JP5983251B2 - Monitoring device and monitoring system - Google Patents

Description

  The present invention relates to a monitoring device and a monitoring system for detecting an article based on a photographed image.

  2. Description of the Related Art Conventionally, a method is known in which a road state is photographed with a camera and an obstacle on a road is detected based on a correlation value between a plurality of photographed images. In the conventional method, a correlation value is repeatedly calculated for an image sampled at regular intervals, and it is determined whether or not an obstacle is reflected in the captured image according to the change state of the correlation value. For example, a moving vehicle is shown in a region where the amount of change in the correlation value between the image taken without an obstacle is large, and an obstacle that does not move is shown in a region where the amount of change in the correlation value is small. (For example, refer to Patent Document 1).

JP 2002-24808 A

  However, since the vehicle moves at various speeds, the correlation value in the region where the vehicle is shown can vary in a wide range. Therefore, if the obstacle is an object that moves on the road, such as a blue sheet or a large cloth, the amount of change in the correlation value of the image of the area where the object is reflected changes the correlation value in the area where the vehicle appears. It may fall within the possible range. In such a case, the conventional monitoring device may misrecognize the moving object as a vehicle, and may not be recognized as a foreign object that may interfere with the traveling of the vehicle.

  Further, the correlation value between images taken at a plurality of timings may change regardless of whether an object exists. For example, when light from a headlight of an automobile traveling in an opposite lane hits a road surface, the correlation value changes even though there is no object on the road being photographed. As a result, there is a problem that a foreign object is erroneously recognized and an alarm is issued even though there is no foreign object.

  Therefore, the present invention has been made in view of these points, and an object thereof is to provide a monitoring device and a monitoring system that can detect a moving object as a foreign object.

  In order to solve the above problem, according to the first aspect of the present invention, an image acquisition unit that acquires a plurality of captured images captured at different times by an imaging unit that captures an image of an object including a vehicle traveling on a road. A detection unit that detects a direction in which an object shown in a plurality of captured images moves, and a foreign object determination unit that determines that the object is a foreign object when the direction in which the detected object moves is different from the traveling direction of the vehicle. A monitoring device is provided.

  For example, the detection unit detects at least one of the moving direction and speed of a plurality of feature points included in the object, and the foreign matter determination unit detects the direction in which at least one of the plurality of feature points moves or When the speed is different from the moving direction or speed of other feature points among the plurality of feature points, the object is determined as a foreign object. The detection unit may detect a moving direction of an object whose moving distance within a unit time is larger than a predetermined threshold as a traveling direction of the vehicle.

  The monitoring device includes a size calculation unit that calculates a size of an object indicated by at least one of a height, an area, and a volume of the object that is determined as a foreign object by the foreign object determination unit, and an object that is calculated by the size calculation unit And a risk level calculation unit that calculates a risk level indicating the level of danger given to the vehicle.

  According to a second aspect of the present invention, there is provided a monitoring system including a monitoring device having a photographing unit that captures an image of an object including a vehicle traveling on a road, and a data management device that receives an image from the monitoring device. The detection unit detects the moving direction of the object shown in the plurality of images taken by the shooting unit, and determines that the object is a foreign object when the detection unit detects that the object is moving in a direction different from the traveling direction of the vehicle. There is provided a monitoring system further comprising a foreign matter determination unit.

  The monitoring system may include a plurality of monitoring devices, and each monitoring device may further include a transmission / reception unit that transmits foreign object information indicating that the foreign object determination unit determines that the foreign object is determined to be a foreign object to an adjacent monitoring device.

  According to the present invention, it is possible to detect a moving object as a foreign object.

1 shows a configuration example of a monitoring system according to a first embodiment. An example of usage of the monitoring system according to the first embodiment is shown. The example of installation in the road of the monitoring apparatus of 1st Embodiment is shown. 1 shows a configuration example of a monitoring apparatus according to a first embodiment. The position coordinate in a picked-up image is shown. An example of the movement vector of the some feature point in a vehicle is shown. An example of the movement vector of the some feature point in a foreign material is shown. An example of the relationship between the position coordinate of a picked-up image and the position on a road is shown. The structure of the monitoring system which concerns on 2nd Embodiment is shown.

