WO2023210397A1 - 観察装置及び観察方法 - Google Patents
観察装置及び観察方法 Download PDFInfo
- Publication number
- WO2023210397A1 WO2023210397A1 PCT/JP2023/015077 JP2023015077W WO2023210397A1 WO 2023210397 A1 WO2023210397 A1 WO 2023210397A1 JP 2023015077 W JP2023015077 W JP 2023015077W WO 2023210397 A1 WO2023210397 A1 WO 2023210397A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- threshold
- control unit
- observation device
- sensor
- condition
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01P—MEASURING LINEAR OR ANGULAR SPEED, ACCELERATION, DECELERATION, OR SHOCK; INDICATING PRESENCE, ABSENCE, OR DIRECTION, OF MOVEMENT
- G01P3/00—Measuring linear or angular speed; Measuring differences of linear or angular speeds
- G01P3/36—Devices characterised by the use of optical means, e.g. using infrared, visible, or ultraviolet light
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/015—Detecting movement of traffic to be counted or controlled with provision for distinguishing between two or more types of vehicles, e.g. between motor-cars and cycles
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
Definitions
- the present disclosure relates to an observation device and an observation method.
- Patent Document 1 discloses an image-based speed detection system that processes image information about a vehicle moving on a road taken by an imaging device to detect the speed and position of the vehicle.
- An observation device includes: Calculating the speed of the object based on position information of the object, and determining whether to adopt the calculated speed of the object based on the result of comparing a value based on the calculated speed of the object with a set threshold value.
- a control unit is provided.
- An observation method includes: Calculating the speed of the object based on position information of the object; The method includes determining whether or not to adopt the calculated speed of the object based on a result of comparing a value based on the calculated speed of the object with a set threshold value.
- FIG. 1 is a diagram showing a schematic configuration of a communication system according to an embodiment of the present disclosure.
- 2 is a block diagram of the communication system shown in FIG. 1.
- FIG. FIG. 7 is a diagram showing an example of reference threshold values set for each type of object.
- 2 is a flowchart showing the flow of a method for calculating the velocity of an object using the observation device shown in FIG. 1.
- FIG. 2 is a flowchart showing a flow of a setting threshold value setting method using the observation device shown in FIG. 1.
- the detection accuracy of sensors decreases due to various factors. If the detection accuracy of the sensor decreases, the error in calculating the velocity of the object may increase. In the conventional technology, there is room for improvement regarding the calculation error of the velocity of an object. According to an embodiment of the present disclosure, it is possible to provide a technique that is improved regarding calculation errors in the velocity of an object.
- the observation device of the present disclosure is a roadside device.
- the observation device of the present disclosure may be applied to any purpose.
- the observation device of the present disclosure may be a surveillance camera device or the like.
- the communication system 1 includes an observation device 10.
- the communication system 1 is, for example, a safe driving support communication system for Intelligent Transport Systems (ITS).
- ITS Intelligent Transport Systems
- the safe driving support communication system is sometimes called a safe driving support system or a safe driving support radio system.
- the observation device 10 is fixed to the structure 3 so as to be able to observe the road surface 2, which is an observation area, for example.
- the structure 3 is, for example, a signal device, a utility pole, a street light, or the like.
- the observation device 10 detects an object 4 existing in the observation area.
- the object 4 is, for example, a vehicle, a motorized bicycle, a bicycle, or a pedestrian.
- the observation device 10 calculates the speed of the detected object 4, as described later.
- the support information includes data on the type of the detected object 4, the speed of the object 4, and the like.
- the observation device 10 wirelessly communicates with a moving object 5 as shown in FIG.
- the observation device 10 notifies the mobile object 5 of the generated support information.
- the moving body 5 exists around the observation device 10 .
- the moving body 5 is a vehicle or the like located on the road surface 2.
- the observation device 10 can be connected to the network 6.
- the network 6 may be any network including a mobile communication network, the Internet, and the like. However, the observation device 10 does not need to be connectable to the network 6.
- the observation device 10 includes a plurality of sensors 11, a communication section 12, a storage section 13, and a control section 14.
- the observation device 10 includes a plurality of sensors 11.
- the number of sensors 11 included in the observation device 10 may be one.
- the sensor 11 captures an image of the observation area and generates an image.
- the sensor 11 is, for example, a monocular camera.
- the monocular camera may be, for example, an imaging device such as a visible light camera or a FIR (Far Infrared Rays) camera.
- the sensor 11 may be an image sensor such as a CMOS (Complementary Metal Oxide Semiconductor) or a CCD (Charge Coupled Device).
- the sensor 11 may be any sensor other than a monocular camera and an image sensor.
- the sensor 11 may be LiDAR (Light Detection And Ranging) or millimeter wave radar.
- the plurality of sensors 11 included in the observation device 10 may be of the same type or may be of different types.
- Each of the plurality of sensors 11 may generate images at a predetermined frame rate.
- the sensor 11 may be configured to include a processing device, a storage device, and the like that can perform image recognition processing, etc., which will be described later, on the generated image data.
- the sensor 11 detects the object 4, the type of the object 4, and the position of the object 4 in the image in real space by performing image recognition processing on the generated image data. You can also obtain information.
- the communication unit 12 is configured to include at least one communication module capable of communicating with the moving object 5 on the road surface 2.
- the communication module is, for example, a communication module compatible with a road-to-vehicle communication standard.
- the communication unit 12 may wirelessly communicate with the mobile object 5 on the road surface 2 using this communication module, for example, in the 700 MHz band allocated to the ITS.
- the communication unit 12 is configured to include at least one communication module connectable to the network 6.
- the communication module is, for example, a communication module compatible with standards such as wired LAN (Local Area Network) or wireless LAN.
- the communication module is not limited to this.
- the communication module may support any communication standard.
- the communication unit 12 is connected to the network 6 via a wired LAN or wireless LAN by a communication module.
- the storage unit 13 is configured to include at least one semiconductor memory, at least one magnetic memory, at least one optical memory, or a combination of at least two of these.
- the semiconductor memory is, for example, RAM (Random Access Memory) or ROM (Read Only Memory).
- the RAM is, for example, SRAM (Static Random Access Memory) or DRAM (Dynamic Random Access Memory).
- the ROM is, for example, an EEPROM (Electrically Erasable Programmable Read Only Memory).
- the storage unit 13 may function as a main storage device, an auxiliary storage device, or a cache memory.
- the storage unit 13 stores data used for the operation of the observation device 10 and data obtained by the operation of the observation device 10.
- correspondence data is stored in the storage unit 13.
- the correspondence data associates the coordinates in the image generated by the sensor 11 with the position information in real space of the object reflected in the pixel of the image corresponding to the coordinates.
- the corresponding data is generated, for example, when the observation device 10 is calibrated.
- the corresponding data may be stored in the storage device of the sensor 11 if the sensor 11 is configured to include a storage device.
- the control unit 14 is configured to include at least one processor, at least one dedicated circuit, or a combination thereof.
- the processor is, for example, a general-purpose processor such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit), or a dedicated processor specialized for specific processing.
- the dedicated circuit is, for example, an FPGA (Field-Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit).
- the control unit 14 executes processing related to the operation of the observation device 10 while controlling each part of the observation device 10.
- the sensor 11 detects the object 4 from the image data by performing image recognition processing on the generated image data.
- the sensor 11 may detect the type of the object 4 by performing image recognition processing on the data of the generated image.
- the type of object 4 is, for example, a vehicle, a motorized bicycle, a bicycle, or a pedestrian.
- the image recognition process is, for example, a process such as pattern matching or machine learning such as deep learning.
- the sensor 11 includes LiDAR or millimeter wave radar
- the sensor 11 generates image data based on point cloud data obtained from measurement results of LiDAR or millimeter wave radar and performs image recognition processing. may be executed.
- the sensor 11 includes a millimeter wave radar
- the sensor 11 may detect the object 4 and the type of the object based on, for example, velocity data obtained from the measurement results of the millimeter wave radar.
- the sensor 11 acquires position information of the object 4 in the image.
- the position of the object 4 in the image is, for example, the position of a pixel in the image where the object 4 appears.
- the sensor 11 identifies the coordinates of a pixel in the image where the object 4 appears.
- the sensor 11 acquires the correspondence data from the storage unit 13 or the storage device included in the sensor 11, and acquires the position information in real space associated with the coordinates specified in the correspondence data as the position information of the object 4 in real space. do.
- the sensor 11 includes LiDAR or millimeter wave radar
- the sensor 11 acquires position information of the object 4 in real space based on data obtained from measurement results of LiDAR or millimeter wave radar, for example. It's okay.
