Shielding detection method and device and vehicle

Abstract

The invention discloses a shielding detection method and device and a vehicle. The method comprises the steps of obtaining point cloud data collected by a millimeter wave radar on the vehicle within a first duration; according to the distance between the point cloud in the point cloud data and the millimeter wave radar and the Doppler velocity of the point cloud in the point cloud data, determining the number of target point clouds meeting effective point cloud conditions from the point cloud data as a target number; if the target number is smaller than or equal to the first number threshold value, it is determined that the millimeter-wave radar is detected to be in a shielded state at this time, so that the shielding condition of the millimeter-wave radar is sensed according to the number of effective point clouds in the point cloud data collected by the millimeter-wave radar, and the shielding detection accuracy is improved while the shielding detection complexity is reduced. And the accuracy of shielding detection is ensured.

Description

Technical Field

[0001] The present application relates to the technical field of vehicles, and more specifically, to an occlusion detection method, device, and vehicle. Background Art

[0002] With the development of science and technology, the autonomous driving technology of vehicles has developed rapidly. In autonomous driving technology, environmental perception is the key to ensuring driving safety. In practical applications, a vehicle can sense the environment through a millimeter-wave radar; however, during the driving process of the vehicle, the millimeter-wave radar may be occluded for various reasons, posing a danger to vehicle control. Therefore, in related technologies, there is a challenge in accurately detecting the occlusion situation of the millimeter-wave radar. Summary of the Invention

[0003] In view of this, embodiments of the present application propose an occlusion detection method, device, and vehicle to improve the above problems.

[0004] In a first aspect, an embodiment of the present application provides an occlusion detection method, the method including: obtaining point cloud data collected by a millimeter-wave radar on a vehicle within a first time period; determining, according to the distance between the point cloud in the point cloud data and the millimeter-wave radar and the Doppler velocity of the point cloud in the point cloud data, the number of target point clouds that meet the effective point cloud condition from the point cloud data as a target number; and if the target number is less than or equal to a first number threshold, determining that the millimeter-wave radar is in an occluded state in this detection.

[0005] In a second aspect, an embodiment of the present application provides an occlusion detection device, the device including: a point cloud data acquisition module, a target number acquisition module, and an occluded state determination module. Among them, the point cloud data acquisition module is configured to obtain point cloud data collected by a millimeter-wave radar on a vehicle within a first time period; the target number acquisition module is configured to determine, according to the distance between the point cloud in the point cloud data and the millimeter-wave radar and the Doppler velocity of the point cloud in the point cloud data, the number of target point clouds that meet the effective point cloud condition from the point cloud data as a target number; and the occluded state determination module is configured to determine that the millimeter-wave radar is in an occluded state in this detection if the target number is less than or equal to a first number threshold.

[0006] In a third aspect, an embodiment of the present application provides a vehicle, including a memory and a processor, the memory being coupled to the processor, the memory storing instructions, and when the instructions are executed by the processor, the processor executes the above method.

[0007] Fourthly, an embodiment of the present application provides a computer-readable storage medium, in which program codes are stored, and the program codes can be called by a processor to execute the above method.

[0008] In the solution of the present application, by obtaining the point cloud data collected by the millimeter-wave radar on the vehicle within the first duration, and according to the distance between the point cloud in the point cloud data and the millimeter-wave radar and the Doppler velocity of the point cloud in the point cloud data, the number of target point clouds that meet the effective point cloud condition is determined from the point cloud data as the target number, and if the target number is less than or equal to the first number threshold, it is determined that the millimeter-wave radar is in an occluded state in this detection. Thus, the occlusion situation of the millimeter-wave radar is sensed only based on the number of effective point clouds in the point cloud data collected by the millimeter-wave radar, avoiding relying on the collaborative work of multiple sensors for occlusion detection, reducing the complexity of occlusion detection, and by optimizing the point cloud data, the occlusion situation of the millimeter-wave radar is sensed based on the number of effective point clouds, ensuring the accuracy of occlusion detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative efforts.

[0010] Figure 1 It shows a schematic flowchart of an occlusion detection method provided by an embodiment of the present application;

[0011] Figure 2 It shows a schematic flowchart of an occlusion detection method provided by an embodiment of the present application;

[0012] Figure 3 It shows a schematic flowchart of an occlusion detection method provided by an embodiment of the present application;

[0013] Figure 4 It shows a block diagram of a module of an occlusion detection device provided by an embodiment of the present application;

[0014] Figure 5 It shows a block diagram of a vehicle for executing the occlusion detection method according to an embodiment of the present application;

[0015] Figure 6 It shows a storage unit for storing or carrying program codes for implementing the occlusion detection method according to an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] To enable those skilled in the art to better understand the solution of this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this application.

[0017] A millimeter-wave radar is a radar that operates in the millimeter-wave band (millimeter wave) for detection. Usually, millimeter waves refer to the frequency domain of 30 - 300 GHz (wavelength of 1 - 10 mm). The wavelength of millimeter waves is between that of microwaves and centimeter waves. Therefore, millimeter-wave radars have some advantages of both microwave radars and optoelectronic radars.

[0018] In autonomous driving technology, environmental perception is the key to ensuring driving safety. As an important sensor, a millimeter-wave radar can provide rich environmental information. However, in actual applications, due to the occlusion of objects, the radar point cloud data may be distorted or missing, resulting in inaccurate perception of the surrounding environment during the vehicle's autonomous driving. In related technologies, the methods for judging the occlusion of radar point cloud information include the method based on signal attenuation, the method based on multi-sensor fusion, etc.

[0019] Among them, the method based on signal attenuation: By analyzing the intensity change of the radar echo signal, it is judged whether the target object is occluded. However, this method is easily affected by environmental noise and interference, resulting in inaccurate judgment. And the method based on multi-sensor fusion: Combining data from other sensors such as lidar and cameras to comprehensively judge the occlusion situation of the radar. But this method requires multiple sensors to work together, increasing the complexity, computational burden and cost of judging the occlusion situation of the radar, and data synchronization and calibration between different sensors are also a challenge.

