MOBILE OBJECT MONITORING DEVICE, MOBILE OBJECT MONITORING METHOD, AND PROGRAM

Abstract

To determine the presence / absence of a lane change with higher accuracy.SOLUTION: A moving body monitoring device comprises: an acquisition unit that acquires off-set information indicating a distance between a moving body and a road division line recognized on the basis of an image captured by a camera mounted on the moving body, attitude information based on a detection value of a yaw rate sensor or a direction sensor mounted on the moving body, and speed information indicating a speed of the moving body; and a determination unit that determines whether or not the moving body has changed a lane on the basis of at least one of the off-set information and the attitude information. The determination unit determines whether or not the moving body has changed the lane by preferentially using the off-set information as the speed increases.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a mobile object monitoring device, a mobile object monitoring method, and a program. [Background technology]

[0002] Conventionally, there is known a lane determination device that determines the driving lane of a vehicle traveling on a road with multiple lanes in each direction, the lane determination device comprising: an imaging means for imaging the road; a lane line recognition means for recognizing lane lines from an image captured by the imaging means; a first trajectory calculation means for calculating a trajectory of the vehicle by repeatedly calculating the distance from the lane line recognized by the lane line recognition means to the imaging means; a second trajectory calculation means for calculating the trajectory of the vehicle based on autonomous navigation; a third trajectory calculation means for calculating the trajectory of the vehicle based on the first trajectory calculated by the first trajectory calculation means and the second trajectory calculated by the second trajectory calculation means; and a driving lane determination means for determining the lane in which the vehicle is traveling based on the third trajectory calculated by the third trajectory calculation means. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 4832489 Summary of the Invention [Problem to be solved by the invention]

[0004] In actual traffic situations, there may be cases where road dividing lines cannot be accurately recognized due to traffic conditions. In such cases, the above-mentioned conventional technology may not be able to accurately determine whether or not a lane change is occurring.

[0005] The present invention has been made in consideration of the above circumstances, and one of its objectives is to provide a moving object monitoring device, a moving object monitoring method, and a program that are capable of more accurately determining whether or not a lane change is occurring. [Means for solving the problem]

[0006] A moving object monitoring device, a moving object monitoring method, and a program according to the present invention employ the following configuration. (1): A mobile object monitoring device according to one embodiment of the present invention includes an acquisition unit that acquires offset information indicating a distance between the mobile object and a road dividing line recognized based on an image captured by a camera mounted on the mobile object, attitude information based on a detection value of a yaw rate sensor or an orientation sensor mounted on the mobile object, and speed information indicating the speed of the mobile object, and a determination unit that determines whether the mobile object has changed lanes based on at least one of the offset information and the attitude information, and the determination unit is more likely to use the offset information preferentially to determine whether the mobile object has changed lanes the higher the speed is.

[0007] (2): In the above aspect (1), the judgment unit judges whether or not the moving body has changed lanes based on the offset information when the speed is equal to or greater than a first threshold, and judges whether or not the moving body has changed lanes based on the attitude information when the speed is less than the first threshold.

[0008] (3) A moving body monitoring device according to another aspect of the present invention includes an acquisition unit that acquires offset information indicating the distance between the moving body and a road dividing line recognized based on an image captured by a camera mounted on the moving body, attitude information based on the detection value of a yaw rate sensor or an orientation sensor mounted on the moving body, and vehicle-to-vehicle distance information indicating the vehicle-to-vehicle distance between the moving body and a preceding moving body traveling immediately before the moving body in the same lane as the moving body, and a determination unit that determines whether the moving body has changed lanes based on at least one of the offset information and the attitude information, and the determination unit is configured to use the offset information preferentially to determine whether the moving body has changed lanes the longer the vehicle-to-vehicle distance is.

[0009] (4): In the above aspect (3), when the vehicle-to-vehicle distance is equal to or greater than a second threshold, the judgment unit judges whether or not the moving body has changed lanes based on the offset information, and when the vehicle-to-vehicle distance is less than the second threshold, the judgment unit judges whether or not the moving body has changed lanes based on the posture information.

[0010] (5): In the above aspect (1), the acquisition unit further acquires vehicle-to-vehicle distance information indicating the vehicle-to-vehicle distance between the moving body and a preceding moving body traveling immediately before the moving body in the same lane as the moving body, and the determination unit determines whether the moving body has changed lanes by using the offset information preferentially the higher the speed and the longer the vehicle-to-vehicle distance.

[0011] (6): In the above aspect (5), the judgment unit judges whether or not the moving body has changed lanes based on the offset information when the speed is equal to or greater than a first threshold and the vehicle-to-vehicle distance is equal to or greater than a second threshold, and judges whether or not the moving body has changed lanes based on the attitude information when the speed is less than the first threshold or the vehicle-to-vehicle distance is less than the second threshold.

[0012] (7): In any of the above aspects (1) to (6), the acquisition unit further acquires weather information indicating the weather in a location where the moving body is located, and when the weather is bad, the determination unit determines whether or not the moving body has changed lanes by increasing the degree of utilization of the attitude information compared to when the weather is not bad.

[0013] (8): In any of the above aspects (1) to (7), the acquisition unit further acquires curvature information regarding the curvature of the road on which the moving body is located, and when the curvature is equal to or greater than a third threshold, the determination unit determines whether or not the moving body has changed lanes by making greater use of the offset information than when the curvature is less than the third threshold.

[0014] (9): In any of the above aspects (1) to (8), the acquisition unit further acquires accuracy information regarding the recognition accuracy of the road dividing line, and when the recognition accuracy is less than a fourth threshold, the determination unit determines whether or not the moving body has changed lanes by increasing the degree of utilization of the posture information compared to when the recognition accuracy is equal to or greater than the fourth threshold.

[0015] (10): In any of the above aspects (1) to (9), the acquisition unit is installed at a location away from the mobile body, and acquires each piece of information through communication with a communication device mounted on the mobile body.

[0016] (11): In any one of the above aspects (1) to (9), the acquisition unit is mounted on the moving body and acquires the information by intra-moving body communication.

[0017] (12): In another aspect of the mobile object monitoring method of the present invention, a computer acquires offset information indicating the distance between the mobile object and a road dividing line recognized based on an image captured by a camera mounted on the mobile object, attitude information based on the detection value of a yaw rate sensor or an orientation sensor mounted on the mobile object, and speed information indicating the speed of the mobile object, and determines whether the mobile object has changed lanes based on at least one of the offset information and the attitude information, and when making the determination, the higher the speed, the more the offset information is used preferentially to determine whether the mobile object has changed lanes.