- the sensor 11 transmits data including the type of the detected object 4 and position information of the object 4 in real space to the control unit 14 .
- the object detection process described above is not limited to the sensor 11, and may be performed by the control unit 14.
- Object detection processing by the control unit 14 will be described below as another example of object detection processing.
- the control unit 14 acquires data of an image generated by the sensor 11 from the sensor 11 .
- the control unit 14 detects the object 4 from the image data by performing image recognition processing on the acquired image data.
- the control unit 14 may detect the type of the object 4 by performing image recognition processing on the data of the acquired image.
- the control unit 14 may acquire point cloud data obtained from the measurement results of LiDAR or millimeter wave radar from the sensor 11, for example.
- the control unit 14 detects the object 4 and the type of the object 4 from the image data by generating image data based on the acquired point cloud data and performing image recognition processing on the generated image data. You may.
- the control unit 14 may acquire, for example, speed data etc. obtained from the measurement results of the millimeter wave radar from the sensor 11.
- the control unit 14 may detect the object 4 and the type of the object 4 based on the acquired velocity data and the like.
- the control unit 14 specifies the coordinates of a pixel in the image where the object 4 appears as position information in the image of the object 4.
- the control unit 14 acquires the correspondence data from the storage unit 13, and acquires the position information in the real space associated with the coordinates specified in the correspondence data as the position information of the object 4 in the real space.
- the control unit 14 may acquire position information of the object 4 in real space based on point cloud data obtained from the measurement results of LiDAR or millimeter wave radar. .
- the control unit 14 calculates the velocity V1 of the object 4 based on the position information of the object 4 in real space detected by the sensor 11 or acquired by the control unit 14.
- the time at which the velocity V1 of the object 4 is calculated (measured) is also referred to as measurement time t1.
- the control unit 14 uses the position information of the object 4 in the real space at the measurement time t1 and the position information of the object 4 in the real space at a predetermined time before the measurement time t1 to determine the position from a predetermined time before to the measurement time t1.
- the distance traveled by the object 4 is calculated.
- the control unit 14 calculates the speed V1 of the object 4 by dividing the calculated moving distance of the object 4 by a predetermined time.
- the predetermined time may be set based on the time interval at which the sensor 11 transmits data including the type of the object 4 and the position information of the object 4 in real space to the control unit 14 .
- the predetermined time may be longer than the time interval at which the sensor 11 transmits the data to the control unit 14 .
- the control unit 14 acquires position information of the object 4 in real space by executing image recognition processing or the like, the predetermined time is determined based on the time interval at which the sensor 11 transmits image data to the control unit 14. , may be set.
- the predetermined time is, for example, 100 [ms].
- the control unit 14 calculates the speed of the object 4 at every predetermined time.
- the control unit 14 calculates the acceleration A1 of the object 4 at the measurement time t1 based on the velocity V1 of the object 4. For example, the control unit 14 acquires data on the velocity V0 of the object 4 that has already been stored in the storage unit 13. The speed V0 of the object 4 is the speed of the object 4 calculated immediately before the measurement time t1. In this embodiment, the control unit 14 calculates the velocity of the object 4 at predetermined intervals, so that the data of the velocity V0 of the object 4 is the same as the data measured at the measurement time t0, which is a predetermined time before the measurement time t1. Become.
- the control unit 14 calculates the acceleration A1 of the object 4 by subtracting the speed V0 from the speed V1 of the object 4 and dividing the difference by a predetermined time.
- the calculated acceleration A1 of the object 4 may be a positive acceleration or a negative acceleration.
- Positive acceleration is acceleration in the same direction as the traveling direction of the object 4.
- Negative acceleration is acceleration in the direction opposite to the direction of movement of the object 4.
- a negative acceleration is also a deceleration of the object 4.
- the control unit 14 calculates the acceleration of the object 4 at predetermined time intervals, as well as the speed of the object 4.
- the control unit 14 determines whether or not to adopt the speed V1 of the object 4 based on the result of comparing the value based on the speed V1 of the object 4 and the set threshold T1.
- the set threshold T1 is set based on predetermined conditions, as will be described later.
- the value based on the velocity V1 of the object 4 will be explained as being the acceleration A1 of the object 4.
- the control unit 14 determines whether or not to adopt the velocity V1 of the object 4 based on the result of comparing the acceleration A1 of the object 4 with the set threshold value T1.
- the value based on the velocity V1 of the object 4 is not limited to the acceleration A1 of the object 4.
- the value based on the velocity V1 of the object 4 may be any value based on the velocity V1 of the object 4.
- the value based on the velocity V1 of the object 4 may be any physical quantity that can be calculated from the velocity V1 of the object 4.
- the control unit 14 determines whether the absolute value of the acceleration A1 of the object 4 is greater than or equal to the set threshold T1 by comparing the acceleration A1 of the object 4 with the set threshold T1.
- the control unit 14 determines that the absolute value of the acceleration A1 of the object 4 is greater than or equal to the set threshold value T1
- the control unit 14 determines not to adopt the velocity V1 of the object 4.
- the control unit 14 determines that the absolute value of the acceleration A1 of the object is less than the set threshold T1
- the control unit 14 determines to adopt the speed V1 of the object 4.
- control unit 14 determines to adopt the speed V1 of the object 4, it executes a predetermined process using the speed V1 of the object 4. As an example of the predetermined process, the control unit 14 generates the above-mentioned support information using the velocity V1 of the object 4. Further, the control unit 14 causes the storage unit 13 to store data on the velocity V1 and acceleration A1 of the object 4 in association with the measurement time t1.
- the control unit 14 determines not to adopt the velocity V1 of the object 4, it acquires the data of the velocity V0 and acceleration A0 of the object 4 stored in the storage unit 13.
- the velocity V0 and acceleration A0 of the object 4 are calculated immediately before the measurement time t1.
- the control unit 14 calculates the acceleration of the object 4 at predetermined time intervals, so that the velocity V0 and acceleration A0 of the object 4 are calculated at the measurement time t0, which is a predetermined time before the measurement time t1. becomes.
- the control unit 14 newly calculates the velocity V1a of the object 4 at the measurement time t1 based on the data of the velocity V0 and acceleration A0 of the object 4. For example, the control unit 14 newly calculates the speed V1a at the measurement time t1 using the following equation (1).
- V1a V0+A0 ⁇ (t1-t0) Formula (1)
- the control unit 14 adopts the newly calculated speed V1a. That is, the control unit 14 executes the above-described predetermined process using the speed V1a. Further, the control unit 14 regards the acceleration A0 as the acceleration at the measurement time t1, and stores the data of the velocity V1a and the acceleration A0 in the storage unit 13 in association with the measurement time t1.
- the control unit 14 sets the set threshold T1 based on predetermined conditions.
- the predetermined condition includes at least one of a first condition, a second condition, a third condition, and a fourth condition.
- the predetermined conditions may be arbitrarily set based on factors that affect the type of object 4 or the detection accuracy of sensor 11, for example.
- the control unit 14 obtains the reference threshold value TH0 based on the first condition.
- the first condition is information regarding the type of object 4.
- the acceleration of the object 4 differs depending on the type of the object 4. For example, the acceleration of the object 4 when the object 4 is a pedestrian is smaller than the acceleration of the object 4 when the object 4 is a vehicle.
- the reference threshold TH0 is set in advance for each type of object 4.
- the reference threshold TH0 may be set in advance based on the absolute value of the average acceleration of the object 4 for each type of object 4.
- the reference threshold value TH0 may be stored in advance in the storage unit 13 in association with each type of object 4.
- the reference threshold value TH0 is set in advance as shown in FIG. In FIG. 3, the vehicle reference threshold TH0 is set to AA [m/s 2 ].
- the reference threshold value TH0 for a motorized bicycle is set to BB [m/s 2 ].
- the bicycle reference threshold TH0 is set to CC [m/s 2 ].
- the pedestrian reference threshold TH0 is set to DD [m/s 2 ].
- the control unit 14 acquires the standard threshold TH0 corresponding to the type of the object 4 from the storage unit 13 to acquire the standard threshold TH0 based on the first condition.
- the control unit 14 sets the set threshold T1 based on the acquired reference threshold TH0. For example, the control unit 14 may set the acquired reference threshold TH0 as the set threshold T1. Alternatively, as described below, the control unit 14 may generate the first threshold TH1 from the reference threshold TH0.
- the control unit 14 generates the first threshold TH1 from the reference threshold TH0 based on the second condition.
- the second condition is a condition regarding the type of sensor 11 that detected the information regarding the position of the object 4 used to calculate the velocity V1 of the object 4.