[0020] Therefore, in related technologies, there are problems of high complexity and low accuracy in detecting the occlusion situation of millimeter-wave radars.

[0021] In view of the above problems, through long-term research, the inventors have proposed the occlusion detection method, device and vehicle provided in the embodiments of this application. By only perceiving the occlusion situation of the millimeter-wave radar based on the number of valid point clouds in the point cloud data collected by the millimeter-wave radar, it avoids relying on the collaborative work of multiple sensors for occlusion detection, reduces the complexity of occlusion detection, and through optimizing the point cloud data, perceives the occlusion situation of the millimeter-wave radar based on the number of valid point clouds, ensuring the accuracy of occlusion detection. Among them, the specific occlusion detection method will be described in detail in the subsequent embodiments.

[0022] The embodiments involved in this application will be described below in conjunction with the accompanying drawings.

[0023] Please refer to Figure 1 , Figure 1The flowchart of the occlusion detection method provided by an embodiment of the present application is shown. In a specific embodiment, the occlusion detection method can be applied to an occlusion detection device 200 as shown in Figure 4 and a vehicle 100 equipped with the occlusion detection device 200 ( Figure 5 ). The following will take the vehicle as an example to illustrate the specific process of this embodiment. Of course, it can be understood that the vehicle to which this embodiment is applied can include devices such as electric vehicles, fuel vehicles, intelligent transportation devices, and vehicle-mounted terminals, which are not limited here. The following will elaborate in detail on the Figure 1 shown process. The occlusion detection method can specifically include the following steps:

[0024] Step S110: Obtain the point cloud data collected by the millimeter-wave radar on the vehicle within the first time period.

[0025] In some embodiments, a millimeter-wave radar can be set on the vehicle. The millimeter-wave radar can emit electromagnetic wave signals. When these signals encounter a target object, part of the energy will be reflected back and captured by the receiver of the millimeter-wave radar, thereby collecting the point cloud data of the surrounding environment. Among them, the vehicle can obtain the point cloud data collected by the millimeter-wave radar and can perceive the environment around the vehicle according to the point cloud data collected by the millimeter-wave radar. Among them, the point cloud data collected by the millimeter-wave radar can be understood as a set of target points detected by the millimeter-wave radar. The point cloud data can include multiple point clouds. Among them, one target point can correspond to one or more point clouds, and each target point can represent an object or a part of an object. Each point cloud can contain information such as the speed, angle, and distance from the millimeter-wave radar of the corresponding target point.

[0026] In some embodiments, the vehicle can receive an occlusion detection instruction input by the user and can, in response to the occlusion detection instruction, obtain the point cloud data collected by the millimeter-wave radar of the vehicle within the first time period. Among them, the first time period can be preset in the vehicle. The first time period can be set independently by the user or obtained through third-party experimental data, which is not limited here. Exemplarily, the first time period can be set independently by the user. For example, it can be 34s, 35s, 36s, etc.

[0027] As an implementable manner, the vehicle can also obtain the point cloud data collected by the millimeter-wave radar on the vehicle during the process of autonomous driving. Exemplarily, the vehicle can obtain the point cloud data collected by the millimeter-wave radar on the vehicle while activating the autonomous driving function in response to an autonomous driving instruction.

[0028] In some embodiments, the vehicle can obtain the vehicle speed of its own vehicle, compare the vehicle speed with a second speed, and determine whether to obtain the point cloud data collected by the millimeter-wave radar on the vehicle within a first duration according to the comparison result. Exemplarily, if the vehicle determines that the vehicle speed is greater than the second speed, it can obtain the point cloud data collected by the millimeter-wave radar on the vehicle within the first duration.

[0029] Optionally, the vehicle can determine the vehicle speed of its own vehicle based on the millimeter-wave radar on the vehicle transmitting a periodic FMCW waveform and receiving an echo signal; the vehicle can also determine the vehicle speed of its own vehicle by collecting the wheel speed of the vehicle in real time. The vehicle can also obtain the vehicle speed of its own vehicle through the global navigation positioning system (GPS) and the on-board diagnostic system provided on the vehicle. In this embodiment, the manner in which the vehicle obtains the vehicle speed of its own vehicle is not limited herein.

[0030] Among them, a second speed can be preset in the vehicle. The second speed can be set independently by the user or obtained through third-party experimental data. Exemplarily, considering detecting the occlusion situation of the millimeter-wave radar during the driving process of the vehicle to improve the driving safety of the vehicle, in this embodiment, the vehicle can detect the occlusion situation of the millimeter-wave radar when it determines that the vehicle is driving. Among them, the second speed can be used as a judgment basis for determining whether the vehicle is in a driving state. Exemplarily, the second speed can be determined through third-party experimental data and is 15 km / h. Correspondingly, the vehicle can detect the occlusion situation of the millimeter-wave radar when the vehicle speed is continuously greater than the second speed to improve the driving safety of the vehicle. Among them, the vehicle can detect the occlusion situation of the millimeter-wave radar at a fixed time period. For example, the first duration is used as the time length of the time window for detecting the occlusion situation of the millimeter-wave radar once, and the occlusion situation of the millimeter-wave radar is detected periodically to improve the accuracy and reliability of the detection of the occlusion situation of the millimeter-wave radar.

[0031] Step S120: Determine the number of target point clouds that meet the effective point cloud condition from the point cloud data as the target number according to the distance between the point cloud in the point cloud data and the millimeter-wave radar and the Doppler speed of the point cloud in the point cloud data.

[0032] In some embodiments, after the vehicle obtains the point cloud data collected by the millimeter-wave radar on the vehicle within the first duration, it can determine the number of target point clouds that meet the effective point cloud condition from the point cloud data as the target number according to the distance between the point cloud in the point cloud data and the millimeter-wave radar and the Doppler speed of the point cloud in the point cloud data. Among them, the Doppler speed of the point cloud refers to detecting whether an object is moving and calculating its speed by measuring the Doppler shift of the returned light of each point in the point cloud.

