CN116394923A - Training data processing method, automatic parking method and related equipment - Google Patents
Training data processing method, automatic parking method and related equipment Download PDFInfo
- Publication number
- CN116394923A CN116394923A CN202310260971.9A CN202310260971A CN116394923A CN 116394923 A CN116394923 A CN 116394923A CN 202310260971 A CN202310260971 A CN 202310260971A CN 116394923 A CN116394923 A CN 116394923A
- Authority
- CN
- China
- Prior art keywords
- data
- vehicle
- sensor data
- gear
- sensor
- 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 49
- 238000012549 training Methods 0.000 title claims abstract description 45
- 238000003672 processing method Methods 0.000 title claims abstract description 13
- 238000001514 detection method Methods 0.000 claims abstract description 28
- 230000004044 response Effects 0.000 claims abstract description 5
- 238000012545 processing Methods 0.000 claims description 13
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000013136 deep learning model Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000005516 engineering process Methods 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
- 230000008447 perception Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
- B60W30/06—Automatic manoeuvring for parking
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The application discloses a training data processing method. The method comprises the following steps: acquiring original data of a vehicle, wherein the original data comprises first sensor data and second sensor data at the same moment, and the second sensor data is acquired when the vehicle is parked; and outputting the second sensor data as target data when the vehicle is parked in response to the first sensor data meeting a preset condition, wherein the target data is used for training a parking obstacle detection model of the vehicle. The application also discloses an automatic parking method and related equipment. The method and the device realize low-cost and effective acquisition of the training data of the parking obstacle detection model.
Description
Technical Field
The disclosed embodiments of the present application relate to the field of autopilot technology, and more particularly, to a training data processing method, an autopilot method, and related devices.
Background
Automatic parking is an important function in assisting driving, and generally, for safety of parking, for example, no collision or scratch, it is required to detect obstacles around the vehicle, particularly obstacles nearer to the vehicle, and the accuracy of detecting the obstacles is also required to be high.
The parking obstacle detection algorithm commonly used in the industry is finished through a deep learning model on a fish-eye image, so that a large amount of data is required to be marked to train the deep learning model. The acquisition vehicle can generate a large amount of original sensor data in the daily driving and parking processes, and the data can be theoretically taken out for manual marking, but the problem of how to acquire training data at low cost is solved because the cost of manual marking is very high and the value of each frame of data to algorithm is not the same.
Disclosure of Invention
According to the embodiment of the application, the application provides a training data processing method, an automatic parking method and related equipment, so that the training data can be obtained effectively at low cost.
The first aspect of the application discloses a method for processing training data, which comprises the following steps: acquiring original data of a vehicle, wherein the original data comprises first sensor data and second sensor data at the same moment, and the second sensor data is acquired when the vehicle is parked; and outputting the second sensor data as target data when the vehicle is parked in response to the first sensor data meeting a preset condition, wherein the target data is used for training a parking obstacle detection model of the vehicle.
In some embodiments, the first sensor data includes at least one of ultrasonic data, speed data, and gear data of the vehicle.
In some embodiments, the first sensor data comprises ultrasonic data of the vehicle; the first sensor data satisfies a preset condition, including: the ultrasonic data indicates the presence of an obstacle within a preset perceived distance of the vehicle.
In some embodiments, the first sensor data comprises speed data of the vehicle; the first sensor data satisfies a preset condition, including: the speed data indicates a vehicle speed less than a preset threshold.
In some embodiments, the first sensor data includes gear data of the vehicle; the first sensor data satisfies a preset condition, including: the gear number indicates that the gear of the vehicle is reverse gear.
In some embodiments, the first sensor data includes ultrasonic data and gear data of the vehicle; the first sensor data satisfies a preset condition, including: the gear data indicates that the gear of the vehicle is not reverse gear; the ultrasonic data indicates the presence of an obstacle within a preset perceived distance of the vehicle.
In some embodiments, the first sensor data includes ultrasonic data, speed data, and gear data of the vehicle; the first sensor data satisfies a preset condition, including: the speed data represents a vehicle speed less than a preset threshold; the gear data indicates that the gear of the vehicle is reverse gear; the ultrasonic data indicates the presence of an obstacle within a preset perceived distance of the vehicle.
