewpoint is given by the measurement data. Specifically, the measurement data is information consisting of a collection of a plurality of measurement point data in which the angle (direction) of transmission and reception of the laser light and the distance to the reflection point are associated with each other. If the reflected light does not return within a predetermined time, it can be considered that there is no object within the range where the laser beam can be irradiated, and the detection means 53 uses predetermined pseudo data (for example, monitoring area) as the distance. 4, an appropriate value greater than the effective measurement distance by laser light, etc.) are set.

Further, the detection means 53 detects a moving object appearing in the monitoring area 4 by comparing the current measurement data and the reference data. Specifically, the difference between the distance value for each scanning angle obtained from the current measurement data and the distance value for each angle stored in the reference data is calculated for each corresponding angle, and the angle at which the distance value has changed is calculated. Let the measurement point of the current measurement data at be the detection point. Then, among the detection point group, adjacent detection points whose distance values are thought to have changed due to the same object to be measured are grouped as distance measurement data and detected as a moving object. Also, as the size of this moving object, the length in the real space between the end points of the grouped detection points, that is, the current width of the moving object, is calculated from the angles and distances of the end points. Also, as the shape of this moving object, the current linearity of the moving object is calculated based on the variation in the distances at the grouped detection points. Specifically, since the variation in distance becomes large when the surface of the object is uneven, a shape with low linearity is used when the variation in distance is large. Note that the size and shape of the moving object may be calculated by the evaluation means 74, which will be described later, using a similar method.

Note that the detection means 53 is not limited to a laser sensor, and can be configured using various sensors capable of detecting the position of an object, such as an ultrasonic sensor.

The tracking means 54 associates the moving objects detected in the previous cycle and the current cycle to generate and update tracking information, and uses this to track the moving object. The association is made based on distance, size, and the like. That is, when the distance between objects detected in both cycles is within the threshold and the variation in size is within the threshold, the moving objects in both cycles are associated as the same object.

The control means 55 is composed of a microcomputer comprising a CPU (Central Processing Unit), ROM, RAM, etc. and its peripheral circuits.

The control means 55 outputs a drive signal to the detection means 53 when a guard start signal is input from the control section 7 via the communication means 51 to start driving the detection means 53 . As a result, the detection means 53 starts emitting laser light, driving a scanning mirror for changing the scanning angle of the laser light, and the like. On the other hand, the control means 55 outputs a drive stop signal to the detection means 53 when the security release signal is input from the control section 7, and stops the driving of the detection means 53 when the scanning at that time is completed. As a result, the emission of laser light, the driving of the scanning mirror, and the like are stopped.

The imaging unit 6 can change the imaging direction in order to track and photograph a moving object. In addition, the imaging unit 6 can perform zoom control in order to obtain an object image with sufficient resolution for an object that is far from the monitoring device 2 . In other words, the imaging unit 6 of the present embodiment is configured using a camera (PTZ camera) capable of pan, tilt and zoom (PTZ) control, and the control unit based on the tracking information of the moving object detected by the object detection unit 5 7, the moving object is imaged by performing PTZ control so that the moving object stays within the angle of view, especially in the center of the angle of view. The camera of the imaging unit 6 is installed at a position facing the monitoring area 4 together with the laser sensor of the object detection unit 5 as described above. Here, the imaging unit 6 can be installed at the same position as the object detection unit 5, or at a position shifted in the vertical direction with respect to the object detection unit 5, or at another location near the object detection unit 5. may be installed.

The imaging unit 6 includes camera driving means 61 , imaging means 62 , communication means 63 and storage means 64 .

The camera drive means 61 includes a drive mechanism for changing the photographing direction (pan, tilt) of the camera and a drive mechanism for driving the zoom lens of the camera to change the angle of view. It operates the drive mechanism to control panning, tilting, and zooming.

The image capturing means 62 is composed of, for example, a camera using an image sensor, and captures images of the monitored area and moving objects.

A communication unit 63 receives a camera control signal from the control unit 7 . Further, the communication means 63 transmits the image captured by the imaging means 62 to the monitoring center 3 via the control section 7 .