<First Embodiment>
[Basic configuration of the monitoring system 10]
FIG. 1 shows a configuration example of a monitoring system 10 according to the first embodiment. FIG. 2 shows an example of how the monitoring system 10 according to the first embodiment is used. FIG. 3 shows an installation example of the monitoring device 100 on a road. As an example, the monitoring device 100 is installed at regular intervals along the road, and images a vehicle traveling on the road from above the road.

  The monitoring system 10 includes, for example, a plurality of monitoring devices 100 (monitoring device 100-1, monitoring device 100-2,..., Monitoring device 100-n, where n is a natural number of 3 or more) connected in a daisy chain. And a data management device 200 connected to the monitoring device 100. The data management device 200 is a server, for example. A plurality of monitoring devices 100 are connected by a communication line 50. The communication line 50 is an 8-core cable for LAN (local area network), for example.

  The monitoring system 10 may include a hub 300 between the data management device 200 and the monitoring device 100-1. Each monitoring device 100 may be connected to the data management device 200 via the hub 300. The monitoring system 10 may include a plurality of groups of a plurality of monitoring devices 100 connected to the hub 300. The monitoring system 10 may include a monitor 400 that displays an image captured by the monitoring device 100 (hereinafter referred to as a captured image).

[Configuration Example of Monitoring Device 100 that Detects Foreign Objects]
FIG. 4 shows a configuration example of the monitoring apparatus 100. The monitoring device 100 includes a control unit 110, a storage unit 120, an imaging unit 130, an image acquisition unit 140, and a transmission / reception unit 150. The control unit 110 is, for example, a microprocessor that detects a foreign object by analyzing an image captured by the control unit 110 by executing a program stored in the storage unit 120. The control unit 110 may display that the foreign object has been detected on the display unit, or may notify the other monitoring device 100 and the data management device 200 through the transmission / reception unit 150 that the foreign object has been detected.

  The storage unit 120 is a storage medium that stores a program for operating the control unit 110 and data generated during the operation of the control unit 110. The storage unit 120 includes, for example, at least one of a ROM and a RAM. The storage unit 120 may be a storage medium built in the monitoring apparatus 100 or a removable storage medium.

  The imaging unit 130 has a lens and a CCD (charge coupled device) and captures an image of an object including a vehicle traveling on a road. The image acquisition unit 140 acquires a plurality of captured images captured by the imaging unit 130 at different times. For example, the image acquisition unit 140 may acquire an image signal output from the photographing unit 130 and input a digital image generated by analog / digital conversion of the acquired image signal to the control unit 110.

  The transmission / reception unit 150 transmits to the data management device 200 that the control unit 110 has detected a foreign object, and receives various types of information from the data management device 200. The transmission / reception unit 150 may transmit / receive data to / from another monitoring device 100 connected in a daisy chain. For example, the transmission / reception unit 150 of the monitoring device 100-2 receives an image from the transmission / reception unit 150 of the adjacent monitoring device 100-3 and transmits the image to the data management device 200 via the transmission / reception unit 150 of the monitoring device 100-1. .

  The control unit 110 includes a detection unit 112, a foreign matter determination unit 114, a size calculation unit 116, and a risk level calculation unit 118. The control unit 110 may function as the detection unit 112, the foreign matter determination unit 114, the size calculation unit 116, and the risk level calculation unit 118 by executing a program.

  The detection unit 112 detects a direction in which an object shown in a plurality of images captured by the imaging unit 130 moves. The detection unit 112 may detect the direction in which the object moves. For example, the detection unit 112 acquires a plurality of images captured by the imaging unit 130 every predetermined time, and detects the direction in which the position of the object shown in the plurality of images changes, thereby moving the object and Detect at least one of the orientations. The detection unit 112 may detect the moving speed of the object based on the amount of change in the position coordinates of the object in a plurality of images taken every predetermined time.

  FIG. 5 shows position coordinates in the captured image. An X axis is provided in a direction parallel to the traveling direction of the vehicle in the captured image, and a Y axis is provided in a direction perpendicular to the X axis. When the resolution of the captured image is, for example, XGA (number of pixels: 1024 × 768), the maximum value of coordinates on the X axis is 1024, and the maximum value of coordinates on the Y axis is 768. In this specification, the position coordinates of an object whose position on the X-axis is x and whose position on the Y-axis is y are expressed as (x, y). For example, the position coordinates of an object shown in the center of a 1024 × 768 captured image is represented as (512, 384).