- the information regarding the position of the object 4 becomes information that allows the position of the object 4 to be specified in the real space by calculating the velocity V1 of the object 4 based on the position information of the object 4 in the real space. For example, when the control unit 14 calculates the velocity V1 of the object 4 based on the position information of the object 4 in real space detected by the sensor 11, the information regarding the position of the object 4 becomes the position information of the object 4 in real space. .
- information regarding the position of the object 4 becomes image data when the control unit 14 acquires position information of the object 4 in real space based on image data generated by the sensor 11.
- the sensors 11 include a type of sensor 11 that detects information regarding the position of the object 4 with high accuracy, and a type of sensor 11 that detects information regarding the position of the object 4 with low accuracy. If the sensor 11 that detected the information regarding the position of the object 4 used to calculate the speed V1 of the object 4 is a type of sensor 11 with low detection accuracy of information regarding the position of the object 4, the calculation error of the speed V1 of the object 4 is likely to become large. On the other hand, if the sensor 11 that detected the information regarding the position of the object 4 used to calculate the velocity V1 of the object 4 is a type of sensor 11 that has high accuracy in detecting information regarding the position of the object 4, then the velocity of the object 4 It is unlikely that the calculation error of V1 will become large.
- the detection accuracy of the information regarding the position of the object 4 may be the resolution of the image.
- the coarser the resolution of the image the lower the detection accuracy of the position information in real space of the object 4 acquired based on the image data.
- the control unit 14 determines whether the type of the sensor 11 that detected the information regarding the position of the object 4 used to calculate the velocity V1 of the object 4 is included in the predetermined types.
- the predetermined type is a type of sensor 11 that has low accuracy in detecting information regarding the position of object 4.
- the predetermined type may be selected in advance based on the desired calculation accuracy of the velocity of the object 4. That is, whether the detection accuracy of the sensor 11 of information regarding the position of the object 4 is low or high may be determined depending on the desired calculation accuracy of the speed of the object 4.
- the control unit 14 determines that the type of the sensor 11 is not included in the predetermined types, the control unit 14 directly acquires the reference threshold TH0 as the first threshold TH1.
- the control unit 14 generates the first threshold TH1 from the reference threshold TH0 by acquiring the reference threshold TH0 as it is as the first threshold TH1.
- the control unit 14 determines that the type of the sensor 11 is included in the predetermined type, the control unit 14 adjusts the reference threshold TH0 to be higher by a first percentage Y1, and acquires the adjusted reference threshold TH0 as the first threshold TH1. do.
- the control unit 14 generates the first threshold TH1 from the reference threshold TH0 by acquiring the adjusted reference threshold TH0 as the first threshold TH1. In adjusting the reference threshold TH0, the control unit 14 adds the first ratio Y1 of the reference threshold TH0 to the reference threshold TH0.
- the first ratio Y1 may be set based on the detection accuracy of a predetermined type of sensor 11.
- the control unit 14 may calculate the first threshold TH1 using the following equation (2).
- the first ratio Y1 is given as a percentage.
- TH1 TH0(1+0.01 ⁇ Y1)
- the control unit 14 sets the set threshold T1 based on the generated first threshold TH1. For example, the control unit 14 may set the generated first threshold TH1 as the set threshold T1. Alternatively, as described below, the control unit 14 may generate the second threshold TH2 from the first threshold TH1.
- the control unit 14 generates the second threshold TH2 from the first threshold TH1 based on the third condition.
- the third condition is a condition regarding the distance from the observation device 10 to the object 4.
- the control unit 14 calculates the velocity V1 of the object 4 based on the position information of the object 4 in real space detected by the sensor 11, the farther the distance from the observation device 10 to the object 4 is, the more the object 4 is detected by the sensor 11. 4, the detection accuracy of position information in real space decreases.
- the control unit 14 acquires the position information of the object 4 in real space based on the data of the image generated by the sensor 11, the longer the distance from the observation device 10 to the object 4, the more the image generated by the sensor 11. The distance per pixel becomes longer. The longer the distance per pixel of the image generated by the sensor 11, the lower the detection error of the position information in real space of the object 4 that the control unit 14 acquires based on the image data.
- the detection accuracy of the position information of the object 4 in real space decreases, the calculation error of the velocity V1 of the object 4 increases.
- the control unit 14 determines whether the distance from the observation device 10 to the object 4 is equal to or greater than the distance threshold.
- the control unit 14 may acquire (calculate) the distance from the observation device 10 to the object 4 from position information of the object 4 in real space or from the sensor 11.
- the distance threshold may be preset based on the boundary between a long distance and a short distance for the sensor 11.
- a long distance for the sensor 11 is a distance at which the detection accuracy of the sensor tends to decrease compared to a short distance for the sensor 11.
- the long distance and short distance for the sensor 11 differ depending on the type of sensor 11. For example, the higher the accuracy of the sensor 11 in detecting information about a distant object, the longer the distance for the sensor 11.
- the distance threshold value may be set for each type of sensor 11 and stored in the storage unit 13 in advance.
- the control unit 14 acquires from the storage unit 13 the distance threshold set for the sensor 11 that detected the information regarding the position of the object 4 used to calculate the velocity V1 of the object 4, and It may be determined whether the distance to is equal to or greater than the acquired distance threshold.
- the control unit 14 determines that the distance from the observation device 10 to the object 4 is less than the distance threshold, the control unit 14 directly acquires the first threshold TH1 as the second threshold TH2.
- the control unit 14 generates the second threshold TH2 from the first threshold TH1 by acquiring the first threshold TH1 as is as the second threshold TH2.
- the control unit 14 adjusts the first threshold TH1 to be higher by the second ratio Y2, and adjusts the adjusted first threshold TH1. is obtained as the second threshold TH2.
- the control unit 14 generates the second threshold TH2 from the first threshold TH1 by acquiring the adjusted first threshold TH1 as the second threshold TH2.
- the control unit 14 adds a second ratio Y2 of the first threshold TH1 to the first threshold TH1.
- the second ratio Y2 may be set depending on the type of sensor 11.
- the control unit 14 may calculate the second threshold TH2 using the following equation (3).
- equation (3) the second ratio Y2 is given as a percentage.
- TH2 TH1(1+0.01 ⁇ Y2) Formula (3)
- the control unit 14 sets the set threshold T1 based on the generated second threshold TH2. For example, the control unit 14 may set the generated second threshold TH2 as the set threshold T1. Alternatively, as described below, the control unit 14 may generate the set threshold T1 from the second threshold TH2.
- the control unit 14 generates the set threshold T1 from the second threshold TH2 based on the fourth condition.
- the fourth condition is a condition regarding the environment around the observation device 10.
- the detection accuracy of the sensor 11 may decrease. For example, when taking the weather as an example of the environment surrounding the observation device 10, when the weather is rain, snow, fog, or a dust storm, the detection accuracy of the sensor 11 is lower than when the weather is sunny or cloudy. . Further, when the sensor 11 is a visible light camera, the detection accuracy of the sensor 11 is lower when the amount of light in the environment surrounding the observation device 10 is low than when the amount of light is high.
- the fourth condition is set to be an environment surrounding the observation device 10 in which the detection accuracy of the sensor 11 is reduced.
- rain, snow, fog, or dust storm is set as a weather condition in which the detection accuracy of the sensor 11 is reduced.
- a nighttime time zone is set as a condition for a time zone in which the detection accuracy of the visible light camera decreases. In the night time period, the amount of light around the observation device 10 is lower than in the daytime time period.
- the control unit 14 determines whether or not the environment around the observation device 10 satisfies the environmental condition in which the detection accuracy of the sensor 11 is reduced, which is set as the fourth condition.
- the control unit 14 receives information about the weather in the area where the observation device 10 is installed from the external server 7 via the network 6. Information is received by the communication unit 12.
- the external server 7 is, for example, a server that provides weather information released by the Japan Meteorological Agency.
- the control unit 14 may estimate the weather in the area where the observation device 10 is installed by analyzing images acquired by the sensor 11, which is a visible light camera. If the weather in the area where the observation device 10 is installed matches the weather condition set as the fourth condition, the control unit 14 detects the sensor 11 in which the environment around the observation device 10 is set as the fourth condition. It is determined that the environmental conditions that reduce accuracy are met.
- the control unit 14 detects the sensor 11 in which the environment around the observation device 10 is set as the fourth condition. It is determined that the environmental conditions that reduce accuracy are not met.