A storage unit 64 is a storage device configured by an HDD, ROM, RAM, etc., and stores captured images. Further, the storage means 64 stores the home position of the camera (angle of view when no moving object is detected).

The control unit 7 is communicably connected to the object detection unit 5 and the imaging unit 6, outputs control signals to them, and receives detection signals and captured images from them. The control unit 7 is communicably connected to a remote monitoring center 3, receives control signals from the monitoring center 3 for the monitoring device 2, and monitors abnormal signals and photographed images detected in the monitoring area 4. It is transmitted to the center 3. For example, communication between the control unit 7 and the monitoring center 3 can be performed via a virtual private network (VPN) built on a wide area network (WAN) such as the Internet.

Further, for example, a user performs an operation for starting or canceling monitoring of the monitoring area 4 using an operation unit provided in the monitoring device 2, or receives an instruction to start or cancel monitoring from the monitoring center 3. As a result, the control unit 7 sets the monitoring state of the monitoring area 4 to start or cancel, and transmits a security start signal or security cancellation signal to the object detection unit 5 .

The control unit 7 includes communication means 71 , storage means 72 , camera control means 73 , evaluation means 74 , type determination means 75 and tracking imaging target setting means 76 . The control unit 7 is composed of a microcomputer comprising a CPU, a ROM, a RAM, etc. and its peripheral circuits. It functions as type determining means 75, tracking imaging target setting means 76, and the like.

The communication unit 71 performs communication between the object detection unit 5 and the imaging unit 6 and the control unit 7 in the monitoring device 2 and communication with the monitoring center 3 . For example, the communication means 71 transmits a security start signal or a security release signal to the object detection unit 5 . Further, to the monitoring center 3, an abnormality signal generated when an abnormality is detected in the monitoring area 4 and a photographed image are transmitted.

The storage unit 72 is a storage device configured by HDD, ROM, RAM, etc., and stores various setting information, programs for operating the control unit 7, and the like. For example, the storage means 72 stores object tracking information. Also, the relative positions of the object detection unit 5 and the imaging unit 6 are stored in advance in the storage unit 72 .

The camera control means 73 generates a signal for giving a control instruction (PTZ control amount and its speed) to the imaging unit 6 based on the detected position and movement speed obtained from the tracking information of the object. It is preferable that the imaging direction (pan, tilt) control is performed so that the object appears in the center of the angle of view, and the zoom control is performed so that the object appears at a predetermined size. Zoom control is performed based on the position of the detected object (distance to the object). Control is performed so that the closer the object is, the lower the zoom magnification is. Furthermore, it is preferable to consider the moving speed of the object in the zoom control. Specifically, the faster the object is, the more the object is zoomed out and photographed.

The evaluation unit 74 evaluates a predetermined feature amount for each moving object detected by the object detection unit 5, and obtains a degree of tracking photography target that indicates the degree of likelihood of a tracking photography target. The tracking imaging target degree may be defined numerically such as "0 to 100%", or may be defined by levels or stages such as "high, medium, low". This evaluation can be performed when a new moving object is detected or at predetermined time intervals.

In the present embodiment, a person or a vehicle is the object of tracking and photographing, and indices such as the size and shape of a moving object are used as feature quantities to be evaluated. ) is obtained.

The evaluation means 74 refers to the tracking information stored in the storage means 72, acquires the size and shape of the moving object to be evaluated, and compares them with the characteristics generally possessed by people and vehicles. For example, distance measurement data indicating a person has characteristics such as the width of the object being within a predetermined range (for example, 20 cm to 100 cm), and the surface of the object being uneven and having low linearity (variation in distance is greater than a predetermined value). The evaluation unit 74 evaluates the tracking shooting target degree (person-likeness) higher as the width and shape of the moving object match the features of the person. Further, the distance measurement data indicating the vehicle has characteristics such as the width of the object being within a predetermined range (for example, 1 m to 5 m), the surface of the object being highly linear, and two straight lines intersecting at right angles. , the more the width and shape of a moving object match the characteristics of the vehicle, the higher the degree of tracking shooting target (vehicle-likeness).