  When the object at the position coordinate (x1, y1) in the captured image at the first time t1 moves to the position coordinate (x2, y2) in the captured image at the second time t2, the detection unit 112 Is calculated as (x2-x1, y2-y1). The detection unit 112 calculates the moving speed of the object by dividing the distance between the position coordinates by the time difference t2-t1 when a plurality of captured images are captured.

  Specifically, the detection unit 112 extracts feature points of the object in the first image, and generates position coordinates of the feature points in the first image. An object feature point is, for example, a position where the direction of the contour changes or the brightness changes like the corner of the object.

  Next, the detection unit 112 detects the feature points of the object extracted from the first image in the second image taken after a predetermined time has elapsed from the first image. For example, the detection unit 112 extracts an image of an area where the correlation value with the image of the area surrounded by the outline of the object extracted in the first image is larger than a predetermined threshold, and based on the outline of the extracted image To detect feature points. The detection unit 112 calculates the position coordinates of the detected feature points.

  Subsequently, the detection unit 112 calculates a feature point movement vector by subtracting the value of the feature point position coordinate detected in the first image from the value of the feature point position coordinate detected in the second image. . For example, when the position coordinates of feature points in the first image are represented by (100, 100) and the position coordinates of feature points in the second image are represented by (100, 150), the movement vector is ( 50, 0), indicating that the feature point has moved by 50 pixels in the Y-axis direction.

  The detection unit 112 may detect the direction in which the vehicle moves. For example, the detection unit 112 detects a moving direction of an object whose moving distance within a unit time is larger than a predetermined threshold as the traveling direction of the vehicle. The detection unit 112 may detect a moving direction of a plurality of objects whose movements are detected within a predetermined time, and a direction in which more objects move than a predetermined ratio among the plurality of objects may be set as a traveling direction of the vehicle.

  The foreign object determination unit 114 determines that the object is a foreign object when the moving direction of the object is different from the traveling direction of the vehicle. The foreign object determination unit 114 may determine that the object is a foreign object when the direction in which the object moves differs from the direction in which the vehicle travels. The foreign matter determination unit 114 may perform determination using a movement vector indicating the traveling direction of the vehicle stored in the storage unit 120 in advance, or may determine using the traveling direction of the vehicle detected by the detection unit 112.

  For example, when the X-axis direction in the image is the traveling direction of the vehicle, the foreign matter determination unit 114 moves the object in a different direction beyond the variation range of the traveling direction of the vehicle with respect to the X-axis direction. The object is determined to be a foreign object. Specifically, when the road is reflected in the X-axis direction of the image, it is considered that the vehicle travels in a direction within a range of ± 30 ° in the X-axis direction even if the lane change occurs. . Accordingly, the foreign object determination unit 114 determines that the object is a foreign object when the direction of the movement vector of the feature point of the object is not within the range of ± 30 ° from the X-axis direction.

  The foreign object determination unit 114 may determine that the object is a foreign object when the difference between the moving speed of the object and the average speed of the plurality of vehicles detected around the object is greater than a predetermined amount. For example, when the average speed of two vehicles detected before and after the object detected by the detection unit 112 is 50 km / h and the moving speed of the object is 5 km / h or less, the foreign matter determination unit 114 detects It is determined that the object is a foreign object.

[Judge based on multiple feature points]
FIG. 6A shows an example of movement vectors of a plurality of feature points in the vehicle. FIG. 6B shows an example of movement vectors of a plurality of feature points in a foreign object. When the photographed object is a vehicle, the plurality of feature points move at the traveling speed of the vehicle. Therefore, the movement vectors of the plurality of feature points in the vehicle have substantially the same direction and size as shown in FIG. 6A. On the other hand, when the photographed object is a sheet-like object, the plurality of feature points move at random, so that the movement vectors of the feature points have different directions and sizes as shown in FIG. 6B. Have

  Therefore, the monitoring apparatus 100 may detect a foreign object based on a plurality of feature points. Specifically, the detection unit 112 detects at least one of the moving direction and speed of a plurality of feature points included in the object. The foreign object determination unit 114 determines that the object is a foreign object when the direction or speed of movement of at least one feature point of the plurality of feature points is different from the direction or speed of movement of other feature points of the plurality of feature points. Is determined. The monitoring device 100 may display that a foreign object has been detected based on a plurality of feature points, or may notify another monitoring device 100 or the data management device 200.