[0018] (13): A program according to another aspect of the present invention causes a computer to acquire offset information indicating a distance between a moving body and a road dividing line recognized based on an image captured by a camera mounted on the moving body, attitude information based on a detection value of a yaw rate sensor or an orientation sensor mounted on the moving body, and speed information indicating the speed of the moving body, and determines whether or not the moving body has changed lanes based on at least one of the offset information and the attitude information, and, when making the determination, the higher the speed, the more the offset information is used preferentially to determine whether or not the moving body has changed lanes.

[0019] (14): A method for monitoring a moving object according to another aspect of the present invention is one in which a computer acquires offset information indicating the distance between the moving object and a road dividing line recognized based on an image captured by a camera mounted on the moving object, attitude information based on the detection value of a yaw rate sensor or an orientation sensor mounted on the moving object, and vehicle-to-vehicle distance information indicating the vehicle-to-vehicle distance between the moving object and a preceding moving object traveling immediately before the moving object in the same lane as the moving object, and determines whether the moving object has changed lanes based on at least one of the offset information and the attitude information, and when making the determination, the longer the vehicle-to-vehicle distance, the more the computer uses the offset information to determine whether the moving object has changed lanes.

[0020] (15): A program according to another aspect of the present invention causes a computer to acquire offset information indicating the distance between a moving body and a road dividing line recognized based on an image captured by a camera mounted on the moving body, attitude information based on the detection value of a yaw rate sensor or an orientation sensor mounted on the moving body, and vehicle-to-vehicle distance information indicating the vehicle-to-vehicle distance between the moving body and a preceding moving body traveling immediately before the moving body in the same lane as the moving body, and determines whether the moving body has changed lanes based on at least one of the offset information and the attitude information, and when making the determination, the longer the vehicle-to-vehicle distance, the more the offset information is used preferentially to determine whether the moving body has changed lanes. Effect of the Invention

[0021] According to aspects (1) to (15), the presence or absence of a lane change can be determined more accurately. [Brief description of the drawings]

[0022] [Figure 1] FIG. 1 is a diagram showing an example of a usage environment of a mobile object monitoring device 100 according to each embodiment. [Diagram 2] 2 is a diagram showing an example of the configuration of a target vehicle M. [Diagram 3] 1 is a diagram illustrating an example of a configuration of a moving object monitoring device 100. [Figure 4] 13 is a diagram showing an example of an image captured by the camera 10 when the speed of the target vehicle M is low. FIG. [Diagram 5] 13 is a diagram showing an example of an image captured by the camera 10 when the speed of the target vehicle M is high. [Figure 6] 4 is a flowchart showing an example of a flow of processing executed by the moving object monitoring device 100 of the first embodiment. [Figure 7] 10 is a flowchart showing an example of a flow of processing executed by a moving object monitoring device 100 of the second embodiment. [Figure 8] 13 is a flowchart showing an example of a flow of processes executed by a moving object monitoring device 100 of the third embodiment. [Figure 9] FIG. 11 is a diagram showing an example of the configuration of a moving object monitoring device 100A according to a second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0023] Hereinafter, an embodiment of a mobile object monitoring device, a mobile object monitoring method, and a program of the present invention will be described with reference to the drawings. A mobile object in the present invention is a four-wheeled vehicle, a two-wheeled vehicle, micromobility, a robot, etc. In the following description, the mobile object is assumed to be a four-wheeled vehicle.

[0024] [Overall configuration] FIG. 1 is a diagram showing an example of a usage environment of a mobile object monitoring device 100 according to each embodiment. The mobile object monitoring device 100 is installed at a location away from the target vehicle and communicates with the target vehicle. In FIG. 1, two target vehicles, target vehicle M(1) and target vehicle M(2), are shown, and the road division lines (described later) recognized by the target vehicle M(1) are indicated as CL-1 and CL-2. The arrows in the figure indicate the traveling direction of each vehicle. In this way, the mobile object monitoring device 100 acquires information from target vehicles, of which a plurality of vehicles may exist at the same time, and determines whether the target vehicle has changed lanes. Hereinafter, when there is no need to distinguish which target vehicle or leading vehicle it is, the symbols after the parentheses will be omitted and the vehicle will be expressed as "target vehicle M" and "leading vehicle mA". The target vehicle M is an example of a "moving object", and the leading vehicle mA is an example of a "leading moving object". The leading vehicle mA is a vehicle that is on the same lane as the target vehicle M and immediately before the target vehicle M, and "immediately before" means that there is no other vehicle between them. The target vehicle M accesses the network NW by wireless communication and communicates with the mobile object monitoring device 100. The network NW includes a wide area network (WAN) such as the Internet and a local area network (LAN). The determination result of the mobile object monitoring device 100 is used for creating a map or for monitoring the traffic volume for each lane, but there is no restriction on this point, and the determination result of the mobile object monitoring device 100 may be used for any purpose.

[0025] First Embodiment [Target vehicle] 2 is a diagram showing an example of the configuration of a target vehicle M. The target vehicle M may be a manually driven vehicle or an autonomous vehicle. The target vehicle M is equipped with, for example, a camera 10, an image recognition device 12, a vehicle sensor 20, a radar device 30, a GPS (Global Positioning System) receiver 40, and a communication device 50.

[0026] The camera 10 is a digital camera using a solid-state imaging element such as a CCD (Charge Coupled Device) or a CMOS (Complementary Metal Oxide Semiconductor). The camera 10 is attached to any location capable of capturing an image of the area in front of the target vehicle M, such as an upper portion of the front windshield or a rear-view mirror. The camera 10 captures an image of the area in front of the target vehicle M in a repeated, periodic manner, for example.

[0027] The image recognition device 12 recognizes the position of the road dividing line in the captured image based on the captured image of the camera. Then, through conversion processing between the position in the captured image plane and the position in the imaginary plane viewed from above, the image recognition device derives the distance between the representative point of the target vehicle M and the road dividing line. The representative point of the target vehicle M is defined arbitrarily, such as the center of gravity, the center of the front end, the left and right ends of the front end, the center of the rear wheel axle, etc. Since there are usually two road dividing lines on the left and right of the vehicle, the image recognition device may derive the distance from each road dividing line. The image recognition device 12 may derive the recognition accuracy (likelihood, reliability) in the recognition processing of the road dividing line by itself, and output accuracy information indicating the recognition accuracy. The image recognition device 12 may be a function of a control device that performs vehicle control such as automatic driving control. Since various methods are publicly known, detailed explanations of the processing of the image recognition device 12 will be omitted.

