Radar failure determination method and device, and storage medium

文档序号：1830253 发布日期：2021-11-12 浏览：8次中文

阅读说明：本技术 雷达失效判定方法及装置、存储介质 (Radar failure determination method and device, and storage medium ) 是由宋旸张乃川舒博正黄琦赵学思夏冰冰石拓于 2021-10-15 设计创作，主要内容包括：本申请公开了一种雷达失效判定方法及装置、存储介质,所述方法包括：根据雷达的点云的属性信息为点云配置权重系数矩阵；检测扫描帧内的异常点,基于所述异常点的权重系数矩阵计算异常点的加权总数；基于所述加权总数确定所述雷达是否失效。本申请对异常点的失效判断更为准确,大大提升了雷达失效的判断准确率。(The application discloses a radar failure judgment method and device and a storage medium, wherein the method comprises the following steps: configuring a weight coefficient matrix for the point cloud according to the attribute information of the point cloud of the radar; detecting abnormal points in a scanning frame, and calculating the total weighted number of the abnormal points based on the weight coefficient matrix of the abnormal points; determining whether the radar is failed based on the weighted total. The failure judgment of the abnormal point is more accurate, and the failure judgment accuracy of the radar is greatly improved.)

1. A method for determining laser radar failure, the method comprising:

configuring a weight coefficient matrix for the point cloud according to the attribute information of the point cloud of the laser radar;

detecting abnormal points in a scanning frame, and calculating the total weighted number of the abnormal points based on the weight coefficient matrix of the abnormal points;

determining whether the radar is failed based on the weighted total.

2. The method of claim 1, wherein the determining whether the radar is failed based on the weighted sum comprises:

and when the weighted sum is determined to be larger than a first threshold value, the radar is invalid.

3. The method according to claim 1 or 2, characterized in that the method further comprises:

determining a maximum local weighted density of the outliers;

the determining whether the radar is failed based on the weighted total includes:

comparing the maximum local weighted density to a third threshold when it is determined that the total number of weights is less than a first threshold and greater than a second threshold; and when the maximum local weighted density is larger than the third threshold value, determining that the radar is invalid.

4. The method according to claim 1 or 2, wherein the configuring a weight coefficient matrix for the point cloud according to the attribute information of the point cloud of the radar comprises:

configuring different first class weight values for point clouds in different areas according to the distribution areas of the point clouds of the radar; and/or configuring different second class weight values for point clouds with different distances according to the distance between the point cloud of the radar and the installation object; and/or configuring different third class weight values for the point clouds with different distribution densities according to the distribution density of the point clouds of the radar;

5. The method of claim 3, wherein determining the maximum local weighted density of outliers comprises:

determining a rotation angle and/or a pitch angle of the point cloud corresponding to the detection target according to the size of the detection target, determining a stereo scanning window of the radar based on the rotation angle and/or the pitch angle, traversing the whole point cloud, calculating the weighted total number of all abnormal points in the stereo scanning window at each traversal position, and determining the weighted total number corresponding to the stereo scanning window with the largest weighted total number as the maximum local weighted density of the abnormal points.

6. The method of claim 3, wherein determining the maximum local weighted density of outliers comprises:

dividing abnormal points in all the point clouds into a plurality of clusters by using a density clustering mode, and determining the weighted sum corresponding to the cluster with the maximum weighted sum of the abnormal points in the plurality of clusters as the maximum local weighted density of the abnormal points.

7. The method of claim 1 or 2, wherein the detecting the outlier in the scan frame comprises:

and detecting the energy of the echo signals corresponding to the point clouds in the scanning frames, and determining the point clouds as abnormal points when the energy of the echo signals of the point clouds in the scanning frames of a continuously set number is lower than a fourth threshold value.

8. A radar failure determination apparatus, characterized by comprising:

the configuration unit is used for configuring a weight coefficient matrix for the point cloud according to the attribute information of the point cloud of the radar;

a detection unit for detecting an abnormal point within the scanning frame;

the calculating unit is used for calculating the total weighted number of the abnormal points based on the weight coefficient matrix of the abnormal points;

a determination unit to determine whether the radar is failed based on the weighted total.