[0033] In some embodiments, after the vehicle acquires point cloud data, it can perform clustering processing on the point cloud data to obtain at least one target point cloud data. Among them, different target point cloud data can correspond to different objects (such as lane lines, traffic signs, traffic lights, pedestrians, vehicles, etc.), and the target point cloud data can be understood as the point cloud set of the corresponding object.

[0034] Optionally, after the vehicle acquires at least one target point cloud data, it can acquire the first point cloud corresponding to each of the at least one target point cloud data, and can determine the number of target point clouds that meet the effective point cloud condition from the first point clouds corresponding to each of the at least one target point cloud data according to the distance between the first point cloud corresponding to each target point cloud data and the millimeter-wave radar, and / or the Doppler velocity of the first point cloud corresponding to each target point cloud data, as the target number.

[0035] Among them, the first point cloud corresponding to the target point cloud data can be any one of the point clouds included in the target point cloud data, which is not limited here. Among them, the target point cloud that meets the effective point cloud condition can be understood as the effective point cloud; among them, the target number can be understood as the total number of effective point clouds of historical frames that meet the effective point cloud condition counted within a fixed time period (i.e., the first time period) using the time window statistical method. Among them, the condition for being an effective point cloud can be a point cloud with a distance from the millimeter-wave radar greater than the target distance, or a point cloud with a Doppler velocity greater than the first velocity, which is not limited here.

[0036] Among them, a target distance can be preset in the vehicle, and the target distance can be set independently by the user or obtained through third-party experimental data. Exemplarily, the target distance is set independently by the user, such as 19m, 20m, 21m, etc. The first velocity can be preset in the vehicle, and can be set independently by the user or obtained through third-party experimental data. Exemplarily, the first velocity is set independently by the user, such as 0.5m / s, 1m / s, 1.5m / s, etc.

[0037] Exemplarily, the vehicle can use, as the target point cloud, the first point cloud determined from the first point clouds corresponding to each of the at least one target point cloud data that has a distance from the millimeter-wave radar greater than the target distance, or can determine the first point cloud with an absolute value of the Doppler velocity greater than the first velocity as the target point cloud, or can also determine the first point cloud that has a distance from the millimeter-wave radar greater than the target distance and an absolute value of the Doppler velocity greater than the first velocity as the target point cloud, which is not limited here. Correspondingly, the vehicle can acquire the number of target point clouds as the target number.

[0038] As an implementable manner, after the vehicle acquires at least one target point cloud data, it can acquire the peak point cloud corresponding to each of the at least one target point cloud data. Among them, the peak point cloud corresponding to each target point cloud data can be the point cloud with the strongest energy among the target point cloud data collected by the millimeter-wave radar.

[0039] Among them, after the vehicle acquires the peak point cloud corresponding to each of the at least one target point cloud data, according to the distance between the peak point cloud corresponding to each target point cloud data and the millimeter-wave radar, and the Doppler velocity of the peak point cloud corresponding to each target point cloud data, it can determine the number of target point clouds that meet the effective point cloud condition from the peak point clouds corresponding to each of the at least one target point cloud data as the target number.

[0040] Optionally, the vehicle can use the peak point cloud with a distance greater than the target distance from the millimeter-wave radar determined from the peak point clouds corresponding to each of the at least one target point cloud data as the target point cloud, or can determine the peak point cloud with an absolute value of the Doppler velocity greater than the first velocity as the target point cloud, or can also determine the peak point cloud with a distance greater than the target distance and an absolute value of the Doppler velocity greater than the first velocity as the target point cloud, which is not limited here.

[0041] As an implementable manner, the vehicle can determine the peak point cloud with a distance greater than the target distance from the millimeter-wave radar and an absolute value of the Doppler velocity greater than the first velocity from the peak point clouds corresponding to each of the at least one target point cloud data as the target point cloud, and acquire the number of this target point cloud as the target number.

[0042] Exemplarily, the target distance can be preset to 20m and the first velocity to 1m / s in the vehicle. Among them, after the vehicle acquires the point cloud data collected by the millimeter-wave radar on the vehicle within the first time period, it can perform clustering processing on the point cloud data to obtain at least one target point cloud data, where different target point cloud data correspond to different objects. Among them, the vehicle can acquire the peak point cloud corresponding to each of the at least one target point cloud data, and can determine the peak point cloud with a distance exceeding 20m from the millimeter-wave radar and an absolute value of the Doppler velocity greater than 1m / s as the effective point cloud. Thus, the point cloud data of the millimeter-wave radar is optimized, and the point clouds with a relatively large distance from the millimeter-wave radar and a certain moving speed are selected for quantity statistics to ensure the accuracy and reliability of the data for detecting the occlusion situation of the millimeter-wave radar.

[0043] Step S130: If the target number is less than or equal to the first number threshold, it is determined that the millimeter-wave radar is in an occluded state in this detection.

[0044] In some embodiments, a first quantity threshold may be preset in the vehicle. The first quantity threshold may be set by the user independently or obtained from third-party experimental data. Exemplarily, the first quantity threshold is set by the user independently to 1500. After the vehicle obtains the target quantity of the target point cloud in the point cloud data, it may compare the target quantity with the first quantity threshold and may determine the occlusion condition of the millimeter-wave radar detected this time according to the comparison result. Exemplarily, if it is determined that the target quantity is less than or equal to the first quantity threshold, it may be determined that the millimeter-wave radar detected this time is in an occluded state. Wherein, the target quantity being less than or equal to the first quantity threshold may indicate that the quantity of valid point clouds within the first duration is small. Correspondingly, the vehicle may determine that the situation where the target quantity is less than or equal to the first quantity threshold is a detection of occlusion of the millimeter-wave radar.

