JP2019046251A - Target detection equipment, driving assist system, and target detection method - Google Patents

Abstract

To improve precision in detecting a target at the time of rain.SOLUTION: Target detection equipment according to an embodiment detects a target, which exists around a vehicle, on the basis of a result of sensing performed by a sensing unit including a camera and radar mounted in the vehicle, and includes a first determination unit, an adjustment unit, and a detection unit. The first determination unit determines a raining state around the vehicle and a contaminated state of a window of the vehicle on the basis of an operating state of either a windshield wiper or washer of the vehicle. The adjustment unit adjusts the degrees of reliability of the camera and radar on the basis of the raining state determined by the first determination unit. The detection unit detects existence of the target on the basis of the degrees of reliability adjusted by the adjustment unit.SELECTED DRAWING: Figure 2

Description

  Embodiments disclosed herein relate to a target detection device, a driving support system, and a target detection method.

  2. Description of the Related Art Conventionally, an apparatus that is mounted on a vehicle and detects a target such as an obstacle ahead of the vehicle using a camera and a millimeter wave radar (hereinafter simply referred to as “radar”) is known (for example, Patent Document 1). reference). In addition, what improves detection accuracy using the sensing results of these different types of sensors is called sensor fusion.

  In sensor fusion, the presence or absence of a target is determined based on the presence probability of the target derived while reflecting the reliability of the sensing result of each sensor.

JP 2008-008679 A

  However, the above-described conventional technology has room for further improvement in improving the accuracy of target detection in rainy weather.

  Specifically, since it is generally known that the image recognition accuracy of a camera decreases when it rains, the above-mentioned reliability can be adjusted according to the rainfall conditions in order to detect a target with high accuracy. preferable.

  Therefore, it is always important to accurately grasp the rainfall situation. In this regard, it is conceivable to acquire information on the rainfall situation using a cloud service. However, in this case, the information provided from the cloud service includes a time or location error, which may be different from the actual rainfall situation around the host vehicle.

  In addition, for example, it is conceivable to determine the rain situation by analyzing a camera image. However, since the image recognition accuracy of the camera is lowered as described above, there is a possibility that an accurate rain situation cannot be obtained.

  One aspect of the embodiments has been made in view of the above, and provides a target detection device, a driving support system, and a target detection method that can improve the detection accuracy of a target in rainy weather. Objective.

  A target detection device according to an aspect of an embodiment is a target detection device that detects a target existing around a vehicle based on a sensing result of a sensing device including a camera and a radar mounted on the vehicle. , A first determination unit, an adjustment unit, and a detection unit. The first determination unit determines a rainfall situation around the vehicle and a contamination status of the window of the vehicle based on an operating situation of either the wiper or the washer of the vehicle. The adjustment unit adjusts reliability of the camera and the radar based on a result determined by the first determination unit. The detection unit detects the presence of the target based on the reliability adjusted by the adjustment unit.

  According to one aspect of the embodiment, it is possible to improve the accuracy of target detection in rainy weather.

FIG. 1A is a schematic explanatory diagram (part 1) of a target detection method according to an embodiment. FIG. 1B is a schematic explanatory diagram (part 2) of the target detection method according to the embodiment. FIG. 2 is a block diagram of the driving support system according to the embodiment. FIG. 3A is an explanatory diagram (part 1) of a rainfall situation determination process. FIG. 3B is an explanatory diagram (part 2) of the rainfall situation determination process. FIG. 3C is an explanatory diagram (part 3) of the rainfall situation determination process. FIG. 3D is an explanatory diagram (part 4) of the rainfall situation determination process. FIG. 3E is an explanatory diagram (part 5) of the rainfall situation determination process. FIG. 4A is an explanatory diagram (part 1) of the reliability adjustment processing. FIG. 4B is an explanatory diagram (part 2) of the reliability adjustment processing. FIG. 4C is an explanatory diagram (part 3) of the reliability adjustment processing. FIG. 4D is an explanatory diagram (part 4) of the reliability adjustment processing. FIG. 4E is an explanatory diagram (part 5) of the reliability adjustment processing. FIG. 5 is a diagram illustrating an example of the target determination process. FIG. 6 is a flowchart illustrating a processing procedure executed by the target detection apparatus according to the embodiment.