- the control unit 14 detects information regarding the position of the object 4 used to calculate the velocity V1 of the object 4. It is determined whether the sensor 11 is a visible light camera. If the control unit 14 determines that the sensor 11 that detected the information regarding the position of the object 4 used to calculate the velocity V1 of the object 4 is a visible light camera, the control unit 14 acquires the current time. The control unit 14 determines whether the current time is included in the night time period set as the fourth condition. When the control unit 14 determines that the current time is included in the night time period set in the fourth condition, the detection accuracy of the sensor 11 in which the environment around the observation device 10 is set in the fourth condition decreases.
- control unit 14 determines that the current time is not included in the night time period set as the fourth condition, the detection accuracy of the sensor 11 in which the environment around the observation device 10 is set as the fourth condition is reduced. It is determined that the environment conditions to be used are not met.
- the control unit 14 determines that the environment around the observation device 10 does not satisfy the environmental condition that reduces the detection accuracy of the sensor 11 set as the fourth condition, the control unit 14 acquires the second threshold TH2 as it is as the set threshold T1. do.
- the control unit 14 generates the setting threshold T1 from the second threshold TH2 by acquiring the second threshold TH2 as it is as the setting threshold T1.
- the second threshold TH2 is increased by a third percentage Y3.
- the adjusted second threshold TH2 is obtained as the set threshold T1.
- the control unit 14 generates the set threshold T1 from the second threshold TH2 by acquiring the adjusted second threshold TH2 as the set threshold T1. In adjusting the second threshold TH2, the control unit 14 adds a third ratio Y3 of the second threshold TH2 to the second threshold TH2.
- FIG. 4 is a flowchart showing a method for calculating the velocity of the object 4 using the observation device 10 shown in FIG.
- This velocity calculation method corresponds to an example of the observation method according to the present embodiment.
- the control unit 14 acquires data including the type of the object 4 and the position information of the object 4 in real space from the sensor 11, it starts the process of step S1.
- the control unit 14 calculates the velocity V1 of the object 4 at the measurement time t1 based on the position information of the object 4 in real space (step S1).
- the control unit 14 acquires data on the velocity V0 of the object 4 that has already been stored in the storage unit 13 (step S2).
- the control unit 14 calculates the acceleration A1 of the object 4 at the measurement time t1 based on the velocity V1 of the object 4 calculated in the process of step S1 and the velocity V0 of the object 4 acquired in the process of step S2 (step S3). .
- the control unit 14 determines whether the absolute value of the acceleration A1 of the object 4 is greater than or equal to the set threshold T1 (step S4). When the control unit 14 determines that the absolute value of the acceleration A1 of the object 4 is less than the set threshold T1 (step S4: NO), the process proceeds to step S5. On the other hand, when the control unit 14 determines that the absolute value of the acceleration A1 of the object 4 is greater than or equal to the set threshold T1 (step S4: YES), the process proceeds to step S7.
- step S5 the control unit 14 determines to adopt the velocity V1 of the object 4.
- the control unit 14 stores the data of the velocity V1 and acceleration A1 of the object 4 in the storage unit 13 in association with the measurement time t1 (step S6).
- the control unit 14 determines not to adopt the velocity V1 of the object 4.
- the control unit 14 acquires the data of the acceleration A0 of the object 4 stored in the storage unit 13 (step S8).
- the control unit 14 newly calculates the velocity V1a of the object 4 at the measurement time t1 based on the velocity V0 of the object 4 acquired in the process of step S2 and the acceleration A0 of the object 4 acquired in the process of step S8 (step S9 ).
- the control unit 14 employs the calculated velocity V1a as the velocity of the object at the measurement time t1 (step S10).
- the control unit 14 stores the data of the velocity V1a and the acceleration A0 in the storage unit 13 in association with the measurement time t1 (step S11).
- the control unit 14 ends the process after executing the process of step S11. However, the control unit 14 may execute the process of step S1 again, for example, after a predetermined period of time.
- control unit 14 may acquire image data from the sensor 11.
- the control unit 14 may start the process of step S1.
- the control unit 14 calculates the velocity V1 of the object 4 at the measurement time t1 based on the position information of the object 4 in the image.
- FIG. 5 is a flowchart showing the flow of a method for setting the setting threshold T1 by the observation device 10 shown in FIG.
- This method of setting the setting threshold T1 corresponds to an example of the observation method according to the present embodiment.
- the control unit 14 may perform processing as shown in FIG. 5 before executing step S4 as shown in FIG. 4.
- the control unit 14 detects the type of the object 4, for example, by acquiring data including the type of the object 4 from the sensor 11 (step S21).
- the control unit 14 acquires the reference threshold value TH0 corresponding to the type of the object 4 from the storage unit 13 (step S22).
- the control unit 14 determines whether the type of sensor 11 is included in the predetermined types (step S23). When the control unit 14 determines that the type of the sensor 11 is included in the predetermined types (step S23: YES), the process proceeds to step S24. On the other hand, when the control unit 14 determines that the type of the sensor 11 is not included in the predetermined types (step S23: NO), the process proceeds to step S25.
- step S24 the control unit 14 adjusts the reference threshold TH0 to be higher by the first percentage Y1, and obtains the adjusted reference threshold TH0 as the first threshold TH1. After executing the process in step S24, the control unit 14 proceeds to the process in step S26.
- step S25 the control unit 14 obtains the reference threshold TH0 as it is as the first threshold TH1. After executing the process in step S25, the control unit 14 proceeds to the process in step S26.
- step S26 the control unit 14 determines whether the distance from the observation device 10 to the object 4 is greater than or equal to the distance threshold.
- step S26: YES the control unit 14 determines that the distance from the observation device 10 to the object 4 is equal to or greater than the distance threshold.
- step S26: NO the control unit 14 determines that the distance from the observation device 10 to the object 4 is less than the distance threshold.
- step S27 the control unit 14 adjusts the first threshold TH1 to be higher by the second percentage Y2, and obtains the adjusted first threshold TH1 as the second threshold TH2.
- step S29 the control unit 14 proceeds to the process in step S29.
- step S28 the control unit 14 obtains the first threshold TH1 as it is as the second threshold TH2. After executing the process in step S28, the control unit 14 proceeds to the process in step S29.
- step S29 the control unit 14 determines whether the weather in the area where the observation device 10 is installed matches a weather condition that reduces the detection accuracy of the sensor 11, which is set as the fourth condition.
- step S29: YES the control unit 14 determines that the weather in the area where the observation device 10 is installed matches the weather set as the fourth condition.
- step S29: NO the control unit 14 determines that the weather in the area where the observation device 10 is installed does not match the weather set as the fourth condition.
- control unit 14 adjusts the second threshold TH2 to be higher by a third proportion Y3, and obtains the adjusted second threshold TH2 as the set threshold T1.
- control unit 14 obtains the second threshold TH2 as it is as the set threshold T1.
- control unit 14 may detect the type of the object 4 by, for example, performing image recognition processing on the image data acquired from the sensor 11.
- the control unit 14 determines whether the sensor 11 that detected the position information of the object 4 used to calculate the velocity V1 of the object 4 is a visible light camera. good. If the control unit 14 determines that the sensor 11 that detected the information regarding the position of the object 4 used to calculate the velocity V1 of the object 4 is a visible light camera, the control unit 14 may acquire the current time. The control unit 14 may determine whether the current time is included in a night time period in which the detection accuracy of the visible light camera set to the fourth condition is reduced. When the control unit 14 determines that the current time is included in the night time period set in the fourth condition (step S29: YES), the control unit 14 may proceed to the process of step S30. If the control unit 14 determines that the current time is not included in the night time period set in the fourth condition (step S29: NO), the control unit 14 may proceed to the process of step S31.
- the control unit 14 calculates the velocity V1 of the object 4 based on the position information of the object 4 in real space.
- the control unit 14 determines whether or not to adopt the speed V1 of the object 4 based on the result of comparing the value based on the speed V1 of the object 4 with the set threshold T1.
- the detection accuracy of the sensor 11 decreases due to various factors. If the detection accuracy of the sensor 11 decreases, the error in calculating the velocity of the object 4 may increase. If the calculation error in the velocity of the object 4 is large, for example, when the moving body 5 that has received support information including data on the velocity of the object 4 displays the position of the object 4 on the display based on its velocity, the object 4 may suddenly move. It may appear to move or stop.
- the detection accuracy of the sensor 11 is reduced by determining whether or not to adopt the speed V1 of the object 4 based on the result of comparing the value based on the speed V1 of the object 4 and the set threshold value T1. In this case, it may be determined not to adopt the velocity V1 of the object 4. In addition, by determining whether or not to adopt the speed V1 of the object 4 based on the result of comparing the value based on the speed V1 of the object 4 and the set threshold value T1, it is possible to detect the object when the detection accuracy of the sensor 11 does not decrease. It can be determined to adopt the speed V1 of 4.
