CN117892138A - Sensor data set establishing method and device, electronic equipment and storage medium - Google Patents
Sensor data set establishing method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN117892138A CN117892138A CN202410165762.0A CN202410165762A CN117892138A CN 117892138 A CN117892138 A CN 117892138A CN 202410165762 A CN202410165762 A CN 202410165762A CN 117892138 A CN117892138 A CN 117892138A
- Authority
- CN
- China
- Prior art keywords
- target
- sensor
- data set
- information
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000003860 storage Methods 0.000 title claims abstract description 17
- 238000006243 chemical reaction Methods 0.000 claims abstract description 114
- 238000007781 pre-processing Methods 0.000 claims abstract description 10
- 239000011159 matrix material Substances 0.000 claims description 63
- 230000009466 transformation Effects 0.000 claims description 45
- 239000013598 vector Substances 0.000 claims description 29
- 238000012545 processing Methods 0.000 claims description 21
- 238000012549 training Methods 0.000 claims description 13
- 230000008859 change Effects 0.000 abstract description 14
- 230000008569 process Effects 0.000 description 8
- 238000009434 installation Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 238000002372 labelling Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 230000008447 perception Effects 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Landscapes
- Radar Systems Or Details Thereof (AREA)
Abstract
The application provides a sensor data set establishing method, a device, electronic equipment and a storage medium, wherein a data set conversion model related to the working state of a target sensor can be determined through corresponding target information of the target sensor, each preprocessing data in the target data set is subjected to data conversion according to the determined data set conversion model, a converted target data set is obtained, the data in the target data set is associated with related information of the target sensor in a data set conversion model mode, the target data set is processed according to the actual working condition of the target sensor, and the problem that one round of data is required to be collected as a new target data set after each working condition change of the sensor in the prior art is avoided, so that the efficiency and the effectiveness of data set establishment are improved.
Description
Technical Field
The present application relates to sensor technologies, and in particular, to a method and apparatus for establishing a sensor data set, an electronic device, and a storage medium.
Background
In the automatic driving field, a vehicle acquires relevant data of vehicle body parameters or surrounding environments based on multiple types of sensors, and further performs functions such as target detection, position correction, automatic operation and fault detection, and in order to ensure the effectiveness of specific functions, a corresponding data set needs to be established based on specific information of the sensors, such as parameters of a vehicle type, a sensor type, sensor parameters, a sensor installation position and the like, so that training of an artificial intelligent model is performed according to the data set.
However, in the current data set building method, when the position information or working parameters of the sensor change, the effectiveness of the existing data is obviously reduced, and the training of the model cannot be performed under a new working condition for the acquired data resource, or the model effect obtained by training is poor, so that the efficiency and effectiveness of data set building are poor. Therefore, a method for creating a sensor data set is needed to improve the efficiency and effectiveness of the data set creation.
Disclosure of Invention
The application provides a method, a device, electronic equipment and a storage medium for establishing a sensor data set, which are used for solving the problem that the efficiency and effectiveness of the data set establishment are poor when the position information or working parameters and the like of a current sensor are changed.
In a first aspect, the present application provides a method of sensor dataset creation, the method being applied to a target dataset, the method comprising:
determining a target sensor and a sensor type of the target sensor;
determining target information of the target sensor, and determining a data set conversion model according to the target information;
according to the target information, determining preprocessing data corresponding to the parameters indicated by the target information in the target data set;
And according to the data set conversion model, carrying out data conversion on the preprocessed data in the target data set to obtain a converted target data set.
As an alternative embodiment, the sensor type of the target sensor includes a radar sensor;
the determining the target information of the target sensor includes:
Determining first space information and second space information of the radar sensor, determining reference space information of a reference object, and taking the first space information, the second space information and the reference space information as target information of the target sensor;
The first spatial information is used for indicating position information corresponding to the target sensor in the target data set before data conversion is performed on the preprocessed data in the target data set, and the second spatial information is used for indicating position information corresponding to the target sensor in the converted target data set.
As an alternative embodiment, the dataset transformation model comprises a transformation matrix, and the transformation matrix comprises a first transformation matrix;
the determining a data set conversion model according to the target information comprises the following steps:
Determining a first vector of the first spatial information transformed to the reference spatial information and determining a second vector of the second spatial information transformed to the reference spatial information;
determining the first transformation matrix according to the first vector and the second vector;
the first conversion matrix is used for indicating a conversion relation of the position information of the radar sensor from the first space information to the second space information.