  Hereinafter, embodiments of a target detection device, a driving support system, and a target detection method disclosed in the present application will be described in detail with reference to the accompanying drawings. In addition, this invention is not limited by embodiment shown below.

  In the following description, an overview of the target detection method according to the present embodiment will be described with reference to FIGS. 1A and 1B, and then a driving support system including the target detection device 10 to which the target detection method according to the embodiment is applied. 1 will be described with reference to FIGS.

  First, an outline of the target detection method according to the present embodiment will be described with reference to FIGS. 1A and 1B. 1A and 1B are schematic explanatory views (No. 1) and (No. 2) of a target detection method according to an embodiment.

  As shown in FIG. 1A, the vehicle C includes a target detection device 10. The target detection device 10 detects, for example, a target in front of the vehicle C by a sensor fusion using a camera and a radar which is a sensing device mounted on the vehicle C. However, as shown in FIG. Recognition accuracy decreases.

  In such a case, in order to detect a target with high accuracy, it is preferable that the reliability of the camera is adjusted based on a real-time rainfall situation around the vehicle C without any time or place error.

  Therefore, in the target detection method according to the present embodiment, first, the rainfall situation is determined from the operating situation of the wiper 2 and the washer 3 (window washer) mounted on the vehicle C (step S1).

  The “operating status” referred to here includes “operating time”, “operating frequency”, “operating frequency” and the like in addition to whether or not the wiper 2 is in an operating state. “Operating time” is the time during which the wiper 2 is in the operating state. The “number of operations” is the number of operations of the wiper 2 and can be derived, for example, by operation speed × ON time. “Operating frequency” is the degree of operation of the wiper 2 repeated within a predetermined time. For example, it is classified into “low” frequency, “medium” frequency, “high” frequency, etc. depending on whether the wiper 2 is intermittently operated or continuously operated. It is done. Further, in the case of the washer 3, the “operation status” includes whether or not it is in an operating state, that is, whether or not the washer liquid is being injected.

  In addition, the “rainfall situation” mentioned here means “whether there is rain” such as whether it is raining (with rain) or not raining (without rain), and if there is rain, the amount of rain is small ( It includes “rainfall” such as low rainfall), moderate (medium rainfall) or heavy (heavy rainfall).

  The wiper 2 and the washer 3 are existing devices that are usually mounted on the vehicle C. By utilizing these devices, it is possible to add a new device and to obtain a rain situation without acquiring information from the outside of the vehicle C. Can be determined.

  In addition, since both the wiper 2 and the washer 3 are operated and operated by the driver of the vehicle C, the actual rainfall situation around the vehicle C visually obtained by the driver can be indirectly obtained by obtaining information from these devices. Is possible.

  In addition, by grasping not only the operation state of the washer 3 but also the wiper 2, it is possible to determine the operation time of the wiper 2 not due to rain but due to dirt or deterioration of the surrounding environment. Therefore, it is possible to determine the rainfall situation more accurately. The details of the method for determining the rainfall situation in step S1 will be described later with reference to FIGS. 3A to 3E.

  In the target detection method according to the present embodiment, the reliability of the camera and the radar is adjusted based on the rainfall situation and wiper performance determined in step S1 (step S2).

  The “wiper performance” referred to here corresponds to the raindrop wiping performance of the wiper 2. As an example of the wiper performance, there is a state of the rubber part of the wiper 2, for example, and when the rubber part is deteriorated due to secular change, the wiper performance is lowered as the deterioration progresses.

  In the target detection method according to the present embodiment, the reliability can be adjusted with higher accuracy by reflecting not only the rain condition but also the wiper performance. Thereby, it can contribute to the improvement of the detection accuracy of the target at the time of rainy weather. Details of the reliability adjustment method in step S2 will be described later with reference to FIGS. 4A to 4E.

  Then, in the target detection method according to the present embodiment, the target is determined based on the adjusted reliability (step S3). In other words, since the target is determined based on the appropriate reliability reflecting the decrease in the image recognition accuracy of the camera during rainy weather, it is possible to improve the target detection accuracy during rainy weather.

  Hereinafter, the driving support system 1 including the target detection device 10 to which the target detection method described above is applied will be described more specifically.

  FIG. 2 is a block diagram of the driving support system 1 according to the present embodiment. In FIG. 2, only components necessary for explaining the features of the present embodiment are represented by functional blocks, and descriptions of general components are omitted.