9. The apparatus of claim 8, wherein the determining unit is further configured to:

and when the weighted sum is determined to be larger than a first threshold value, the radar is invalid.

10. The apparatus according to claim 8 or 9, wherein the determining unit is further configured to: determining a maximum local weighted density of the outliers;

11. The apparatus of claim 10, wherein the configuration unit is further configured to:

12. The apparatus of claim 10, wherein the determining unit is further configured to:

13. The apparatus of claim 10, wherein the determining unit is further configured to:

14. The apparatus according to claim 8 or 9, wherein the detecting unit is further configured to:

15. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the radar failure determination method according to any one of claims 1 to 7.

Technical Field

The embodiment of the application relates to a laser radar technology, in particular to a radar failure determination method and device and a storage medium.

Background

In recent years, laser radar (LIDAR) has been widely used in the field of automatic driving. When the automatic driving vehicle is used for large-scale road measurement, bad weather and muddy road conditions can be met, the optical outer cover of the laser radar is polluted, and when the pollution is heavy, echo signals of a large number of point positions are weakened or even disappear. On the other hand, the aging and the failure of the optical components, the scanning components and the receiving module of the device can also cause a great amount of loss of point clouds, which can cause the obstacle recognition capability of the laser radar to be seriously affected and threaten the driving safety in an automatic driving state.

At present, a detection means aiming at a point cloud failure mode is not mature.

Disclosure of Invention

In view of this, the present application provides a radar failure determination method and apparatus, and a storage medium.

According to a first aspect of an embodiment of the present application, there is provided a radar failure determination method, including:

configuring a weight coefficient matrix for the point cloud according to the attribute information of the point cloud of the radar;

detecting abnormal points in a scanning frame, and calculating the total weighted number of the abnormal points based on the weight coefficient matrix of the abnormal points;

determining whether the radar is failed based on the weighted total.

In one embodiment, said determining whether said radar has failed based on said weighted sum comprises:

and when the weighted sum is determined to be larger than a first threshold value, the radar is invalid.

In one embodiment, the method further comprises:

determining a maximum local weighted density of the outliers;

the determining whether the radar is failed based on the weighted total includes:

In one embodiment, the configuring a weight coefficient matrix for the point cloud according to the attribute information of the point cloud of the radar includes:

In one embodiment, the determining the maximum local weighted density of the outliers comprises:

In one embodiment, the detecting an outlier within a scan frame comprises:

According to a second aspect of embodiments of the present application, there is provided a radar failure determination device including:

the configuration unit is used for configuring a weight coefficient matrix for the point cloud according to the attribute information of the point cloud of the radar;

a detection unit for detecting an abnormal point within the scanning frame;

the calculating unit is used for calculating the total weighted number of the abnormal points based on the weight coefficient matrix of the abnormal points;

a determination unit to determine whether the radar is failed based on the weighted total.

In one embodiment, the determining unit is further configured to:

and when the weighted sum is determined to be larger than a first threshold value, the radar is invalid.

In one embodiment, the determining unit is further configured to: determining a maximum local weighted density of the outliers;

In one embodiment, the configuration unit is further configured to:

In one embodiment, the determining unit is further configured to:

In one embodiment, the detection unit is further configured to:

According to a third aspect of embodiments of the present application, there is provided a computer-readable storage medium having stored therein a computer program, which when executed by a processor, implements the steps of the radar failure determination method.

According to the radar failure determination method and device and the storage medium, corresponding weights are distributed for point cloud data in a scanning frame, when abnormal points appear in the scanning frame, the total weight of the abnormal points is determined according to the weights corresponding to the abnormal points, and therefore whether the abnormal points can affect normal work of a laser radar is determined. The embodiment of the application has more accurate judgment on the failure of the laser radar.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below. It is obvious that the drawings in the following description are some embodiments of the invention, and that for a person skilled in the art, other drawings can be derived from them without inventive effort.