- the value based on the velocity V1 of the object 4 may be the acceleration A1 of the object 4.
- the control unit 14 may determine whether or not to adopt the speed of the object 4 based on the result of comparing the acceleration A1 of the object 4 and the set threshold value T1. As described above, when the detection accuracy of the sensor 11 decreases due to some factor and the calculation error of the velocity V1 of the object 4 increases, the absolute value of the acceleration A1 of the object 4 increases. By using the acceleration A1 of the object 4 as a value based on the speed V1 of the object 4, the control unit 14 can more accurately determine whether to employ the speed V1 of the object 4.
- control unit 14 when the control unit 14 determines to adopt the calculated velocity V1 of the object 4, it may store the acceleration A1 of the object 4 and the velocity V1 of the object 4 in association with the measurement time t1.
- the control unit 14 determines not to adopt the velocity of the object 4 calculated at the measurement time t2 after the measurement time t1, the control unit 14 updates the velocity of the object 4 at the measurement time t2 using the stored acceleration A1 and the velocity V1 of the object 4. It can be calculated as follows.
- control unit 14 may newly calculate the velocity V1a of the object 4 at the measurement time t1 based on the stored acceleration A0 and velocity V0 of the object 4. good.
- the acceleration A0 and velocity V0 of the object 4 may be measured (calculated) immediately before the measurement time t1.
- the control unit 14 can calculate the velocity V1a of the object 4 at the measurement time t1 with higher accuracy.
- control unit 14 may set the setting threshold T1 based on predetermined conditions.
- the predetermined conditions may be arbitrarily set based on factors that affect the type of object 4 or the detection accuracy of sensor 11, for example. With such a configuration, it is possible to prevent the setting threshold T1 from being set unnecessarily high or unnecessarily low. Therefore, the control unit 14 can more accurately determine whether or not to adopt the velocity V1 of the object 4.
- control unit 14 may obtain the reference threshold TH0 based on the first condition regarding the type of the object 4.
- the control unit 14 may obtain the reference threshold TH0 corresponding to the type of the object 4 by obtaining the reference threshold TH0 based on the first condition.
- the acceleration of the object 4 differs depending on the type of the object 4.
- the control unit 14 generates the first threshold TH1 from the reference threshold TH0 based on a second condition regarding the type of the sensor 11 that detected the information regarding the position of the object 4 used to calculate the velocity V1 of the object 4. It's okay.
- a second condition regarding the type of the sensor 11 that detected the information regarding the position of the object 4 used to calculate the velocity V1 of the object 4. It's okay.
- control unit 14 may determine whether the type of sensor 11 is included in the predetermined types. When the control unit 14 determines that the type of the sensor 11 is included in the predetermined type, the control unit 14 adjusts the reference threshold TH0 to be higher by a first proportion Y1, and obtains the adjusted reference threshold TH0 as the first threshold TH1.
- the first threshold TH1 may be generated from the reference threshold TH0.
- the predetermined type is the type of sensor 11 in which the accuracy of detecting information regarding the position of the object 4 is low.
- the first The threshold value TH1 can be increased.
- the setting threshold value T1 that is set based on the first threshold value TH1 can be increased depending on the type of sensor 11.
- the control unit 14 may generate the first threshold TH1 from the reference threshold TH0 by acquiring the reference threshold TH0 as it is as the first threshold TH1. good.
- the sensor 11 that detects information regarding the position of the object 4 used to calculate the velocity V1 of the object 4 is a type of sensor 11 that has high accuracy in detecting information regarding the position of the object 4, the first It is possible to prevent the threshold value TH1 from becoming unnecessarily high. By suppressing the first threshold value TH1 from becoming unnecessarily high, it is possible to suppress the setting threshold value T1 that is set based on the first threshold value TH1 from becoming unnecessarily high.
- control unit 14 may generate the second threshold TH2 from the first threshold TH1 based on a third condition regarding the distance from the observation device 10 to the object 4. As described above, the longer the distance from the observation device 10 to the object 4, the lower the detection accuracy of the position information of the object 4 in real space.
- the control unit 14 may generate the second threshold TH2 from the first threshold TH1 based on the third condition, it is possible to prevent the setting threshold T1 set based on the second threshold TH2 from becoming unnecessarily high or unnecessarily low. Can be suppressed.
- the control unit 14 may adjust the first threshold TH1 to be higher by the second ratio Y2.
- the control unit 14 may generate the second threshold TH2 from the first threshold TH1 by acquiring the adjusted first threshold TH1 as the second threshold TH2.
- the distance threshold value may be set for each type of sensor 11. As described above, the long distance and short distance for the sensor 11 differ depending on the type of sensor 11.
- the second threshold TH2 is increased according to the type of sensor 11 by adjusting the first threshold TH1 to be higher by a second proportion Y2 when the distance from the observation device 10 to the object 4 is equal to or greater than the distance threshold. I can do it. With such a configuration, it is possible to increase the setting threshold T1 that is set based on the second threshold TH2 depending on the type of sensor 11.
- the control unit 14 determines that the distance from the observation device 10 to the object 4 is less than the distance threshold, the control unit 14 changes the first threshold TH1 to the second threshold TH2 by acquiring the first threshold TH1 as it is as the second threshold TH2. may be generated.
- the second threshold value TH2 it is possible to prevent the second threshold value TH2 from becoming unnecessarily high depending on the type of sensor 11.
- By suppressing the second threshold TH2 from becoming unnecessarily high it is possible to suppress the setting threshold T1, which is set based on the second threshold TH2, from becoming unnecessarily high.
- control unit 14 may generate the set threshold T1 from the second threshold TH2 based on a fourth condition regarding the environment around the observation device 10. As described above, depending on the environment around the observation device 10, the detection accuracy of the sensor 11 may decrease. By generating the set threshold T1 from the second threshold TH2 based on the fourth condition, it is possible to prevent the set threshold T1 from becoming unnecessarily high or low.
- the observation device includes: Calculating the speed of the object based on position information of the object, and determining whether to adopt the calculated speed of the object based on the result of comparing a value based on the calculated speed of the object with a set threshold value.
- a control unit is provided.
- the value based on the velocity of the object is the acceleration of the object
- the control unit determines whether to adopt the calculated velocity of the object based on a result of comparing the acceleration of the object with the set threshold.
- the control unit includes: Comparing the acceleration of the object with the set threshold, determining whether the absolute value of the acceleration of the object is equal to or greater than the set threshold; If it is determined that the absolute value of the acceleration of the object is greater than or equal to the set threshold, it is determined that the calculated speed of the object is not adopted.
- the control unit includes: Comparing the acceleration of the object with the set threshold, determining whether the absolute value of the acceleration of the object is equal to or greater than the set threshold; If it is determined that the absolute value of the acceleration of the object is less than the set threshold, it is determined that the calculated speed of the object is to be adopted.
- control unit determines to employ the calculated velocity of the object
- the control unit stores the acceleration of the object calculated based on the calculated velocity of the object and the calculated velocity of the object.
- control unit determines not to use the calculated velocity of the object
- the control unit newly calculates the velocity of the object based on the stored acceleration and velocity of the object.
- the set threshold value is set based on a predetermined condition.
- the predetermined conditions are: a first condition regarding the type of the object; a second condition regarding the type of sensor that detected the information regarding the position of the object used to calculate the speed of the object; a third condition regarding the distance from the observation device to the object; and a fourth condition regarding the environment surrounding the observation device; Contains at least one of the following.
- the control unit includes: obtaining a reference threshold based on the first condition; The set threshold is set based on the reference threshold.
- the control unit obtains the reference threshold value corresponding to the type of the object.
- the control unit includes: generating a first threshold from the reference threshold based on the second condition; The set threshold is set based on the first threshold.
- the control unit includes: When it is determined that the type of the sensor is included in the predetermined type, the reference threshold value is adjusted to be higher by a first percentage, and the adjusted reference threshold value is obtained as the first threshold value, thereby increasing the reference threshold value from the reference threshold value by a first percentage. generate a first threshold; When it is determined that the type of the sensor is not included in the predetermined type, the first threshold is generated from the reference threshold by acquiring the reference threshold as the first threshold.
- the control unit includes: generating a second threshold from the first threshold based on the third condition; The set threshold is set based on the second threshold.
- the control unit includes: If it is determined that the distance from the observation device to the object is equal to or greater than a distance threshold, the first threshold is adjusted to be higher by a second percentage, and the adjusted first threshold is obtained as the second threshold. generating the second threshold from the first threshold; When it is determined that the distance from the observation device to the object is less than the distance threshold, the second threshold is generated from the first threshold by acquiring the first threshold as is as the second threshold.