  In other words, each component illustrated in FIG. 2 is functionally conceptual and does not necessarily need to be physically configured as illustrated. For example, the specific form of distribution / integration of each functional block is not limited to the one shown in the figure, and all or a part thereof is functionally or physically distributed in arbitrary units according to various loads or usage conditions.・ It can be integrated and configured.

  As shown in FIG. 2, the driving support system 1 includes a wiper 2, a washer 3, a performance detection device 4, a sensing device 5, a target detection device 10, a vehicle control device 20, a brake 30, an accelerator. 40, a speaker 50, and a display 60.

  The wiper 2 is a device that secures the driver's field of view by wiping off water and dirt adhering to the window during operation during rain or when the surrounding environment deteriorates. The washer 3 is a device that has a washer fluid ejection mechanism, ejects the washer fluid, and is used together with the wiper 2 to facilitate removal of dirt and the like attached to the window.

  The performance detection device 4 is a device for detecting the wiper performance, and includes a wiper cumulative operation counter 4a, a cumulative activation time counter 4b, and a travel distance counter 4c. The wiper cumulative operation counter 4a measures the cumulative number of operations of the wiper 2.

  The cumulative activation time counter 4b measures the cumulative activation time of the driving support system 1. The travel distance counter 4c measures the travel distance of the vehicle C. The wiper cumulative operation counter 4a, the cumulative activation time counter 4b, and the travel distance counter 4c are preferably reset by a driver operation or the like when the wiper 2 is replaced with a new one, for example.

  The sensing device 5 includes a camera 5a and a radar 5b. The camera 5a includes an image sensor such as a charge coupled device (CCD) or a complementary metal oxide semiconductor (CMOS), and is provided at the front portion of the vehicle C. The camera 5a detects the imaging information around the vehicle C captured by the image sensor. Output to the device 10.

  The radar 5 b is, for example, a millimeter wave radar or an ultrasonic sensor mounted on the vehicle C, and outputs target information such as an obstacle existing around the vehicle C to the target detection device 10.

  The vehicle control device 20 is an ECU (Electronic Control Unit) that controls each device of the vehicle C. The vehicle control device 20 is electrically connected to each of the brake 30, the accelerator 40, the speaker 50, and the display 60, for example.

  The vehicle control device 20 performs vehicle control such as ACC (Adaptive Cruise Control) and PCS (Pre-Crash Safety System) based on the target information acquired from the target detection device 10.

  For example, when performing ACC, the vehicle control device 20 uses the target information acquired from the target detection device 10 so that the vehicle C follows the preceding vehicle while keeping the distance between the preceding vehicle and the vehicle at a constant distance. In addition, the accelerator 40 and the brake 30 are controlled.

  In addition, for example, when performing the PCS, the vehicle control device 20 uses the target information acquired from the target detection device 10, and an obstacle such as a preceding vehicle or a stationary object having a risk of collision in the traveling direction of the vehicle C is detected. When it is detected that the vehicle exists, the brake 30 is controlled to decelerate the vehicle C. Further, for example, a warning is given to the passenger of the vehicle C including the driver by using the speaker 50 or the display 60, or the passenger is fixed to the seat by pulling a seat belt in the passenger compartment.

  The target detection device 10 includes a control unit 11 and a storage unit 12. The control unit 11 includes a rainfall situation determination unit 11a, a wiper performance determination unit 11b, a reliability adjustment unit 11c, a target determination unit 11d, and a target information generation unit 11e.

  The storage unit 12 is a storage device such as a hard disk drive, a nonvolatile memory, or a register, and stores processing information 12a. The process information 12a includes various information necessary for each process, such as determination condition information used in a rain condition determination process, which will be described later, and a calculation formula used in the reliability adjustment process.

  The control unit 11 controls the entire target detection apparatus 10. The rainfall situation determination unit 11a acquires the operating status of at least one of the wiper 2 and the washer 3, and determines the rainfall status and the contamination status of the window of the vehicle C based on the operating status.

  Specifically, the rain condition determination process will be described with reference to FIGS. 3A to 3E. 3A to 3E are explanatory views (No. 1) to (No. 5) of the rain condition determination processing.

  As illustrated in FIG. 3A, the rain condition determination unit 11 a performs “no rain” or “rain” along the four patterns 1 to 4 according to the combination of the acquired operating conditions of the wiper 2 and the washer 3. Determine whether.

  In short, in the case of the pattern 2 in which the wiper 2 is “ON” (operating) and the washer 3 is “OFF” (stopped), the rain condition determination unit 11a has “rain”, that is, at least rain. It is determined that is falling. For patterns 1, 3 and 4 other than pattern 2, it is determined that there is no rain.

  In the case of pattern 2 as well, if the wiper 2 is erroneously operated, it is determined that there is no rain. This point will be described later with reference to FIG. 3E. In addition, the pattern 3 in which only the washer 3 operating together with the wiper 2 is normally “ON” is unlikely to occur, but it may be generated depending on the operation status acquisition timing. The situation in which at least the washer 3 of the patterns 3 and 4 is operating is “no rain”, and specifically, it can be determined that the surrounding environment other than dirt or rain is deteriorated. Of course, since the wiper 2 and the washer 3 are both “OFF”, the pattern 1 is of course “no rain”.

  In addition, when it is determined that “rain is present”, the rain condition determination unit 11a determines the amount of rainfall according to the operating frequency of the wiper 2, as illustrated in FIG. 3B. Specifically, the rain condition determination unit 11a determines that the amount of rainfall is “low” when the operation frequency of the wiper 2 is “low”, and the rain amount when the operation frequency is “medium”. When the amount is determined to be “medium” and the operation frequency is “high”, the rainfall amount is determined to be “high”.

  The method for determining the operating status of the wiper 2 and the washer 3 will be described more specifically. As shown in FIG. 3C, the operating status can be determined by, for example, the wiper 2 and the washer 3 switches.

  In this case, the rain condition determination unit 11a acquires the “switch position” selected by the driver from the wiper 2 and the washer 3, and determines “OFF / ON” and “operation frequency” from the switch position.

  As illustrated in FIG. 3C, the rain condition determination unit 11a determines that the wiper 2 is “OFF” when the switch position of the wiper 2 is “OFF”. When the switch position of the wiper 2 is “intermittent operation”, for example, the rain condition determination unit 11a determines that the wiper 2 is “ON” and the operation frequency is “low”. Therefore, in this case, the rainfall is determined to be “low”.

  In addition, when the switch position of the wiper 2 is, for example, “continuous operation (low)”, the rain condition determination unit 11a determines that the wiper 2 is “ON” and the operation frequency is “medium”. judge. Therefore, in this case, the rainfall amount is determined to be “medium”.

  In addition, when the switch position of the wiper 2 is, for example, “continuous operation (high)”, the rain condition determination unit 11a determines that the wiper 2 is “ON” and the operation frequency is “high”. judge. Therefore, in this case, the rainfall amount is determined to be “many”.

  Further, the rain condition determination unit 11a determines that the washer 3 is “OFF” or “ON” according to the switch position.

  As another example, the operating status can be determined by signals sent to the wiper 2 and the washer 3 as shown in FIG. 3D.

  In this case, the rain condition determination unit 11a acquires signals sent to the wiper 2 and the washer 3, and determines “OFF / ON” and “operation frequency” from the pulses of the signals.

  As illustrated in FIG. 3D, the rain condition determination unit 11 a determines that the wiper 2 or the washer 3 is “OFF” if the pulse is sent to the wiper 2 or the washer 3 if “none”. If the presence / absence of the pulse is “Yes”, the rain condition determination unit 11a determines that the wiper 2 or the washer 3 is “ON”.

  Further, the rain condition determination unit 11a determines, for example, “low”, “medium”, and “high” according to the number of pulses per unit time for the operation frequency when the wiper 2 is “ON”. Based on the results, the rainfall is determined as “low”, “medium”, and “high” in order.

  Note that the wiper 2 may be operated unintentionally due to an erroneous operation of the driver. Therefore, even in the case of the pattern 2 in which it is determined that “rain is present” in FIG. 3A, the rain condition determination unit 11 a determines that the operation is erroneous if the predetermined determination condition corresponding to the erroneous operation is satisfied. ".

  Specifically, as shown in FIG. 3E, for the wiper 2, when the operation status determination type is “switch” (see FIG. 3C), the rain condition determination unit 11a is in an ON state less than a predetermined time. In the case, it is determined that the operation is erroneous. Also, the rain condition determination unit 11a determines that the operation is erroneous even when the number of operations (= operation speed × ON time) is less than the predetermined number.