As an alternative embodiment, the conversion matrix further comprises a second conversion matrix, the method further comprising:
Determining first target data of the target sensor and determining second target data corresponding to the target sensor in the target data set;
the first target data are used for indicating data characteristics and data contents which are expected to be obtained by the target sensor, the second target data are used for indicating data characteristics and data contents which correspond to the data which are obtained by the target sensor, and the second target data comprise third space information;
Determining the second transformation matrix;
The second conversion matrix is used for converting the second target data into the first target data;
and determining target space information of the target sensor according to the second conversion matrix and the third space information.
As an optional implementation manner, after the data conversion is performed on the preprocessed data according to the data set conversion model and the converted target data set is obtained, the method further includes:
training a preset model according to the target data set to obtain a target model;
Determining working parameters of a target vehicle according to the target model, and executing a target operation flow according to the working parameters;
The target operation flow is used for indicating the corresponding flow of the target vehicle for acquiring the running data or adjusting the running state under the working condition corresponding to the working parameter.
In a second aspect, the present application provides a sensor dataset creation apparatus, the apparatus comprising:
the acquisition module is used for determining a target sensor and a sensor type of the target sensor;
the processing module is used for determining target information of the target sensor and determining a data set conversion model according to the target information;
The processing module is further used for determining preprocessing data corresponding to the parameters indicated by the target information in the target data set according to the target information;
The processing module is further used for performing data conversion on the preprocessed data in the target data set according to the data set conversion model to obtain a converted target data set.
As an alternative embodiment, the sensor type of the target sensor includes a radar sensor;
the processing module determines a specific mode of target information of the target sensor, including:
Determining first space information and second space information of the radar sensor, determining reference space information of a reference object, and taking the first space information, the second space information and the reference space information as target information of the target sensor;
The first spatial information is used for indicating position information corresponding to the target sensor in the target data set before data conversion is performed on the preprocessed data in the target data set, and the second spatial information is used for indicating position information corresponding to the target sensor in the converted target data set.
As an alternative embodiment, the dataset transformation model comprises a transformation matrix, and the transformation matrix comprises a first transformation matrix;
The processing module determines a specific mode of the data set conversion model according to the target information, and comprises the following steps:
Determining a first vector of the first spatial information transformed to the reference spatial information and determining a second vector of the second spatial information transformed to the reference spatial information;
determining the first transformation matrix according to the first vector and the second vector;
the first conversion matrix is used for indicating a conversion relation of the position information of the radar sensor from the first space information to the second space information.
As an alternative embodiment, the conversion matrix further comprises a second conversion matrix, and the processing module is further configured to:
Determining first target data of the target sensor and determining second target data corresponding to the target sensor in the target data set;
the first target data are used for indicating data characteristics and data contents which are expected to be obtained by the target sensor, the second target data are used for indicating data characteristics and data contents which correspond to the data which are obtained by the target sensor, and the second target data comprise third space information;
Determining the second transformation matrix;
The second conversion matrix is used for converting the second target data into the first target data;
and determining target space information of the target sensor according to the second conversion matrix and the third space information.
As an alternative embodiment, the processing module is further configured to, after performing data conversion on the preprocessed data according to the data set conversion model and obtaining the converted target data set,
Training a preset model according to the target data set to obtain a target model;
Determining working parameters of a target vehicle according to the target model, and executing a target operation flow according to the working parameters;
The target operation flow is used for indicating the corresponding flow of the target vehicle for acquiring the running data or adjusting the running state under the working condition corresponding to the working parameter.
In a third aspect, the present application also provides an electronic device, including:
At least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method as in the first aspect.
In a fourth aspect, the application also provides a computer-readable storage medium having stored therein computer-executable instructions which, when executed by a processor, are adapted to carry out the method of the first aspect.
According to the sensor data set establishing method, the sensor data set establishing device, the electronic equipment and the storage medium, the data set conversion model related to the working state of the target sensor can be determined through the corresponding target information of the target sensor, each piece of preprocessed data in the target data set is subjected to data conversion according to the determined data set conversion model, the converted target data set is obtained, the data in the target data set is associated with the related information of the target sensor in a data set conversion model mode, the target data set is processed according to the actual working condition of the target sensor, the problem that one round of data is acquired as a new target data set after each time of working condition change of the sensor in the prior art is avoided, and therefore the efficiency and the effectiveness of data set establishment are improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.
FIG. 1 is a flow chart of a method for establishing a sensor dataset according to an embodiment of the present invention;
FIG. 2 is a flow chart of another method for sensor dataset creation as disclosed in an embodiment of the present invention;
FIG. 3 is a schematic diagram of a sensor dataset creation system according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a sensor dataset creation apparatus according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device for creating a sensor dataset according to an embodiment of the present invention.