- the control unit includes: The set threshold is generated from the second threshold based on the fourth condition.
- the fourth condition includes an environment surrounding the observation device in which the detection accuracy of a sensor that detects position information of the object is reduced;
- the control unit includes: When the environment around the observation device satisfies the environmental condition set in the fourth condition, the second threshold is adjusted to be higher by a third percentage, and the adjusted second threshold is set as the set threshold. generating the set threshold from the second threshold by acquiring; If the environment around the observation device does not satisfy the environmental conditions set in the fourth condition, the second threshold is directly acquired as the set threshold, thereby generating the set threshold from the second threshold.
- the observation method includes: Calculating the speed of the object based on position information of the object; The method includes determining whether or not to adopt the calculated speed of the object based on a result of comparing a value based on the calculated speed of the object with a set threshold value.
- each functional unit, each means, each step, etc. may be added to other embodiments so as not to be logically contradictory, or each functional unit, each means, each step, etc. of other embodiments may be added to other embodiments to avoid logical contradiction. It is possible to replace it with Further, in each embodiment, it is possible to combine or divide a plurality of functional units, means, steps, etc. into one. Further, each embodiment of the present disclosure described above is not limited to being implemented faithfully to each described embodiment, but may be implemented by combining each feature or omitting a part as appropriate. You can also do that.
- the predetermined conditions are described as including the first condition, the second condition, the third condition, and the fourth condition.
- the predetermined conditions may include any one of the first condition, the second condition, the third condition, and the fourth condition.
- the predetermined conditions may include only the first condition and the fourth condition.
- the control unit 14 obtains the reference threshold TH0 based on the first condition, as described above.
- the control unit 14 generates the set threshold T1 from the reference threshold TH0 based on the fourth condition using the same or similar processing as described above.
- the method of calculating the velocity V1 and acceleration A1 of the object 4 is not limited to the example described above. Another example of the method for calculating the velocity V1 of the object 4 will be described below.
- the control unit 14 uses the position information of the object 4 in real space at the measurement time t1 and the position information of the object 4 in the real space at a set time before the measurement time t1 to determine the position from before the set time to the measurement time t1.
- the distance traveled by the object 4 may be calculated.
- the control unit 14 may calculate the speed V1 of the object 4 by dividing the calculated moving distance by the set time.
- the set time may be longer than the predetermined time.
- the set time is the same as the time interval at which the sensor 11 transmits the above-mentioned data to the control unit 14, or It may be longer than the interval.
- the control unit 14 calculates the acceleration A1 of the object 4 by subtracting the velocity before the measurement time t1 from the velocity V1 of the object 4, and dividing the difference by the set time. You may calculate the acceleration A1 of . Even when calculating the speed and acceleration of the object 4 in other examples, the control unit 14 may calculate the speed and acceleration of the object 4 at predetermined time intervals.
- control unit 14 was described as setting the set threshold value T1 for comparison with the absolute value of the acceleration A1 of the object 4.
- the control unit 14 may set the setting threshold T1 based on predetermined conditions for other uses.
- the control unit 14 may set a set threshold T1 in order to determine whether objects detected by a plurality of different sensors 11 are the same object.
- the control unit 14 may determine whether the objects detected by the plurality of different sensors 11 are the same object.
- the plurality of sensors 11 include a sensor 11A and a sensor 11B. The type of sensor 11A and the type of sensor 11B are different.
- the control unit 14 uses the position of the object detected by the sensor 11A in real space and the position of the object detected by the sensor 11B in real space. It is determined whether or not the position is within a set threshold value T1. If the control unit 14 determines that the position of the object detected by the sensor 11A in real space and the position of the object detected by the sensor 11B in real space are within the set threshold T1, the control unit 14 controls the objects detected by the sensors 11A and 11B, respectively. are determined to be the same object.
- the control unit 14 determines that the position of the object detected by the sensor 11A in the real space and the position of the object detected by the sensor 11B in the real space are not within the set threshold T1, the control unit 14 controls the sensors 11A and 11B respectively. It is determined that the detected objects are not the same object.
- the detection accuracy of the sensor 11 decreases due to various factors. When the detection accuracy of the sensor 11 decreases, the measurement error of the position in real space of the object detected by each of the plurality of sensors 11 may increase. Even in such a case, by determining whether the positions of the objects detected by the sensors 11A and 11B in real space are within the set threshold T1, it is possible to determine whether the objects detected by the sensors 11A and 11B are the same object.
