Observation apparatus and observation method

Abstract

Continuously monitor the detection performance of the observation device. [Solution] The observation device includes an observation unit, a storage unit, and a control unit. The observation unit observes a predetermined area. The storage unit stores the viewing distance, which indicates the maximum distance at which an observation target within the predetermined area can be identified, and a threshold value. Based on the results of the first observation by the observation unit, the control unit obtains the maximum observation distance, which indicates the distance to the location of the furthest identified first observation target, and sets the viewing distance and threshold value based on the comparison result between the maximum observation distance and the threshold value. When predetermined conditions are met, the control unit decreases the threshold value.

Description

Technical Field

[0001] The present disclosure relates to an observation device and an observation method.

Background Art

[0002] Observation devices that confirm the surrounding situation by sensors and perform information processing, and systems using the same have been developed. For example, in the field of transportation systems, an observation device is installed on the roadside to detect the presence of observation targets such as vehicles and pedestrians, and depending on the distance to the observation target, a safety driving support system that notifies an approaching vehicle of the presence of the observation target has been developed (see, for example, Patent Document 1). It is preferable that the operating status of such an observation device can be grasped at all times. The observation device described in Patent Document 1 constantly provides information indicating whether or not the safety driving support service is operating normally to vehicles traveling in the vicinity. As a result, the driver of the vehicle can grasp the operating status of the driving support service, and in a situation where the driving support service is not provided, avoid the risk of relying on the driving support service and performing dangerous driving.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, even when the observation device is operational, the range detectable by the device may fluctuate due to influences from the surrounding environment. For example, the sensing performance of roadside observation devices may deteriorate due to weather conditions such as heavy rain or dense fog. In situations where the observation device cannot correctly detect the target, a vehicle receiving driving assistance services from the roadside observation device may not be able to distinguish between a situation where the target does not exist and a situation where the target exists but the observation device cannot detect it. As a result, driving assistance for the vehicle may not be performed properly, and the vehicle may be exposed to risks such as accidents. In such situations, the reliability of the entire system, including the observation device, may be compromised.

[0005] Therefore, in light of the problems of the prior art described above, the purpose of this disclosure is to enable continuous monitoring of the detection performance of the observation device. [Means for solving the problem]

[0006] In one embodiment, (1) the observation device includes an observation unit for observing a predetermined area, a storage unit for storing a viewing distance indicating the maximum distance at which an object to be observed within the predetermined area can be identified, and a threshold, and a control unit that, based on the first observation result of the observation unit, acquires the maximum observation distance indicating the distance to the location of the furthest identified first object to be observed, and sets the viewing distance and the threshold based on the result of comparing the maximum observation distance and the threshold, wherein the control unit decreases the threshold when predetermined conditions are met.

[0007] (2) In the observation device described in (1) above, the control unit may set the viewing distance and the threshold to the same length as the maximum observation distance when the value of the maximum observation distance is greater than the threshold.

[0008] (3) In the observation apparatus of (1) or (2) above, the predetermined conditions may include the value of the maximum observation distance being the same as or less than the threshold.

[0009] (4) In any of the observation devices described in (1) to (3) above, the predetermined conditions may include the fact that the first object of observation is different from the second object of observation that is located furthest away and was identified in the second observation performed prior to the first observation.

[0010] (5) In any of the observation devices described in (1) to (4) above, the control unit may decrease the threshold by a predetermined percentage at predetermined intervals when the predetermined conditions are met.

[0011] (6) In any of the observation devices described in (1) to (4) above, the control unit may decrease the threshold by a decrease amount that changes at predetermined time intervals when the predetermined conditions are met.

[0012] (7) In any of the observation devices described in (1) to (6) above, the observation unit may include any of a visible light camera, an FIR camera, a LiDAR, a millimeter-wave radar, and an ultrasonic sonar.

[0013] (8) In any of the observation devices described in (1) to (7) above, the observation unit includes a sensor that recognizes the weather in the predetermined area, and the control unit can initialize the visibility distance and the threshold value based on the recognized weather.

[0014] In one embodiment, (9) the observation method is an observation method performed by an observation device, which includes: obtaining observation results from an observation unit after observing a predetermined area; storing a viewing distance indicating the maximum distance at which an object to be observed within the predetermined area can be identified, and a threshold in a storage unit; obtaining a maximum observation distance indicating the distance to the location of the furthest identified first object to be observed based on the observation results; setting the viewing distance and the threshold based on a comparison result between the maximum observation distance and the threshold; and decreasing the threshold when a predetermined condition is met. [Effects of the Invention]

[0015] According to the observation device described above, the detection performance of the observation device can be continuously monitored.

Brief Description of the Drawings

[0016] [Figure 1] It is a diagram showing a configuration example of a communication system including an observation device according to an embodiment. [Figure 2] It is a block diagram showing a schematic configuration of the observation device of FIG. 1. [Figure 3] It is a state diagram showing the fixed state of the observation device of FIG. 1. [Figure 4] It is a flowchart for explaining the processing executed by the control unit of FIG. 2. [Figure 5] It is a diagram showing an example of changes in the visual range distance and the distance threshold value accompanying the movement of the observation target observed by the observation device. [Figure 6] It is a diagram showing an example of changes in the visual range distance and the distance threshold value accompanying the movement of the observation target observed by the observation device. [Figure 7] It is a diagram showing an example of changes in the visual range distance and the distance threshold value accompanying the movement of the observation target observed by the observation device. [Figure 8] It is a diagram showing an example of changes in the visual range distance and the distance threshold value accompanying the movement of the observation target observed by the observation device. [Figure 9] It is a diagram showing an example of changes in the visual range distance and the distance threshold value accompanying the movement of the observation target observed by the observation device.

Embodiments for Carrying Out the Invention

[0017] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings.

[0018] (Configuration of a Communication System Including an Observation Device) FIG. 1 shows a configuration example of a communication system 11 including an observation device 10 according to an embodiment. The communication system 11 is, for example, a safety driving support communication system of an advanced road traffic system (ITS: Intelligent Transport Systems). The safety driving support communication system may be called a safety driving support system or a safety driving support wireless system.

[0019] Observation device 10 may be a device that observes observation targets such as vehicles, objects, and people on the road. The observation device 10 may be, for example, a roadside unit, a surveillance camera device, etc. In the present embodiment, the observation device 10 is a roadside unit and may be arranged near an intersection where a plurality of roads 12 (lanes) intersect to observe the road surface. For example, the observation device 10 may observe the road surface in the extending direction of the road connected from the intersection. The observation device 10 may be arranged on the roadside other than the intersection.

[0020] The observation device 10 may notify the vehicle 13 of notification information for assisting the safe driving of the driver of the vehicle 13. The notification information may include information regarding the observation targets existing on the road to be observed. The information regarding the observation targets may include the presence or absence of the observation targets, the positions of the observation targets, the types of the existing observation targets, the distance to the observation device 10, the moving speed, and the traveling direction. The notification information may further include information regarding the visibility distance described later.

[0021] The vehicle 13 may acquire various information notified from the observation device 10 etc. by the electronic devices mounted thereon. The electronic devices mounted on the vehicle 13 may be, for example, a car navigation system etc. The electronic devices mounted on the vehicle 13 may assist the safe driving of the driver by giving notifications such as warnings based on the information notified from the observation device 10. The notification to the driver may be the types, positions, speeds, traveling directions, etc. of other vehicles 13 and pedestrians etc. near the intersection being traveled. As described above, the communication system 11 may assist the safe driving of the driver of the vehicle 13. The vehicle 13 is not limited to automobiles. For example, the vehicle 13 may include motorcycles, buses, and streetcars.

[0022] (Configuration of the Observation Device) The details of the observation device 10 will be described below. As shown in FIG. 2, the observation device 10 includes an observation unit 17, a storage unit 18, and a control unit 19. The observation device 10 may further include a communication unit 20.

[0023] The observation unit 17 observes a predetermined region. More specifically, the observation unit 17 may observe the predetermined region by detecting electromagnetic waves or sound waves incident from that region. The observation unit 17 may include at least one sensor.

[0024] The sensor may detect electromagnetic waves or sound waves incident from a predetermined area. The sensor may be, for example, a camera such as a visible light camera or an FIR camera that captures far-infrared images, and a distance measuring sensor such as a millimeter-wave radar, LiDAR, and ultrasonic sonar. A visible light camera can capture a normal image (RGB image) of a subject. An FIR camera can capture a far-infrared image corresponding to temperature and can detect the temperature of the subject being observed. A distance measuring sensor may emit a projected wave and measure the distance to the reflection point on an object based on the time from the time the projected wave is emitted to the time the reflected wave from the object to which the projected wave is received.

[0025] The sensor may generate a detection signal based on the detection of electromagnetic waves or sound waves. In a configuration where the sensor is a camera, the detection signal may be an image. In a configuration where the sensor is a distance measuring sensor, the detection signal may be a distance distribution including distance values ​​for each direction in which reflected waves are generated for projected waves such as millimeter waves, near-infrared light, and sound waves. The sensor may generate the detection signal at a predetermined period. The generation period of the detection signal is, for example, 100 ms.

[0026] An observation coordinate system may be defined in the observation unit 17. The observation coordinate system may be a three-dimensional coordinate system with an origin at an arbitrary position in the observation unit 17 and three mutually perpendicular axes passing through the origin as coordinate axes. The origin of the observation coordinate system is, for example, the intersection of the detection axis of any sensor in the observation unit 17 and the detection element. The observation coordinate system includes, for example, a line parallel to the detection axis of the arbitrary sensor as one of its coordinate axes. The detection axis may be the central axis of the sensor's detection range. In the case of a camera, for example, the detection axis is the optical axis.

[0027] As shown in Figure 3, the observation device 10 may be fixed to a structure 22 that has a height capable of capturing images of the scenery including the roads 12 outdoors, such as a traffic signal device, utility pole, or streetlamp near an intersection where roads 12 intersect. The position and orientation of the observation unit 17 relative to the structure 22 may be predetermined. For example, by fixing the observation device 10 to the structure 22 such that the upper end of the detection range of the observation device 10 is parallel to a part of the road 12, observation can be performed over a greater distance.

[0028] The position of the observation unit 17 refers to the position of the origin of the observation coordinate system relative to a reference position in the world coordinate system. The orientation of the observation unit 17 refers to the inclination of the coordinate axes of the observation coordinate system relative to the coordinate axes of the world coordinate system. In this disclosure, "world coordinate system" refers to a coordinate system set based on the three-dimensional space outside the observation unit 17. The world coordinate system may have axes in the vertical direction of real space and two directions parallel to and perpendicular to the horizontal plane.

[0029] The position and orientation of the observation unit 17 may be determined such that the detection axis dx of the observation unit 17 intersects the road surface of the road 12. The position and orientation of the observation unit 17 may be determined such that the detection range of the observation unit 17 includes a predetermined area defined relative to the observation device 10.

[0030] The observation unit 17 may further include a weather recognition sensor. The weather recognition sensor may be a sensor common to any of the aforementioned visible light camera and FIR camera that captures far-infrared images, as well as distance measuring sensors such as millimeter-wave radar, LiDAR, and ultrasonic sonar, or it may be a sensor different from those sensors. For example, the visible light camera and FIR camera can recognize changes in weather such as heavy rain or dense fog based on changes in the image. The visible light camera and FIR camera may be provided as weather recognition sensors separately from sensors that detect objects to be observed within a predetermined area. In addition, the weather recognition sensor may include one or more arbitrary sensors such as a temperature sensor, humidity sensor, illuminance meter, barometer, and rain gauge.

[0031] In Figure 2, the storage unit 18 includes any storage device, such as RAM (Random Access Memory) and ROM (Read Only Memory). The storage unit 18 may store various programs that enable the control unit 19 to function, and various information used by the control unit 19.

[0032] The memory unit 18 may store distance values ​​from the distance measuring sensor to the road surface or floor surface separately for each direction, in a configuration in which the observation unit 17 includes a distance measuring sensor. The distance values ​​from the distance measuring sensor to the road surface may be sampled by fixing the observation unit 17 to the structure 22 and allowing the distance measuring sensor to detect the distance when there is nothing on the road surface or floor surface. "On the road surface or floor surface" may mean a state in contact with the road surface or floor surface.

[0033] The memory unit 18 may store a conversion formula or conversion table for converting the coordinates of pixels in a two-dimensional coordinate system to the world coordinate system when the pixels constituting the image acquired from the camera represent objects on the road or floor. Using this conversion formula or conversion table, the position in the world coordinate system and the distance to the observation unit 17 of the objects on the road or floor included in the image acquired from the camera can be obtained.

[0034] The memory unit 18 stores the visibility distance. The visibility distance is the maximum distance at which the control unit 19 can identify the presence of an object in a predetermined area based on the detection signal. Identifying the presence of an object means determining that an object exists and, further, being able to identify the type of object present. The memory unit 18 may store a single visibility distance. The memory unit 18 may store the visibility distance for each type of object. Examples of object types include pedestrians, bicycles, motorcycles, passenger cars, and large vehicles. The memory unit 18 may store the initial and current values ​​of the visibility distance, as well as the initial and current values ​​of the distance threshold, which is a threshold set for comparison with the maximum observation distance described later. The initial value of the visibility distance may be set to 0 or a sufficiently short value assuming that the surrounding environment is considerably deteriorated. The initial value of the distance threshold may be set to the same value as the initial value of the visibility distance. The current values ​​of the visibility distance and the distance threshold may be the visibility distance and distance threshold set immediately before the observation process being executed.

[0035] The memory unit 18 stores information about a second observation target, which is the furthest identifiable observation target detected in at least one previous observation among the observations sequentially and repeatedly performed by the observation device 10. The memory unit 18 may store at least one of the following information about the second observation target: an image, its position in the world coordinate system, its size, its velocity, and its direction of travel. This information may be used to determine whether a first observation target, which is the furthest identifiable observation target observed at a given point in time, is the same as or different from the second observation target observed in the previous observation.

[0036] In Figure 2, the control unit 19 includes one or more processors and memory. The processors may include general-purpose processors that load specific programs and execute specific functions, and dedicated processors specialized for specific processing. The dedicated processors may include application-specific integrated circuits (ASICs). The processors may include programmable logic devices (PLDs). The PLDs may include field-programmable gate arrays (FPGAs). The control unit 19 may be either a system-on-a-chip (SoC) or a system-in-a-package (SiP) in which one or more processors cooperate.

[0037] In a configuration where the sensor included in the observation unit 17 is a camera, the control unit 19 may detect a subject image corresponding to the object to be observed by known image recognition methods such as pattern matching and deep learning on the image as a detection signal. The control unit 19 may determine the presence or absence of the object to be observed by detecting the subject image. The control unit 19 may identify the type of object to be observed by image recognition along with the detection of the subject image. The control unit 19 may calculate the position in the world coordinate system of the object to be observed corresponding to the subject image by converting the position of the pixels of the part of the detected subject image that is in contact with the road surface from a two-dimensional coordinate system to a world coordinate system. The control unit 19 may obtain the distance from the observation device 10 to the object to be observed from the position in the world coordinate system of the observation device 10 and the position in the world coordinate system of the object to be observed. The acquisition of the distance to the object to be observed may be performed each time an image is acquired by the observation device 10. For example, in a configuration where the sensor included in the observation unit 17 is a 30fps camera, the acquisition of the distance to the object to be observed may be performed at a frequency of 30 times per second.

[0038] In a configuration where the sensor included in the observation unit 17 is a distance measuring sensor, the control unit 19 may detect an object on the road or floor by extracting distance values ​​from the distance distribution as a detection signal that are different from the distance value to the road or floor, along with the corresponding direction. The control unit 19 may separately detect groups of distance values ​​from among the distance values ​​corresponding to the detected object, where the difference between the distance values ​​is less than or equal to a predetermined value and the corresponding directions are close to each other. The control unit 19 may detect these groups of distance values ​​as objects to be observed. The control unit 19 may obtain the distance to the objects to be observed by, for example, averaging the groups of distance values. The control unit 19 may estimate the size of the objects to be observed based on the distances and the spread of the corresponding directions of the groups of distance values. The control unit 19 may identify the type of objects to be observed based on the size of the objects to be observed.

[0039] The control unit 19 may acquire and identify the speed and direction of travel of the detected object based on a plurality of detection signals with consecutive detection times. The control unit 19 may perform tracking processing of the detected object based on a plurality of detection signals with consecutive detection times.

[0040] The control unit 19 updates the line of sight distance stored in the memory unit 18 based on the distance to the location of the first observation target, which is the furthest observation target among the identified one or more observation targets. In the following description, the observation target will be described as a vehicle 13. However, the observation target is not limited to a vehicle 13, but may also be a pedestrian 14.

[0041] The control unit 19 acquires the maximum observation distance, which indicates the distance to the location of the furthest observable vehicle 13, the first observation target, based on the observation results from the observation unit 17 at each point in time. The control unit 19 may determine the maximum observation distance to be the maximum value among the distances to the locations of multiple vehicles 13 identified based on a single detection signal. Alternatively, the control unit 19 may determine the maximum observation distance to be the maximum value among the distances to the locations of identified vehicles 13 among multiple detection signals. Alternatively, the control unit 19 may determine the maximum observation distance to be the maximum distance at which vehicles 13 determined to be the same are detected among multiple detection signals.

[0042] The control unit 19 can set the viewing distance based on the comparison result between the maximum observation distance and the distance threshold. For example, when the value of the maximum observation distance is greater than the distance threshold, the control unit 19 sets the viewing distance and the distance threshold to the same length as the maximum observation distance. The control unit 19 is also configured to continuously decrease the distance threshold when predetermined conditions are met. That is, in an environment where the maximum observation distance is reduced, the control unit 19 continuously decreases the distance threshold, and when the distance threshold becomes smaller than the value of the maximum observation distance, it sets the viewing distance to the maximum observation distance. In this way, the control unit 19 can reduce the viewing distance in accordance with the reduction in the maximum observation distance. On the other hand, in an environment where the maximum observation distance is increasing, the maximum observation distance immediately becomes longer than the distance threshold, so the viewing distance can be increased in accordance with the increase in the maximum observation distance. The control unit 19 may perform the process for updating the viewing distance periodically or periodically.

[0043] Thus, the control unit 19 uses a distance threshold that changes according to the maximum observation distance, and updates the visibility distance only when the value of the maximum observation distance is greater than the distance threshold. The control unit 19 does not change the visibility distance each time the maximum observation distance changes. As a result, the calculated visibility distance is less affected by changes in the position of the furthest vehicle 13 that happens to be traveling on the road 12. Therefore, the calculated visibility distance becomes a stable distance that corresponds to the distance at which the observation device 10 can actually identify the observation target.

[0044] The control unit 19 may set the visibility distance and distance threshold to a length obtained by correcting the maximum observation distance when the value of the maximum observation distance is greater than the distance threshold. For example, the control unit 19 may set the visibility distance and distance threshold by considering the average length of the vehicle 13. Alternatively, for example, the control unit 19 may set the visibility distance and distance threshold by considering the time difference from observation by the sensor to setting the visibility distance, based on the speed of the vehicle 13 related to the maximum observation distance.

[0045] The predetermined conditions under which the control unit 19 reduces the distance threshold include the maximum observation distance being equal to or less than the distance threshold. That is, the control unit 19 sequentially reduces the distance threshold when it is equal to or greater than the maximum observation distance. For example, if the distance at which the observation device 10 can identify an object becomes shorter due to the effects of weather, the maximum observation distance based on the vehicle 13 actually being observed also becomes shorter. The control unit 19 repeatedly reduces the distance threshold in response to the shortening of the maximum observation distance, and when the maximum observation distance becomes longer than the distance threshold, it sets the maximum observation distance to the visibility distance.

[0046] The aforementioned predetermined conditions under which the control unit 19 reduces the distance threshold include the fact that the vehicle 13 (first observation target) located furthest from the observation device 10 in the current observation (first observation) is different from the vehicle 13 (second observation target) located furthest in the previous observation (second observation). This condition is set to prevent the distance threshold from being reduced in accordance with the same vehicle 13 approaching the observation device 10 from a distance, even though the visibility distance has not changed, when there are few vehicles 13 traveling on the road 12. This prevents the visibility distance from being set shorter than the distance at which the observation device 10 can actually identify.

[0047] The control unit 19 may decrease the distance threshold by a predetermined percentage at predetermined time intervals when the predetermined conditions described above are met. The predetermined time and predetermined percentage can be set arbitrarily. For example, the predetermined time can be 100 ms and the predetermined percentage can be 90 percent. In this case, the distance threshold will decrease to about half of the original distance threshold in about 600 ms. For example, if the distance at which the observation device 10 can identify decreases from 200 m to 100 m due to a sudden change in weather, the distance threshold will follow this decrease in about 600 ms, so the control unit 19 can set the visibility distance to about 100 ms after about 600 ms.

[0048] The control unit 19 may reduce the distance threshold by a time-varying decrease when the predetermined conditions described above are met. For example, the control unit 19 may reduce the distance threshold to 50% from the start when the maximum observation distance rapidly decreases. Alternatively, the control unit 19 may sequentially increase the amount or percentage of reduction of the distance threshold, for example, by setting the distance threshold to 90%, 80%, 70%, etc., of the previous value. In this way, the control unit 19 can respond to rapid environmental changes and quickly update the visibility distance.

[0049] If the observation unit 17 includes a weather sensor, the control unit 19 may directly reduce the visibility distance and distance threshold to predetermined values ​​when it determines, based on the output of the weather sensor, that weather conditions such as heavy rain or dense fog are affecting the detection performance of the observation device 10. For example, the predetermined values ​​may be initial values. In other words, the control unit 19 may initialize the visibility distance and distance threshold based on the recognized weather conditions. This allows the control unit 19 to immediately shorten the visibility distance when it determines, based on the weather sensor, that the weather has changed rapidly.

[0050] The control unit 19 does not need to change either the visibility distance or the distance threshold when it does not detect a vehicle 13 on the road 12. This is because the absence of vehicles 13 on the road 12 due to low traffic volume is unrelated to the change in the visibility distance of the observation device 10. However, if no vehicle 13 is detected for a certain period of time, the control unit 19 may generate notification information indicating that no vehicle 13 has been detected for that period of time. The control unit 19 may control the communication unit 20 to notify vehicles 13 or pedestrians 14, etc., around the observation device 10 of the generated notification information.

[0051] The communication unit 20 may be controlled by the control unit 19 to communicate wirelessly with the vehicle 13. The communication unit 20 may consist of a communication circuit and an antenna. The antenna may be, for example, an omnidirectional antenna. The communication unit 20 may communicate wirelessly using, for example, the 700 MHz band allocated to ITS. Alternatively, the communication unit 20 may communicate wirelessly using, for example, a wireless LAN (Local Area Network).

[0052] The communication unit 20 may perform various processing, such as amplification, on the signal received by the antenna and output the processed received signal to the control unit 19. The control unit 19 may perform various processing on the input received signal to obtain information contained in the received signal. The communication unit 20 may perform various processing, such as amplification, on the information obtained from the control unit 19 and wirelessly transmit the processed transmission signal from the antenna.

[0053] (Processing procedure executed by the control unit) Next, the processing procedure of the observation method executed by the control unit 19 in this embodiment will be described using the flowchart in Figure 4. The following processing procedure of the observation method can be executed by the processor constituting the control unit 19 included in the observation device 10 according to a program. Such a program can be stored in a non-temporary computer-readable medium. Examples of non-temporary computer-readable media include, but are not limited to, hard disks, ROMs, flash memory, CD-ROMs, optical storage devices, magnetic storage devices, etc.

[0054] When observation by the observation device 10 begins, the control unit 19 performs initialization processing (step S101). The control unit 19 sets the viewing distance and distance threshold to initial values. If the control unit 19 has information about the observation target used in a previous observation remaining in the storage unit 18, it may erase it.

[0055] In the following, the control unit 19 repeatedly executes the processes from step S102 to step S110. The control unit 19 may execute the processes from step S102 to step S110 at predetermined time intervals. In the following description, the processes of the routine from step S102 to step S110 that are currently being executed will be described as the "current" processes. The processes of the routine from step S102 to step S110 that were executed one cycle prior to the currently executing routine will be described as the "previous" processes.

[0056] In step S102, the control unit 19 determines whether the observation result from the observation unit 17 includes the object to be observed. The sensors included in the observation unit 17 may repeatedly observe a predetermined area at a speed faster than the repetition rate of the routine from steps S102 to S110 in the flowchart of Figure 4. The control unit 17 may acquire a portion of the observation result from the sensors of the observation unit 17 at an appropriate timing. Specifically, the observation result is a detection signal, which may be a single, most recent detection signal, or a group of detection signals from the start of the update process up to a predetermined time interval prior. If the observation result in step S102 does not include the object to be observed, the control unit 19 proceeds to the process in step S110. If the observation result includes the object to be observed, the control unit 19 proceeds to the process in step S103.

[0057] In step S103, the control unit 19 detects the furthest identifiable object (the first object) and turns OFF a flag indicating whether or not to update the distance threshold. The flag is related to whether or not to perform the process of reducing the distance threshold in step S109, which will be described later. The control unit 19 may detect multiple objects and calculate the distance to each object. Based on the calculated distance to each object, the control unit 19 may extract the first object.

[0058] After step S103, the control unit 19 determines whether the first object of observation is the same object as the object that was located furthest away and identifiable during the previous observation (the second object of observation) (step S104). If the observation unit 17 is a visible light camera or an FIR camera, the control unit 19 may determine identity by comparing the image of the previously observed object (the second object of observation) stored in the memory unit 18 with the image of the first object of observation observed this time. Alternatively, the control unit 19 may determine identity with the first object of observation by sequentially detecting the position, velocity, and direction of the second object of observation and tracking the change in position. The control unit 19 may assign an identifier to each of the multiple objects of observation detected in the previous observation, track their movement, and determine identity between the first and second objects of observation.

[0059] In step S104, if the first object of observation is different from the second object of observation (step S104: No), the control unit 19 turns the flag ON in step S105 and proceeds to step S106. The control unit 19 may also proceed to step S106 via step S105 when it performs the processing of step S104 for the first time after step S101. In step S104, if the first object of observation is the same as the second object of observation (step S104: Yes), the control unit 19 proceeds to step S106 without changing the flag from OFF.

[0060] In step S106, the control unit 19 determines whether the value of the maximum observation distance obtained from the current observation is greater than the distance threshold (step S106). If the maximum observation distance is greater than the distance threshold (step S106: Yes), the control unit 19 sets the viewing distance and the distance threshold to be the same as the maximum observation distance and turns the flag OFF (step S107). If the value of the maximum observation distance in step S106 is less than or equal to the distance threshold (step S106: No), and after step S107, the control unit 19 proceeds to step S108.

[0061] In step S108, the control unit 19 checks a flag (step S108). If the flag is ON (step S108: Yes), the control unit 19 performs a process to reduce the distance threshold (step S109). For example, the control unit 19 sets a predetermined percentage of the current distance threshold as the new distance threshold. The predetermined percentage is, for example, 90%, but is not limited to this. In step S109, the control unit 19 reduces the distance threshold each time the furthest detected observation target changes in the routine from step S102 to step S110, in environments where the maximum observation distance has been shortened due to bad weather, etc. If the flag is OFF in step S108 (step S108: No), and after step S109, the control unit 19 proceeds to the process in step S110.

[0062] In step S110, the control unit 19 returns to step S102 unless it receives a signal from an external source to terminate the process (step S110: No). The control unit 19 has a timer and may adjust the time to return to step S102 so that the observation of step S102 is performed at predetermined time intervals. The predetermined time interval can be, for example, 100 ms, but is not limited to this. In step S110, if the control unit 19 receives a signal from an external source to terminate the process (step S110: Yes), it terminates the process shown in the flowchart of Figure 4.

[0063] (Example of observation device operation) Next, an example of the operation of the observation device 10 will be explained using Figures 5 to 9. In Figures 5 to 9, the detection limit Dl indicates the physical limit at which the observation device 10 can identify a vehicle 13 at a distance from the observation device 10. In Figures 5 to 9, different vehicles 13 are labeled as Vehicle 13A to Vehicle 13H to distinguish them. In Figures 5 to 9, it is assumed that the observation device 10 can detect a vehicle 13 when the center of the vehicle 13 is located on the side of the observation device 10 at the detection limit Dl, which is the limit at which the observation device 10 can identify the vehicle 13. In Figures 5 to 9, vehicles 13 that are not detected by the observation device 10 are shown with dashed lines.

[0064] First, let's assume that vehicles 13A through 13D are traveling towards the observation device 10, as shown in Figures 5 through 7. In Figures 5 through 7, the position of the detection limit Dl is assumed to remain unchanged.

[0065] Figure 5 shows the state after the first observation by the observation device 10 has started. In Figure 5, the furthest identifiable observation target is vehicle 13C. In step S107 of the flowchart in Figure 4, the control unit 19 sets the visibility distance Dv and the distance threshold Td to the distance to vehicle 13C.

[0066] Next, let's assume that as time passes, vehicles 13A to 13D move towards the observation device 10, resulting in the state shown in Figure 6. The furthest observation target remains vehicle 13C. In this case, step S104 in the flowchart of Figure 4 becomes "Yes," and S105 is not executed, so the flag remains OFF. Because the flag is OFF, step S108 becomes "No," and the reduction of the distance threshold (step S109) is not executed. As a result, in Figure 6, the visibility distance Dv and the distance threshold Td remain unchanged from the state in Figure 5. That is, even if vehicle 13C, the furthest observation target, moves towards the observation device 10, the visibility distance Dv does not change.

[0067] As time progresses from Figure 6, and as shown in Figure 7, vehicle 13D moves inside the detection limit Dl and becomes the furthest observation target that can be identified from the observation device 10. The distance of vehicle 13D from the observation device 10 in Figure 7 is assumed to be greater than the distance of vehicle 13C in Figure 5. In this case, step S106 in the flowchart of Figure 4 becomes "Yes," so in step S107, the visibility distance Dv and the distance threshold Td are set to the distance from the observation device 10 to vehicle 13D. In this way, the visibility distance Dv approaches the detection limit Dl of the observation device 10. That is, the control unit 19 is set to a stable distance without fluctuating finely in response to the movement of the observation target at each point in time.

[0068] Next, Figure 8 shows the case where time has progressed from the state in Figure 5, and the detection limit Dl has moved closer to the observation device 10 due to changes in weather, etc. In this case, if the furthest vehicle 13 changes from the previous observation point in step S104 of the flowchart in Figure 4 (step S104: No), the flag is turned ON in step S105. At the stage in Figure 8, the value of the maximum observation distance, which is the distance to the furthest vehicle 13F (first observation target) that the observation device 10 can identify, is smaller than the distance threshold (step S106: No), so the control unit 19 reduces the distance threshold in step S109. In this way, the distance threshold is reduced each time the first observation target changes.

[0069] Furthermore, suppose that from the state in Figure 8, vehicles 13E to 13H move towards the observation device 10, as shown in Figure 9, and vehicle 13G becomes the first observation target. In this case, at step S106 of the flowchart in Figure 4, the distance from the observation device 10 to vehicle 13G becomes greater than the distance threshold Td (step S106: Yes). Therefore, in step S107, the control unit 19 sets the visibility distance Dv and the distance threshold Td to the distance from the observation device 10 to vehicle 13G. As a result, the visibility distance Dv approaches the detection limit Dl of the observation device 10 after the change.

[0070] Furthermore, even when the vehicle 13 is moving away from the observation device 10, the viewing distance can be updated to the maximum distance at which the observation device 10 can actually identify the object by processing the flowchart in Figure 4.

[0071] As described above, the observation device 10 of this embodiment can quickly update its visibility range even when the observable range changes due to influences from the surrounding environment, such as changes in weather. Therefore, the observation device 10 can continuously grasp its own detection performance. In addition, the observation device 10 can notify the outside of its visibility range. This maintains the reliability of the communication system 11, including the observation device 10. For example, when the observation device 10 is installed on the roadside, the observation device 10 can transmit the visibility range to surrounding vehicles 13, etc., at an appropriate timing. As a result, surrounding vehicles 13, etc., can obtain information on the range in which the observation device 10 can detect the target, enabling safer driving control.

[0072] In the above embodiment, the observation device 10 is a device on the road 12, such as a roadside unit or a surveillance camera. However, the observation device 10 is not limited to a device on the road 12 and can be applied to various systems under various circumstances. For example, the observation device 10 can be used as a device for observing ships and / or aircraft. Furthermore, the observation device 10 does not need to be fixed and may be movable. In that case, the predetermined area observed by the observation unit 17 may move together with the observation device 10.

[0073] Furthermore, in the above embodiment, the observation device 10 transmits the visibility distance as notification information to surrounding devices, but the observation device 10 does not have to transmit the visibility distance itself to the outside. The observation device 10 may perform processing based on the latest visibility distance in the control unit 19 and notify the outside of the processing results. For example, when the visibility distance becomes shorter than a predetermined value, the observation device 10 may notify the outside that the information from the observation device 10 is unavailable. For example, the observation device 10 may notify the outside of information that quantitatively indicates the current sensing performance, such as a numerical value or rank indicating the ratio of the current visibility distance to the ideal visibility distance based on the spec data of the observation device 10. For example, the observation device 10 may notify the outside of areas where the presence of an observation target can be identified and areas where the presence of an observation target cannot be identified based on the current visibility distance. For example, when the visibility distance becomes shorter than a predetermined value, the observation device 10 may notify the outside of the weather around the observation device 10 (heavy rain, dense fog, etc.) that the weather is deteriorating.

[0074] Furthermore, in the above embodiment, the observation device 10 directly transmits the visibility distance to the outside. However, the observation device 10 may transmit the visibility distance, or the processing result of the processing based on the latest visibility distance, to another communication device, and the other communication device may then notify the outside of the visibility distance, or the processing result of the processing based on the latest visibility distance.

[0075] While embodiments relating to this disclosure have been described based on the drawings and examples, it should be noted that those skilled in the art will find it easy to make various modifications or alterations based on this disclosure. Therefore, it should be noted that these modifications or alterations are within the scope of this disclosure. For example, the functions, etc., included in each component or step, etc., can be rearranged in a logically consistent manner, and multiple components or steps, etc., can be combined into one or divided. [Explanation of symbols]

[0076] 10 Observation device 11. Communication Systems 12 Road 13 Vehicles (objects of observation) 14. Pedestrians (subjects of observation) 15 Traffic lights 16 Pedestrian crossing 17 Observation Department 18 Memory section 19 Control Unit 20 Communications Department 22 Structures dx detection axis DV visibility distance Td Distance threshold (threshold) Dl detection limit

Claims

1. An observation unit for observing a predetermined area, A storage unit that stores the viewing distance, which indicates the maximum distance at which an object to be observed within the predetermined area can be identified, and a threshold value, The system includes a control unit that, based on the results of the first observation by the observation unit, acquires the maximum observation distance, which indicates the distance to the location of the furthest identified first observation target, and sets the viewing distance and the threshold based on the comparison result between the maximum observation distance and the threshold, The control unit reduces the threshold when a predetermined condition is met. Observation device.

2. The observation apparatus according to claim 1, wherein the control unit sets the viewing distance and the threshold to the same length as the maximum observation distance when the value of the maximum observation distance is greater than the threshold.

3. The observation apparatus according to claim 1, wherein the predetermined condition includes the value of the maximum observation distance being equal to or less than the threshold.

4. The observation apparatus according to claim 1, wherein the predetermined condition includes the first observation target being different from the second observation target located furthest away, which was identified in a second observation performed prior to the first observation.

5. The control unit reduces the threshold by a predetermined percentage at predetermined intervals when the predetermined conditions are met, according to the observation apparatus of claim 1.

6. The observation apparatus according to claim 1, wherein the control unit reduces the threshold by a decrease amount that changes at predetermined time intervals when the predetermined conditions are met.

7. The observation apparatus according to claim 1, wherein the observation unit includes any of a visible light camera, an FIR camera, a LiDAR, a millimeter-wave radar, and an ultrasonic sonar.

8. The observation device according to claim 1, wherein the observation unit includes a sensor that recognizes the weather in the predetermined area, and the control unit initializes the visibility distance and the threshold based on the recognized weather.

9. An observation method performed by an observation device, Obtaining observation results from the observation unit after observing a predetermined area, The system stores in the memory the viewing distance, which indicates the maximum distance at which an object to be observed within the predetermined area can be identified, and a threshold value. Based on the aforementioned observation results, the maximum observation distance is obtained, which indicates the distance to the location of the furthest identified first observation target. The visibility distance and the threshold are set based on the comparison result between the maximum observation distance and the threshold, When predetermined conditions are met, the threshold is reduced. Observation methods including those mentioned.

Images