[0028] The vehicle sensor 20 includes a yaw rate sensor that detects the angular velocity of the target M around the vertical axis, a direction sensor that detects the attitude of the target vehicle relative to a reference plane (a plane assumed to be a horizontal plane), a speed sensor that detects speed, and an acceleration sensor that detects acceleration.

[0029] The radar device 30 emits radio waves such as millimeter waves ahead of the target vehicle M, and detects radio waves (reflected waves) reflected by the object to detect at least the position (distance and direction) of the object. The radar device 30 may detect the position and speed of the object by an FM-CW (Frequency Modulated Continuous Wave) method. The radar device 30 detects and outputs the inter-vehicle distance between the leading vehicle mA and the target vehicle M. The function of detecting and outputting the inter-vehicle distance may be realized by the camera 10 and the image recognition device 12.

[0030] The GPS receiver 40, based on signals received from GPS satellites, identifies the position of the target vehicle M. Instead of the GPS receiver 40, the target vehicle M may be equipped with another type of GNSS (Global Navigation Satellite System) receiver.

[0031] The communication device 50 acquires (1) offset information indicating the distance from the road dividing line derived by the image recognition device 12 and accuracy information regarding the recognition of the road dividing line, (2) attitude information based on the detection value of the yaw rate sensor or the direction sensor, (3) speed information indicating the speed detected by the speed sensor, (4) position information of the target vehicle M, etc. from each of the above components, and transmits the acquired information to the mobile object monitoring device 100 via the network NW. The communication device 50 may acquire information from each of the above components via various control devices.

[0032] [Mobile monitoring device] 3 is a diagram showing an example of the configuration of the mobile object monitoring device 100. The mobile object monitoring device 100 includes, for example, a communication unit 110, an acquisition unit 120, a determination unit 130, and a storage unit 150. The determination unit 130 includes a first determination unit 132 and a second determination unit 134. The acquisition unit 120 and the determination unit 130 are each realized by, for example, a hardware processor such as a CPU (Central Processing Unit) executing a program (software). Some or all of these components may be realized by hardware (including circuitry) such as an LSI (Large Scale Integration), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or a GPU (Graphics Processing Unit), or may be realized by cooperation between software and hardware. The program may be stored in advance in a storage device (a storage device equipped with a non-transient storage medium) such as a hard disk drive (HDD) or flash memory, or may be stored in a removable storage medium (non-transient storage medium) such as a DVD or CD-ROM, and installed by inserting the storage medium into a drive device. The storage unit 150 stores, for example, map information 152. The map information 152 represents roads in the form of nodes and links, and further describes lane information, curvature information, gradient information, and the like, associated with the links.

[0033] The communication unit 110 is a communication interface such as a network card for accessing the network NW.

[0034] The acquisition unit 120 acquires various information from the target vehicle M via the communication unit 110 and stores the information in a working memory such as a RAM (Random Access Memory). The acquisition unit 120 may also acquire weather information at the position of the target vehicle M from a server (not shown) that distributes weather information. The weather information may be acquired by receiving, from the target vehicle M, detection values ​​of a rainfall sensor or an illuminance sensor provided on the target vehicle M. The acquisition unit 120 may refer to map information 152 and acquire the curvature of the road at the position of the target vehicle M.

[0035] The determination unit 130 determines whether the target vehicle M has changed lanes based on at least one of the offset information and the attitude information. As described below, the determination unit 130 determines whether the target vehicle M has changed lanes by using the offset information with a higher priority when the speed of the target vehicle M is higher, and determines whether the target vehicle M has changed lanes by using the attitude information with a higher priority when the speed of the target vehicle M is lower.

[0036] For example, when the speed VM of the target vehicle M is equal to or greater than the first threshold value Th1, the determination unit 130 determines whether the moving body has changed lanes based on the offset information. At this time, the first determination unit 132 makes the determination. The first determination unit 132 determines that the target vehicle M has changed lanes, for example, when the distance DL (there are two distances, but the smaller one is used) between the target vehicle M and the road dividing line approaches zero and becomes negative (or a value close to zero is acquired as the distance DL on the opposite left and right side in conjunction with a lane change).

[0037] When the speed VM of the target vehicle M is less than the first threshold Th1, the determination unit 130 determines whether the target vehicle M has changed lanes based on the attitude information. At this time, the second determination unit 134 makes the determination. Here, it is assumed that the attitude information is an angular velocity (yaw rate). The second determination unit 134, for example, obtains an azimuth angle with respect to a straight running path (meaning a running path in a section where the angular velocity was approximately zero) in a time series, which is obtained from an accumulated value of the angular velocity of the target vehicle M, obtains a movement amount of the target vehicle M in the road width direction from the azimuth angle and the speed, and determines that the target vehicle M has changed lanes when the movement amount in the road width direction exceeds, for example, 1 / 2 of a general lane width (set to about 4 [m]). When the attitude information is information on an azimuth angle, the azimuth angle may be used directly. The first threshold Th1 is, for example, a value of about 30 [km / h]. This numerical value is merely an example and does not limit the scope of the rights of the present invention.

[0038] In addition, the determination unit 130 may, for example, calculate a weighted sum of the lateral movement amount of the target vehicle M based on the attitude information and the lateral movement amount of the target vehicle M based on the offset information (for example, calculated by subtracting the distance DL from 1 / 2 of a general lane width), and determine that the target vehicle M has changed lanes when the weighted sum exceeds 1 / 2 of a general lane width. In this case, as another example of determining whether the target vehicle M has changed lanes by preferentially using the attitude information, a coefficient multiplied by the lateral movement amount of the target vehicle M based on the attitude information may be increased, and a coefficient multiplied by the lateral movement amount of the target vehicle M based on the offset information may be decreased. Conversely, as another example of determining whether the target vehicle M has changed lanes by preferentially using the offset information, a coefficient multiplied by the lateral movement amount of the target vehicle M based on the attitude information may be decreased, and a coefficient multiplied by the lateral movement amount of the target vehicle M based on the offset information may be increased.

[0039] If the lane dividing lines are recognized with sufficient accuracy, it is more accurate to determine whether or not the lane is changed based on the distance DL, and a highly reliable determination result can be obtained. However, when the speed of the target vehicle M is low, it is estimated that the traffic volume is heavy, and therefore it is estimated that the inter-vehicle distance DAM between the leading vehicle mA and the target vehicle M is short, and furthermore, the frequency with which other vehicles cut in from other lanes in front of the target vehicle M is high. As a result, the leading vehicle mA is reflected in most of the angle of view of the camera 10, so that it is highly likely that the road dividing lines are not sufficiently captured. FIG. 4 is a diagram showing an example of an image captured by the camera 10 when the speed of the target vehicle M is low. As shown in the figure, the road dividing lines, especially on the left side, cannot be sufficiently recognized. In contrast, when the speed of the target vehicle M is high, it is highly likely that the road dividing lines can be sufficiently recognized. FIG. 5 is a diagram showing an example of an image captured by the camera 10 when the speed of the target vehicle M is high. In the embodiment, the judgment unit 130 judges whether or not there has been a lane change based on the offset information when the speed VM of the target vehicle M is greater than or equal to the first threshold value Th1, and judges whether or not there has been a lane change based on the attitude information when the speed VM of the target vehicle M is not greater than or equal to the first threshold value Th1, thereby suppressing a decrease in judgment accuracy in either case.