  For example, the detection unit 112 detects a plurality of corners of the object as a plurality of feature points, and calculates a movement vector of each feature point based on a plurality of images taken at different times. The foreign matter determination unit 114 determines that the object is a vehicle when all the movement vectors calculated by the detection unit 112 have substantially the same direction and size. The foreign object determination unit 114 determines that the object is a foreign object when the movement vectors having different directions or sizes are included in the plurality of movement vectors. In order to increase the accuracy of the determination, the foreign matter determination unit 114 detects the object when the moving speeds of the plurality of feature points are within a predetermined range and at least some of the plurality of feature points move in different directions. May be determined as a foreign object.

  As described above, when the monitoring apparatus 100 detects a foreign object based on a plurality of feature points in the object, it is possible to detect a foreign object that changes its shape like a blue sheet with high accuracy. Furthermore, by displaying that there is a foreign object whose shape changes, it is possible to call attention to the driver or the road manager.

[Detecting the movement of an object by associating position coordinates with a position on the road]
FIG. 7 shows an example of the relationship between the position coordinates of the captured image and the position on the road. When the monitoring device 100 is installed at the end of the road, as shown in FIG. 7, the length on the road per pixel differs depending on the position in the captured image. Therefore, it is preferable that the detection unit 112 calculates the direction, orientation, or speed of the object based on the relationship between the position coordinates and the position on the road.

  The trapezoid shown in FIG. 7 indicates an area on the road that is reflected in the image captured by the imaging unit 130. The points A, B, C, D, E, and F on the boundary line of the photographed area are the position coordinates (0, 0), (0, 384), (0, 768), (1024, 0), respectively. , (1024, 384), (1024, 768).

  In the example of FIG. 7, it can be seen that the distance between AD is 5 m and the distance between CFs is 10 m, and the actual length per pixel in the X-axis direction varies depending on the position in the Y-axis direction. Similarly, although the number of pixels between AB and the number of pixels between BC are equal, the actual distance between AB is shorter than the distance between BC. Thus, the actual length per pixel in the Y-axis direction also varies depending on the position in the Y-axis direction. The storage unit 120 may store the relationship between the position coordinates in the captured image and the actual position on the road.

  The detection unit 112 calculates the direction, direction, or speed in which the object moves based on the relationship between the position coordinates and the actual position on the road. The detection unit 112 may use the relationship between the position information stored in the storage unit 120 and the actual position, and based on the horizontal position and the vertical position with respect to the road where the monitoring device 100 is installed, The actual position on the road with respect to the position coordinates may be calculated.

  As described above, even if the monitoring device 100 is installed obliquely above the road by detecting the movement of the object by associating the position coordinates with the position on the road, the object It is possible to detect the direction and speed of the movement with high accuracy. As a result, the monitoring apparatus 100 can detect a foreign object with high accuracy.

[Calculate the size of the foreign object]
The monitoring device 100 may calculate the size of the foreign matter and display or report according to the size of the foreign matter. Based on the image acquired from the image acquisition unit 140, the size calculation unit 116 calculates the size of the object indicated by at least one of the height, area, and volume of the object determined by the foreign object determination unit 114 as a foreign object. .

  The size calculation unit 116 calculates, for example, the height of the highest position on the contour line of the object determined as a foreign object as the height of the object. When the object is deformed like a blue sheet, the size calculation unit 116 sets the height of the highest position in the deformed state as the height of the object. It is preferable that the size calculation unit 116 calculates the height by using a stereoscopic image captured by the imaging unit 130 having a plurality of lenses.

  The size calculation unit 116 calculates the area when the object is viewed from above based on the position coordinates of a plurality of feature points on the contour line of the object. For example, the size calculation unit 116 calculates the position of each feature point on the road based on a table indicating the relationship between the position coordinates and the distance from the reference position on the road, and calculates the position on the road. Based on this, the area is calculated. The size calculator 116 calculates the volume of the object based on the calculated height and area.

  The risk level calculation unit 118 calculates a risk level indicating the level of danger given to the vehicle based on the size of the object calculated by the size calculation unit 116. The risk level calculation unit 118 compares the height, area, and volume with threshold values, for example, if the height, area, and volume are clearly dangerous, the risk level 3 may be dangerous. Assume that the risk level is 2 and the risk level is low.

  The control unit 110 may notify the other monitoring device 100 and the data management device 200 when the risk calculated by the risk calculation unit 118 satisfies a predetermined condition. For example, when at least one of height, area, and volume has a degree of danger greater than 2, the control unit 110 displays a danger or notifies the data management apparatus 200 that there is a dangerous foreign object. To do.