Fig. 1 is a schematic flowchart of a radar failure determination method according to an embodiment of the present application;

FIG. 2 is a schematic flowchart of a radar failure determination method according to an embodiment of the present application

Fig. 3 is a schematic structural diagram of a radar failure determination apparatus according to an embodiment of the present application;

fig. 4 shows a block diagram of an electronic device of an embodiment of the invention.

Detailed Description

The essence of the technical solution of the embodiments of the present application is explained in detail below with reference to the accompanying drawings.

Fig. 1 is a schematic flowchart of a radar failure determination method according to an embodiment of the present application, and as shown in fig. 1, the radar failure determination method according to the embodiment of the present application includes:

step 101, configuring a weight coefficient matrix for the point cloud according to the attribute information of the point cloud of the radar.

In this embodiment, the attribute information of the point cloud includes position information of the point cloud, such as whether the point cloud is located in an edge region or a center region. The attribute information of the point cloud also comprises the distribution density information of the point cloud, such as point cloud density and other information.

Specifically, different first class weight values can be configured for point clouds in different areas according to the distribution area of the point clouds of the radar; and/or configuring different second class weight values for point clouds with different distances according to the distance between the point cloud of the radar and the installation object; and/or configuring different third class weight values for the point clouds with different distribution densities according to the distribution density of the point clouds of the radar;

forming a weight coefficient matrix by the weight value of each point cloud according to the point cloud position distribution information; when the category of the weight values configured for the point cloud is more than two categories, the product of the more than two categories of the weight values is used as the weight value of the point cloud. Here, for convenience of operation, according to the position distribution condition of each point cloud in the laser radar, a weight coefficient matrix is set for the point cloud of the laser radar, that is, corresponding weight coefficient matrices are respectively set for the point clouds in each row and each column, so that each point cloud corresponds to the weight coefficient at the corresponding position in the weight coefficient matrix according to the position of the point cloud, and thus, when an abnormal point cloud is determined in the point cloud data of the laser radar, the weight coefficient of the point cloud can be known at the corresponding position in the corresponding weight coefficient matrix, and the learning of the weight coefficient in the point cloud and the corresponding operation are more convenient.

And 102, detecting abnormal points in the scanning frame, and calculating the total weighting number of the abnormal points based on the weighting coefficient matrix of the abnormal points.

In this embodiment, the energy of the echo signal corresponding to the point cloud in the scan frame may be detected, and when the energy of the echo signal of the point cloud in the scan frames of the continuously set number is lower than the fourth threshold, the point cloud is determined to be an abnormal point. The fourth threshold value here is set empirically or determined through related experiments.

And 103, determining whether the radar fails or not based on the weighted total number.

In the embodiment of the application, when the weighted total number of the abnormal points in the scanning frame is determined to exceed the first threshold value, the point cloud data is determined to be abnormal, and the radar is invalid.

In the embodiment of the application, when it is determined that the laser radar fails and cannot work normally, alarm information can be further output to prompt a user to perform corresponding maintenance or repair.

In the embodiment of the application, in order to make the judgment result of whether the radar fails more accurate, whether the laser radar fails can be further determined by combining the maximum local weighted density of the abnormal points. In particular, when it is determined that the total number of weights is less than a first threshold and greater than a second threshold, the maximum local weighted density is compared to a third threshold; and when the maximum local weighted density is larger than the third threshold value, determining that the radar is invalid.

In the embodiment of the present application, determining the maximum local weighted density of the outlier includes: determining a rotation angle and/or a pitch angle of the point cloud corresponding to the detection target according to the size of the detection target, determining a stereo scanning window of the radar based on the rotation angle and/or the pitch angle, traversing the whole point cloud, calculating the weighted total number of all abnormal points in the stereo scanning window at each traversal position, and determining the weighted total number corresponding to the stereo scanning window with the largest weighted total number as the maximum local weighted density of the abnormal points. Or dividing the abnormal points in all the point clouds into a plurality of clusters by using a density clustering mode, and determining the weighted sum corresponding to the cluster with the maximum weighted sum of the abnormal points in the plurality of clusters as the maximum local weighted density of the abnormal points.

The technical scheme of the embodiment of the application can be used for judging the point cloud abnormal condition of the laser radar in the automatic driving system in real time, provides accurate reference basis for automatic dirty cleaning and automatic fault troubleshooting of the laser radar or prompting manual intervention, and improves the functional safety of the automatic driving system.

The technical solutions of the embodiments of the present application are described in detail below.

In practical applications, it is necessary to detect abnormal points in each frame of point cloud in real time, and generally, a certain echo energy threshold E is set according to practical situations_thAt a point where the energy of successive frames is less than E_thThen the point is considered to be an outlier. And adding the corresponding weight values of all the abnormal points detected in a certain frame in the weight matrix to obtain the total number of the abnormal points in the frame.

And configuring a weight coefficient matrix for the point cloud in the scanning frame of the laser radar. The specific configuration means comprises:

the embodiment of the application configures the weight coefficient matrix for the point cloud because each point in the point cloud has different functions in the point cloud data analysis in practical application, and if abnormality occurs due to some reason, the influence on the overall detection capability of the point cloud is small. Whether the point cloud is invalid or not is judged according to the total number of the abnormal points by the current common method, which is equivalent to that all the points are considered to have the same weight, and the method is obviously inconsistent with the actual situation. Therefore, in the embodiment of the present application, the importance of each point needs to be measured in combination with the actual application condition, and a corresponding weight coefficient needs to be configured for each point, and the weight coefficient of the point cloud forms a weight coefficient matrix.

As an example, the weight coefficients may be configured for the point cloud in the following manner:

1) and configuring different first class weight values a for the point clouds in different areas according to the distribution areas of the point clouds of the radar.

After the lidar is mounted to an application object such as an autonomous vehicle, the point cloud coverage area of the lidar may also be different depending on the mounting position and angle of the lidar. Thus, the point clouds in different areas are focused differently in specific application scenarios. Because the laser pulse flight distance is often far in the point cloud edge region, the echo is weak, and in most cases, the corresponding echo signal cannot be detected, which has little influence on the point cloud detection capability. As an example, the weighting factor a of the edge area should be configured to be smaller, even 0, and correspondingly, the value of the inner area point a is configured to be 1, even larger. In addition, when the lidar is practically used, a situation that a certain area has special importance in a scene often occurs, and extra attention is needed, for example, the lidar is installed right in front of a vehicle, obviously, a point cloud right in front is configured with higher weight than two sides, and in this case, a can be configured as a value larger than 1.

2) And configuring different second class weight values b for the point clouds with different distances according to the distance between the point cloud of the radar and the installation object.

When most of laser radars are installed on a vehicle, part of point clouds are irradiated on the ground in an oblique downward direction, and due to the fact that obstacle missing detection is easy to occur in a region close to the vehicle body, the threat to the automatic driving safety is larger than that of missing detection occurring in a far position, and therefore the b value is configured according to a method that the position, corresponding to the point clouds, of a laser beam irradiated on the ground is in inverse proportion to the distance between the vehicle body and the laser beam.

3) According to the distribution density of the point clouds of the radar, different third class weight values c are configured for the point clouds with different distribution densities

In the embodiment of the application, when abnormal points appear in an area with high point cloud density, enough identification of normal point cloud supporting obstacles still can be achieved. Here, the calculation of the point cloud density needs to take the influence of the laser emission angle into consideration because the maximum light receiving surface of an important obstacle such as a rider or a pedestrian is perpendicular to the ground, and the maximum obstacle point can be obtained only when the laser emission angle is perpendicular to the maximum light receiving surface. Therefore, as an example, an effective method for configuring the weight coefficient c is to place a fixed-size reflector perpendicular to the ground in a target area of a point cloud field of view, record the number n of points on the reflector, and configure the weight value c of the area to be inversely proportional to n; in another configuration, an average distance l between each point and an adjacent point on the reflector is calculated, and the weight value c is configured to be proportional to l. Here, the selection method and the number of adjacent points are specifically defined according to different point cloud distribution modes, for example, in a point cloud distributed in a checkered shape, four points, i.e., upper, lower, left, and right points of each point, may be taken as adjacent points.