There has been shown in the drawings, and will hereinafter be described, specific embodiments of the application with the understanding that the present disclosure is to be considered in all respects as illustrative, and not restrictive, the scope of the inventive concepts being indicated by the appended claims.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the application. Rather, they are merely examples of apparatus and methods consistent with aspects of the application as detailed in the accompanying claims.
The data driving and data closed-loop technology gradually becomes a high-order automatic driving core technology route, the data driving core is characterized in that the data set is acquired and managed, the normal acquisition way of the data set is changed for a data acquisition vehicle, data acquisition, data cleaning, data labeling and data set manufacturing, so that the perception performance of AI models such as perception, prediction and the like is continuously improved, the data volume demand is larger and larger, and the data set manufacturing becomes the link of the most manpower and fund consumption of automatic driving; particularly, when the position of the sensor changes, the usability of the data set is greatly reduced, and the operations of data acquisition, labeling, data set manufacturing and the like are required to be carried out again, so that large investment is required for manpower, capital and period;
Aiming at the production of a data set after the sensor installation position conversion, the application provides a data set generation scheme based on the sensor installation position conversion processing, which utilizes the existing data set to improve the training effect on the perception performance, thereby reducing the dependence on subsequent data, reducing the requirement on the subsequent data amount and shortening the deployment period of a new vehicle-type perception algorithm. Based on the transformation relation of the sensors, the original data set is utilized to adapt the data set, the usability of the existing data set is improved, and based on the mutual position transformation relation of the sensors, the adaptation can be realized through a transformation matrix for labeling the position distance and other information of the target object.
In a specific application scene, the relative position of the label of the radar target object after the position of the radar sensor is transformed, a new installation position can be adapted, and the original data set can be applied to generate a data set after the radar update position after the radar position is transformed;
The technical concept of the application is that a data set conversion model related to the working state of the target sensor can be determined through corresponding target information of the target sensor, each preprocessing data in the target data set is subjected to data conversion according to the determined data set conversion model, a converted target data set is obtained, and the data in the target data set is linked with the related information of the target sensor in a data set conversion model mode, so that the target data set is processed according to the actual working condition of the target sensor, the problem that one round of data is required to be collected as a new target data set after each working condition change of the sensor in the prior art is avoided, and the efficiency and the effectiveness of the data set establishment are improved.
Example 1
Referring to fig. 1, fig. 1 is a flow chart of a method for establishing a sensor dataset according to an embodiment of the invention. As shown in fig. 1, the method is applied to a target data set, the method comprising:
s101, determining a sensor type of a target sensor;
s102, determining target information of a target sensor, and determining a data set conversion model according to the target information;
For the process of determining the target sensor, the method specifically can further comprise determining static device parameters or dynamic working parameters of the target sensor, when a plurality of target sensors are provided, the process of constructing the data set conversion model is more complex, the data set conversion model can be constructed according to each sensor, and meanwhile, the corresponding data set conversion model can be constructed according to the relative relation among the sensors.
The target information can comprise static device parameters and dynamic working parameters, the device parameters are used for indicating parameters of the principle, structure, selection and the like of the target sensor about the physical state of the device, the working parameters are used for indicating parameters of the installation position, the installation quantity and the like about the working state of the target sensor, parameters such as temperature, humidity, electromagnetic environment and the like can be further included in some scenes, the whole target information can be used for indicating the working condition of the target sensor, further, a transformation relation can be constructed according to the working condition of the target sensor, and a corresponding data set transformation model is established.
In the present application, the spatial information related to the position is mostly taken as an example for explanation, but in the practical application scenario, the target information should not be limited to the spatial information simply, and for specific device parameters or working parameters, a corresponding data set conversion model can be designed according to modes of mechanism modeling, experimental modeling, etc. so as to process the target data set.
S103, according to the target information, determining preprocessing data corresponding to the parameters indicated by the target information in a target data set;
It should be noted that, in S103 and S102, the data set conversion model portion is determined according to the target information, and there is no explicit order in logic, and only the execution after the target information is determined is ensured.
S104, according to the data set conversion model, carrying out data conversion on the preprocessed data in the target data set to obtain a converted target data set.
In the present application, the target data set is used to indicate a data set established based on data related to target information of the target sensor. For example, if the target information of the target sensor is determined to be spatial information in an application scenario, the target data set includes a sufficient amount of preprocessed data formed according to spatial information of the target sensor itself and/or other sensors with high correlation or similarity with the target sensor, and some or all dimensions in the preprocessed data are related to the spatial information.