[0045] The occlusion detection method provided by an embodiment of the present application obtains the point cloud data collected by the millimeter-wave radar on the vehicle within the first duration, and determines the quantity of target point clouds that meet the valid point cloud condition in the point cloud data as the target quantity according to the distance between the point cloud in the point cloud data and the millimeter-wave radar and the Doppler velocity of the point cloud in the point cloud data. And if the target quantity is less than or equal to the first quantity threshold, it is determined that the millimeter-wave radar detected this time is in an occluded state. Thus, the occlusion condition of the millimeter-wave radar is sensed only based on the quantity of valid point clouds in the point cloud data collected by the millimeter-wave radar, avoiding relying on the collaborative work of multiple sensors for occlusion detection, reducing the complexity of occlusion detection, and sensing the occlusion condition of the millimeter-wave radar based on the quantity of valid point clouds by optimizing the point cloud data, ensuring the accuracy of occlusion detection.

[0046] Please refer to Figure 2 , Figure 2 which shows a schematic flowchart of the occlusion detection method provided by an embodiment of the present application. This method is applied to the above-mentioned vehicle, and the following will elaborate in detail on the Figure 2 shown process. The occlusion detection method may specifically include the following steps:

[0047] Step S210: Obtain the point cloud data collected by the millimeter-wave radar on the vehicle within the first duration.

[0048] Step S220: Determine the quantity of target point clouds that meet the valid point cloud condition in the point cloud data as the target quantity according to the distance between the point cloud in the point cloud data and the millimeter-wave radar and the Doppler velocity of the point cloud in the point cloud data.

[0049] Step S230: If the target quantity is less than or equal to the first quantity threshold, determine that the millimeter-wave radar detected this time is in an occluded state.

[0050] For the specific descriptions of steps S210 - S230, please refer to the descriptions of steps S110 - S130 above, and they will not be elaborated here one by one.

[0051] Step S240: If the target quantity is greater than the first quantity threshold and less than or equal to the second quantity threshold, it is determined that the millimeter - wave radar is in an unobstructed state this time, where the second quantity threshold is greater than the first quantity threshold.

[0052] In some embodiments, a second quantity threshold can be preset in the vehicle. The second quantity threshold can be set independently by the user or obtained through third - party experimental data, where the second quantity threshold is greater than the first quantity threshold. Exemplarily, the first quantity threshold is set by the user to 1500, and the second quantity threshold is set by the user to 12000.

[0053] After the vehicle obtains the target quantity of the target point cloud in the point cloud data, the target quantity can be compared with the first quantity threshold and the second quantity threshold respectively, and the occlusion situation of the millimeter - wave radar can be determined according to the comparison result. Exemplarily, if it is determined that the target quantity is greater than the first quantity threshold and less than or equal to the second quantity threshold, it can be determined that the millimeter - wave radar is in an unobstructed state this time. Wherein, the target quantity being greater than the first quantity threshold and less than or equal to the second quantity threshold can indicate that the number of valid point clouds in the first time period is relatively large. Correspondingly, the vehicle can determine the situation where the target quantity is greater than the first quantity threshold and less than or equal to the second quantity threshold as detecting that the millimeter - wave radar has no occlusion.

[0054] As an implementable way, if the vehicle determines that the target quantity is greater than the second quantity threshold, it can output a second prompt message. The second prompt message can be used to prompt that the millimeter - wave radar is in an unobstructed state. Wherein, the target quantity being greater than the second quantity threshold can indicate that the environment perceived by the current millimeter - wave radar is relatively clear and the occlusion situation is less. Correspondingly, the vehicle can output the second prompt message indicating that the millimeter - wave radar is in an unobstructed state when the target quantity is greater than the second quantity threshold.

[0055] Exemplarily, a first quantity threshold of 1500, a second quantity threshold of 12000, and a second vehicle speed of 15 km / h are preset in the vehicle. Among them, if the quantity of valid point clouds obtained by the vehicle within the first duration exceeds 12000, it can be determined that the environment perceived by the current millimeter-wave radar is relatively clear and there is less occlusion. Correspondingly, the vehicle can output a second prompt message indicating that the millimeter-wave radar is in an unoccluded state when the target quantity exceeds 12000; conversely, if the target quantity is less than 12000, it can imply that there is occlusion in the environment perceived by the current millimeter-wave radar. Among them, if the vehicle is traveling at a speed greater than 15 km / h and the quantity of valid point clouds obtained within the first duration is less than 1500, it can be determined that the millimeter-wave radar is in an occluded state during this detection.

[0056] Step S250: Obtain the results of continuously detecting the occlusion situation of the millimeter-wave radar for a preset number of times. Among them, the length of the time window for each detection of the occlusion situation of the millimeter-wave radar is equal to the first duration, and the occlusion situation includes being in an occluded state or an unoccluded state.

[0057] In some embodiments, a preset number of times can be preset in the vehicle. This preset number of times can be set by the user independently or obtained through third-party experimental data. Exemplarily, this preset number of times can be set by the user independently to 50 times. Among them, the vehicle can obtain the results of continuously detecting the occlusion situation of the millimeter-wave radar of the vehicle for a preset number of times; among them, the length of the time window for each detection of the occlusion situation of the millimeter-wave radar is equal to the first duration.

[0058] Among them, the occlusion situation of the millimeter-wave radar can include being in an occluded state or an unoccluded state. The results of continuously detecting the occlusion situation of the millimeter-wave radar of the vehicle for a preset number of times can be understood as the number of valid occlusion judgments; the results of this detection can be recorded in the form of an array, and the number of times the millimeter-wave radar is in an occluded state and the number of times the millimeter-wave radar is in an unoccluded state during the continuous preset number of times can be recorded in this array.

[0059] Optionally, the vehicle can determine that the situation where the quantity of target point clouds in the point cloud data collected by the millimeter-wave radar within the first duration is less than or equal to the first quantity threshold is a valid occlusion judgment, or it can also determine that the situation where the quantity of target point clouds in the point cloud data collected by the millimeter-wave radar within the first duration is greater than the first quantity threshold and less than the second quantity is a valid occlusion judgment. It can determine that the situation where the quantity of target point clouds in the point cloud data collected by the millimeter-wave radar within the second duration is greater than the second quantity threshold is an invalid occlusion judgment.