[0040] When the weather information indicates that the weather is bad, the determination unit 130 may determine whether the target vehicle M has changed lanes by preferentially using the attitude information or by using the attitude information to a greater extent than when the weather is not bad. Bad weather includes rain, snowfall, and the like. For example, when the weather information indicates that the weather is bad, the determination unit 130 changes the first threshold value Th1 to a larger value, making it more difficult to determine whether the moving body has changed lanes based on the offset information. This allows the determination to be made by preferentially using the attitude information (i.e., by using the attitude information to a greater extent than when the weather is not bad) in bad weather, when the recognition accuracy of road dividing line decreases, and thus makes it possible to suppress a decrease in the determination accuracy. As another example of increasing the degree of use of the attitude information to determine whether the target vehicle M has changed lanes, for example, on the assumption that the determination is based on a weighted sum, the coefficient by which the lateral movement amount of the target vehicle M based on the attitude information is multiplied may be made larger than the coefficient when the weather is not bad, and instead of or in addition to this, the coefficient by which the lateral movement amount of the target vehicle M based on the offset information is multiplied may be made smaller than the coefficient when the weather is not bad. Also, on the assumption that the determination is based on a weighted sum, the coefficient by which the lateral movement amount of the target vehicle M based on the attitude information is multiplied may be made larger than the coefficient by which the lateral movement amount of the target vehicle M based on the offset information is multiplied.

[0041] When the curvature of the road on which the target vehicle M is located is equal to or greater than the third threshold Th3, the determination unit 130 may determine whether the target vehicle M has changed lanes by preferentially using the offset information or by increasing the degree of use of the offset information compared to when the curvature is less than the third threshold Th3. For example, when the curvature of the road on which the target vehicle M is located is equal to or greater than the third threshold Th3, the determination unit 130 makes it difficult to determine whether the moving body has changed lanes based on the attitude information by changing the first threshold Th1 to a smaller value. As a result, on a curved road where it is difficult to make a determination based on the attitude of the target vehicle M, the offset information is preferentially used (i.e., the degree of use of the offset information is increased compared to when the curvature of the road is less than a predetermined value), and a decrease in the accuracy of the determination can be suppressed. As another example of determining whether the target vehicle M has changed lanes by increasing the degree of use of offset information, for example, on the premise that the determination is made based on a weighted sum, the coefficient by which the lateral movement amount of the target vehicle M based on the attitude information is multiplied may be set smaller than the coefficient when the road curvature is less than the third threshold value Th3, and instead of or in addition to this, the coefficient by which the lateral movement amount of the target vehicle M based on the offset information is multiplied may be set larger than the coefficient when the road curvature is less than the third threshold value Th3. Also, on the premise that the determination is made based on a weighted sum, the coefficient by which the lateral movement amount of the target vehicle M based on the attitude information is multiplied may be set smaller than the coefficient by which the lateral movement amount of the target vehicle M based on the offset information is multiplied.

[0042] When the recognition accuracy indicated by the accuracy information is less than the fourth threshold Th4, the determination unit 130 may determine whether or not the target vehicle M has changed lanes by preferentially using the attitude information, or by increasing the degree of use of the attitude information compared to when the recognition accuracy is equal to or greater than the fourth threshold Th4. For example, when the recognition accuracy indicated by the accuracy information is less than the fourth threshold Th4, the determination unit 130 changes the first threshold Th1 to a larger value, making it more difficult to determine whether or not the moving body has changed lanes based on the offset information. This allows the determination to be made by preferentially using the attitude information (i.e., by increasing the degree of use of the attitude information compared to when the recognition accuracy is equal to or greater than a predetermined value) when the recognition accuracy of the road dividing line has decreased, thereby suppressing a decrease in the determination accuracy. As another example of determining whether the target vehicle M has changed lanes by increasing the degree of use of the attitude information, for example, on the premise that the determination is made based on the weighted sum, the coefficient by which the lateral movement amount of the target vehicle M based on the attitude information is multiplied may be made larger than the coefficient when the recognition accuracy is equal to or greater than the fourth threshold value Th4, and instead of or in addition to this, the coefficient by which the lateral movement amount of the target vehicle M based on the offset information is multiplied may be made smaller than the coefficient when the recognition accuracy is equal to or greater than the fourth threshold value Th4. Also, on the premise that the determination is made based on the weighted sum, the coefficient by which the lateral movement amount of the target vehicle M based on the attitude information is multiplied may be made larger than the coefficient by which the lateral movement amount of the target vehicle M based on the offset information is multiplied.

[0043] 6 is a flowchart showing an example of the flow of processing executed by the moving object monitoring device 100 of the first embodiment. The processing of this flowchart is executed repeatedly at a predetermined cycle, for example.

[0044] First, the determination unit 130 sets the first threshold value Th1 to a default value (step S100). Next, the acquisition unit 120 acquires various pieces of information from the target vehicle M (step S102).

[0045] Next, the determination unit 130 determines whether the weather indicated by the weather information is bad weather or not (step S104). If it is determined that the weather indicated by the weather information is bad weather, the determination unit 130 changes the first threshold value Th1 to a larger value (step S106).

[0046] Next, the determination unit 130 determines whether the curvature of the road on which the target vehicle M is located is equal to or greater than the third threshold value Th3 (step S108). If it is determined that the curvature of the road on which the target vehicle M is located is equal to or greater than the third threshold value Th3, the determination unit 130 changes the first threshold value Th1 to a smaller value (step S110).

[0047] Next, the determination unit 130 determines whether the recognition accuracy indicated by the accuracy information is less than the fourth threshold Th4 (step S112). If it is determined that the recognition accuracy indicated by the accuracy information is less than the fourth threshold Th4, the determination unit 130 changes the first threshold Th1 to a larger value (step S114).