  The risk level calculation unit 118 may calculate information indicating the overall risk level based on information indicating the risk level set in advance according to the height, area, and volume values of the object. Specifically, the risk level calculation unit 118 sets the overall risk level to 3 × 2 when the risk level based on the height is 3, the risk level based on the area is 2, and the risk level based on the volume is 2. X2 = 12. The control unit 110 may display a danger or notify the data management apparatus 200 that there is a dangerous foreign object when the total risk value is larger than a threshold value.

  As described above, the monitoring device 100 calculates the size of the foreign matter, and displays or reports information according to the size, thereby alerting the driver and the road manager.

[Detect the direction in which the object moves after the vehicle passes]
When an object to be detected as a foreign object has a thin shape like a blue sheet, the vehicle may pass over the object. Since the object does not move while the vehicle passes over the object, the detection unit 112 cannot detect the moving direction. Therefore, the detection unit 112 may detect the direction in which the object moves after the vehicle passes the position of the object whose direction is to be detected.

  Specifically, after detecting an object that moves at a predetermined speed or more, the detection unit 112 detects a moving direction of the object that is reflected in the image that is captured after the object is not reflected in the image. . For example, when the monitoring device 100 is installed along a road where most vehicles travel at a speed of 20 km / h or more, the detection unit 112 detects that a vehicle moving at a speed of 20 km / h or more is reflected in the image. The direction in which the object moves is detected based on the position coordinates of the object in a plurality of images taken after a predetermined time has elapsed.

  The sheet-like foreign matter that has floated immediately after the vehicle has passed may become stuck to the ground when time passes after the vehicle passes. In a state where the sheet-like foreign matter is stuck on the ground, the risk level calculation unit 118 cannot accurately calculate the risk level of the sheet-like foreign matter. Therefore, it is preferable that the detection unit 112 detects the direction in which the object moves before a predetermined time elapses after the vehicle passes the position of the object whose direction is to be detected.

  As described above, when the monitoring device 100 detects a foreign substance within a predetermined period after the vehicle passes, it becomes easy to detect a sheet-like foreign substance that is attached to the road or floats.

[Notify other monitoring device 100 that foreign matter has been detected]
When the foreign object determination unit 114 determines that the object detected by the detection unit 112 is a foreign object, the control unit 110 may notify the other monitoring device 100 that the foreign object has been detected. For example, when the foreign matter determination unit 114 of the monitoring device 100-2 detects a foreign matter moving toward the position where the monitoring device 100-1 is installed, the monitoring device 100-2 detects that the foreign matter is a monitoring device. The monitoring device 100-1 is informed that it is moving toward 100-1.

  When the monitoring device 100-1 receives a notification regarding a foreign object, the foreign material determination unit 114 of the monitoring device 100-1 may change a reference for determining whether the object detected by the detection unit 112 is a foreign material. For example, the foreign matter determination unit 114 normally determines that an object moving in a direction different from the traveling direction of the vehicle is a foreign matter, and receives a notification about the foreign matter from the adjacent monitoring device 100, the direction of movement is determined. First, the foreign object is determined based on at least one of the moving speed and shape of the object. By determining whether or not the object is a foreign object based on information from the other monitoring devices 100, the foreign object determination unit 114 can quickly detect the presence of the foreign object.

<Second Embodiment>
[Monitoring system 10 in which the data management apparatus 200 detects a foreign object]
FIG. 8 shows a configuration of the monitoring system 10 according to the second embodiment. A monitoring system 10 according to the present embodiment includes a monitoring device 100 having a photographing unit 130 that captures an image of an object including a vehicle traveling on a road, and a data management device that detects foreign matter based on an image received from the monitoring device 100. 200.

  The monitoring device 100 includes a control unit 110, a photographing unit 130, and a transmission / reception unit 150. The data management apparatus 200 includes a control unit 210, a storage unit 220, an image acquisition unit 240, and a transmission / reception unit 250. The control unit 210, the storage unit 220, and the image acquisition unit 240 correspond to the control unit 110, the storage unit 120, and the image acquisition unit 140 illustrated in FIG. The control unit 110 includes a detection unit 212, a foreign object determination unit 214, a size calculation unit 216, and a risk level calculation unit 218 corresponding to the detection unit 112, the foreign object determination unit 114, the size calculation unit 116, and the risk level calculation unit 118. .