According to the embodiment, the data set conversion model related to the working state of the target sensor can be determined through the corresponding target information of the target sensor, the data conversion is carried out on all the preprocessed data in the target data set according to the determined data set conversion model, the converted target data set is obtained, and the data in the target data set and the related information of the target sensor are linked in a mode of the data set conversion model, so that the target data set is processed according to the actual working condition of the target sensor, the problem that one round of data is required to be collected as a new target data set after each sensor working condition change in the prior art is avoided, and the efficiency and the effectiveness of data set establishment are improved.
Example two
Referring to fig. 2, fig. 2 is a flowchart of another method for establishing a sensor dataset according to an embodiment of the invention. As shown in fig. 2, the method includes:
S201, determining a target sensor and a sensor type of the target sensor, wherein the sensor type of the target sensor comprises a radar sensor;
S202, determining first space information and second space information of a radar sensor, determining reference space information of a reference object, and taking the first space information, the second space information and the reference space information as target information of a target sensor;
the first space information is used for indicating the position information corresponding to the target sensor in the target data set, and the second space information is used for indicating the position information corresponding to the target sensor in the converted target data set;
In a scene where data set conversion is required, a commonly used sensor is a radar sensor, wherein the most important data information is position information, the radar sensor can be applied to a target vehicle to acquire point cloud information of a target object so as to construct position information of the target object, when the position of the radar sensor changes, corresponding working parameters change obviously, therefore, a data set conversion model is required to be constructed according to the space information before and after the change as target information, meanwhile, reference space information of a reference object can be set as intermediate information in the data set conversion model determining process, and corresponding information of each target sensor realizes transfer transition through the reference space information so as to simplify calculation.
S203, determining a data set conversion model according to the target information;
s204, according to the target information, determining preprocessing data corresponding to the parameters indicated by the target information in a target data set;
S205, performing data conversion on the preprocessed data in the target data set according to the data set conversion model to obtain a converted target data set.
For the corresponding descriptions of S201, S203, S204, and S205, reference may be made to the related descriptions of the first embodiment.
As an alternative embodiment, the dataset transformation model comprises a transformation matrix, and the transformation matrix comprises a first transformation matrix;
determining a dataset transformation model from the target information, comprising:
determining a first vector of the first spatial information transformed to the reference spatial information and determining a second vector of the second spatial information transformed to the reference spatial information;
Determining a first transformation matrix from the first vector and the second vector;
the first conversion matrix is used for indicating a conversion relation of the position information of the radar sensor from the first space information to the second space information.
For the application scene related to the position information, the transformation matrix is a simpler realization model, and the vector for transformation can be determined according to the position information of the target sensor relative to the reference space information before and after the change, so as to form a first transformation matrix.
The position information before and after the working condition conversion of the radar sensor is converted into the vector corresponding to the reference space information, one of the vectors can be transposed to determine the first conversion matrix, and further the part of each data in the target data set, which is related to the position information, can be converted through the first conversion matrix, so that the target data set is processed according to the actual working condition of the target sensor, the problem that one round of data is required to be collected as a new target data set after the working condition of each sensor changes in the prior art is avoided, and the efficiency and the effectiveness of the data set establishment are improved.
As an alternative embodiment, the conversion matrix further comprises a second conversion matrix, the method further comprising:
determining first target data of the target sensor and determining second target data corresponding to the target sensor in the target data set;
The first target data are used for indicating data characteristics and data contents which are expected to be obtained by the target sensor, the second target data are used for indicating data characteristics and data contents which correspond to the data which are obtained by the target sensor, and the second target data comprise third space information;
The spatial information of the first target data, namely the target spatial information mentioned later is the data to be determined, and the spatial information in the first target data is reversely deduced according to the third spatial information carried in the second target data, so that the tasks of designing the position of the sensor and the like are completed.
Determining a second conversion matrix for converting the second target data into the first target data according to the first target data and the second target data;
And determining target space information of the target sensor according to the second conversion matrix and the third space information.
Specifically, in an actual application scenario, the method may be applied to determining the target position of the target sensor, for example, the target sensor currently has a data form and data information expected to be obtained, but the target position is unknown, and accordingly, the method of the embodiment may perform the backward pushing of the position information to obtain the spatial information of the target sensor.