[0048] Next, the determination unit 130 determines whether the speed of the target vehicle M is equal to or greater than the first threshold Th1 (step S116). If it is determined that the speed of the target vehicle M is equal to or greater than the first threshold Th1, the first determination unit 132 determines whether or not a lane change has occurred based on the offset information (step S118). If a negative determination result is obtained in step S116, the second determination unit 134 determines whether or not a lane change has occurred based on the attitude information (step S120).

[0049] According to the first embodiment described above, the vehicle is provided with an acquisition unit 120 that acquires offset information representing the distance between the target vehicle M recognized based on an image captured by the camera 10 mounted on the target vehicle M and a road dividing line, attitude information based on the detection value of a yaw rate sensor or an orientation sensor mounted on the target vehicle M, and speed information representing the speed of the target vehicle M, and a determination unit 130 that determines whether the target vehicle M has changed lanes based on at least one of the offset information and the attitude information, and the higher the speed of the target vehicle M, the more the determination unit 130 uses the offset information preferentially to determine whether the target vehicle M has changed lanes, thereby making it possible to more accurately determine whether or not the target vehicle M has changed lanes.

[0050] <Second embodiment> The second embodiment will be described below. In the second embodiment, the communication device 50 of the target vehicle M acquires (1) offset information indicating the distance from the road dividing line derived by the image recognition device 12 and accuracy information related to the recognition of the road dividing line, (2) attitude information based on the detection value of the yaw rate sensor or the direction sensor, (3) following distance information indicating the following distance between the leading vehicle mA and the target vehicle M, (4) position information of the target vehicle M, and the like from each of the above-mentioned components, and transmits the acquired information to the mobile object monitoring device 100 via the network NW. The communication device 50 may acquire information from each of the above-mentioned components via various control devices.

[0051] In the second embodiment, the determination unit 130 determines whether the target vehicle M has changed lanes based on at least one of the offset information and the attitude information. As described below, the longer the distance between the leading vehicle mA and the target vehicle M, the more the determination unit 130 uses the offset information to determine whether the target vehicle M has changed lanes, and the shorter the distance between the leading vehicle mA and the target vehicle M, the more the determination unit 130 uses the attitude information to determine whether the target vehicle M has changed lanes.

[0052] For example, when the inter-vehicle distance DAM between the preceding vehicle mA and the target vehicle M is equal to or greater than the second threshold value Th2, the determination unit 130 determines whether or not the moving body has changed lanes based on the offset information. At this time, the first determination unit 132 makes the determination. The first determination unit 132 determines that the target vehicle M has changed lanes, for example, when the distance DL (there are two distances, but the smaller one is adopted) between the target vehicle M and the road dividing line approaches zero and becomes negative (or a value close to zero is acquired as the distance DL on the opposite left and right side in conjunction with a lane change).

[0053] When the inter-vehicle distance DAM between the preceding vehicle mA and the target vehicle M is less than the second threshold value Th2, the determination unit 130 determines whether the target vehicle M has changed lanes based on the attitude information. At this time, the second determination unit 134 makes the determination. Here, it is assumed that the attitude information is angular velocity (yaw rate). The second determination unit 134, for example, obtains an azimuth angle with respect to a straight running path (meaning a running path in a section where the angular velocity was approximately zero) in a time series obtained from an accumulated value of the angular velocity of the target vehicle M, obtains the amount of movement of the target vehicle M in the road width direction from the azimuth angle and the speed, and determines that the target vehicle M has changed lanes when the amount of movement in the road width direction exceeds, for example, 1 / 2 of a general lane width (set to about 4 [m]). When the attitude information is azimuth angle information, the azimuth angle may be used directly. The second threshold value Th2 is, for example, a value of about 10 [m]. This numerical value is merely an example and does not limit the scope of the rights of the present invention.

[0054] The purpose of the above processing is as explained in the first embodiment.

[0055] When the weather information indicates that the weather is bad, the determination unit 130 may determine whether the target vehicle M has changed lanes by using the attitude information preferentially, or by increasing the degree of use of the attitude information compared to when the weather is not bad. Bad weather is rain, snowfall, and the like. For example, when the weather information indicates that the weather is bad, the determination unit 130 changes the second threshold value Th2 to a larger value, making it difficult to determine whether the moving body has changed lanes based on the offset information. As a result, in bad weather when the recognition accuracy of the road dividing line decreases, the determination is made by using the attitude information preferentially, and the decrease in the determination accuracy can be suppressed. Other examples of determining whether the target vehicle M has changed lanes by increasing the degree of use of the attitude information are the same as those in the first embodiment.

[0056] When the curvature of the road on which the target vehicle M is present is equal to or greater than the third threshold Th3, the determination unit 130 may determine whether the target vehicle M has changed lanes by preferentially using the offset information, or by increasing the degree of use of the offset information compared to when the curvature is less than the third threshold Th3. For example, when the curvature of the road on which the target vehicle M is present is equal to or greater than the third threshold, the determination unit 130 changes the second threshold Th2 to a smaller value, making it difficult to determine whether the moving body has changed lanes based on the attitude information. As a result, on a curved road where it is difficult to make a determination based on the attitude of the target vehicle M, the offset information is preferentially used for the determination, and a decrease in the accuracy of the determination can be suppressed. Other examples of determining whether the target vehicle M has changed lanes by increasing the degree of use of the offset information are the same as those in the first embodiment.

[0057] When the recognition accuracy indicated by the accuracy information is less than the fourth threshold Th4, the determination unit 130 may determine whether the target vehicle M has changed lanes by preferentially using the attitude information, or by increasing the degree of use of the attitude information compared to when the recognition accuracy is equal to or greater than the fourth threshold Th4. For example, when the recognition accuracy indicated by the accuracy information is less than the fourth threshold Th4, the determination unit 130 changes the second threshold Th2 to a larger value, making it difficult to determine whether the moving body has changed lanes based on the offset information. As a result, when the recognition accuracy of the road dividing line is reduced, the determination is made by preferentially using the attitude information, and the reduction in the determination accuracy can be suppressed. Other examples of determining whether the target vehicle M has changed lanes by increasing the degree of use of the attitude information are the same as those in the first embodiment.

[0058] 7 is a flowchart showing an example of the flow of processing executed by the moving object monitoring device 100 of the second embodiment. The processing of this flowchart is executed repeatedly at a predetermined cycle, for example.

[0059] First, the determination unit 130 sets the second threshold value Th2 to a default value (step S200). Next, the acquisition unit 120 acquires various pieces of information from the target vehicle M (step S202).

[0060] Next, the determination unit 130 determines whether the weather indicated by the weather information is bad weather (step S204). If it is determined that the weather indicated by the weather information is bad weather, the determination unit 130 changes the second threshold value Th2 to a larger value (step S206).

[0061] Next, the determination unit 130 determines whether the curvature of the road on which the target vehicle M is located is equal to or greater than the third threshold value Th3 (step S208). If it is determined that the curvature of the road on which the target vehicle M is located is equal to or greater than the third threshold value Th3, the determination unit 130 changes the second threshold value Th2 to a smaller value (step S210).

[0062] Next, the determination unit 130 determines whether the recognition accuracy indicated by the accuracy information is less than the fourth threshold Th4 (step S212). If it is determined that the recognition accuracy indicated by the accuracy information is less than the fourth threshold Th4, the determination unit 130 changes the second threshold Th2 to a larger value (step S214).

[0063] Next, the determination unit 130 determines whether or not the inter-vehicle distance DAM between the leading vehicle mA and the target vehicle M is equal to or greater than a second threshold value (step S216).

[0064] If a positive determination result is obtained in step S216, the first determination unit 132 determines whether or not a lane change has occurred based on the offset information (step S218). If a negative determination result is obtained in step S216, the second determination unit 134 determines whether or not a lane change has occurred based on the attitude information (step S220).

[0065] According to the second embodiment described above, the vehicle is equipped with an acquisition unit 120 that acquires offset information indicating the distance between the target vehicle M recognized based on an image captured by the camera 10 mounted on the target vehicle M and a road dividing line, attitude information based on the detection value of a yaw rate sensor or an orientation sensor mounted on the target vehicle M, and inter-vehicle distance information indicating the inter-vehicle distance between the target vehicle M and a leading vehicle mA traveling immediately before the target vehicle M in the same lane as the target vehicle M, and a judgment unit 130 that judges whether the target vehicle M has changed lanes based on at least one of the offset information and the attitude information.The longer the inter-vehicle distance between the leading vehicle mA and the target vehicle M, the more the judgment unit 130 uses the offset information preferentially to determine whether the target vehicle M has changed lanes, thereby making it possible to more accurately judge whether or not the target vehicle M has changed lanes.

[0066] <Third embodiment> A third embodiment will be described below. In the third embodiment, the communication device 50 of the target vehicle M acquires (1) offset information indicating the distance from the road dividing line derived by the image recognition device 12 and accuracy information related to the recognition of the road dividing line, (2) attitude information based on the detection value of the yaw rate sensor or the direction sensor, (3) speed information indicating the speed detected by the speed sensor, (4) following distance information indicating the following distance between the leading vehicle mA and the target vehicle M, (5) position information of the target vehicle M, and the like from each of the above-mentioned components, and transmits the acquired information to the mobile object monitoring device 100 via the network NW. The communication device 50 may acquire information from each of the above-mentioned components via various control devices.

[0067] In the third embodiment, the determination unit 130 determines whether the target vehicle M has changed lanes based on at least one of the offset information and the attitude information. As described below, the determination unit 130 preferentially uses the offset information to determine whether the target vehicle M has changed lanes when the speed of the target vehicle M is higher and when the distance between the leading vehicle mA and the target vehicle M is longer, and preferentially uses the attitude information to determine whether the target vehicle M has changed lanes when the speed of the target vehicle M is lower and when the distance between the leading vehicle mA and the target vehicle M is shorter.

[0068] For example, when the speed VM of the target vehicle M is equal to or greater than the first threshold value Th1 and the inter-vehicle distance DAM between the target vehicle M and the preceding vehicle mA is equal to or greater than the second threshold value Th2, the determination unit 130 determines whether or not the moving body has changed lanes based on the offset information. At this time, the first determination unit 132 makes the determination. The first determination unit 132 determines that the target vehicle M has changed lanes, for example, when the distance DL (there are two distances, but the smaller one is adopted) between the target vehicle M and the road dividing line approaches zero and becomes negative (or a value close to zero is acquired as the distance DL on the opposite left and right side in conjunction with a lane change).

[0069] When the speed VM of the target vehicle M is less than the first threshold value Th1, or when the inter-vehicle distance DAM between the preceding vehicle mA and the target vehicle M is less than the second threshold value Th2, the determination unit 130 determines whether the target vehicle M has changed lanes based on the attitude information. At this time, the second determination unit 134 makes the determination. Here, it is assumed that the attitude information is angular velocity (yaw rate). For example, the second determination unit 134 obtains an azimuth angle with respect to a straight running path (meaning a running path in a section where the angular velocity was approximately zero) in a time series, which is obtained from the cumulative value of the angular velocity of the target vehicle M, obtains the amount of movement of the target vehicle M in the road width direction from the azimuth angle and the speed, and determines that the target vehicle M has changed lanes when the amount of movement in the road width direction exceeds, for example, 1 / 2 of a general lane width (set to about 4 [m]). When the attitude information is azimuth angle information, the azimuth angle may be used directly. The first threshold Th1 is, for example, a value of about 30 [km / h], and the second threshold Th2 is, for example, a value of about 10 [m]. These numerical values ​​are merely examples and do not limit the scope of the present invention.

[0070] The purpose of the above processing is as explained in the first embodiment.

[0071] When the weather information indicates that the weather is bad, the determination unit 130 may determine whether the target vehicle M has changed lanes by using the attitude information preferentially, or by increasing the degree of use of the attitude information compared to when the weather is not bad. Bad weather is rain, snowfall, and the like. For example, when the weather information indicates that the weather is bad, the determination unit 130 changes one or both of the first threshold value Th1 and the second threshold value Th2 to a larger value, making it difficult to determine whether the moving body has changed lanes based on the offset information. As a result, in bad weather when the recognition accuracy of the road dividing line decreases, the determination is made by using the attitude information preferentially, and the decrease in the determination accuracy can be suppressed. Other examples of determining whether the target vehicle M has changed lanes by increasing the degree of use of the attitude information are the same as those in the first embodiment.

[0072] When the curvature of the road on which the target vehicle M is present is equal to or greater than the third threshold Th3, the determination unit 130 may determine whether the target vehicle M has changed lanes by preferentially using the offset information, or by increasing the degree of use of the offset information compared to when the curvature is less than the third threshold Th3. For example, when the curvature of the road on which the target vehicle M is present is equal to or greater than the third threshold, the determination unit 130 changes one or both of the first threshold Th1 and the second threshold Th2 to smaller values, making it difficult to determine whether the moving body has changed lanes based on the attitude information. As a result, on a curved road where it is difficult to make a determination based on the attitude of the target vehicle M, the offset information is preferentially used for the determination, and a decrease in the accuracy of the determination can be suppressed. Other examples of determining whether the target vehicle M has changed lanes by increasing the degree of use of the offset information are the same as those in the first embodiment.

[0073] When the recognition accuracy indicated by the accuracy information is less than the fourth threshold Th4, the determination unit 130 may determine whether the target vehicle M has changed lanes by preferentially using the attitude information, or by increasing the degree of use of the attitude information compared to when the recognition accuracy is equal to or greater than the fourth threshold Th4. For example, when the recognition accuracy indicated by the accuracy information is less than the fourth threshold Th4, the determination unit 130 changes one or both of the first threshold Th1 and the second threshold Th2 to a larger value, making it difficult to determine whether the moving body has changed lanes based on the offset information. As a result, when the recognition accuracy of the road dividing line is reduced, the determination is made by preferentially using the attitude information, and the reduction in the determination accuracy can be suppressed. Other examples of determining whether the target vehicle M has changed lanes by increasing the degree of use of the attitude information are the same as those in the first embodiment.

[0074] 8 is a flowchart showing an example of the flow of processing executed by the moving object monitoring device 100 of the third embodiment. The processing of this flowchart is executed repeatedly at a predetermined cycle, for example.

[0075] First, the determination unit 130 sets the first threshold value Th1 and the second threshold value Th2 to default values ​​(step S300). Next, the acquisition unit 120 acquires various pieces of information from the target vehicle M (step S302).

[0076] Next, the determination unit 130 determines whether the weather indicated by the weather information is bad weather (step S304). If it is determined that the weather indicated by the weather information is bad weather, the determination unit 130 changes one or both of the first threshold value Th1 and the second threshold value Th2 to a larger value (step S306).

[0077] Next, the determination unit 130 determines whether the curvature of the road on which the target vehicle M is located is equal to or greater than a third threshold value Th3 (step S308). If it is determined that the curvature of the road on which the target vehicle M is located is equal to or greater than the third threshold value Th3, the determination unit 130 changes one or both of the first threshold value Th1 and the second threshold value Th2 to smaller values ​​(step S310).

[0078] Next, the determination unit 130 determines whether the recognition accuracy indicated by the accuracy information is less than a fourth threshold Th4 (step S312). If it is determined that the recognition accuracy indicated by the accuracy information is less than the fourth threshold Th4, the determination unit 130 changes one or both of the first threshold Th1 and the second threshold Th2 to a larger value (step S314).

[0079] Next, the determination unit 130 determines whether the speed of the target vehicle M is equal to or greater than a first threshold value Th1 (step S316). If it is determined that the speed of the target vehicle M is equal to or greater than the first threshold value Th1, the determination unit 130 determines whether the inter-vehicle distance DAM between the leading vehicle mA and the target vehicle M is equal to or greater than a second threshold value (step S318).

[0080] If a positive determination result is obtained in both steps S316 and S318, the first determination unit 132 determines whether or not a lane change has occurred based on the offset information (step S320). If a negative determination result is obtained in at least one of steps S316 and S318, the second determination unit 134 determines whether or not a lane change has occurred based on the attitude information (step S322).

[0081] According to the third embodiment described above, the system is equipped with an acquisition unit 120 that acquires offset information indicating the distance between the target vehicle M recognized based on an image captured by the camera 10 mounted on the target vehicle M and a road dividing line, attitude information based on the detection value of a yaw rate sensor or an orientation sensor mounted on the target vehicle M, speed information indicating the speed of the target vehicle M, and inter-vehicle distance information indicating the inter-vehicle distance between the target vehicle M and a leading vehicle mA traveling immediately before the target vehicle M in the same lane as the target vehicle M, and a judgment unit 130 that judges whether the target vehicle M has changed lanes based on at least one of the offset information and the attitude information.The judgment unit 130 preferentially uses the offset information to determine whether the target vehicle M has changed lanes the higher the speed of the target vehicle M and the longer the inter-vehicle distance between the leading vehicle mA and the target vehicle M, thereby making it possible to more accurately judge whether or not the target vehicle M has changed lanes.

[0082] <Fourth embodiment> The fourth embodiment will be described below. In the first to third embodiments, the moving object monitoring device 100 is installed at a location away from the target vehicle M, and acquires offset information, attitude information, speed information, vehicle distance information, and other information through communication with the communication device 50 mounted on the target vehicle M. In contrast, in the second embodiment, the moving object monitoring device 100A is mounted on the target vehicle M, and acquires offset information, attitude information, speed information, vehicle distance information, and other information through intra-vehicle communication.

[0083] FIG. 9 is a diagram showing an example of the configuration of a moving object monitoring device 100A according to the fourth embodiment. The moving object monitoring device 100A is mounted on a target vehicle M, and the communication unit 110A is a communication interface (e.g., a CAN transceiver) for connecting to an in-vehicle network. Regarding weather information, the moving object monitoring device 100A may acquire weather information at the position of the target vehicle M from a server (not shown) that distributes weather information using, for example, a communication device (configured like the communication device 50 in the first embodiment) of the target vehicle M, or may estimate the weather information based on detection values ​​of a rainfall sensor or an illuminance sensor provided on the target vehicle M. Regarding the curvature of the road, the curvature may be acquired by referring to map information 152 held by the moving object monitoring device 100A itself, or may be calculated based on the distribution (degree of curvature) of road division lines in an image captured by the camera 10. Each component of the moving object monitoring device 100A according to the fourth embodiment performs the same process as any of the first to third embodiments.

[0084] The determination result by the moving object monitoring device 100A according to the fourth embodiment may be provided to, for example, a driving assistance device or an automatic driving control device mounted on the target vehicle M and used to determine the completion of an automobile lane change. In addition, the determination result by the moving object monitoring device 100A may be transmitted to a cloud server via the network NW and used to create a map or monitor the traffic volume for each lane, as in the first embodiment.

[0085] According to the fourth embodiment described above, it is possible to achieve the same effects as the first to third embodiments.

[0086] The above-described embodiment can be expressed as follows. A storage device storing a program; a hardware processor; The hardware processor executes the program stored in the storage device, Acquire offset information indicating a distance between the moving body and a road dividing line recognized based on an image captured by a camera mounted on the moving body, attitude information based on a detection value of a yaw rate sensor or an orientation sensor mounted on the moving body, and speed information indicating a speed of the moving body, determining whether the moving object has changed lanes based on at least one of the offset information and the attitude information; When making the determination, the higher the speed, the higher the offset information is used to determine whether the moving object has changed lanes. The mobile object monitoring device is configured as follows.

[0087] The above-described embodiment can also be expressed as follows. A storage device storing a program; a hardware processor; The hardware processor executes the program stored in the storage device, Acquire offset information indicating a distance between the moving body and a road dividing line recognized based on an image captured by a camera mounted on the moving body, attitude information based on a detection value of a yaw rate sensor or an orientation sensor mounted on the moving body, and following distance information indicating a following distance between the moving body and a preceding moving body traveling immediately before the moving body in the same lane as the moving body, determining whether the moving object has changed lanes based on at least one of the offset information and the attitude information; When making the determination, the longer the inter-vehicle distance is, the more the offset information is used to determine whether the moving object has changed lanes. The mobile object monitoring device is configured as follows.

[0088] The above describes the form for carrying out the present invention using an embodiment, but the present invention is not limited to such an embodiment, and various modifications and substitutions can be made within the scope that does not deviate from the gist of the present invention. [Explanation of symbols]

[0089] 10. Camera 12 Image Recognition Device 20 Vehicle Sensors 30 Radar Equipment 40 GPS receiver 50 Communication Equipment 100, 100A Mobile monitoring device 110, 110A Communication Department 120 Acquisition Department 130 Judgment section 132 1st Judgment Department 134 Second Judgment Section 150 Storage section 152 Map Information

Claims

1. an acquisition unit that acquires offset information that indicates a distance between the moving body and a road dividing line recognized based on an image captured by a camera mounted on the moving body, attitude information based on a detection value of a yaw rate sensor or an orientation sensor mounted on the moving body, and speed information that indicates a speed of the moving body; a determination unit that determines whether the moving object has changed lanes based on at least one of the offset information and the attitude information, When making the determination, the determination unit preferentially uses the offset information as the speed increases. Mobile monitoring equipment.

2. The determination unit determines whether the moving object has changed lanes based on the offset information when the speed is equal to or greater than a first threshold, and determines whether the moving object has changed lanes based on the attitude information when the speed is less than the first threshold.

2. The moving object monitoring device according to claim 1.

3. an acquisition unit that acquires offset information that indicates a distance between the moving body and a road dividing line recognized based on an image captured by a camera mounted on the moving body, attitude information based on a detection value of a yaw rate sensor or an orientation sensor mounted on the moving body, and vehicle distance information that indicates a vehicle distance between the moving body and a preceding moving body that is traveling immediately before the moving body in the same lane as the moving body; a determination unit that determines whether the moving object has changed lanes based on at least one of the offset information and the attitude information, The determination unit, when making the determination, preferentially uses the offset information as the inter-vehicle distance becomes longer. Mobile monitoring device.

4. the determination unit determines whether the moving object has changed lanes based on the offset information when the vehicle-to-vehicle distance is equal to or greater than a second threshold, and determines whether the moving object has changed lanes based on the attitude information when the vehicle-to-vehicle distance is less than the second threshold.

4. The moving object monitoring device according to claim 3.

5. The acquisition unit further acquires inter-vehicle distance information representing a distance between the moving body and a preceding moving body traveling immediately before the moving body in the same lane as the moving body, The determination unit, when making the determination, preferentially uses the offset information as the speed is higher or the inter-vehicle distance is longer.

2. The moving object monitoring device according to claim 1.

6. the determination unit determines whether the moving object has changed lanes based on the offset information when the speed is equal to or greater than a first threshold and the vehicle-to-vehicle distance is equal to or greater than a second threshold, and determines whether the moving object has changed lanes based on the attitude information when the speed is less than the first threshold or the vehicle-to-vehicle distance is less than the second threshold.

6. The moving object monitoring device according to claim 5.

7. The acquisition unit further acquires weather information representing the weather at a location where the moving object is located, When the weather is bad, the determination unit increases the degree of utilization of the attitude information relative to the offset information by lowering the priority of the use of the offset information in comparison with a case where the weather is not bad.

7. A moving object monitoring device according to claim 1.

8. The acquisition unit further acquires curvature information regarding a curvature of a road on which the moving object is located, When the curvature is equal to or greater than a third threshold value, the determination unit increases a priority level for preferentially using the offset information compared to when the curvature is less than the third threshold value, thereby increasing a degree of use of the offset information for the posture information. A moving object monitoring device according to any one of claims 1 to 7.

9. The acquisition unit further acquires accuracy information regarding recognition accuracy of the road dividing line, When the recognition accuracy is less than a fourth threshold value, the determination unit increases a degree of utilization of the posture information relative to the offset information by lowering a priority level for preferentially utilizing the offset information compared to a case where the recognition accuracy is equal to or greater than a fourth threshold value. The moving object monitoring device according to any one of claims 1 to 8.

10. Installed at a location away from the moving object, The acquisition unit acquires the information through communication with a communication device mounted on the moving object. The moving object monitoring device according to any one of claims 1 to 9.

11. Mounted on the moving body, The acquisition unit acquires the information through intra-mobile communication. The moving object monitoring device according to any one of claims 1 to 9.

12. The computer Acquire offset information indicating a distance between the moving body and a road dividing line recognized based on an image captured by a camera mounted on the moving body, attitude information based on a detection value of a yaw rate sensor or an orientation sensor mounted on the moving body, and speed information indicating a speed of the moving body, determining whether the moving object has changed lanes based on at least one of the offset information and the attitude information; When making the determination, the higher the speed, the higher the use of the offset information. Mobile surveillance method.

13. On the computer, acquiring offset information representing a distance between the moving body and a road dividing line recognized based on an image captured by a camera mounted on the moving body, attitude information based on a detection value of a yaw rate sensor or an orientation sensor mounted on the moving body, and speed information representing a speed of the moving body; determining whether the moving object has changed lanes based on at least one of the offset information and the attitude information; When making the determination, the higher the speed, the higher the use of the offset information. program.

14. The computer Acquire offset information indicating a distance between the moving body and a road dividing line recognized based on an image captured by a camera mounted on the moving body, attitude information based on a detection value of a yaw rate sensor or an orientation sensor mounted on the moving body, and following distance information indicating a following distance between the moving body and a preceding moving body traveling immediately before the moving body in the same lane as the moving body, determining whether the moving object has changed lanes based on at least one of the offset information and the attitude information; When making the determination, the longer the inter-vehicle distance is, the more preferentially the offset information is used. Mobile surveillance method.

15. On the computer, acquire offset information indicating a distance between the moving body and a road dividing line recognized based on an image captured by a camera mounted on the moving body, attitude information based on a detection value of a yaw rate sensor or an orientation sensor mounted on the moving body, and vehicle distance information indicating a vehicle distance between the moving body and a preceding moving body traveling immediately before the moving body in the same lane as the moving body, determining whether the moving object has changed lanes based on at least one of the offset information and the attitude information; When making the determination, the offset information is used with a higher priority as the inter-vehicle distance becomes longer. program.

Images