The second aspect of the application discloses an automatic parking method, which comprises the following steps: acquiring sensor data of a vehicle, wherein the sensor data is acquired by the vehicle while the vehicle is parked; inputting the sensor data into a parking obstacle detection model of the vehicle to detect obstacle information around the vehicle; controlling the vehicle to park based on the obstacle information; wherein the parking obstacle detection model is trained using target data obtained by the processing method of the training data as described in the first aspect.
A third aspect of the present application discloses an electronic device, including a memory and a processor coupled to each other, where the processor is configured to execute program instructions stored in the memory to implement the method for processing training data described in the first aspect, or to implement the auto-park method described in the second aspect.
A fourth aspect of the present application discloses a non-transitory computer-readable storage medium having stored thereon program instructions that, when executed by a processor, implement the method of processing training data described in the first aspect, or implement the auto-park method described in the second aspect.
The beneficial effects of this application are: the method comprises the steps of obtaining original data of a vehicle, wherein the original data comprise first sensor data and second sensor data at the same moment, the second sensor data are collected when the vehicle parks, when the first sensor data meet preset conditions, the second sensor data are output to be target data when the vehicle parks, the target data are used for training a parking obstacle detection model of the vehicle, and further training data of the parking obstacle detection model are obtained effectively at low cost.
Drawings
The application will be further described with reference to the accompanying drawings and embodiments, in which:
FIG. 1 is a flow chart of a method for processing training data according to an embodiment of the present application;
FIG. 2 is a partial flow chart of the first sensor data meeting the preset condition according to the embodiment of the present application;
FIG. 3 is a flow chart of a method for processing training data according to an embodiment of the present application;
FIG. 4 is a flow chart of an automated parking method according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of a nonvolatile computer-readable storage medium according to an embodiment of the present application.
Detailed Description
Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
The term "and/or" in this application is merely an association relation describing an associated object, and indicates that three relations may exist, for example, a and/or B may indicate: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship. Further, "a plurality" herein means two or more than two. In addition, the term "at least one" herein means any one of a plurality or any combination of at least two of a plurality, for example, including at least one of A, B, C, and may mean including any one or more elements selected from the group consisting of A, B and C. Furthermore, the terms "first," "second," and "third" in this application are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated.
In order to enable those skilled in the art to better understand the technical solutions of the present application, the technical solutions of the present application are described in further detail below with reference to the accompanying drawings and the detailed description.
Referring to fig. 1, fig. 1 is a flow chart of a processing method of training data according to an embodiment of the present application. The execution subject of the method can be an electronic device with a computing function, such as a microcomputer, a server, a mobile device such as a notebook computer, a tablet computer, and the like.
It should be noted that, if there are substantially the same results, the method of the present application is not limited to the flow sequence shown in fig. 1.
In some possible implementations, the method may be implemented by a processor invoking computer readable instructions stored in a memory, as shown in fig. 1, and may include the steps of:
s11: the method comprises the steps of acquiring original data of a vehicle, wherein the original data comprise first sensor data and second sensor data at the same moment, and the second sensor data are acquired when the vehicle is parked.
The original data of the vehicle comprises first sensor data and second sensor data at the same moment, namely, data of the vehicle when the vehicle is parked are collected in the running process of the vehicle, for example, the original data at 0-T moment is collected, wherein 100ms can be taken as a moment, namely, one frame, the first sensor data of the vehicle at the T moment can be an ultrasonic signal, a vehicle speed signal, a vehicle gear signal and the like, and the second sensor data of the vehicle at the T moment can be image data, point cloud data, radar data and the like.
Raw data of the vehicle is acquired through a sensor device, wherein the vehicle can be a vehicle planned to park, the sensor device comprises an ultrasonic sensor, an image sensor and a radar sensor, and the radar sensor can be radar equipment which is used for automatic driving and meets the precision requirement and is used for providing point cloud perception. Image data may be acquired using an image sensor, such as a camera or the like. The point cloud data is collected using radar sensors, such as millimeter wave radar, lidar, etc. The image sensor and the radar sensor may be mounted on a mobile device, such as an autonomous vehicle or the like. The lidar may include a mechanical lidar, a semi-solid state lidar, a solid state lidar, or the like.
In an application scene, an automatic driving vehicle runs on a road, and image data for describing an environment space where vehicle-mounted equipment is located is acquired through an image sensor arranged on the automatic driving vehicle to obtain an initial data set; acquiring point cloud data for describing an environment space where the vehicle-mounted equipment is located by using a radar sensor to obtain an initial data set; the method comprises the steps of acquiring obstacle data used for describing an environment space where the vehicle-mounted equipment is located by using an ultrasonic sensor, and obtaining an initial data set.
Each sensor perceives and captures an initial data set for describing the environment space where the vehicle-mounted equipment is located, each initial data set corresponds to one sensor, and at least two sensors capture at least two initial data sets, wherein the types of the initial data sets include, but are not limited to, image data and point cloud data.
S12: and outputting the second sensor data as target data when the vehicle is parked in response to the first sensor data meeting the preset condition, wherein the target data is used for training a parking obstacle detection model of the vehicle.
Judging whether the first sensor data meet preset conditions, for example judging whether the ultrasonic signal, the vehicle speed signal and the vehicle gear signal of the vehicle meet preset conditions, if the first sensor data meet the preset conditions, outputting the second sensor data as target data when the vehicle is parked, namely outputting image data, point cloud data and radar data at corresponding moments of the vehicle as the target data, and further marking the target data for training a parking obstacle detection model of the vehicle.
In this embodiment, raw data of a vehicle is acquired, where the raw data includes first sensor data and second sensor data at the same time, where the second sensor data is acquired when the vehicle parks, and when the first sensor data meets a preset condition, the second sensor data is output as target data when the vehicle parks, where the target data is used for training a parking obstacle detection model of the vehicle, so that training data of the parking obstacle detection model is acquired effectively at low cost.
In some embodiments, the first sensor data includes at least one of ultrasonic data, speed data, and gear data of the vehicle.
The original data of the vehicle comprises first sensor data and second sensor data at the same moment, wherein the first sensor data comprises at least one of ultrasonic data, speed data and gear data of the vehicle, for example, when the vehicle is parked, the first sensor data can be collected ultrasonic data, speed data and gear data at a certain moment, namely an ultrasonic signal, a vehicle speed signal and a vehicle gear signal, and whether the second sensor data at the corresponding moment can be output as target data when the vehicle is parked is judged by analyzing whether the first sensor data meets preset conditions or not.
In some embodiments, the first sensor data comprises ultrasonic data of the vehicle; the first sensor data satisfies a preset condition, comprising: the ultrasonic data indicates the presence of an obstacle within a predetermined perceived distance of the vehicle.
And outputting the second sensor data at the corresponding moment as target data when the vehicle is parked when the first sensor data meets the preset condition, wherein the target data is used for training a parking obstacle detection model of the vehicle. Wherein the first sensor data satisfying the preset condition includes that the ultrasonic data indicates that an obstacle exists in a preset sensing distance of the vehicle, for example, the obstacle is sensed in the preset sensing distance by the ultrasonic sensor of the vehicle, and the preset sensing distance may be 5m. For example, when the vehicle is parked, the ultrasonic sensor of the vehicle senses an obstacle within 5m, that is, indicates that an obstacle exists near the vehicle, and at this time, the second sensor data at the time corresponding to the ultrasonic data may be output as target data when the vehicle is parked, and the target data may be labeled, so that training of the parking obstacle detection model of the vehicle may be performed.
In some embodiments, the first sensor data comprises speed data of the vehicle; the first sensor data satisfies a preset condition, comprising: the speed data indicates a vehicle speed less than a preset threshold.
And outputting the second sensor data at the corresponding moment as target data when the vehicle is parked when the first sensor data meets the preset condition, wherein the target data is used for training a parking obstacle detection model of the vehicle. The first sensor data satisfies a preset condition, which includes that the vehicle speed represented by the speed data is smaller than a preset threshold, that is, the vehicle speed of the vehicle is judged, for example, the vehicle speed is smaller than 30km/h and larger than 0km/k, or the vehicle speed is smaller than 30km/h and larger than 2km/h, that is, the vehicle possibly enters a parking state, at the moment, the second sensor data at the moment corresponding to the speed data can be output as target data when the vehicle parks, so that the target data is marked, and therefore training of a parking obstacle detection model of the vehicle is performed.
In some embodiments, the first sensor data includes gear data of the vehicle; the first sensor data satisfies a preset condition, comprising: the gear number indicates that the gear of the vehicle is reverse.
And outputting the second sensor data at the corresponding moment as target data when the vehicle is parked when the first sensor data meets the preset condition, wherein the target data is used for training a parking obstacle detection model of the vehicle. The first sensor data meets the preset condition and comprises gear data representing that the gear of the vehicle is reverse gear, namely, the gear state of the vehicle is judged, for example, the vehicle is in reverse gear, namely, the vehicle possibly enters a parking state, at the moment, the second sensor data at the moment corresponding to the gear data can be output as target data when the vehicle is parked, so that the target data are marked, and training of a parking obstacle detection model of the vehicle is carried out.
In some embodiments, the first sensor data includes ultrasonic data, speed data, and gear data of the vehicle; the first sensor data satisfies a preset condition, comprising: the vehicle speed represented by the speed data is less than a preset threshold; the gear number indicates that the gear of the vehicle is reverse gear; the ultrasonic data indicates the presence of an obstacle within a predetermined perceived distance of the vehicle.
And outputting the second sensor data at the corresponding moment as target data when the vehicle is parked when the first sensor data meets the preset condition, wherein the target data is used for training a parking obstacle detection model of the vehicle. Wherein the first sensor data satisfying the preset condition includes: the ultrasonic data indicates that an obstacle exists in a preset sensing distance of the vehicle, for example, the obstacle is sensed in the preset sensing distance through an ultrasonic sensor of the vehicle; the speed data indicates a vehicle speed less than a preset threshold, for example, a vehicle speed less than 30km/h and greater than 0km/k, or a vehicle speed less than 30km/h and greater than 2km/h, i.e., the vehicle may enter a park state; and the gear number indicates that the gear of the vehicle is reverse, for example, the vehicle is in reverse, i.e., the vehicle may enter a park state. At this time, when the first sensor data satisfies the corresponding condition, the second sensor data at the corresponding time is further output as target data when the vehicle is parked.
In order to facilitate understanding, an application scenario of the method for processing training data in the embodiment of the present application is described in detail, raw data of a vehicle is obtained, the raw data includes first sensor data and second sensor data at the same time, the second sensor data are collected when the vehicle parks, the second sensor data are output as target data when the vehicle parks in response to the first sensor data satisfying a preset condition, and the target data are used for training a parking obstacle detection model of the vehicle. The first sensor data meets preset conditions, wherein the ultrasonic data indicates that an obstacle exists in a preset sensing distance of the vehicle, the vehicle speed indicated by the speed data is smaller than a preset threshold value, and the gear data indicates that the gear of the vehicle is reverse gear, and the arrangement and combination of the preset conditions and the judgment sequence of the preset conditions are not limited.
Specifically, as shown in fig. 2, fig. 2 is a schematic partial flow chart of the first sensor data of the embodiment of the present application, after the original data of the vehicle is obtained, the first sensor data of the vehicle is analyzed and processed, for example, when the first sensor data meets a preset condition 1, target data is output, the preset condition 1 includes that the vehicle speed is smaller than a preset value, the vehicle gear is a reverse gear, and an obstacle exists in a preset sensing distance of the vehicle, for example, second sensor data meeting a condition that the vehicle speed is smaller than 30km/h, the gear is a reverse gear, and a moment corresponding to the first sensor data of the obstacle exists in the preset sensing distance of the vehicle is output, as the target data, where the determining sequence of the vehicle speed, the vehicle gear and the obstacle is not limited in the application.
Or when the first sensor data meets the preset condition 2, outputting target data, wherein the preset condition 2 comprises that the vehicle speed is smaller than a preset value, the vehicle gear is a reverse gear, for example, when the vehicle speed is smaller than 30km/h, and the vehicle gear is the reverse gear, whether an obstacle exists in a preset sensing distance of the vehicle or not is not considered, and outputting the second sensor data corresponding to the moment as the target data, wherein the judging sequence of the vehicle speed and the vehicle gear is not limited in the application. Or when the first sensor data meets the preset condition 3, outputting target data, wherein the preset condition 3 comprises that the vehicle speed is smaller than a preset value, an obstacle exists in a preset sensing distance of the vehicle, for example, the vehicle speed is smaller than 30km/h, the obstacle exists in the preset sensing distance of the vehicle, and further, outputting second sensor data at a corresponding moment to serve as the target data, and the judging sequence of the vehicle speed and the obstacle is not limited in the application.
Further, when the first sensor data meets a preset condition N, outputting second sensor data corresponding to the moment as target data when the vehicle is parked, wherein the target data is used for training a parking obstacle detection model of the vehicle, and the preset condition N met by the first sensor data can be obtained by 3 condition permutation and combination that obstacles exist in a preset sensing distance of the vehicle, the speed of the vehicle is smaller than a preset threshold value, and the gear of the vehicle is reverse gear.
In some embodiments, the first sensor data includes ultrasonic data and gear data of the vehicle; the first sensor data satisfies a preset condition, comprising: the gear number indicates that the gear of the vehicle is not reverse gear; the ultrasonic data indicates the presence of an obstacle within a predetermined perceived distance of the vehicle.
The preset conditions met by the first sensor data further include that the gear data indicate that the gear of the vehicle is not reverse gear, the ultrasonic data indicate that an obstacle exists in a preset sensing distance of the vehicle, specifically, as shown in fig. 3, fig. 3 is a flow chart of a processing method of training data according to an embodiment of the present application, raw data of the vehicle are obtained, whether the vehicle speed at time T is smaller than a preset value is judged, if the vehicle speed is not smaller than the preset value, the raw data are further obtained continuously, and whether the vehicle speed at time t+1 is smaller than the preset value is judged; if the vehicle speed is smaller than a preset value, judging whether the gear of the vehicle is a reverse gear, and if the gear of the vehicle is the reverse gear, outputting second sensor data corresponding to the first sensor data at the moment T as target data; if the gear of the vehicle is not reverse gear, judging whether an obstacle exists in a preset sensing distance of the vehicle, and if the obstacle exists in the preset sensing distance of the vehicle, outputting second sensor data corresponding to the time T of the first sensor data as target data; if no obstacle exists in the preset sensing distance of the vehicle, continuing to acquire the original data to judge whether the vehicle speed at the moment T+1 is smaller than a preset value.
The processing method of the training data can be used for data mining, namely valuable data can be selected from a large amount of original data to be marked manually, for example, target data can be selected from a large amount of original data of vehicles to be marked manually, wherein the target data can be training data suitable for a parking obstacle detection model, and further the efficiency of manual marking is improved.
Referring to fig. 4, fig. 4 is a flow chart of an automatic parking method according to an embodiment of the present application, and the method may be applied to an electronic device with computing functions. It should be noted that, if there are substantially the same results, the method of the present application is not limited to the flow sequence shown in fig. 4.
In some possible implementations, the method may be implemented by a processor invoking computer readable instructions stored in a memory, as shown in fig. 4, and may include the steps of:
s41: sensor data of the vehicle is acquired, wherein the sensor data is acquired while the vehicle is parked.
The sensor data may be image data, point cloud data, radar data, etc. acquired when the vehicle is parked.
S42: sensor data is input into a parking obstacle detection model of the vehicle to detect obstacle information around the vehicle.
The image data, the point cloud data, the radar data, and the like acquired when the vehicle is parked are input into a parking obstacle detection model of the vehicle, for example, a trained deep learning model can be used for detecting obstacle information around the vehicle.
The parking obstacle detection model is trained by utilizing target data, the target data is obtained through the training data processing method, specifically, raw data of a vehicle are obtained, the raw data comprise first sensor data and second sensor data at the same moment, the second sensor data are acquired when the vehicle parks, and the second sensor data are output as target data when the vehicle parks when the first sensor data meet preset conditions.
S43: based on the obstacle information, the vehicle is controlled to park.
According to the obtained obstacle information, the vehicle is controlled to park in the target position so that the vehicle can safely park.
It will be appreciated by those skilled in the art that in the above-described method of the specific embodiments, the written order of steps is not meant to imply a strict order of execution but rather should be construed according to the function and possibly inherent logic of the steps.
Referring to fig. 5, fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application. The electronic device 50 comprises a memory 51 and a processor 52 coupled to each other, the processor 52 being adapted to execute program instructions stored in the memory 51 for performing the steps of the above-described method embodiment of processing training data or for performing the steps of the above-described method embodiment of automatic parking. In one particular implementation scenario, electronic device 50 may include, but is not limited to: the microcomputer and the server are not limited herein.
In particular, the processor 52 is adapted to control itself and the memory 51 to implement the steps of the above-described processing method embodiment of training data or to implement the steps of the above-described automatic parking method embodiment. The processor 52 may also be referred to as a CPU (Central Processing Unit ), and the processor 52 may be an integrated circuit chip with signal processing capabilities. Processor 52 may also be a general purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a Field programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. In addition, the processor 52 may be commonly implemented by an integrated circuit chip.
Referring to fig. 6, fig. 6 is a schematic structural diagram of a non-volatile computer readable storage medium according to an embodiment of the present application. The non-transitory computer-readable storage medium 60 is used to store a computer program 601, which computer program 601, when executed by a processor, for example by the processor 52 in the above-described embodiment of fig. 5, is used to implement the steps of the above-described embodiment of the processing method for training data, or to implement the steps of the above-described embodiment of the automatic parking method.
The foregoing description of various embodiments is intended to highlight differences between the various embodiments, which may be the same or similar to each other by reference, and is not repeated herein for the sake of brevity.
In the several embodiments provided in this application, it should be understood that the disclosed methods and related devices may be implemented in other ways. For example, the above-described embodiments of related devices are merely illustrative, e.g., the division of modules or elements is merely a logical functional division, and there may be additional divisions of actual implementation, e.g., elements or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication disconnection between the illustrated or discussed elements may be through some interface, indirect coupling or communication disconnection of a device or element, electrical, mechanical, or other form.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in part or all or part of the technical solution contributing to the prior art or in the form of a software product stored in a storage medium, including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (processor) to perform all or part of the steps of the methods of the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Those skilled in the art will readily appreciate that many modifications and variations are possible in the device and method while maintaining the teachings of the present application. Accordingly, the above disclosure should be viewed as limited only by the scope of the appended claims.
Claims (10)
1. A method for processing training data, comprising:
acquiring original data of a vehicle, wherein the original data comprises first sensor data and second sensor data at the same moment, and the second sensor data is acquired when the vehicle is parked;
and outputting the second sensor data as target data when the vehicle is parked in response to the first sensor data meeting a preset condition, wherein the target data is used for training a parking obstacle detection model of the vehicle.
2. The method of claim 1, wherein the first sensor data comprises at least one of ultrasonic data, speed data, and gear data of the vehicle.
3. The method of claim 2, wherein the first sensor data comprises ultrasonic data of the vehicle;
the first sensor data satisfies a preset condition, including:
the ultrasonic data indicates the presence of an obstacle within a preset perceived distance of the vehicle.
4. The method of claim 2, wherein the first sensor data comprises speed data of the vehicle;
the first sensor data satisfies a preset condition, including:
the speed data indicates a vehicle speed less than a preset threshold.
5. The method of claim 2, wherein the first sensor data comprises gear data of the vehicle;
the first sensor data satisfies a preset condition, including:
the gear number indicates that the gear of the vehicle is reverse gear.
6. The method of claim 2, wherein the first sensor data comprises ultrasonic data and gear data of the vehicle;
the first sensor data satisfies a preset condition, including:
the gear data indicates that the gear of the vehicle is not reverse gear;
the ultrasonic data indicates the presence of an obstacle within a preset perceived distance of the vehicle.
7. The method of claim 2, wherein the first sensor data comprises ultrasonic data, speed data, and gear data of the vehicle;
the first sensor data satisfies a preset condition, including:
the speed data represents a vehicle speed less than a preset threshold;
the gear data indicates that the gear of the vehicle is reverse gear;
the ultrasonic data indicates the presence of an obstacle within a preset perceived distance of the vehicle.
8. An automatic parking method, comprising:
acquiring sensor data of a vehicle, wherein the sensor data is acquired by the vehicle while the vehicle is parked;
inputting the sensor data into a parking obstacle detection model of the vehicle to detect obstacle information around the vehicle;
controlling the vehicle to park based on the obstacle information;
wherein the parking obstacle detection model is trained using target data obtained by the training data processing method according to any one of claims 1 to 7.
9. An electronic device comprising a memory and a processor coupled to each other, the processor configured to execute program instructions stored in the memory to implement the method of processing training data according to any one of claims 1 to 7, or to implement the auto-park method according to claim 8.
10. A non-transitory computer-readable storage medium having stored thereon program instructions, which when executed by a processor, implement the method of processing training data according to any one of claims 1 to 7, or implement the auto-park method according to claim 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310260971.9A CN116394923A (en) | 2023-03-10 | 2023-03-10 | Training data processing method, automatic parking method and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310260971.9A CN116394923A (en) | 2023-03-10 | 2023-03-10 | Training data processing method, automatic parking method and related equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116394923A true CN116394923A (en) | 2023-07-07 |
Family
ID=87008291
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310260971.9A Pending CN116394923A (en) | 2023-03-10 | 2023-03-10 | Training data processing method, automatic parking method and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116394923A (en) |
-
2023
- 2023-03-10 CN CN202310260971.9A patent/CN116394923A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109305165B (en) | Intelligent ultrasonic system, vehicle rear collision warning device and control method thereof | |
| US20180211403A1 (en) | Recurrent Deep Convolutional Neural Network For Object Detection | |
| DE112017000643T5 (en) | Detecting a partially occluded object using context and depth order | |
| JP2022505759A (en) | Methods and equipment for testing driver assistance systems | |
| US20160217335A1 (en) | Stixel estimation and road scene segmentation using deep learning | |
| CN111683840B (en) | Interaction method and system of movable platform, movable platform and storage medium | |
| CN110610137B (en) | Method and device for detecting vehicle running state, electronic equipment and storage medium | |
| CN112009470B (en) | Vehicle running control method, device, equipment and storage medium | |
| CN112654998B (en) | Lane line detection method and device | |
| CN110659548B (en) | Vehicle and target detection method and device thereof | |
| US10279793B2 (en) | Understanding driver awareness through brake behavior analysis | |
| CN114119955A (en) | Method and device for detecting potential dangerous target | |
| CN116394923A (en) | Training data processing method, automatic parking method and related equipment | |
| CN107452230B (en) | Obstacle detection method and device, terminal equipment and storage medium | |
| KR20210055746A (en) | Driver's working condition detection method, device, device and computer storage medium | |
| CN107255470B (en) | Obstacle detection device | |
| EP3217357B1 (en) | Estimation of movement of a target object | |
| CN112700658B (en) | System for image sharing of a vehicle, corresponding method and storage medium | |
| CN116265277A (en) | Vehicle starting control method, device, equipment and storage medium | |
| CN112183413B (en) | Parking space detection method and device, storage medium and vehicle | |
| US20230386222A1 (en) | Method for detecting three-dimensional objects in roadway and electronic device | |
| US20230419682A1 (en) | Method for managing driving and electronic device | |
| US11670092B2 (en) | Electronic device for controlling driving vehicle and operation method of the electronic device | |
| EP4336467A1 (en) | Method and apparatus for modeling object, storage medium, and vehicle control method | |
| CN109795464B (en) | Braking method, braking device 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 |