  The transmission / reception unit 250 transmits / receives data to / from the transmission / reception unit 150 of the monitoring apparatus 100. For example, the transmission / reception unit 250 transmits a message for controlling the plurality of monitoring devices 100 and receives images taken by the plurality of monitoring devices 100. The transmission / reception unit 250 inputs the received image to the image acquisition unit 240.

  As described above, in the monitoring system 10, the monitoring device 100 detects the foreign matter based on the image acquired from the monitoring device 100 by the data management device 200, so that the monitoring device 100 detects the detection unit 112, the foreign matter determination unit 114, the size calculation unit 116, and Even if the risk calculation unit 118 is not provided, a foreign object can be detected. Further, when the data management apparatus 200 detects a foreign object based on a plurality of images acquired from the plurality of monitoring apparatuses 100, the monitoring system 10 grasps the shape of the foreign object and the state of movement in detail, and the driver and the road Appropriate information can be provided to the administrator of

  As mentioned above, although this invention was demonstrated using embodiment, the technical scope of this invention is not limited to the range as described in the said embodiment. It will be apparent to those skilled in the art that various modifications or improvements can be added to the above-described embodiment. For example, even if the monitoring device 100 has some of the detection unit 112, the foreign matter determination unit 114, the size calculation unit 116, and the risk calculation unit 118 and the data management device 200 has the other part, There exists an effect equivalent to said embodiment. It is apparent from the scope of the claims that the embodiments added with such changes or improvements can be included in the technical scope of the present invention.

DESCRIPTION OF SYMBOLS 10 ... Monitoring system, 50 ... Communication line, 100 ... Monitoring apparatus, 110 ... Control part, 112 ... Detection part, 114 ... Foreign substance determination part, 116 ... Calculation part, 118 ... Risk level calculation unit, 120 ... Storage unit, 130 ... Imaging unit, 140 ... Image acquisition unit, 150 ... Transmission / reception unit, 200 ... Data management device, 210 ... Control unit 212... Detection unit 214 214 foreign matter determination unit 216 calculation unit 218 risk level calculation unit 220 storage unit 240 image acquisition unit 250 ... Transmission / reception unit, 300 ... Hub, 400 ... Monitor

Claims (6)

An image acquisition unit that acquires a plurality of captured images captured at different times by an imaging unit that captures an image of an object including a vehicle traveling on a road;
A detection unit for detecting at least one of a moving direction and a speed of a plurality of feature points included in an object shown in the plurality of captured images;
The direction in which the feature point of the object moves is different from the predetermined traveling direction of the vehicle , and the direction or speed at which at least one of the feature points moves is the plurality of feature points. And a foreign substance determination unit that determines the object as a foreign object when the other feature point is different from the moving direction or speed . The monitoring device according to claim 1, wherein the detection unit detects a moving direction of an object whose moving distance within a unit time is larger than a predetermined threshold as a traveling direction of the vehicle. A size calculation unit that calculates the size of the object indicated by at least one of the height, area, and volume of the object that the foreign object determination unit determines to be the foreign object;
The monitoring apparatus according to claim 1, further comprising: a risk level calculation unit that calculates a risk level indicating a level of danger given to the vehicle based on the size of the object calculated by the size calculation unit. . The detection unit is in a state in which the object moving at a predetermined speed or higher is not reflected in the image after a predetermined time has elapsed since the object moving at a predetermined speed or higher has been detected. The monitoring device according to any one of claims 1 to 3, wherein a direction in which an object shown in the image taken from the side moves is detected . A monitoring device having a photographing unit for photographing an image of an object including a vehicle traveling on a road;
A monitoring system comprising: a data management device that receives the image from the monitoring device;
A detection unit for detecting at least one of a moving direction and a speed of a plurality of feature points included in an object captured in the plurality of images captured by the imaging unit;
The feature point of the object is moving in a direction different from the traveling direction of the vehicle specified in advance , and the moving direction or speed of at least one feature point of the plurality of feature points is that of the plurality of feature points. A monitoring system further comprising: a foreign substance determination unit that determines that the object is a foreign object when the detection unit detects that the other feature point is different from a moving direction or speed . Comprising a plurality of the monitoring devices;
The monitoring system according to claim 5, wherein each of the monitoring devices further includes a transmission / reception unit that transmits foreign object information indicating that the foreign object determination unit determines the foreign object to the adjacent monitoring device.

Images