The second conversion matrix which is converted from the original data into the expected data can be determined through the first target data of the target sensor and the second target data in the original data, the target space information can be determined through the second conversion matrix, namely, the second target data in the target data set carrying the third space information is converted into the first target data carrying the target space information, and therefore the design of the expected position of the sensor is achieved, the target data set is processed according to the actual working condition of the target sensor, the problem that one round of data is required to be collected as a new target data set after the working condition of the sensor changes each time in the prior art is avoided, and the efficiency and the effectiveness of the data set establishment are improved.
As an alternative embodiment, after performing data conversion on the preprocessed data according to the data set conversion model and obtaining the converted target data set, the method further includes:
training a preset model according to the target data set to obtain a target model;
determining working parameters of a target vehicle according to the target model, and executing a target operation flow according to the working parameters;
The target operation flow is used for indicating the corresponding flow of the target vehicle for acquiring the running data or adjusting the running state under the working condition corresponding to the working parameter.
After preprocessing in the target data set and obtaining the processed target data set, the target data set can be used for training a target model and being used in an actual working scene, for example, by determining working parameters of a target vehicle, so as to execute functions of target detection, position correction, automatic operation, fault detection and the like.
Through the determined target data set, the preset model can be trained, the target model is further obtained, a corresponding process for acquiring running data or adjusting the running state of the target vehicle can be executed in an actual application scene according to the target model, and the practicability and the effectiveness of the model are improved.
As an alternative implementation manner, referring to fig. 3, fig. 3 is a schematic view of a sensor dataset creation system according to an embodiment of the present invention, as shown in fig. 3, a position of a sensor of a vehicle changes due to a design change, when the position of the sensor of the vehicle changes, an angle of view of Lidar will change, an acquired point cloud will also change, and a new sensor installation position needs to be trained by a point cloud sensing algorithm. The conventional method is to re-acquire point cloud data, then make labeling, make a data set and then train an algorithm model.
Based on multiplexing of the data set of sensor position transformation, the original position of the laser radar is set as P1, the position of the laser radar after position adjustment is set as P2, the conversion relation T between P1 and P2 can be obtained through a laser radar external parameter calibration method, a laser radar coordinate system is transferred to a vehicle body coordinate system, and the conversion matrixes are set as T_v1 and T_v2 respectively; if t=tjv1 (t_v2) -1, let the spatial information of a point in the lidar coordinate system of the original position of the lidar be (x 1, y1, z 1), the spatial information of a point in the lidar coordinate system after the adjustment of the lidar position be (x 2, y2, z 2), the position of the point in the vehicle body coordinate system be (x, y, z), if (x, y, z) = (x 1, y1, z 1) t_v1, (x, y, z) = (x 2, y2, z 2) t_v2), the data set of the point cloud contains information such as the category of the target, the position of the center point, the target ID, etc., wherein the category information, the target ID is not affected by the sensor position conversion, the position of the center point, the influence of the position conversion of the heading angle lidar, if the target is marked in the original lidar coordinate system, the center point is (x_o, y_o, z_o), if the radar position is (x, y_o), the new coordinate system is marked in the new radar coordinate system (x_o, y_2, z_o) = (x_2, y_z_2), and the data set of the new coordinate system can be converted by (x_2, y_z_2), if the data set of the new coordinate system is marked in the new radar coordinate system is (x_1, y_z_2), and the data set of the data set is obtained by converting the data set. Based on the data set, training is performed, and the training result is closer to the real data labeling result than the original data set, so that a better training effect is achieved.
According to the embodiment, the position information of the radar sensor before and after the working condition change is used as reference data for establishing a data set conversion model, the reference space information corresponding to the preset reference object is used as a datum for the radar sensor position information confirmation process, the target data set is processed according to the actual working condition of the target sensor in an application scene of the data set needing to be determined in the position information, the problem that one round of data is required to be collected as a new target data set after the working condition of the sensor changes each time in the prior art is avoided, and therefore the efficiency and the effectiveness of data set establishment are improved.
Example III
The embodiment of the invention also provides a device for establishing the sensor data set to realize the method, please refer to fig. 4, fig. 4 is a schematic structural diagram of the device for establishing the sensor data set disclosed in the embodiment of the invention. As shown in fig. 4, in any other embodiment, the apparatus includes:
an acquisition module 31 for determining the target sensor and the sensor type of the target sensor;
a processing module 32 for determining target information of the target sensor and determining a dataset conversion model based on the target information;
And the processing module 32 is further configured to determine, in the target data set, pre-processing data corresponding to the parameter indicated by the target information according to the target information;
The processing module 32 is further configured to perform data conversion on the preprocessed data in the target data set according to the data set conversion model, so as to obtain a converted target data set.