  The rain condition determination unit 11a determines that the wiper 2 is an erroneous operation when the operation condition determination type is “signal” (see FIG. 3D) and the pulse interval is less than the predetermined time. Also, the rain condition determination unit 11a determines that the operation is erroneous even when the number of pulses within the predetermined time is less than the predetermined number.

  In addition, about the washer 3, the rainfall condition determination part 11a does not determine a misoperation irrespective of the determination classification of an operation condition. This is because even if it is an erroneous operation, the wiper 2 is expected to operate afterwards for the washer 3, and therefore it can be handled in the same manner as the pattern 3 or 4 in FIG. 3A.

  Returning to the description of FIG. The rainfall situation determination unit 11a outputs the determined determination result to the reliability adjustment unit 11c. The wiper performance determination unit 11b acquires the contents of the counters 4a to 4c of the performance detection device 4, derives parameters indicating the wiper performance according to the contents, and outputs the parameters to the reliability adjustment unit 11c. The parameter indicating the wiper performance will be described later with reference to FIG.

  The reliability adjustment unit 11c adjusts the reliability of the camera 5a and the radar 5b based on the determination result of the rain condition determination unit 11a and the determination result of the wiper performance determination unit 11b. Specifically, assuming that there is no rain, the information is obtained from the camera 5a and the radar 5b at a ratio of A: B. If there is rain, A, that is, the camera 5a. And the reliability is adjusted so that the reliability of B, that is, the radar 5b increases.

  This will be described more specifically with reference to FIGS. 4A to 4E. 4A to 4E are explanatory diagrams (No. 1) to (No. 5) of the reliability adjustment processing. The reliability adjustment unit 11c adjusts the reliability based on the adjustment method illustrated in FIG. 4A according to the rainfall situation.

  First, when there is no rain, prescribed reliability A and B are set in the camera 5a and the radar 5b as standard conditions. Then, when there is rainfall, the reliability adjustment unit 11c calculates the reliability of the camera 5a and the radar 5b based on each equation in the figure according to the amount of rainfall.

  The rainfall parameters of the camera 5a when there is rainfall are represented by (1-p), (1-q), and (1-r) in the order of the rainfall “low”, “medium”, and “high”. . Similarly, the rainfall amount parameter of the radar 5b is represented by (1 + p), (1 + q), and (1 + r). It is assumed that p <q <r.

  In addition, since the image recognition accuracy of the camera 5a changes depending on the wiper performance, in the case of rain, the wiper performance is reflected in the reliability by the wiper performance parameter, which can contribute to increase the target detection accuracy. .

  As shown in FIG. 4B, the value x of the wiper performance parameter takes a positive value when the wiper performance is “good” and takes a negative value when it is “bad”. For example, when it is considered that the rubber part of the wiper 2 has deteriorated over time, the value of x is a negative value. Further, as the deterioration proceeds, the value of x increases in the negative direction. In the case of “0”, the standard state is assumed.

  As shown in FIG. 4B, the above-described wiper performance determination unit 11b sets the value of x so that the wiper performance becomes worse as the cumulative number of wiper operations increases, and the better as the number of wiper cumulative operations increases. Also, for example, the value of x is set so that the longer the cumulative startup time of the system is, the worse the wiper performance is, and the shorter is the better. For example, the value of x is set so that the longer the travel distance of the vehicle C, the worse the wiper performance and the shorter the shorter the better.

  Here, a specific example of the adjustment result of the reliability by the reliability adjustment unit 11c is given. First, FIG. 4C shows an example in which the wiper performance is in a standard state. That is, x = 0. As shown in FIG. 4C, it is assumed that A = 50, B = 50, p = 0.2, q = 0.4, and r = 0.6.

  In such a case, it can be seen that the reliability of the camera 5a is adjusted to decrease as the rainfall amount increases. On the other hand, it can be seen that the reliability of the radar 5b is adjusted to increase as the amount of rainfall increases.

  FIG. 4D shows an example in which the wiper performance is good. That is, x is a positive value. Assume that x = 0.03, and A, B, p, q, and r have the same values as in FIG. 4C.

  In such a case, as shown in FIG. 4D, the reliability is adjusted so that the reliability of the camera 5a is raised and the reliability of the radar 5b is lowered when “rain is present” as compared with the case of the standard state of FIG. 4C. You can see that

  On the other hand, FIG. 4E shows an example in which the wiper performance is poor. That is, x is a negative value. It is assumed that x = −0.03, and A, B, p, q, and r have the same values as those in FIGS. 4C and 4D.

  In such a case, as shown in FIG. 4E, the reliability of the camera 5a in the case of “rainfall” is lowered and the reliability of the radar 5b is raised more than in the standard state of FIG. 4C. It can be seen that is adjusted.

  By adjusting the reliability based on the rain condition and the wiper performance in this way, it is possible to set the reliability according to the decrease in the actual image recognition accuracy of the camera 5a. Can help to improve.

  Returning to the description of FIG. The reliability adjustment unit 11c outputs the adjusted adjustment result to the target determination unit 11d. The target determination unit 11d determines the target based on the information from the sensing device 5 and the adjustment result of the reliability adjustment unit 11c. That is, the target determination unit 11d detects the presence of the target based on the reliability adjusted by the reliability adjustment unit 11c adjustment unit.

  This will be specifically described with reference to FIG. FIG. 5 is a diagram illustrating an example of the target determination process. In the first place, the camera 5a and the radar 5b have different characteristics. For example, as shown in FIG. 5, the sensing ranges are also different.

  In general, the camera 5a has an excellent viewing angle, and the lateral position (position in the vehicle width direction) where the target is present has a wider sensing range than the radar 5b. On the other hand, the radar 5b can perform sensing at a longer distance than the camera 5a with respect to the vertical position (position in the traveling direction).

  Therefore, as shown in FIG. 5, for example, assuming the areas indicated by A1 to A3, B1 to B3, and C1 to C3 in front of the vehicle C, the sensing ranges of the camera 5a and the radar 5b are included in the areas. The reliability of the camera 5a and the radar 5b is set in advance in accordance with the degree of overlap of each other. This corresponds to, for example, the reliability of the standard state described above. And the reliability adjustment part 11c adjusts the reliability of at least one of the camera 5a and the radar 5b about the area | region where the sensing range of the camera 5a and the radar 5b overlaps, for example.

  And the reliability adjustment part 11c delivers the adjustment result which adjusted the reliability of each area | region according to the rain condition to the target determination part 11d, respectively. Then, the target determination unit 11d derives the existence probability of the target in each region according to the information from the sensing device 5 and the reliability of each region (step S51).

  For example, the target determination unit 11d weights the information from the camera 5a with the reliability of the camera 5a, weights the information from the radar 5b with the reliability of the radar 5b, and combines each of the information based on the combined information obtained by combining these. Deriving the existence probability of the target in the area.

  Then, the target determining unit 11d determines a target based on the derived existence probability (step S52). For example, the target determining unit 11d determines that the target exists in the region when the existence probability exceeds a predetermined threshold.

  Returning to the description of FIG. The target determination unit 11d outputs the determined determination result to the target information generation unit 11e. The target information generation unit 11e generates target information to be output to the vehicle control device 20 according to the position of each region where the target is determined to exist, the magnitude of the existence probability, and the like, and sends the target information to the vehicle control device 20. Output.

  Next, a processing procedure executed by the target detection apparatus 10 according to the present embodiment will be described with reference to FIG. FIG. 6 is a flowchart showing a processing procedure executed by the target detection apparatus 10 according to the present embodiment. Note that this processing procedure is periodically executed.

  First, the rainfall situation determination unit 11a acquires the operating conditions of the wiper 2 and the washer 3 (step S101). Then, the rainfall situation determination unit 11a determines whether or not the washer 3 is operating (step S102).

  Here, when the washer 3 is not in operation (step S102, No), the rainfall situation determination unit 11a determines whether or not the wiper 2 is in operation (step S103).

  When the washer 3 is in operation at step S102 (step S102, Yes), or when the wiper 2 is not in operation at step S103 (step S103, No), the rain condition determination unit 11a determines that there is no rain. (Step S104), the reliability is set to the standard state (Step S105), and control is transferred to Step S116. If the washer 3 is in operation in step S102 (step S102, Yes), it may be determined that the wiper 2 is in operation not only due to rain but also due to dirt or deterioration of the surrounding environment.

  When the wiper 2 is operating in step S103 (step S103, Yes), the wiper performance determination unit 11b derives the wiper performance based on the information from the performance detection device 4 (step S106).

  And the rain condition determination part 11a determines the operating frequency of the wiper 2 based on the operating condition of the wiper 2 (step S107). Here, when the operation frequency of the wiper 2 is “low”, the rain condition determination unit 11a determines that there is a small amount of rainfall (step S108), and based on the result, the reliability adjustment unit 11c determines that the camera 5a and The reliability of the radar 5b is adjusted when the amount of rain is small (step S109).

  When the operation frequency of the wiper 2 is “medium”, the rain condition determination unit 11a determines that there is a moderate amount of rainfall (step S110), and based on the result, the reliability adjustment unit 11c uses the camera 5a and the radar. The reliability of 5b is adjusted at the time of heavy rain (step S111).

  When the operation frequency of the wiper 2 is “high”, the rain condition determination unit 11a determines that there is heavy rainfall (step S112), and based on the result, the reliability adjustment unit 11c performs the camera 5a and the radar. The reliability of 5b is adjusted at the time of heavy rainfall (step S113).

  When the operation frequency of the wiper 2 is other (“else”), the rain condition determination unit 11a determines that there is rain (step S114), and based on the result, the reliability adjustment unit 11c uses the camera 5a and the radar. The reliability of 5b is adjusted based on an arbitrary rainfall (step S115). That is, the reliability of the camera 5a and the radar 5b is adjusted after appropriately adjusting the above-described rainfall parameter.

  Then, the target determination unit 11d acquires a sensing result from the sensing device 5, that is, information from the camera 5a and the radar 5b (step S116), and determines a target according to the sensing result and the reliability (step S117). ). Then, the target information generation unit 11e generates target information, outputs the target information (step S118), and ends the process.

  As described above, the target detection device 10 according to the present embodiment detects a target existing around the vehicle C based on the sensing result of the sensing device 5 including the camera 5a and the radar 5b mounted on the vehicle C. A target detection device 10 to detect, a rain condition determination unit 11a (corresponding to an example of “first determination unit”), a reliability adjustment unit 11c (corresponding to an example of “adjustment unit”), and target determination 11d (corresponding to an example of “detection unit”).

  The rain condition determination unit 11a determines the rain condition around the vehicle C and the window contamination condition of the vehicle C based on the operating condition of at least one of the wiper 2 and the washer 3 of the vehicle C. The reliability adjustment unit 11c adjusts the reliability of the camera 5a and the radar 5b based on the result determined by the rainfall situation determination unit 11a. The target determination unit 11d detects the presence of the target based on the reliability adjusted by the reliability adjustment unit 11c.

  Therefore, according to the target detection apparatus 10 according to the present embodiment, it is possible to improve the target detection accuracy during rainy weather.

  In addition, the reliability adjustment unit 11c adjusts the reliability of at least one of the camera 5a and the radar 5b in a region where the sensing ranges of the camera 5a and the radar 5b overlap.

  Therefore, according to the target detection apparatus 10 according to the present embodiment, it is possible to further improve the target detection accuracy in a region where the sensing ranges of different types of sensors (that is, the camera 5a and the radar 5b) overlap. .

  Moreover, the rain condition determination part 11a determines with the malfunction of the wiper 2 when the operation time or the frequency | count of operation of the wiper 2 derived | led-out from the said operation condition is less than predetermined value.

  Therefore, according to the target detection apparatus 10 according to the present embodiment, it is possible to prevent the reliability of the camera 5a and the radar 5b from being inappropriately adjusted based on a malfunction.

  Moreover, the rain condition determination part 11a derives a rainfall amount based on the operation frequency of the wiper 2 derived from the operation condition, and determines a rain condition based on the rain amount.

  Therefore, according to the target detection apparatus 10 according to the present embodiment, it is possible to adjust an appropriate reliability according to the amount of rainfall.

  Further, the rain condition determination unit 11 a determines the operation condition based on a control signal sent to the wiper 2 or the washer 3.

  Therefore, according to the target detection apparatus 10 according to the present embodiment, it is possible to perform the same determination as in the case of continuous operation even in a case where single operation is repeated.

  Moreover, the target detection apparatus 10 according to the present embodiment acquires information related to the wiping performance of the raindrops of the wiper 2 and determines the wiping performance of the wiper performance determining unit 11b (corresponding to an example of a “second determining unit”). The reliability adjustment unit 11c adjusts the reliability of the camera 5a and the radar 5b based on the wiping performance determined by the wiper performance determination unit 11b.

  Therefore, according to the target detection apparatus 10 according to the present embodiment, the reliability of the camera 5a and the radar 5b can be adjusted to an appropriate value according to the actual performance of the wiper 2 as well as the rainfall situation.

  Further, in the target detection apparatus 10 according to the present embodiment, the reliability adjustment unit 11c adjusts so that the reliability of the camera 5a decreases as the rainfall amount increases.

  Therefore, according to the target detection apparatus 10 according to the present embodiment, the target can be determined based on the reliability of the camera that is appropriately adjusted according to the rainfall situation. Accuracy can be improved.

  In the above-described embodiment, the operating state of the washer 3 is acquired based on the switch of the washer 3 and the control signal to the washer 3. However, for example, the change rate of the washer liquid storage amount per predetermined time, etc. May be obtained by

  In the above-described embodiment, the camera 5a and the radar 5b are shown as the sensing device 5. However, an optical sensor (Lidar: Light Detection and Ranging / Laser Imaging Detection and Ranging) is used instead of or together with the radar 5b. ) Or a sound wave sensor (Sonar: Sound navigation and ranging) may be used.

  Further effects and modifications can be easily derived by those skilled in the art. Thus, the broader aspects of the present invention are not limited to the specific details and representative embodiments shown and described above. Accordingly, various modifications can be made without departing from the spirit or scope of the general inventive concept as defined by the appended claims and their equivalents.

DESCRIPTION OF SYMBOLS 1 Driving support system 2 Wiper 3 Washer 4 Performance detection apparatus 4a Wiper cumulative operation counter 4b Cumulative starting time counter 4c Travel distance counter 5 Sensing apparatus 5a Camera 5b Radar 10 Target detection apparatus 11 Control unit 11a Rain condition determination unit 11b Wiper performance determination Unit 11c reliability adjustment unit 11d target determination unit 11e target information generation unit 12 storage unit 12a processing information 20 vehicle control device 30 brake 40 accelerator 50 speaker 60 display C vehicle

Claims (9)

A target detection device that detects a target existing around the vehicle based on a sensing result of a sensing device including a camera and a radar mounted on the vehicle,
A first determination unit that determines a rainfall situation around the vehicle and a pollution situation of the window of the vehicle based on an operating situation of either the wiper or the washer of the vehicle;
An adjustment unit that adjusts reliability of the camera and the radar based on a result determined by the first determination unit;
And a detection unit that detects the presence of the target based on the reliability adjusted by the adjustment unit. The adjustment unit is
The target detection apparatus according to claim 1, wherein the reliability of either the camera or the radar is adjusted for an area where the sensing ranges of the camera and the radar overlap. The first determination unit includes:
The target detection apparatus according to claim 1 or 2, wherein when the operating time or the number of operating times of the wiper derived from the operating status is less than a predetermined value, it is determined that the wiper is malfunctioning. The first determination unit includes:
The target according to claim 1, 2, or 3, wherein a rainfall amount is derived based on an operation frequency of the wiper derived from the operation state, and the rain state is determined based on the rainfall amount. Detection device. The first determination unit includes:
The target detection apparatus according to claim 1, wherein the operation status is determined based on a control signal sent to the wiper or the washer. A second determination unit that obtains information on the wiper performance of the wiper's raindrops and determines the wiper performance;
The adjustment unit is
The target according to any one of claims 1 to 5, wherein the reliability of either the camera or the radar is adjusted based on the wiping performance determined by the second determination unit. Detection device. The adjustment unit is
The target detection apparatus according to claim 4, wherein the reliability of the camera is adjusted to decrease as the rainfall amount increases. The target detection device according to any one of claims 1 to 7,
A driving support system comprising: a vehicle control device that controls the vehicle based on a detection result of the target detection device. A target detection method using a target detection device for detecting a target existing around the vehicle based on a sensing result of a sensing device including a camera and a radar mounted on the vehicle,
A first determination step of determining a rainfall situation around the vehicle and a pollution situation of the window of the vehicle based on an operating situation of any one of the wiper and the washer of the vehicle;
An adjustment step of adjusting the reliability of the camera and the radar based on the result determined by the first determination step;
And a detection step of detecting the presence of the target based on the reliability adjusted by the adjustment step.

Images