[0060] As an implementable manner, if the vehicle determines that the target quantity is greater than the second quantity threshold, it can, while outputting the second prompt message, not count the result of detecting the occlusion situation of the millimeter-wave radar this time into the result of this detection. Wherein, the target quantity being greater than the second quantity threshold can indicate that the environment perceived by the current millimeter-wave radar is relatively clear and the occlusion situation is less. Correspondingly, it can be determined that the occlusion situation of the millimeter-wave radar is in an unoccluded state, so as to give an unoccluded prompt and improve the efficiency of occlusion situation warning. Optionally, the vehicle can also, when it is determined that the occlusion situation of the millimeter-wave radar is in an unoccluded state, clear the number of times that the millimeter-wave radar is in an occluded state recorded in the results of continuously preset detections of the occlusion situation of the millimeter-wave radar, so as to save the resource consumption of detecting the occlusion situation while accurately detecting the occlusion situation.

[0061] In some embodiments, the vehicle can, when the vehicle speed is continuously greater than the second speed, obtain the results of continuously preset detections of the occlusion situation of the millimeter-wave radar, so as to detect the occlusion situation of the millimeter-wave radar during the driving of the vehicle and improve the driving safety of the vehicle. Wherein, the vehicle can stop detecting the occlusion of the millimeter-wave radar when the vehicle speed is less than the second vehicle speed; by way of example, the vehicle can clear the results of continuously preset detections of the occlusion situation of the millimeter-wave radar of the vehicle, or can also clear the number of times that the millimeter-wave radar is in an occluded state recorded in the results of continuously preset detections of the occlusion situation of the millimeter-wave radar of the vehicle.

[0062] In some embodiments, the vehicle can detect the vehicle speed in real time. If the vehicle, after outputting the second prompt message, detects again that the vehicle speed is greater than the second speed, or, detects again that the vehicle speed is greater than the second speed and lasts for the second duration, it can be determined to clear the number of times that the millimeter-wave radar is in an occluded state recorded in the results of continuously preset detections of the occlusion situation of the millimeter-wave radar of the vehicle, so as to indicate that the millimeter-wave radar has returned to the normal working state.

[0063] Step S260: If, based on the result of the detection, it is determined that the number of times the millimeter-wave radar is detected to be in an occluded state is greater than or equal to the first number threshold, output a first prompt message, where the first prompt message is used to prompt that the millimeter-wave radar has been occluded for a long time.

[0064] In some embodiments, after the vehicle obtains the results of continuously preset detections of the occlusion situation of the millimeter-wave radar, it can, based on the result of this detection, determine whether to output a first prompt message, or output a second prompt message, or obtain the result of the next continuously preset detection of the occlusion situation of the millimeter-wave radar. Wherein, the first prompt message can be used to prompt that the millimeter-wave radar has been occluded for a long time; the second prompt message can be used to prompt that the millimeter-wave radar is in an unoccluded state.

[0065] Among them, the vehicle can output the first prompt message and the second prompt message based on voice prompts, indicator light prompts, interface prompts, etc. Among them, the output methods of the first prompt message and the second prompt message can be the same or different, which is not limited here.

[0066] Among them, a first number threshold can be preset in the vehicle. The first number threshold can be set independently by the user or obtained through third-party experimental data. Exemplarily, the first number threshold can be set independently by the user to 50 times. Among them, after the vehicle obtains the detection results of the occlusion situation of the millimeter-wave radar for continuously preset times, the vehicle can compare the number of times the millimeter-wave radar is in the occluded state recorded in the detection results with the first number threshold, and based on the detection results, output the first prompt message when it is determined that the number of times the millimeter-wave radar is in the occluded state is greater than or equal to the first number threshold. Among them, if the vehicle determines, based on the detection results, that the number of times the millimeter-wave radar is in the occluded state is less than or equal to the second number threshold, the second prompt message can be output; among them, when the vehicle determines, based on the detection results, that the number of times the millimeter-wave radar is in the occluded state is greater than the second number threshold and less than the first number threshold, the number of valid occlusion judgment times recorded in the detection results can be cleared, and the vehicle can return to the step of obtaining the detection results of the occlusion situation of the millimeter-wave radar for continuously preset times, so as to detect the occlusion situation of the millimeter-wave radar in real time, output prompt messages according to the detection results for warning, improve the stability and reliability of the millimeter-wave radar operation, improve the safety of vehicle driving, and improve the user experience.

[0067] Exemplarily, please refer to Figure 3 , which shows a schematic flowchart of an occlusion detection method provided by an embodiment of the present application. Among them, a millimeter-wave radar can be set on the vehicle, and the vehicle can collect point cloud data corresponding to the vehicle's environment through the millimeter-wave radar. Among them, the vehicle can obtain the vehicle speed of its own vehicle in real time, and compare the vehicle speed with a second speed. If it is determined that the vehicle speed is greater than the second vehicle speed (such as, 15 km / s, etc.), the vehicle can obtain the point cloud data collected by the millimeter-wave radar and determine the valid point cloud for each frame of point cloud data. Among them, when the vehicle speed continues to be greater than the second speed, the vehicle can obtain the point cloud data collected by the millimeter-wave radar on the vehicle within a first duration (such as, 35 s, etc.), and count the total number of valid point clouds in the historical frames of the point cloud data within the first duration to obtain a target number.