- descriptions such as “first” and “second” are identifiers for distinguishing the configurations.
- the numbers in the configurations can be exchanged.
- the first condition and the second condition can exchange the identifiers "first” and "second”.
- the exchange of identifiers takes place simultaneously.
- the configurations are distinguished.
- Identifiers may be removed.
- Configurations with removed identifiers are distinguished by codes. The description of identifiers such as “first” and “second” in this disclosure should not be used to interpret the order of the configuration or to determine the existence of lower-numbered identifiers.
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Electromagnetism (AREA)
- Power Engineering (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
Description
物体の位置情報に基づいて前記物体の速度を算出し、算出した前記物体の速度に基づく値と設定閾値とを比較した結果に基づいて前記算出した物体の速度を採用するか否かを決定する制御部を備える。
物体の位置情報に基づいて前記物体の速度を算出することと、
算出した前記物体の速度に基づく値と設定閾値とを比較した結果に基づいて前記算出した物体の速度を採用するか否かを決定することと、を含む。
センサ11は、生成した画像のデータに対して画像認識処理を実行することにより、画像のデータから物体4を検出する。センサ11は、生成した画像のデータに対して画像認識処理を実行することにより、物体4の種類を検出してもよい。物体4の種類は、例えば、車両、原動機付自転車、自転車又は歩行者等である。画像認識処理は、例えば、パターンマッチング又は深層学習等の機械学習等の処理である。センサ11がLiDAR又はミリ波レーダを含んで構成される場合、センサ11は、例えば、LiDAR又はミリ波レーダの測定結果から得られた点群データを基に画像のデータを生成して画像認識処理を実行してもよい。センサ11がミリ波レーダを含んで構成される場合、センサ11は、例えば、ミリ波レーダの測定結果から得られた速度データ等を基に物体4及び物体の種類を検出してもよい。
制御部14は、センサ11から、センサ11が生成した画像のデータを取得する。制御部14は、取得した画像のデータに対して画像認識処理を実行することにより、画像のデータから物体4を検出する。制御部14は、取得した画像のデータに対して画像認識処理を実行することにより、物体4の種類を検出してもよい。センサ11がLiDAR又はミリ波レーダを含んで構成される場合、制御部14は、例えば、センサ11から、LiDAR又はミリ波レーダの測定結果から得られた点群データを取得してよい。制御部14は、取得した点群データを基に画像のデータを生成し、生成した画像のデータに対して画像認識処理を実行することにより、画像のデータから物体4及び物体4の種類を検出してもよい。センサ11がミリ波レーダを含んで構成される場合、制御部14は、例えば、センサ11から、ミリ波レーダの測定結果から得られた速度データ等を取得してよい。制御部14は、取得した速度データ等を基に、物体4及び物体4の種類を検出してもよい。
制御部14は、センサ11が検出した又は制御部14が取得した物体4の実空間における位置情報に基づいて、物体4の速度V1を算出する。以下、物体4の速度V1を算出(測定)する時刻は、測定時刻t1とも記載される。制御部14は、測定時刻t1での物体4の実空間における位置情報と、測定時刻t1よりも所定時間前での物体4の実空間における位置情報とによって、所定時間前から測定時刻t1までに物体4が移動した移動距離を算出する。制御部14は、算出した物体4の移動距離を所定時間で除算することより、物体4の速度V1を算出する。所定時間は、センサ11が制御部14に、物体4の種類と、物体4の実空間における位置情報とを含むデータを送信する時間間隔に基づいて、設定されてよい。所定時間は、センサ11が制御部14に当該データを送信する時間間隔よりも長くてよい。なお、制御部14が画像認識処理等を実行することにより物体4の実空間における位置情報を取得する場合、所定時間は、センサ11が制御部14に画像のデータを送信する時間間隔に基づいて、設定されてよい。所定時間は、例えば、100[ms]である。以下、制御部14は、所定時間毎に物体4の速度を算出するものとする。
V1a=V0+A0×(t1-t0) 式(1)
制御部14は、所定条件に基づいて、設定閾値T1を設定する。所定条件は、第1条件、第2条件、第3条件及び第4条件の少なくとも何れかを含む。ただし、所定条件は、例えば物体4の種類又はセンサ11の検出精度に影響する要因に基づいて、任意に設定されてよい。
制御部14は、第1条件に基づいて、基準閾値TH0を取得する。第1条件は、物体4の種類に関する情報である。物体4の種類に応じて、物体4の加速度が異なる。例えば、物体4が歩行者である場合の物体4の加速度は、物体4が車両である場合の物体4の加速度よりも小さくなる。
制御部14は、第2条件に基づいて、基準閾値TH0から第1閾値TH1を生成する。第2条件は、物体4の速度V1の算出に用いられた物体4の位置に関する情報を検出したセンサ11の種類に関する条件である。物体4の位置に関する情報は、物体4の速度V1が物体4の実空間における位置情報に基づいて算出されることにより、物体4の位置を実空間において特定可能な情報となる。例えば、物体4の位置に関する情報は、センサ11が検出した物体4の実空間における位置情報に基づいて制御部14が物体4の速度V1を算出した場合、物体4の実空間における位置情報となる。例えば、物体4の位置に関する情報は、センサ11が生成した画像のデータに基づいて制御部14が物体4の実空間における位置情報を取得した場合、画像のデータとなる。
TH1=TH0(1+0.01×Y1) 式(2)
制御部14は、第3条件に基づいて、第1閾値TH1から第2閾値TH2を生成する。第3条件は、観察装置10から物体4までの距離に関する条件である。ここで、センサ11が検出した物体4の実空間における位置情報に基づいて制御部14が物体4の速度V1を算出する場合、観察装置10から物体4までの距離が遠いほど、センサ11の物体4の実空間における位置情報の検出精度が低下する。また、センサ11が生成した画像のデータに基づいて制御部14が物体4の実空間における位置情報を取得する場合、観察装置10から物体4までの距離が遠いほど、センサ11が生成する画像の1画素あたりの距離が長くなる。センサ11が生成する画像の1画素あたりの距離が長いほど、制御部14が画像のデータに基づいて取得する物体4の実空間における位置情報の検出誤差が低下する。
TH2=TH1(1+0.01×Y2) 式(3)
制御部14は、第4条件に基づいて、第2閾値TH2から設定閾値T1を生成する。第4条件は、観察装置10の周囲の環境に関する条件である。観察装置10の周囲の環境によっては、センサ11の検出精度が低下する場合がある。例えば、観察装置10の周囲の環境として天気を例に挙げる場合、天気が雨、雪、霧又は砂塵嵐であるとき、天気が晴れ又は曇りであるときよりも、センサ11の検出精度が低下する。また、センサ11が可視光カメラである場合、観察装置10の周囲の環境として周囲の光量が低いときは、光量が高いときよりも、センサ11の検出精度が低下する。
T1=TH2(1+0.01×Y3) 式(4)
図4は、図1に示す観察装置10による物体4の速度の算出方法の流れを示すフローチャートである。この速度の算出方法は、本実施形態に係る観察方法の一例に相当する。例えば、制御部14は、センサ11から物体4の種類と、物体4の実空間における位置情報とを含むデータを取得すると、ステップS1の処理を開始する。
物体の位置情報に基づいて前記物体の速度を算出し、算出した前記物体の速度に基づく値と設定閾値とを比較した結果に基づいて前記算出した物体の速度を採用するか否かを決定する制御部を備える。
前記物体の速度に基づく値は、前記物体の加速度であり、
前記制御部は、前記物体の加速度と前記設定閾値とを比較した結果に基づいて、前記算出した物体の速度を採用するか否かを決定する。
前記制御部は、
前記物体の加速度と前記設定閾値とを比較することとして、前記物体の加速度の絶対値が前記設定閾値以上であるか否かを判定し、
前記物体の加速度の絶対値が前記設定閾値以上であると判定した場合、前記算出した物体の速度を採用しないと決定する。
前記制御部は、
前記物体の加速度と前記設定閾値とを比較することとして、前記物体の加速度の絶対値が前記設定閾値以上であるか否かを判定し、
前記物体の加速度の絶対値が前記設定閾値を下回ると判定した場合、前記算出した物体の速度を採用すると決定する。
前記制御部は、前記算出した物体の速度を採用すると決定した場合、前記算出した物体の速度に基づいて算出される前記物体の加速度と、前記算出した物体の速度とを保存する。
前記制御部は、前記算出した物体の速度を採用しないと決定した場合、前記物体の速度を保存済みの前記物体の加速度及び速度に基づいて新たに算出する。
前記保存済みの物体の加速度及び速度は、前記採用するか否かが決定される前記物体の速度を算出した時刻の直前に算出されたものである。
前記設定閾値は、所定条件に基づいて設定される。
前記所定条件は、
前記物体の種類に関する第1条件、
前記物体の速度の算出に用いられた前記物体の位置に関する情報を検出したセンサの種類に関する第2条件、
前記観察装置から前記物体までの距離に関する第3条件、及び、
前記観察装置の周囲の環境に関する第4条件、
の少なくとも何れかを含む。
前記制御部は、
前記第1条件に基づいて基準閾値を取得し、
前記基準閾値に基づいて前記設定閾値を設定する。
前記制御部は、前記物体の種類に対応する前記基準閾値を取得する。
前記制御部は、
前記第2条件に基づいて前記基準閾値から第1閾値を生成し、
前記第1閾値に基づいて前記設定閾値を設定する。
前記制御部は、
前記センサの種類が所定種類に含まれると判定した場合、前記基準閾値が第1割合高くなるように調整し、調整後の前記基準閾値を前記第1閾値として取得することにより前記基準閾値から前記第1閾値を生成し、
前記センサの種類が所定種類に含まれないと判定した場合、前記基準閾値をそのまま前記第1閾値として取得することにより前記基準閾値から前記第1閾値を生成する。
前記制御部は、
前記第3条件に基づいて前記第1閾値から第2閾値を生成し、
前記第2閾値に基づいて前記設定閾値を設定する。
前記制御部は、
前記観察装置から前記物体までの距離が距離閾値以上であると判定した場合、前記第1閾値が第2割合高くなるように調整し、調整後の前記第1閾値を前記第2閾値として取得することにより前記第1閾値から前記第2閾値を生成し、
前記観察装置から前記物体までの距離が前記距離閾値を下回ると判定した場合、前記第1閾値をそのまま前記第2閾値として取得することにより前記第1閾値から前記第2閾値を生成する。
前記制御部は、
前記第4条件に基づいて前記第2閾値から前記設定閾値を生成する。
前記第4条件には、前記観察装置の周囲の環境であって、前記物体の位置情報を検出するセンサの検出精度が低下する環境の条件が設定され、
前記制御部は、
前記観察装置の周囲の環境が前記第4条件に設定された環境の条件を満たす場合、前記第2閾値が第3割合高くなるように調整し、調整後の前記第2閾値を前記設定閾値として取得することにより前記第2閾値から前記設定閾値を生成し、
前記観察装置の周囲の環境が前記第4条件に設定された環境の条件を満たさない場合、前記第2閾値をそのまま前記設定閾値として取得することにより前記第2閾値から前記設定閾値を生成する。
物体の位置情報に基づいて前記物体の速度を算出することと、
算出した前記物体の速度に基づく値と設定閾値とを比較した結果に基づいて前記算出した物体の速度を採用するか否かを決定することと、を含む。
2 路面
3 構造物
4 物体
5 移動体
6 ネットワーク
7 サーバ
10 観察装置
11,11A,11B センサ
12 通信部
13 記憶部
14 制御部
A0 加速度
A1 加速度
T1 設定閾値