After the configuration mode of the three weight coefficients is considered, the weight value of the point cloud can be any one of a, b and c, or the product of any two or the product of the three, and after the weight coefficients of all the point clouds are calculated, point cloud weight matrixes are recorded in the point cloud in a one-to-one correspondence mode according to the positions in the point cloud, and are recorded in a storage medium of the laser radar to serve as the weight coefficient matrixes of the point cloud. It should be noted that the weight coefficient matrix of the embodiment of the present application is variable, and the current scene characteristics can be monitored in real time through the point cloud and allocated in real time along with the change of the automatic driving scene. For example, when a vehicle enters a relatively open scene and the number of points at the edge of the point cloud without echoes increases for a long time, the weight value of the edge area corresponding to the weight coefficient a can be appropriately enlarged. In a longer application period, the weight matrix can be configured into an optimized value, an algorithm model is established on the basis of the three principles, the number of misjudgments and missed judgments of point cloud failure judgment is used as a penalty function, and a more accurate weight matrix value can be solved through a large amount of on-road test data.

In the embodiment of the present application, the method may further include a step of calculating a maximum local weighting density.

The maximum local weighted density of the outliers is the maximum of the sum of the weights of the outliers in all the defined local regions in the point cloud. The definition method of the local area is related to the point cloud characteristics and the detection capability requirement on the obstacle. The reason why the point cloud failure is determined by using the maximum local weighted density is that even if the total number of the abnormal points is equal, if the abnormal points are distributed differently, the point cloud failure is still affected differently. As an example: supposing that half of the point clouds are abnormal, there are two situations that firstly, abnormal points are uniformly distributed, secondly, the abnormal points are gathered in a certain area, obviously, the recognition capability of the former point cloud is not greatly influenced, and the latter point cloud can be seriously disabled. Therefore, the embodiment of the application also separately considers the occurrence density of the abnormal points in all the local areas, and judges whether the point cloud is invalid according to the maximum value of the occurrence density, so that the situation can be avoided.

In the embodiment of the present application, determining the maximum local weighted density of the outlier includes the following two ways:

the method comprises the steps of firstly, determining a rotation angle and/or a pitch angle of a point cloud corresponding to a detection target according to the size of the detection target, determining a stereo scanning window of the radar based on the rotation angle and/or the pitch angle, traversing the whole point cloud, calculating the total weight number of all abnormal points in the stereo scanning window at each traversal position, and determining the total weight number corresponding to the stereo scanning window with the maximum total weight number as the maximum local weighting density of the abnormal points.

A common definition of a local area is to determine a solid angle range using the rotation angle a and the pitch angle B, and to determine all the point clouds within the solid angle range, the parameters a and B usually being determined by the smallest dimensions of the lidar main detection target. For example, the common obstacles of the laser radar are vehicles and pedestrians, wherein young children are the obstacle with the smallest size, and then the solid angles of the young children in different local areas in the laser emission direction are found according to the point cloud distribution after the radar is installed, so that the rotation angle a and the pitch angle B can be just selected to cover. When calculating the maximum local weighted density of the abnormal points, the solid angle window is used for traversing the whole point cloud, the total weighted number of all the abnormal points in the selection window is calculated at each position, and the maximum value of the result obtained in all the selection windows is found.

The second way,

Dividing abnormal points in all the point clouds into a plurality of clusters by using a density clustering mode, and determining the weighted sum corresponding to the cluster with the maximum weighted sum of the abnormal points in the plurality of clusters as the maximum local weighted density of the abnormal points.

Specifically, for the abnormal points in all the point clouds, a density clustering (DBSCAN) method is used to divide all the point clouds into a plurality of clusters, where a cluster is equivalent to a local area, and the maximum value of the sum of the weights of the abnormal points in all the clusters is the maximum local weighted density under the definition. In the DBSCAN algorithm, the measurement of the distance between two point clouds is obtained by calculating the direction angle of the spherical coordinates of the two points by using the included angle of the emission directions of the two point clouds. And wherein the parameters of the density clustering model are: the neighborhood radius epsilon and the neighborhood minimum sample number MinPts can be determined according to the detection requirement of the laser radar, the size of a concerned obstacle is smaller, the epsilon is correspondingly smaller, the value of MinPts is increased and decreased along with the size of the epsilon, meanwhile, the point cloud density of the MinPts and the laser radar is related, the point cloud with high density has more redundant resources for obstacle identification, and therefore the MinPts can appropriately take a larger value.

Fig. 2 is a schematic flowchart of a radar failure determination method according to an embodiment of the present application, and as shown in fig. 2, the radar failure determination method according to the embodiment of the present application includes the following processing steps:

for the point cloud in any scanning frame, firstly calculating the total weight number N of abnormal points, wherein N exceeds a first threshold value N₁When the point cloud is invalid, the point cloud is directly judged, namely the current condition can influence practical application such as distance measurement based on the point cloud. If N is less than N₁Then, N is compared with a second threshold value N₂If N is less than N₂It is determined that the point cloud is not stale. If N exceeds N₂Then calculating the maximum local weighted density M of the abnormal point of the point cloud and a third threshold value M₁Making comparison, M is greater than M₁And judging whether the point cloud is invalid or not, and judging whether the point cloud is still in an effective state or not, so that the practical application of distance measurement based on the point cloud and the like is influenced.

In the embodiment of the present application, the threshold N₁、N₂、M₁The selection method can be used for building a simulation experiment scene for measurement and calculation. The specific method comprises the following steps:

common highway pavements are selected as experimental sites.

And (3) quantizing and classifying the abnormal conditions of the point clouds: the quantification simulates different kinds of abnormal situations that may occur. For example, mud shelters from the condition of radar printing opacity cover, can use the water proof membrane to beat the round hole respectively according to different radiuses and different intervals to cover in the experiment one by one in the printing opacity cover surface, use the water proof membrane of tearing off again after the mud covers, can quantify the condition of sheltering from that the mud point of simulation different radiuses produced under the splash density of difference. In addition, for example, when the damage of the APD is simulated, the APD faults with different damaged areas can be simulated by covering the APD with shading tapes with different sizes according to the position of the corresponding receiving end light-transmitting cover of the APD on the optical path.

And inspecting the obstacle identification effectiveness of the point cloud under different abnormal conditions. Specifically, the identification criteria for different types of obstacles may be set according to the types of common obstacles encountered in practical applications and combined with the requirements in practical applications, for example, the determination of successful identification may be set to require that an obstacle be detected and correctly classified, or only an obstacle be detected. In the experimental process, obstacles are required to be present in all local areas of the point cloud as much as possible, recognition results of all positions are counted, and the ratio p of successful recognition is calculated. In practical operation, for example, if a pedestrian is used as an obstacle, the pedestrian can be designed to traverse the point cloud covering range in a snake-shaped path, and the corresponding p value can be calculated by counting the recognition result of each frame of point cloud in the whole process.

Determining a corresponding failure determination threshold from the test results: according to the requirements for the detection object and the identification capability in practical application, the minimum identification rate p required when the requirements are completely met can be set₁And the highest recognition rate p when the requirement is not met at all₂（p₁＞p₂). Finding that the p value is larger than p in point cloud identification test₁Calculating the total number of abnormal point weights in all the states, and taking the average value as the threshold N₂Likewise, find all p values less than p₂Using the average of the weighted sum of the abnormal points as the threshold N₁. In addition, the point cloud data under all conditions in the test need to be classified frame by frame according to effective and ineffective conditions, and the classified point cloud dataTaking the data as a training set, then carrying out maximum local weighted density calculation on the training set data according to the used local weighted density algorithm model, comparing the calculation result with the classification condition, and determining M₁The value of (a). When the DBSCAN algorithm is used, the maximum local weighted density values under the two classifications easily generate distribution areas with overlapped sizes, and M is difficult to determine₁The values of the parameters epsilon and MinPts need to be flexibly adjusted according to the characteristics of the radar use scene and the data expression of the training set in practical use. If the training set is too large, the optimization algorithm model can be used to find the parameters ε, MinPts and M₁The optimal matching of the values enables the calculation result to be optimally matched with the classification condition of the training set.

Fig. 3 is a schematic structural diagram of a composition of the radar failure determination device according to the embodiment of the present application, and as shown in fig. 3, the radar failure determination device according to the embodiment of the present application includes:

a configuration unit 30, configured to configure a weight coefficient matrix for the point cloud according to the attribute information of the point cloud of the radar;

a detection unit 31 for detecting an abnormal point within the scanning frame;

a calculating unit 32, configured to calculate a total number of weights of the outliers based on the weight coefficient matrix of the outliers;

a determination unit 33 for determining whether the radar has failed based on the weighted total.

In one embodiment, the determining unit 33 is further configured to:

and when the weighted sum is determined to be larger than a first threshold value, the radar is invalid.

In one embodiment, the determining unit 33 is further configured to: determining a maximum local weighted density of the outliers;

In one embodiment, the configuration unit 30 is further configured to:

In one embodiment, the determining unit 33 is further configured to:

In an embodiment, the detecting unit 31 is further configured to:

In an exemplary embodiment, the configuration Unit 30, the detection Unit 31, the calculation Unit 32, the determination Unit 33, and the like may be implemented by one or more Central Processing Units (CPUs), Graphic Processing Units (GPUs), Baseband Processors (BPs), Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Programmable Logic Devices (PLDs), Complex Programmable Logic Devices (CPLDs), Field Programmable Gate Arrays (FPGAs), general purpose processors, controllers, Micro Controllers (MCUs), microprocessors (microprocessors), or other electronic elements for performing the steps of the radar failure determination method based on the information of the foregoing embodiments.

In the embodiment of the present disclosure, the specific manner in which each unit in the radar failure determination apparatus shown in fig. 3 performs operations has been described in detail in the embodiment related to the method, and will not be described in detail here.

As shown in fig. 4, the electronic device 11 includes one or more processors 111 and memory 112.

The processor 111 may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in the electronic device 11 to perform desired functions.

Memory 112 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, Random Access Memory (RAM), cache memory (cache), and/or the like. The non-volatile memory may include, for example, Read Only Memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium and executed by processor 111 to implement the radar failure determination methods of the various embodiments of the present application described above and/or other desired functions. Various contents such as an input signal, a signal component, a noise component, etc. may also be stored in the computer-readable storage medium.

In one example, the electronic device 11 may further include: an input device 113 and an output device 114, which are interconnected by a bus system and/or other form of connection mechanism (not shown).

The input device 113 may include, for example, a keyboard, a mouse, and the like.

The output device 114 may output various information including the determined distance information, direction information, and the like to the outside. The output devices 114 may include, for example, a display, speakers, a printer, and a communication network and remote output devices connected thereto, among others.

Of course, for simplicity, only some of the components of the electronic device 11 relevant to the present application are shown in fig. 4, omitting components such as buses, input/output interfaces, and the like. In addition, the electronic device 11 may include any other suitable components, depending on the particular application.

In addition to the above-described methods and apparatus, embodiments of the present application may also be a computer program product comprising computer program instructions that, when executed by a processor, cause the processor to perform the steps in the methods according to the various embodiments of the present application described in the "exemplary methods" section of this specification, above.

It should be appreciated that reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. It should be understood that, in various embodiments of the present invention, the sequence numbers of the above-mentioned processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application. The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments.

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are only illustrative, for example, the division of the unit is only one logical function division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not present.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

The above description is only an embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of changes or substitutions within the technical scope of the present invention, and all such changes or substitutions are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.

14页详细技术资料下载

上一篇：一种医用注射器针头装配设备

下一篇：基于改进的联邦滤波的水下AUV传感器时间配准方法

Radar failure determination method and device, and storage medium

相关技术

网友询问留言