[0068] Among them, during the process of the vehicle determining the valid point cloud for each frame of point cloud data, the vehicle can perform clustering processing on each frame of point cloud data to obtain at least one target point cloud data. Among them, different target point cloud data correspond to different objects, and the vehicle can obtain the peak point cloud corresponding to each of the at least one target point cloud data. Among them, the peak point cloud corresponding to each target point cloud data is the point cloud with the strongest energy among the target point cloud data collected by the millimeter-wave radar; and the vehicle can determine, from the peak point clouds corresponding to each of the at least one target point cloud data, the peak point cloud with a distance greater than the target distance (such as, 20 m, etc.) from the millimeter-wave radar and an absolute value of the Doppler velocity greater than the first velocity (such as, 1 m / s, etc.) as the target point cloud; so that the vehicle can obtain the number of target point clouds in the point cloud data within the first time period as the target number.

[0069] Among them, if the vehicle determines that the target number is less than or equal to the first number threshold (such as, 1500, etc.), it can be determined that the millimeter-wave radar is in an occluded state during this detection. Among them, if the vehicle determines that the target number is greater than the first number threshold and less than or equal to the second number threshold (such as, 12000, etc.), it can be determined that the millimeter-wave radar is in an unoccluded state during this detection, where the first number threshold is less than the second number threshold. Among them, if the vehicle determines that the target number is greater than the second number threshold, it can output a second prompt message, where the second prompt message can be used to prompt that the millimeter-wave radar is in an unoccluded state. Thus, the vehicle can perform occlusion judgment only based on the point cloud data collected by the millimeter-wave radar without relying on the collaborative work of multiple sensors, making the occlusion judgment logic of the millimeter-wave radar simple, reducing the complexity and cost of the occlusion judgment of the millimeter-wave radar, and improving the accuracy and effectiveness of the occlusion judgment by optimizing the number of valid point clouds obtained from the point cloud data, improving the vehicle's perception ability of the surrounding environment during the driving process, and enhancing the driving safety.

[0070] Among them, when the vehicle speed remains greater than the second speed, the vehicle can obtain the results of detecting the occlusion situation of the millimeter-wave radar in the most recent consecutive preset number of times (such as 50 times, etc.). Among them, the length of the time window for detecting the occlusion situation of the millimeter-wave radar each time is equal to the first duration. Among them, during the process of detecting the occlusion situation of the millimeter-wave radar in the consecutive preset number of times, if the vehicle detects that the vehicle speed is less than the second speed, the number of times the millimeter-wave radar is in the occluded state recorded in the results of detecting the occlusion situation of the millimeter-wave radar in the consecutive preset number of times can be cleared. Among them, the occlusion situation includes being in the occluded state or being in the non-occluded state. Among them, the vehicle can record the results of detecting the occlusion situation of the millimeter-wave radar in the consecutive preset number of times in the form of an array. Among them, the vehicle can judge the current occlusion situation of the millimeter-wave radar according to the number of valid point clouds in the time window of each first duration; if it is judged to be in the occluded state, the number of times the millimeter-wave radar is in the occluded state can be incremented by 1, and the "occluded" state can be written into the array of the most recent consecutive preset number of valid occlusion judgments; if it is judged to be in the non-occluded state, the "non-occluded" state can be written into the array of the most recent consecutive preset number of valid occlusion judgments.

[0071] Among them, if the vehicle determines, based on the results of this detection, that the number of times the millimeter-wave radar is detected to be in the occluded state is greater than or equal to the first number threshold (such as 50 times), the vehicle can output a first prompt message, where the first prompt message can be used to prompt that the millimeter-wave radar has been in the occluded state for a long time. Among them, if the vehicle determines, based on the results of this detection, that the number of times the millimeter-wave radar is detected to be in the occluded state is less than or equal to the second number threshold (such as 1 time), the vehicle can output a second prompt message, where the second number threshold is less than the first number threshold. Thus, by comprehensively considering the judgment of valid point clouds, the statistics of the number of valid point clouds, and the statistics of the number of valid occlusion judgments, an alarm for the occlusion situation of the millimeter-wave radar is carried out, improving the reliability and stability of the operation of the millimeter-wave radar.

[0072] Among them, when the vehicle determines that the number of targets corresponding to the point cloud data collected by the millimeter-wave radar within the first duration is greater than the second number threshold, the vehicle can also output a second prompt message and not include the results of detecting the occlusion situation of the millimeter-wave radar this time in the detection results.

[0073] Among them, after the vehicle determines to output the second prompt message, the vehicle speed can be detected, and when it is detected again that the vehicle speed is greater than the second speed and lasts for the second duration, it is determined that the millimeter-wave radar is in the normal working state, and the number of times the millimeter-wave radar is in the occluded state recorded in the results of detecting the occlusion situation of the millimeter-wave radar in the consecutive preset number of times can be cleared, so as to improve the stability and reliability of the occlusion judgment of the millimeter-wave radar.

[0074] The occlusion detection method provided by an embodiment of the present application, compared with Figure 1 the occlusion detection method shown, this embodiment can also determine that the millimeter-wave radar is in an unoccluded state during this detection if the number of targets is greater than the first quantity threshold and less than or equal to the second quantity threshold, where the second quantity threshold is greater than the first quantity threshold, thereby effectively judging the unoccluded situation of the millimeter-wave radar and improving the accuracy of millimeter-wave radar occlusion detection. This embodiment can also obtain the results of continuously preset detections of the occlusion situation of the millimeter-wave radar, where the length of the time window for each detection of the occlusion situation of the millimeter-wave radar is equal to the first duration, and the occlusion situation includes being in an occluded state or in an unoccluded state; if it is determined based on the detection results that the number of times the millimeter-wave radar is detected to be in an occluded state is greater than or equal to the first number threshold, a first prompt message is output, where the first prompt message is used to prompt that the millimeter-wave radar has been in an occluded state for a long time, thereby comprehensively considering the judgment of effective point clouds, the statistics of the number of effective point clouds, and the statistics of the number of effective occlusion judgments to perform alarm for the occlusion situation of the millimeter-wave radar, improving the effectiveness of millimeter-wave radar occlusion judgment, and improving the reliability and stability of the operation of the millimeter-wave radar.

[0075] Please refer to Figure 4 , Figure 4 which shows a block diagram of an occlusion detection device provided by an embodiment of the present application. The occlusion detection device 200 is applied to the above vehicle, and the following will elaborate in detail on the Figure 4 process shown. The occlusion detection device 200 includes: a point cloud data acquisition module 210, a target quantity acquisition module 220, and an occluded state determination module 230, where:

[0076] The point cloud data acquisition module 210 is configured to acquire the point cloud data collected by the millimeter-wave radar on the vehicle within the first duration.

[0077] The target quantity acquisition module 220 is configured to determine, from the point cloud data, the number of target point clouds that meet the effective point cloud condition as the target quantity according to the distance between the point clouds in the point cloud data and the millimeter-wave radar and the Doppler velocity of the point clouds in the point cloud data.

[0078] The occluded state determination module 230 is configured to determine that the millimeter-wave radar is in an occluded state during this detection if the target quantity is less than or equal to the first quantity threshold.

[0079] Further, the target quantity acquisition module 220 may include: a point cloud data clustering unit, a peak point cloud acquisition unit, and an effective point cloud quantity acquisition unit, where:

[0080] A point cloud data clustering unit for clustering the point cloud data to obtain at least one target point cloud data, where different target point cloud data correspond to different objects.

[0081] A peak point cloud acquisition unit for acquiring the peak point cloud corresponding to each of the at least one target point cloud data, where the peak point cloud corresponding to each target point cloud data is the point cloud with the strongest energy among the target point cloud data collected by the millimeter-wave radar.

[0082] An effective point cloud quantity acquisition unit for determining the quantity of target point clouds that meet the effective point cloud condition from the peak point clouds corresponding to each of the at least one target point cloud data according to the distance between the peak point cloud corresponding to each target point cloud data and the millimeter-wave radar and the Doppler velocity of the peak point cloud corresponding to each target point cloud data, and taking it as the target quantity.

[0083] Further, the effective point cloud quantity acquisition unit may include: a target point cloud determination unit and a target quantity acquisition subunit, where:

[0084] The target point cloud determination unit is used to determine, from the peak point clouds corresponding to each of the at least one target point cloud data, the peak point cloud with a distance greater than the target distance from the millimeter-wave radar and an absolute value of the Doppler velocity greater than the first velocity as the target point cloud.

[0085] The target quantity acquisition subunit is used to acquire the quantity of the target point clouds as the target quantity.

[0086] Further, the occlusion detection device 200 may further include: a result acquisition unit for continuous preset times of detection and a first prompt information output unit, where:

[0087] The result acquisition unit for continuous preset times of detection is used to acquire the results of continuously preset times of detecting the occlusion situation of the millimeter-wave radar, where the length of the time window for each detection of the occlusion situation of the millimeter-wave radar is equal to the first duration, and the occlusion situation includes being in an occluded state or an unoccluded state.

[0088] The first prompt information output unit is used to output the first prompt information if, based on the detection results, it is determined that the number of times the millimeter-wave radar is detected to be in the occluded state is greater than or equal to the first number threshold, where the first prompt information is used to prompt that the millimeter-wave radar is in the occluded state for a long time.

[0089] Further, the occlusion detection device 200 may further include: an unoccluded state determination unit, where:

[0090] An unobstructed state determination unit, configured to determine that the millimeter-wave radar is in an unobstructed state in this detection if the target quantity is greater than the first quantity threshold and less than or equal to the second quantity threshold, where the second quantity threshold is greater than the first quantity threshold.

[0091] Further, the occlusion detection device 200 may further include: a second prompt information output first unit or a second prompt information output second unit, where:

[0092] The second prompt information output first unit is configured to output second prompt information if the target quantity is greater than the second quantity threshold, and not include the result of the occlusion situation of the millimeter-wave radar detected in this time in the detection result, where the second prompt information is used to prompt that the millimeter-wave radar is in an unobstructed state.

[0093] The second prompt information output second unit is configured to output the second prompt information if, based on the detection result, the number of times of determining that the millimeter-wave radar is in an occluded state is less than or equal to the second number threshold, and the second number threshold is less than the first number threshold.

[0094] Further, the point cloud data acquisition module 210 may include: a vehicle speed acquisition unit and a point cloud data acquisition sub-unit, where:

[0095] The vehicle speed acquisition unit is configured to acquire the vehicle speed of the vehicle.

[0096] The point cloud data acquisition sub-unit is configured to acquire the point cloud data collected by the millimeter-wave radar on the vehicle within the first duration if the vehicle speed is greater than the second speed.

[0097] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0098] In several embodiments provided in the present application, the coupling between modules may be electrical, mechanical, or other forms of coupling.

[0099] In addition, in each embodiment of the present application, the various functional modules may be integrated in one processing module, or each module may exist physically alone, or two or more modules may be integrated in one module. The above integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0100] Please refer to Figure 5, which shows a structural block diagram of a vehicle 100 provided by an embodiment of the present application. The vehicle 100 may be an electric vehicle, a gasoline vehicle, a robot, an intelligent transportation device, or other vehicles with processing capabilities. The vehicle 100 in the present application may include one or more of the following components: a processor 110, a memory 120, and one or more application programs, where one or more application programs may be stored in the memory 120 and configured to be executed by one or more processors 110, and one or more programs are configured to execute the methods described in the foregoing method embodiments.

[0101] Among them, the processor 110 may include one or more processing cores. The processor 110 uses various interfaces and lines to connect various parts within the entire vehicle 100, and by running or executing instructions, programs, code sets, or instruction sets stored in the memory 120, and calling data stored in the memory 120, it executes various functions of the vehicle 100 and processes data. Optionally, the processor 110 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 110 may integrate one or several combinations of a central processing unit (CPU), a graphics processing unit (GPU), and a modem, etc. Among them, the CPU mainly processes the operating system, user interface, and application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed; the modem is used to process wireless communication. It can be understood that the above modem may not be integrated into the processor 110 and may be implemented separately through a communication chip.

[0102] The memory 120 may include random access memory (RAM), and may also include read-only memory. The memory 120 can be used to store instructions, programs, codes, code sets, or instruction sets. The memory 120 may include a program storage area and a data storage area. Among them, the program storage area may store instructions for implementing the operating system, instructions for implementing at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the following various method embodiments, etc. The data storage area may also store data created during the use of the vehicle 100 (such as phone books, audio and video data, chat record data, etc.).

[0103] Among them, the vehicle 100 can be applied to the field of high-precision environmental perception; a millimeter-wave radar can be provided on the vehicle 100 or the vehicle 100 can be communicatively connected to the millimeter-wave radar; the vehicle 100 can also be communicatively connected to a movable device provided with a millimeter-wave radar, which is not limited herein.

[0104] Please refer to Figure 6 , which shows a structural block diagram of a computer-readable storage medium provided by an embodiment of the present application. Program code is stored in the computer-readable medium 300, and the program code can be called by a processor to execute the method described in the above method embodiment.

[0105] The computer-readable storage medium 300 can be an electronic memory such as a flash memory, EEPROM (electrically erasable programmable read-only memory), EPROM, hard disk, or ROM. Optionally, the computer-readable storage medium 300 includes a non-transitory computer-readable storage medium. The computer-readable storage medium 300 has a storage space for the program code 310 that executes any method step in the above method. These program codes can be read out from or written into one or more computer program products. The program code 310 can be compressed in an appropriate form, for example.

[0106] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An occlusion detection method, characterized in that, The method includes: Obtaining point cloud data collected by a millimeter-wave radar on a vehicle within a first duration; Determining, from the point cloud data, the number of target point clouds that meet the effective point cloud condition based on the distance between the point cloud in the point cloud data and the millimeter-wave radar and the Doppler velocity of the point cloud in the point cloud data, and taking the number as the target number; If the target number is less than or equal to a first number threshold, determining that the millimeter-wave radar is in an occluded state in this detection.

2. The method according to claim 1, wherein The determining, from the point cloud data, the number of target point clouds that meet the effective point cloud condition based on the distance between the point cloud in the point cloud data and the millimeter-wave radar and the Doppler velocity of the point cloud in the point cloud data, and taking the number as the target number includes: Performing clustering processing on the point cloud data to obtain at least one target point cloud data, where different target point cloud data correspond to different objects; Obtaining the peak point cloud corresponding to each of the at least one target point cloud data, where the peak point cloud corresponding to each target point cloud data is the point cloud with the strongest energy in each of the target point cloud data collected by the millimeter-wave radar; Determining, from the peak point clouds corresponding to each of the at least one target point cloud data, the number of target point clouds that meet the effective point cloud condition based on the distance between the peak point cloud corresponding to each target point cloud data and the millimeter-wave radar and the Doppler velocity of the peak point cloud corresponding to each target point cloud data, and taking the number as the target number.

3. The method according to claim 2, wherein The determining, from the peak point clouds corresponding to each of the at least one target point cloud data, the number of target point clouds that meet the effective point cloud condition based on the distance between the peak point cloud corresponding to each target point cloud data and the millimeter-wave radar and the Doppler velocity of the peak point cloud corresponding to each target point cloud data, and taking the number as the target number includes: Determining, from the peak point clouds corresponding to each of the at least one target point cloud data, the peak point cloud with a distance greater than a target distance from the millimeter-wave radar and an absolute value of the Doppler velocity greater than a first velocity as the target point cloud; Obtaining the number of the target point clouds as the target number.

4. The method according to any one of claims 1 to 3, characterized in that, The method further includes: Obtaining the results of continuously detecting the occlusion situation of the millimeter-wave radar for a preset number of times, where the length of the time window for each detection of the occlusion situation of the millimeter-wave radar is equal to the first duration, and the occlusion situation includes being in an occluded state or an unoccluded state; If, based on the detection results, it is determined that the number of times the millimeter-wave radar is detected to be in an occluded state is greater than or equal to a first number threshold, outputting a first prompt message, where the first prompt message is used to prompt that the millimeter-wave radar is in an occluded state for a long time.

5. The method according to claim 4, characterized in that, The method further includes: If the target number is greater than the first number threshold and less than or equal to a second number threshold, determining that the millimeter-wave radar is in an unoccluded state in this detection, where the second number threshold is greater than the first number threshold.

6. The method according to claim 5, characterized in that, The method further includes: If the target quantity is greater than the second quantity threshold, output a second prompt message and do not include the result of detecting the occlusion status of the millimeter-wave radar this time in the detection result, where the second prompt message is used to prompt that the millimeter-wave radar is in an unoccluded state; or If, based on the detection result, it is determined that the number of times the millimeter-wave radar is detected to be in an occluded state is less than or equal to the second number threshold, output the second prompt message, where the second number threshold is less than the first number threshold.

7. The method according to claim 1, wherein The obtaining of the point cloud data collected by the millimeter-wave radar on the vehicle within the first duration includes: Obtain the vehicle speed of the vehicle; If the vehicle speed is greater than the second speed, obtain the point cloud data collected by the millimeter-wave radar on the vehicle within the first duration.

8. An occlusion detection device, characterized in that, The device includes: A point cloud data acquisition module, configured to obtain the point cloud data collected by the millimeter-wave radar on the vehicle within the first duration; A target quantity acquisition module, configured to determine, from the point cloud data, the quantity of target point clouds that meet the effective point cloud condition as the target quantity according to the distance between the point cloud in the point cloud data and the millimeter-wave radar and the Doppler velocity of the point cloud in the point cloud data; An occluded state determination module, configured to determine that the millimeter-wave radar is in an occluded state this time if the target quantity is less than or equal to the first quantity threshold.

9. A vehicle, characterized in that, Includes: One or more processors; A memory; One or more applications, where the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to execute the method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores program code, and the program code can be called by the processor to execute the method according to any one of claims 1-7.

Images