The data set conversion model related to the working state of the target sensor can be determined through the corresponding target information of the target sensor, the data conversion is carried out on all the preprocessed data in the target data set according to the determined data set conversion model, the converted target data set is obtained, the data in the target data set and the related information of the target sensor are linked in a mode of the data set conversion model, and therefore the target data set is processed according to the actual working condition of the target sensor, the problem that one round of data is required to be collected as a new target data set after the working condition of the sensor changes in the prior art is avoided, and the efficiency and the effectiveness of the data set establishment are improved.
As an alternative embodiment, the sensor type of the target sensor includes a radar sensor;
the specific manner in which the processing module 32 determines the target information for the target sensor includes:
Determining first space information and second space information of a radar sensor, determining reference space information of a reference object, and taking the first space information, the second space information and the reference space information as target information of a target sensor;
The first space information is used for indicating the position information corresponding to the target data set before the target sensor performs data conversion on the preprocessed data in the target data set, and the second space information is used for indicating the position information corresponding to the target sensor in the converted target data set.
The position information of the radar sensor before and after the working condition change is used as reference data for establishing a data set conversion model, the reference space information corresponding to a preset reference object is used as a benchmark for the position information confirmation process of the radar sensor, and the target data set is processed according to the actual working condition of the target sensor in an application scene needing to determine the data set related to the position information, so that the problem that one round of data is required to be acquired as a new target data set after the working condition of the sensor changes each time in the prior art is avoided, and the efficiency and the effectiveness of data set establishment are improved.
As an alternative embodiment, the dataset transformation model comprises a transformation matrix, and the transformation matrix comprises a first transformation matrix;
The processing module 32 determines a specific mode of the data set transformation model according to the target information, including:
determining a first vector of the first spatial information transformed to the reference spatial information and determining a second vector of the second spatial information transformed to the reference spatial information;
Determining a first transformation matrix from the first vector and the second vector;
the first conversion matrix is used for indicating a conversion relation of the position information of the radar sensor from the first space information to the second space information.
The position information before and after the working condition conversion of the radar sensor is converted into the vector corresponding to the reference space information, one of the vectors can be transposed to determine the first conversion matrix, and further the part of each data in the target data set, which is related to the position information, can be converted through the first conversion matrix, so that the corresponding target data set is obtained, the target data set is processed according to the actual working condition of the target sensor, the problem that one round of data is required to be collected as a new target data set after each working condition change of the sensor in the prior art is avoided, and the efficiency and the effectiveness of the data set establishment are improved.
As an alternative embodiment, the conversion matrix further comprises a second conversion matrix, and the processing module 32 is further configured to:
determining first target data of the target sensor and determining second target data corresponding to the target sensor in the target data set;
The first target data are used for indicating data characteristics and data contents which are expected to be obtained by the target sensor, the second target data are used for indicating data characteristics and data contents which correspond to the data which are obtained by the target sensor, and the second target data comprise third space information;
Determining a second conversion matrix;
The second conversion matrix is used for converting the second target data into the first target data;
And determining target space information of the target sensor according to the second conversion matrix and the third space information.
The second conversion matrix which is converted from the original data into the expected data can be determined through the first target data of the target sensor and the second target data in the original data, the target space information can be determined through the second conversion matrix, namely, the second target data in the target data set carrying the third space information is converted into the first target data carrying the target space information, and therefore the design of the expected position of the sensor is achieved, the target data set is processed according to the actual working condition of the target sensor, the problem that one round of data is required to be collected as a new target data set after the working condition of the sensor changes each time in the prior art is avoided, and the efficiency and the effectiveness of the data set establishment are improved.
As an alternative embodiment, the processing module 32 is further configured to, after data converting the pre-processed data according to the data set conversion model and obtaining the converted target data set,
Training a preset model according to the target data set to obtain a target model;
determining working parameters of a target vehicle according to the target model, and executing a target operation flow according to the working parameters;
The target operation flow is used for indicating the corresponding flow of the target vehicle for acquiring the running data or adjusting the running state under the working condition corresponding to the working parameter.
Through the determined target data set, the preset model can be trained, the target model is further obtained, a corresponding process for acquiring running data or adjusting the running state of the target vehicle can be executed in an actual application scene according to the target model, and the practicability and the effectiveness of the model are improved.
Example IV
The present application provides an electronic device including:
At least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method as in any one of the embodiments.
The present application provides a computer readable storage medium having stored therein computer executable instructions which when executed by a processor are adapted to carry out a method as in any of the embodiments.