TH0 基準閾値
TH1 第1閾値
TH2 第2閾値
V0,V1,V1a 速度
Y1 第1割合
Y2 第2割合
Y3 第3割合
t0,t1 測定時刻
Claims (18)
- 物体の位置情報に基づいて前記物体の速度を算出し、算出した前記物体の速度に基づく値と設定閾値とを比較した結果に基づいて前記算出した物体の速度を採用するか否かを決定する制御部を備える、観察装置。
- 前記物体の速度に基づく値は、前記物体の加速度であり、
前記制御部は、前記物体の加速度と前記設定閾値とを比較した結果に基づいて、前記算出した物体の速度を採用するか否かを決定する、請求項1に記載の観察装置。 - 前記制御部は、
前記物体の加速度と前記設定閾値とを比較することとして、前記物体の加速度の絶対値が前記設定閾値以上であるか否かを判定し、
前記物体の加速度の絶対値が前記設定閾値以上であると判定した場合、前記算出した物体の速度を採用しないと決定する、請求項2に記載の観察装置。 - 前記制御部は、
前記物体の加速度と前記設定閾値とを比較することとして、前記物体の加速度の絶対値が前記設定閾値以上であるか否かを判定し、
前記物体の加速度の絶対値が前記設定閾値を下回ると判定した場合、前記算出した物体の速度を採用すると決定する、請求項2に記載の観察装置。 - 前記制御部は、前記算出した物体の速度を採用すると決定した場合、前記算出した物体の速度に基づいて算出される前記物体の加速度と、前記算出した物体の速度とを保存する、請求項1から4までの何れか一項に記載の観察装置。
- 前記制御部は、前記算出した物体の速度を採用しないと決定した場合、前記物体の速度を保存済みの前記物体の加速度及び速度に基づいて新たに算出する、請求項1から4までの何れか一項に記載の観察装置。
- 前記保存済みの物体の加速度及び速度は、前記採用するか否かが決定される前記物体の速度を算出した時刻の直前に算出されたものである、請求項6に記載の観察装置。
- 前記設定閾値は、所定条件に基づいて設定される、請求項1に記載の観察装置。
- 前記所定条件は、
前記物体の種類に関する第1条件、
前記物体の速度の算出に用いられた前記物体の位置に関する情報を検出したセンサの種類に関する第2条件、
前記観察装置から前記物体までの距離に関する第3条件、及び、
前記観察装置の周囲の環境に関する第4条件、
の少なくとも何れかを含む、請求項8に記載の観察装置。 - 前記制御部は、
前記第1条件に基づいて基準閾値を取得し、
前記基準閾値に基づいて前記設定閾値を設定する、請求項9に記載の観察装置。 - 前記制御部は、前記物体の種類に対応する前記基準閾値を取得する、請求項10に記載の観察装置。
- 前記制御部は、
前記第2条件に基づいて前記基準閾値から第1閾値を生成し、
前記第1閾値に基づいて前記設定閾値を設定する、請求項10又は11に記載の観察装置。 - 前記制御部は、
前記センサの種類が所定種類に含まれると判定した場合、前記基準閾値が第1割合高くなるように調整し、調整後の前記基準閾値を前記第1閾値として取得することにより前記基準閾値から前記第1閾値を生成し、
前記センサの種類が所定種類に含まれないと判定した場合、前記基準閾値をそのまま前記第1閾値として取得することにより前記基準閾値から前記第1閾値を生成する、請求項12に記載の観察装置。 - 前記制御部は、
前記第3条件に基づいて前記第1閾値から第2閾値を生成し、
前記第2閾値に基づいて前記設定閾値を設定する、請求項12に記載の観察装置。 - 前記制御部は、
前記観察装置から前記物体までの距離が距離閾値以上であると判定した場合、前記第1閾値が第2割合高くなるように調整し、調整後の前記第1閾値を前記第2閾値として取得することにより前記第1閾値から前記第2閾値を生成し、
前記観察装置から前記物体までの距離が前記距離閾値を下回ると判定した場合、前記第1閾値をそのまま前記第2閾値として取得することにより前記第1閾値から前記第2閾値を生成する、請求項14に記載の観察装置。 - 前記制御部は、
前記第4条件に基づいて前記第2閾値から前記設定閾値を生成する、請求項14に記載の観察装置。 - 前記第4条件には、前記観察装置の周囲の環境であって、前記物体の位置情報を検出するセンサの検出精度が低下する環境の条件が設定され、
前記制御部は、
前記観察装置の周囲の環境が前記第4条件に設定された環境の条件を満たす場合、前記第2閾値が第3割合高くなるように調整し、調整後の前記第2閾値を前記設定閾値として取得することにより前記第2閾値から前記設定閾値を生成し、
前記観察装置の周囲の環境が前記第4条件に設定された環境の条件を満たさない場合、前記第2閾値をそのまま前記設定閾値として取得することにより前記第2閾値から前記設定閾値を生成する、請求項16に記載の観察装置。 - 物体の位置情報に基づいて前記物体の速度を算出することと、
算出した前記物体の速度に基づく値と設定閾値とを比較した結果に基づいて前記算出した物体の速度を採用するか否かを決定することと、を含む、観察方法。
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2024517194A JPWO2023210397A1 (ja) | 2022-04-26 | 2023-04-13 | |
| US18/859,090 US20250290945A1 (en) | 2022-04-26 | 2023-04-13 | Observation device and observation method |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2022072588 | 2022-04-26 | ||
| JP2022-072588 | 2022-04-26 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2023210397A1 true WO2023210397A1 (ja) | 2023-11-02 |
Family
ID=88518513
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/JP2023/015077 Ceased WO2023210397A1 (ja) | 2022-04-26 | 2023-04-13 | 観察装置及び観察方法 |
Country Status (3)
| Country | Link |
|---|---|
| US (1) | US20250290945A1 (ja) |
| JP (1) | JPWO2023210397A1 (ja) |
| WO (1) | WO2023210397A1 (ja) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002022832A (ja) * | 2000-07-10 | 2002-01-23 | Denso Corp | 物体認識方法及び装置、記録媒体 |
| JP2016192169A (ja) * | 2015-03-31 | 2016-11-10 | 株式会社デンソー | 物体検知装置、及び物体検知方法 |
| WO2018079297A1 (ja) * | 2016-10-27 | 2018-05-03 | 日立オートモティブシステムズ株式会社 | 故障検知装置 |
-
2023
- 2023-04-13 WO PCT/JP2023/015077 patent/WO2023210397A1/ja not_active Ceased
- 2023-04-13 US US18/859,090 patent/US20250290945A1/en active Pending
- 2023-04-13 JP JP2024517194A patent/JPWO2023210397A1/ja active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002022832A (ja) * | 2000-07-10 | 2002-01-23 | Denso Corp | 物体認識方法及び装置、記録媒体 |
| JP2016192169A (ja) * | 2015-03-31 | 2016-11-10 | 株式会社デンソー | 物体検知装置、及び物体検知方法 |
| WO2018079297A1 (ja) * | 2016-10-27 | 2018-05-03 | 日立オートモティブシステムズ株式会社 | 故障検知装置 |
Also Published As
| Publication number | Publication date |
|---|---|
| JPWO2023210397A1 (ja) | 2023-11-02 |
| US20250290945A1 (en) | 2025-09-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112215306B (zh) | 一种基于单目视觉与毫米波雷达融合的目标检测方法 | |
| US11538241B2 (en) | Position estimating device | |
| US20220373353A1 (en) | Map Updating Method and Apparatus, and Device | |
| CN109829351B (zh) | 车道信息的检测方法、装置及计算机可读存储介质 | |
| WO2021259344A1 (zh) | 车辆检测方法、装置、车辆和存储介质 | |
| US7580548B2 (en) | Abnormality detecting apparatus for imaging apparatus | |
| JP2021117048A (ja) | 変化点検出装置及び地図情報配信システム | |
| CN109993060B (zh) | 深度摄像头的车辆全向障碍物检测方法 | |
| CN111461048B (zh) | 基于视觉的停车场可行驶区域检测与局部地图构建方法 | |
| CN106203272B (zh) | 确定可移动对象的移动的方法和装置 | |
| US20060114318A1 (en) | Abnormality detecting apparatus for imaging apparatus | |
| CN112666535A (zh) | 一种基于多雷达数据融合的环境感知方法及系统 | |
| US10839522B2 (en) | Adaptive data collecting and processing system and methods | |
| WO2014192137A1 (ja) | 移動軌跡予測装置及び移動軌跡予測方法 | |
| US11189162B2 (en) | Information processing system, program, and information processing method | |
| JP2022079777A (ja) | 情報処理装置 | |
| CN120065228B (zh) | 一种基于视觉及雷达融合的矿用车辆安全行驶检测系统 | |
| US12525024B2 (en) | Electronic device, method, and computer readable storage medium for detection of vehicle appearance | |
| CN113734176A (zh) | 智能驾驶车辆的环境感知系统、方法、车辆及存储介质 | |
| CN108021899A (zh) | 基于双目相机的车载智能前车防撞预警方法 | |
| JP5910180B2 (ja) | 移動物体位置姿勢推定装置及び方法 | |
| CN116071730B (zh) | 背景对象的检测方法、装置、设备以及自动驾驶车辆 | |
| CN117765724A (zh) | 车辆事故预警方法、设备及系统 | |
| CN115512542B (zh) | 一种基于路侧激光雷达的考虑遮挡的轨迹复原方法及系统 | |
| WO2023210397A1 (ja) | 観察装置及び観察方法 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 23796141 Country of ref document: EP Kind code of ref document: A1 |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 2024517194 Country of ref document: JP |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 18859090 Country of ref document: US |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 23796141 Country of ref document: EP Kind code of ref document: A1 |
|
| WWP | Wipo information: published in national office |
Ref document number: 18859090 Country of ref document: US |