In addition, you may use a moving speed as a feature-value to evaluate. In this case, the evaluation means 74 calculates the moving speed of the moving object from the moving history included in the tracking information, and evaluates the degree of tracking shooting object more highly as the moving speed matches the characteristics of the person or the vehicle. For example, when a person is targeted for tracking photography, the degree of tracking photography is evaluated so that the closer the moving speed is to 10 km/h or less, the higher the degree of tracking photography is. Evaluation is made so that the closer to 60 km, the higher the tracking imaging target degree.

The type determination means 75 determines the type of moving object based on the detection result of the object detection section 5 . In this embodiment, the type determining means 75 determines at least vehicle and person as the types of detected objects. The type determining means 75 determines the type based on, for example, the size, shape, and moving speed of the detected object. For example, if the detected object has a size larger than a predetermined size, a shape including a right angle, and a moving speed higher than a predetermined value, the type of the detected object can be determined as a car. Further, the type of the moving object may be determined based on whether the tracking shooting target degree of human-likeness or vehicle-likeness is equal to or higher than a predetermined value (for example, "50%" or "medium").

The tracking shooting target setting means 76 is the shooting target setting means of the present invention, and sets an object to be a tracking shooting target based on the tracking shooting target degree of the detected object. If only one moving object is detected by the object detection unit 5, the tracking shooting target setting means 76 sets the moving object as the tracking shooting target regardless of the degree of the tracking shooting target. If so, a moving object with a high degree of tracking photography target is preferentially set as a tracking photography target. For example, among a plurality of moving objects, the one with the highest degree of tracking photography target can be set as the tracking photography target.

The tracking imaging target setting unit 76 can also set the tracking imaging target by combining the tracking imaging target degree and other criteria. For example, when there are a plurality of moving objects with the highest degree of tracking imaging target, it is possible to select a tracking imaging target from among the plurality of moving objects according to other criteria.

For example, if a plurality of moving objects have the same degree of tracking shooting target, the tracking shooting target setting means 76 sets a currently moving object among the moving objects as a tracking shooting target (“Movement Priority”). ). By the way, the tracking information can be used to determine whether the object is currently moving or stationary.

Regarding the classification determined by the classification determination means 75, the priority (imaging priority) when setting a moving object as a tracking photographing target is determined in advance, and not only the tracking photographing target but also the photographing priority is taken into consideration. You can select the object to be tracked and photographed by pressing the For example, when a plurality of moving objects have the same degree of tracking shooting target, an object with a high shooting priority can be set as a tracking shooting target.

In addition, it is also possible to preferentially set the latest or oldest detected object among the plurality of moving objects as the tracking photographing target. Giving priority to the most recently detected moving object is called "late priority", and giving priority to the oldest detected moving object is called "early priority".

The tracking imaging target setting means 76 can set the tracking imaging target in synchronization with the timing at which the evaluation means 74 sets the degree of tracking imaging target. Each time a plurality of moving objects are detected, the tracking shooting target is set again.

FIG. 3 is a schematic flow chart of control related to tracking photographing of the monitoring device 2. As shown in FIG. When a moving object is detected by the object detection unit 5, the monitoring device 2 starts control related to tracking photography (step S1), and the evaluation means 74 evaluates the tracking information (size, shape, moving speed, etc.) of the moving object. Based on this, the tracking imaging target degree is evaluated (step S2). If there are a plurality of objects detected by the object detection unit 5 ("Yes" in step S3), the tracking shooting target setting means 76 performs tracking based on the tracking shooting target degrees of the plurality of objects. A shooting target is set (step S4). Specifically, the object with the highest degree of tracking imaging is set as the tracking imaging target. On the other hand, when the number of objects detected by the object detection unit 5 is one ("No" in step S3), the object is set as the tracking photographing target regardless of the tracking photographing target degree of the object. (step S5). In this way, when an object to be tracked and photographed among the objects detected by the object detection unit 5 is set, the camera control means 73, based on the detection position of the object set as the object to be tracked and photographed, A control instruction including PTZ control is issued to the imaging unit 6, and the imaging unit 6 performs PTZ control of the camera to track and photograph an object (step S6).

4 and 5 are schematic diagrams for explaining an example of processing by the tracking imaging target setting means 76. FIG. Here, the tracking imaging target degree is defined in the range of 0 to 100[%]. Also, a person and a vehicle are subject to tracking photographing, and the evaluation means 74 obtains a tracking photographing object degree representing human-likeness and a tracking photographing object degree representing vehicle-likeness for each detected object. 4 and 5 show in tabular form the object ID of the detected object and each degree of tracking shooting object in association with each other. They are the shooting target degree and the tracking shooting target degree of vehicle-likeness.

FIG. 4A shows the case where only one moving object is detected. The value "40" for the "likeness of a person" and the value "20" for the "likeness of a car" are such low values that it is difficult to say whether the detected object "ID1" is a person or a car. A reference numeral 76 sets the object "ID1" as a tracking photographing target regardless of the degree of tracking photographing.

FIGS. 4(b) and 4(c) are cases where three moving objects are detected. When a plurality of moving objects are detected in this manner, basically, the tracking shooting target setting means 76 sets the object with the highest tracking shooting target degree as the tracking shooting target. Therefore, in the example of FIG. 4B, the object "ID3" having the highest value of "80" between "person-likeness" and "vehicle-likeness" is set as the tracking photographing target.

On the other hand, in the example of FIG. 4(c), objects "ID2" and "ID3" have the highest values. When there are a plurality of objects having the highest degree of tracking imaging, it is possible to determine the tracking imaging target by using other criteria in combination. For example, the tracking shooting target setting unit 76 sets the tracking shooting target according to the shooting priority, first priority, rear priority, movement priority, and the like.

In this case, a person and a vehicle are equally targeted for tracking and photographing. However, when only a person is targeted for tracking and photographing, the tracking and photographing object should be set based only on the likeness of a person without evaluating the likeness of a vehicle. can be done. In that case, in the examples of FIGS. 4B and 4C, the object "ID3" is set as the tracking photographing target.

FIG. 5 shows an example in which the degree of tracking imaging target is used as a basic determination criterion, and the imaging priority related to the type is used as an auxiliary determination criterion. Here, it is assumed that the photographing priority is set higher for "vehicle" than for "person". 5 are the same as in FIG. 4, and in FIG. 5C, as described in FIG. ” or “ID3”. In this respect, as described with reference to FIG. 4(c), the photographing priority is used to give priority to the object "ID2" whose type is "vehicle" and the object "ID3" whose type is "person". Specifically, in the example of FIG. 5(c), the tracking shooting target setting means 76 sets the object "ID2" having a high shooting priority as the tracking shooting target.

Note that when there is one detected object shown in FIG. 5(a), there is no need for selection, as in the case of FIG. 4(a). is set as a tracking shooting target. In the case of FIG. 5(b), one object can be set as the tracking/photographing target only by the degree of tracking/photographing, that is, the object "ID3" as in FIG. 4(b). That is, in this case, the tracking shooting target setting unit 76 sets the tracking shooting target without considering the shooting priority.

The monitoring device 2 using the present invention described above evaluates the degree of tracking photography for the object detected by the object detection unit 5, and when there are a plurality of detected objects, tracking photography is performed based on the degree of tracking photography. Determine the object to be detected. Specifically, as a basic configuration, the degree of tracking photography target is compared for a plurality of detected objects, and an object with the highest degree of tracking photography target is set as the tracking photography target. As a result, when a plurality of objects are detected, for example, it is possible to preferentially track and photograph an object that is more likely to be an intruder among them.

It should be noted that the present invention is not limited to the above-described embodiments, and can be modified in various ways without departing from the gist of the present invention.

For example, the evaluation means 74 may have a function of determining whether or not the moving object is an intruding object that has entered the monitoring area based on the evaluation of the feature amount of the moving object. In this case, when the size, shape, etc. of the moving object satisfy the notification criteria indicating a person or vehicle, the evaluation means 74 determines that there is an intrusion abnormality, reports the occurrence of the abnormality to the monitoring center 3, and detects the intrusion of the moving object. Perform tracking processing as an object. Then, the tracking imaging target degree for a moving object determined as an intruding object is evaluated so as to be higher than the tracking imaging target degree for a moving object not determined as an intruding object. Intruding objects are determined based on the feature values that indicate the object's size and shape, which indicate the object's likelihood of being tracked and photographed, as well as the elapsed time since the moving object was first detected, the moving distance, and the moving trajectory (moving direction, moving route, etc.). ) may be used.

In addition, the evaluation of the degree of tracking imaging that indicates the human-likeness or vehicle-likeness of a moving object and the evaluation of the degree of tracking imaging based on whether or not the moving object is determined to be an intruding object may be used together. For example, the evaluation means 74 obtains a tracking shooting target degree of "0 to 100%" for each detected moving object, and determines whether or not the moving object is an intruding object that satisfies a predetermined alarm criterion. It is possible to perform point addition and weighting processing so as to upwardly correct the tracking shooting target degree of a moving object determined to be an object.

Further, instead of directly reflecting the tracking imaging target degree, one evaluation method may be mainly used and the other may be used as an auxiliary. Specifically, the tracking shooting target setting unit 76 preferentially sets a moving object determined as an intruding object among a plurality of moving objects as a tracking shooting target. or when there are only multiple moving objects that have not been determined to be intruding objects, set the moving object with a high degree of tracking photography target calculated from the size and shape of each moving object as the tracking photography target. can do. Conversely, based on the principle of prioritizing the tracking shooting target degree obtained from the size and shape of each moving object and setting the tracking shooting target, the tracking shooting target degree "High/Medium/Low" is the highest. When there are a plurality of moving objects, a moving object determined as an intruding object to be abnormal among those moving objects may be set as a tracking photographing target.

Reference Signs List 1 monitoring system 2 monitoring device 3 monitoring center 4 monitoring area 5 object detection unit 6 imaging unit 7 control unit 51, 63, 71 communication means 52, 64, 72 storage means 53 detection means 54 Tracking means 55 Control means 61 Camera drive means 62 Imaging means 73 Camera control means 74 Evaluation means 75 Type determination means 76 Tracking object setting means.

Claims (4)

In a monitoring device for tracking and photographing a moving object in a monitoring area,
an object detection unit that detects the moving object within the monitoring area and outputs a detection result including the position of the moving object;
an imaging unit capable of changing the shooting direction;
a control unit that controls the imaging unit based on the detection result;
evaluation means for evaluating a predetermined feature amount for each of the detected moving objects to obtain a degree of tracking photography target that indicates the degree of likelihood of a tracking photography target;
When only one moving object is detected by the object detection unit, the moving object is set as a tracking photographing target regardless of the degree of the tracking photographing object, and on the other hand, when a plurality of moving objects are detected, a shooting target setting unit that preferentially sets a moving object with a high degree of tracking shooting target as a tracking shooting target;
with
The photographing object setting means is characterized in that, when the degree of tracking photographing object is the same for a plurality of moving objects, the currently moving object among the moving objects is set as the tracking photographing object . surveillance equipment. In a monitoring device for tracking and photographing a moving object in a monitoring area,
an object detection unit that detects the moving object within the monitoring area and outputs a detection result including the position of the moving object;
an imaging unit capable of changing the shooting direction;
a control unit that controls the imaging unit based on the detection result;
evaluation means for evaluating a predetermined feature amount for each of the detected moving objects to determine a degree of tracking photography target that indicates the degree of likelihood of a tracking photography target;
When only one moving object is detected by the object detection unit, the moving object is set as a tracking photographing target regardless of the degree of tracking photographing object, and when a plurality of moving objects are detected, a shooting target setting unit that preferentially sets a moving object with a high degree of tracking shooting target as a tracking shooting target;
with
The evaluation means determines whether or not the moving object is an intruding object that satisfies a predetermined alarm condition based on the feature quantity, and determines the tracking imaging target degree of the moving object when the moving object is determined to be the intruding object to be: A monitoring apparatus characterized in that the tracking imaging target degree is set to be higher than when the object is not determined to be an intruding object. 3. Each time a moving object is newly detected in the monitoring area, the photographing object setting means resets the tracking photographing object of the plurality of detected moving objects. The monitoring device according to . The evaluation means evaluates the moving object such that the closer the size of the moving object based on at least the detection result is to a predetermined standard, the higher the tracking imaging target degree is.
The monitoring device according to any one of claims 1 to 3 , characterized by:

Images