Specifically, referring to fig. 5, fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. As shown in fig. 5, the electronic device may include:
A Processor 291, the apparatus further comprising a Memory 292 in which executable program code is stored; a communication interface (Communication Interface) 293 and bus 294 may also be included. The processor 291, the memory 292, and the communication interface 293 may communicate with each other via the bus 294. Communication interface 293 may be used for information transfer. The processor 291 is coupled to the memory 292, and the processor 291 may call logic instructions (executable program code) in the memory 292 to perform the methods of any of the embodiments described above.
Further, the logic instructions in memory 292 described above may be implemented in the form of software functional units and stored in a computer-readable storage medium when sold or used as a stand-alone product.
The memory 292 is a computer readable storage medium, and may be used to store a software program, a computer executable program, and program instructions/modules corresponding to the methods in the embodiments of the present application. The processor 291 executes functional applications and data processing by running software programs, instructions and modules stored in the memory 292, i.e., implements the methods of the method embodiments described above.
Memory 292 may include a storage program area that may store an operating system, at least one application program required for functionality, and a storage data area; the storage data area may store data created according to the use of the terminal device, etc. Further, memory 292 may include high-speed random access memory, and may also include non-volatile memory.
The embodiment of the invention also provides a computer readable storage medium, wherein computer executable instructions are stored in the computer readable storage medium, and the computer executable instructions are used for realizing the method in any embodiment when being called.
Embodiments of the present invention also disclose a computer program product comprising a non-transitory computer readable storage medium storing a computer program, the computer program being operable to cause a computer to perform the steps of the method described in any of the embodiments.
The apparatus embodiments described above are merely illustrative, in which the modules illustrated as separate components may or may not be physically separate, and the components shown as modules may or may not be physical, i.e., may be located in one place, or may be distributed over multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above detailed description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course by means of hardware. Based on such understanding, the foregoing technical solutions may be embodied essentially or in part in the form of a software product that may be stored in a computer-readable storage medium including read-only memory (ROM), random access memory (Random Access Memory, RAM), programmable read-only memory (Programmable Read-only memory, PROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, EPROM), one-time programmable read-only memory (OTPROM), electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (Compact Disc Read-only memory, CD-ROM) or other optical disc memory, magnetic disc memory, tape memory, or any other medium that can be used for computer-readable carrying or storing data.
Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It is to be understood that the application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (10)
1. A method of sensor dataset creation, the method being applied to a target dataset, the method comprising:
determining a target sensor and a sensor type of the target sensor;
determining target information of the target sensor, and determining a data set conversion model according to the target information;
according to the target information, determining preprocessing data corresponding to the parameters indicated by the target information in the target data set;
And according to the data set conversion model, carrying out data conversion on the preprocessed data in the target data set to obtain a converted target data set.
2. The method of claim 1, wherein the sensor type of the target sensor comprises a radar sensor;
the determining the target information of the target sensor includes:
Determining first space information and second space information of the radar sensor, and determining reference space information of a reference object;
The first spatial information is used for indicating position information corresponding to the target sensor in the target data set before data conversion is performed on the preprocessed data in the target data set, and the second spatial information is used for indicating position information corresponding to the target sensor in the converted target data set.
3. The method of claim 2, wherein the dataset transformation model comprises a transformation matrix and the transformation matrix comprises a first transformation matrix;
the determining a data set conversion model according to the target information comprises the following steps:
Determining a first vector of the first spatial information transformed to the reference spatial information and determining a second vector of the second spatial information transformed to the reference spatial information;
determining the first transformation matrix according to the first vector and the second vector;
the first conversion matrix is used for indicating a conversion relation of the position information of the radar sensor from the first space information to the second space information.
4. A method according to claim 3, wherein the transformation matrix further comprises a second transformation matrix, the method further comprising:
Determining first target data of the target sensor and determining second target data corresponding to the target sensor in the target data set;
the first target data are used for indicating data characteristics and data contents which are expected to be obtained by the target sensor, the second target data are used for indicating data characteristics and data contents which correspond to the data which are obtained by the target sensor, and the second target data comprise third space information;
Determining the second transformation matrix;
The second conversion matrix is used for converting the second target data into the first target data;
and determining target space information of the target sensor according to the second conversion matrix and the third space information.
5. The method according to any one of claims 1-4, wherein after data converting the pre-processed data according to the data set conversion model and obtaining a converted target data set, the method further comprises:
training a preset model according to the target data set to obtain a target model;
Determining working parameters of a target vehicle according to the target model, and executing a target operation flow according to the working parameters;
The target operation flow is used for indicating the corresponding flow of the target vehicle for acquiring the running data or adjusting the running state under the working condition corresponding to the working parameter.
6. A sensor dataset creation apparatus, the apparatus comprising:
the acquisition module is used for determining a target sensor and a sensor type of the target sensor;
the processing module is used for determining target information of the target sensor and determining a data set conversion model according to the target information;
the processing module is further used for determining preprocessing data corresponding to the parameters indicated by the target information in the target data set according to the target information;
The processing module is further used for performing data conversion on the preprocessed data according to the data set conversion model, and obtaining a converted target data set.
7. The apparatus of claim 6, wherein the sensor type of the target sensor comprises a radar sensor;
the processing module determines a specific mode of target information of the target sensor according to the sensor type of the target sensor, and comprises the following steps:
Determining first space information and second space information of the radar sensor, determining reference space information of a reference object, and taking the first space information, the second space information and the reference space information as target information of the target sensor;
The first spatial information is used for indicating position information corresponding to the target sensor in the target data set before data conversion is performed on the preprocessed data in the target data set, and the second spatial information is used for indicating position information corresponding to the target sensor in the converted target data set.
8. The apparatus of claim 7, wherein the dataset transformation model comprises a transformation matrix, and wherein the processing module determines a particular manner of dataset transformation model based on the target information, comprising:
Determining a first vector of the first spatial information transformed to the reference spatial information and determining a second vector of the second spatial information transformed to the reference spatial information;
Determining a first transformation matrix according to the first vector and the second vector;
the first conversion matrix is used for indicating a conversion relation of the position information of the radar sensor from the first space information to the second space information.
9. An electronic device, comprising:
At least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-5.
10. A computer readable storage medium having stored therein computer executable instructions which when executed by a processor are adapted to carry out the method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410165762.0A CN117892138A (en) | 2024-02-05 | 2024-02-05 | Sensor data set establishing method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410165762.0A CN117892138A (en) | 2024-02-05 | 2024-02-05 | Sensor data set establishing method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117892138A true CN117892138A (en) | 2024-04-16 |
Family
ID=90647404
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410165762.0A Pending CN117892138A (en) | 2024-02-05 | 2024-02-05 | Sensor data set establishing method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117892138A (en) |
-
2024
- 2024-02-05 CN CN202410165762.0A patent/CN117892138A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111536964B (en) | Robot positioning method and device, and storage medium | |
| CN110852949A (en) | Point cloud data completion method and device, computer equipment and storage medium | |
| CN112414403B (en) | Robot positioning and attitude determining method, equipment and storage medium | |
| EP4250593A1 (en) | Satellite terminal access management method, core network, computer apparatus, and storage medium | |
| CN109598670A (en) | EMS memory management process, device, storage medium and the system of cartographic information acquisition | |
| CN114819134A (en) | Method, apparatus and computer program product for updating a machine learning model | |
| CN114240779B (en) | Point cloud denoising method, device, equipment and storage medium | |
| CN114689036A (en) | Map updating method, automatic driving method, electronic device and storage medium | |
| CN110887490B (en) | Key frame selection method, medium, terminal and device for laser positioning navigation | |
| CN114338416B (en) | Space-time multi-index prediction method and device and storage medium | |
| CN117892138A (en) | Sensor data set establishing method and device, electronic equipment and storage medium | |
| CN117392181A (en) | Motion information prediction method, computer equipment, storage medium and intelligent equipment | |
| US20230342626A1 (en) | Model processing method and related apparatus | |
| CN112925416A (en) | User sight tracking method, device and system | |
| CN117036607A (en) | Automatic driving scene data generation method and system based on implicit neural rendering | |
| CN116337072A (en) | Construction method, construction equipment and readable storage medium for engineering machinery | |
| US20240011792A1 (en) | Method and apparatus for updating confidence of high-precision map | |
| CN115391725A (en) | Method, system, equipment and medium for identifying parameters of fractional order chaotic system | |
| CN110764462A (en) | PLC intelligent electric cabinet control method and device and PLC control server | |
| CN110956697B (en) | Memory optimization method, medium, terminal and device based on laser slam | |
| CN117058330B (en) | Three-dimensional reconstruction method, reconstruction model and related equipment for electric power corridor | |
| CN115577769B (en) | Measurement data fitting method based on two-way neural network autoregressive model | |
| CN111474927B (en) | Preprocessing method and device for distance transformation | |
| CN113343973A (en) | Depth estimation method, storage medium, and computer device | |
| CN118259708A (en) | Temperature control method and device for greenhouse, terminal equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |