CN112440980A - Parking space detection method and device, storage medium and vehicle - Google Patents
Parking space detection method and device, storage medium and vehicle Download PDFInfo
- Publication number
- CN112440980A CN112440980A CN201910809746.XA CN201910809746A CN112440980A CN 112440980 A CN112440980 A CN 112440980A CN 201910809746 A CN201910809746 A CN 201910809746A CN 112440980 A CN112440980 A CN 112440980A
- Authority
- CN
- China
- Prior art keywords
- distance
- data
- preset
- parking space
- target
- 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.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 95
- 230000003247 decreasing effect Effects 0.000 claims abstract description 111
- 230000009191 jumping Effects 0.000 claims abstract description 25
- 238000000034 method Methods 0.000 claims description 41
- 238000005457 optimization Methods 0.000 claims description 12
- 238000012795 verification Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 6
- 125000004122 cyclic group Chemical group 0.000 claims description 5
- 238000010200 validation analysis Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 15
- 230000008569 process Effects 0.000 description 9
- 101000922137 Homo sapiens Peripheral plasma membrane protein CASK Proteins 0.000 description 8
- 102100031166 Peripheral plasma membrane protein CASK Human genes 0.000 description 8
- 101100181929 Caenorhabditis elegans lin-3 gene Proteins 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 230000004888 barrier function Effects 0.000 description 3
- 102100027206 CD2 antigen cytoplasmic tail-binding protein 2 Human genes 0.000 description 2
- 101000914505 Homo sapiens CD2 antigen cytoplasmic tail-binding protein 2 Proteins 0.000 description 2
- 230000001174 ascending effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010998 test method Methods 0.000 description 2
- 201000004569 Blindness Diseases 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000001960 triggered effect 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
- B60W30/06—Automatic manoeuvring for parking
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Measurement Of Velocity Or Position Using Acoustic Or Ultrasonic Waves (AREA)
Abstract
The invention relates to a parking space detection method, a device, a storage medium and a vehicle, which can collect distance data between the vehicle and a target obstacle according to a preset period, obtain time sequence distance data according to collection time, determine an increasing jump distance and a decreasing jump distance in the time sequence distance data through a preset vehicle-locating algorithm, specifically, determine distance data with an increasing amplitude larger than or equal to a preset distance threshold value in the time sequence distance data, determine distance data with continuous preset number of increasing data before the distance data as the increasing jump distance, determine distance data with a decreasing amplitude larger than or equal to the preset distance threshold value in the time sequence distance data, and determine distance data with continuous preset number of decreasing data after the distance data as the decreasing jump distance, and determining the target size data of the target parking space according to the incremental jumping distance and the incremental jumping distance.
Description
Technical Field
The disclosure relates to the technical field of automatic parking, in particular to a parking space detection method, a parking space detection device, a storage medium and a vehicle.
Background
With the improvement of the quality of life of the people, the number of the domestic automobiles is increased year by year, meanwhile, the demand of parking spaces is more tense, the space is narrower, and the problems are troubled for many drivers.
In the method for detecting the parking space provided by the related technology, the edge of the obstacle is obtained by fitting a plurality of relative distances between the side edge of the vehicle body and the obstacle detected in the driving process of the vehicle, two adjacent jumping edges are found in the edge, and the position of the parking space can be further determined according to the distance between the two jumping edges, however, in the method for detecting the parking space, the jumping edge refers to the edge with jumping data, and at the jumping position, the data with certain length on the left side and the right side are kept unchanged, but the data at the jumping position are suddenly changed, that is, only an increasing point or a decreasing point appears in the detected edges, the jumping edge is determined, but the deviation between the relative distance detected by an actual distance detection device (such as an ultrasonic sensor) due to the influence of external factors and the actual distance between the vehicle and the obstacle is considered, at this time, if a change point (an increasing point or a decreasing point) occurs in the relative distance, the change point is determined as the jumping edge, which will inevitably affect the accuracy of the detected parking space size data, and further reduce the accuracy of parking space detection.
Disclosure of Invention
The invention aims to provide a parking space detection method, a parking space detection device, a storage medium and a vehicle.
In a first aspect, a method for detecting a parking space is provided, the method comprising: acquiring distance data between a vehicle and a target obstacle according to a preset period, and acquiring time series distance data according to acquisition moments, wherein the target obstacle is an obstacle in a preset range of a target parking space; determining an increasing jump distance and a decreasing jump distance in the time sequence distance data through a preset vehicle position searching algorithm; determining target size data of the target parking space according to the incremental jumping distance and the incremental jumping distance; the preset parking space searching algorithm comprises the following steps: determining distance data to be processed from the time series distance data in sequence according to the acquisition time; if the distance data to be processed is nth continuously increasing data and the difference value between the distance data to be processed and the distance data acquired at the previous moment is greater than or equal to a preset distance threshold, determining the distance data acquired at the previous moment as the increasing jump distance; if the distance data to be processed is nth continuously decreasing distance data, and in the continuously decreasing distance data, the difference value between the first continuously decreasing distance data and the first distance data is greater than or equal to the preset distance threshold value, determining that the first continuously decreasing distance data is the decreasing jump distance, where the first distance data is distance data acquired at a previous time of acquiring the first continuously decreasing distance data, and n is a preset positive integer greater than 1.
Optionally, before the determining the target size data of the target parking space according to the incremental jump distance and the incremental jump distance, the method further includes: acquiring a preset detection angle, wherein the preset detection angle is the maximum detection angle of the obstacle detection device for acquiring the distance data; acquiring a first wheel speed pulse of the vehicle acquired at an increasing moment, a second wheel speed pulse of the vehicle acquired at a decreasing moment, and a first preset distance corresponding to a single wheel speed pulse of the vehicle; the increasing moment is the collecting moment corresponding to the increasing jump distance, and the decreasing moment is the collecting moment corresponding to the decreasing jump distance; the determining the target size data of the target parking space according to the incremental jump distance and the incremental jump distance comprises: calculating to obtain a first size according to the increasing jump distance and the preset detection angle, and calculating to obtain a second size according to the decreasing jump distance and the preset detection angle; calculating to obtain a third size according to the first wheel speed pulse, the second wheel speed pulse and the first preset distance; and taking the sum of the first size, the second size and the third size as target size data of the target parking space.
Optionally, after the determining the target size data of the target parking space according to the incremental jump distance and the incremental jump distance, the method further includes: verifying whether the preset parking space searching algorithm is the optimal parking space searching algorithm or not according to the target size data and the actual size data of the target parking space; and if the preset parking space searching algorithm is not the optimal parking space searching algorithm, optimizing the preset parking space searching algorithm.
Optionally, the verifying whether the preset parking space searching algorithm is the optimal parking space searching algorithm according to the target size data and the actual size data of the target parking space includes: calculating an error of the target dimension data relative to the actual dimension data; and if the error is within a preset error range, determining the preset vehicle-position searching algorithm as an optimal vehicle-position searching algorithm.
Optionally, before verifying whether the preset parking space searching algorithm is the optimal parking space searching algorithm according to the target size data and the actual size data of the target parking space, the method further includes:
circularly executing the step of acquiring distance data between the vehicle and a target obstacle according to a preset period, acquiring time sequence distance data according to acquisition time, and determining target size data of the target parking space according to the incremental jumping distance and the decremental jumping distance until the number of times of circular execution reaches a preset number of times to obtain a plurality of target size data; the verifying whether the preset parking space searching algorithm is the optimal parking space searching algorithm or not according to the target size data and the actual size data of the target parking space comprises the following steps: calculating an error of each of the target dimensional data relative to the actual dimensional data; acquiring the proportion of the number of the target size data with the error within a preset error range in all the target size data; and if the ratio is greater than or equal to a preset ratio threshold value, determining that the preset parking space searching algorithm is the optimal parking space searching algorithm.
Optionally, the optimizing the preset parking space searching algorithm includes: and updating the n value and/or the preset distance threshold according to a preset updating amplitude.
In a second aspect, there is provided a parking space detection apparatus, the apparatus comprising: the upper computer acquisition module is used for acquiring distance data between the vehicle and a target obstacle according to a preset period and acquiring time series distance data according to acquisition moments, wherein the target obstacle is an obstacle in a preset range of a target parking space; the first determining module is used for determining an increasing jump distance and a decreasing jump distance in the time sequence distance data through a preset vehicle-locating algorithm; the second determination module is used for determining target size data of the target parking space according to the increasing jump distance and the decreasing jump distance; the preset parking space searching algorithm comprises the following steps: determining distance data to be processed from the time series distance data in sequence according to the acquisition time; if the distance data to be processed is nth continuously increasing data and the difference value between the distance data to be processed and the distance data acquired at the previous moment is greater than or equal to a preset distance threshold, determining the distance data acquired at the previous moment as the increasing jump distance; if the distance data to be processed is nth continuously decreasing distance data, and in the continuously decreasing distance data, the difference value between the first continuously decreasing distance data and the first distance data is greater than or equal to the preset distance threshold value, determining that the first continuously decreasing distance data is the decreasing jump distance, where the first distance data is distance data acquired at a previous time of acquiring the first continuously decreasing distance data, and n is a preset positive integer greater than 1.
Optionally, the apparatus further comprises: a first obtaining module, configured to obtain a preset detection angle, where the preset detection angle is a maximum detection angle of an obstacle detection device used for acquiring the distance data; the second acquisition module is used for acquiring a first wheel speed pulse of the vehicle acquired at an increasing moment, a second wheel speed pulse of the vehicle acquired at a decreasing moment and a first preset distance corresponding to a single wheel speed pulse of the vehicle; the increasing moment is the collecting moment corresponding to the increasing jump distance, and the decreasing moment is the collecting moment corresponding to the decreasing jump distance; the second determining module is configured to calculate a first size according to the incremental jump distance and the preset detection angle, and calculate a second size according to the incremental jump distance and the preset detection angle; calculating to obtain a third size according to the first wheel speed pulse, the second wheel speed pulse and the first preset distance; and taking the sum of the first size, the second size and the third size as target size data of the target parking space.
Optionally, the apparatus further comprises: the algorithm verification module is used for verifying whether the preset parking space searching algorithm is the optimal parking space searching algorithm or not according to the target size data and the actual size data of the target parking space; and the algorithm optimization module is used for optimizing the preset parking space searching algorithm if the preset parking space searching algorithm is not the optimal parking space searching algorithm.
Optionally, the algorithm verification module is configured to calculate an error of the target dimension data relative to the actual dimension data; and if the error is within a preset error range, determining the preset vehicle-position searching algorithm as an optimal vehicle-position searching algorithm.
Optionally, the apparatus further comprises: the cyclic execution module is used for cyclically executing the steps from acquiring distance data of a vehicle and a target obstacle according to a preset period, obtaining time sequence distance data according to acquisition time, determining target size data of the target parking space according to the increasing jump distance and the decreasing jump distance until the number of times of cyclic execution reaches a preset number of times, and obtaining a plurality of target size data; the algorithm verification module is used for calculating the error of each target size data relative to the actual size data; acquiring the proportion of the number of the target size data with the error within a preset error range in all the target size data; and if the ratio is greater than or equal to a preset ratio threshold value, determining that the preset parking space searching algorithm is the optimal parking space searching algorithm.
Optionally, the algorithm optimization module is configured to update the n value and/or the preset distance threshold according to a preset update amplitude.
In a third aspect, a computer readable storage medium is provided, on which a computer program is stored, which program, when being executed by a processor, carries out the steps of the method according to the first aspect of the disclosure.
In a fourth aspect, a vehicle is provided, comprising the parking space detection device of the second aspect of the present disclosure.
By the technical scheme, the distance data between the vehicle and the target barrier is collected according to the preset period, and obtaining time series distance data according to the acquisition time, wherein the target barrier is a barrier of the target parking space in a preset range, determining an increasing jump distance and a decreasing jump distance in the time series distance data through a preset vehicle position searching algorithm, determining target size data of the target parking space according to the incremental jump distance and the incremental jump distance, specifically, the distance data to be processed can be determined from the time series distance data according to the acquisition time in turn, and if the distance data to be processed is the nth continuously increasing data, and the difference value between the distance data to be processed and the distance data acquired at the previous moment is greater than or equal to a preset distance threshold value, and the distance data acquired at the previous moment is determined as the incremental jump distance; if the distance data to be processed is nth continuously decreasing distance data, and in the continuously decreasing distance data, a difference value between the first continuously decreasing distance data and the first distance data is greater than or equal to the preset distance threshold, determining that the first continuously decreasing distance data is the decreasing jump distance, where the first distance data is distance data acquired at a previous time of an acquisition time at which the first continuously decreasing distance data is acquired, and n is a preset positive integer greater than 1, that is, the present disclosure may determine distance data having an increasing amplitude greater than or equal to the preset distance threshold in the time series distance data, and determine distance data having a continuously preset number of increasing data before the distance data as the increasing jump distance, and determine distance data having a decreasing amplitude greater than or equal to the preset distance threshold in the time series distance data, compared with a method for determining a jump distance as soon as an increment point or a decrement point occurs in the related technology, the jump distance determining method provided by the disclosure is more in line with the actual parking space detection precision requirement, so that the target size data of the target parking space determined according to the jump distance is more accurate, the reliability of the detected parking space data is ensured, and the automatic parking path can be more accurately planned.
Additional features and advantages of the disclosure will be set forth in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure without limiting the disclosure. In the drawings:
FIG. 1 is a flow chart illustrating a first method of detecting a parking spot in accordance with an exemplary embodiment;
FIG. 2 is a flow chart illustrating a second method of detecting a parking spot in accordance with an exemplary embodiment;
FIG. 3 is a schematic diagram illustrating a distribution of ultrasonic sensors on a vehicle in accordance with an exemplary embodiment;
FIG. 4 is a diagram illustrating a method for storing the time series distance data in the form of an image according to an exemplary embodiment;
FIG. 5 is a schematic illustration of a first type of parking space detection scenario, according to an exemplary embodiment;
FIG. 6 is a schematic diagram illustrating a second type of parking space detection scenario in accordance with an exemplary embodiment;
FIG. 7 is a block diagram illustrating a first type of parking space detection device in accordance with an exemplary embodiment;
FIG. 8 is a block diagram illustrating a second type of parking space detection device in accordance with an exemplary embodiment;
FIG. 9 is a block diagram illustrating a third type of parking space detection device in accordance with an exemplary embodiment;
FIG. 10 is a block diagram illustrating a fourth means for detecting a parking spot in accordance with an exemplary embodiment;
FIG. 11 is a block diagram of a vehicle shown in accordance with an exemplary embodiment.
Detailed Description
The following detailed description of specific embodiments of the present disclosure is provided in connection with the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating the present disclosure, are given by way of illustration and explanation only, not limitation.
First, an application scenario of the present disclosure is introduced, and the present disclosure is mainly applied to a scenario in which a vehicle automatically parks a vehicle through an automatic parking system, and the automatic parking system generally includes: the parking space detection method comprises a parking space detection module, a parking track planning module and an instruction control execution module, wherein the accuracy and stability of parking space detection depend on a parking space searching algorithm in the parking space detection module, the parking space searching algorithm can determine an increasing jump distance and a decreasing jump distance in time series distance data between a target obstacle detected by the parking space detection module, and further calculate size data of the target parking space according to the increasing jump distance and the decreasing jump distance, in the related technology, edges of the obstacle are obtained by fitting a plurality of relative distances between a side edge of a vehicle body and the obstacle detected in the driving process of the vehicle, so that the edge is determined as the jump edge only by the increasing point or the decreasing point, but the deviation between the relative distance detected by an actual distance detection device (such as an ultrasonic sensor) due to the influence of external factors and the actual distance between the vehicle and the obstacle is considered, at this time, if a change point (an increasing point or a decreasing point) occurs in the relative distance, the change point is determined as the jumping edge, which will inevitably affect the accuracy of the detected parking space size data, and further reduce the accuracy of parking space detection.
In order to solve the existing problems, the present disclosure provides a parking space detection method, device, storage medium and vehicle, which may include adding an upper computer acquisition module in the automatic parking system, acquiring distance data between the vehicle and a target obstacle according to a preset period through the upper computer acquisition module, obtaining time series distance data according to an acquisition time, recording and storing the time series distance data, determining an incremental jump distance and a decremental jump distance in the time series distance data through a preset vehicle-locating algorithm, specifically, determining distance data having an incremental amplitude greater than or equal to a preset distance threshold in the time series distance data, determining distance data having a continuous preset number of incremental data before the distance data as the incremental jump distance, determining distance data having a decremental amplitude greater than or equal to the preset distance threshold in the time series distance data, and the distance data with continuous preset number of descending data is determined as the descending jump distance after the distance data, so that the target size data of the target parking space is determined according to the ascending jump distance and the descending jump distance.
Fig. 1 is a flow chart illustrating a method of detecting a parking space, which may be applied to a vehicle, according to an exemplary embodiment, as shown in fig. 1, the method including the steps of:
in step 101, distance data between a vehicle and a target obstacle is collected according to a preset period, and time series distance data is obtained according to a collection time.
The vehicle is a vehicle which performs automatic parking through an automatic parking system, the target obstacle is an obstacle within a preset range of a target parking space, and the preset range can include areas on the left side and the right side of the target parking space or in second preset distances on the front side and the rear side of the target parking space.
In a possible implementation manner, the target obstacle may be detected by an obstacle detection device (e.g., an ultrasonic sensor) installed on the vehicle according to the preset period (e.g., once every 1 second is acquired), and the detected obstacle information is converted into the distance data, in addition, the automatic parking system in the present disclosure may include an upper computer acquisition module, so that after a start instruction for the automatic parking system of the vehicle is obtained, the obstacle detection device on the vehicle starts to detect the target obstacle according to the preset period, then the distance data between the vehicle and the target obstacle is acquired, and then the upper computer acquisition module may record and store the distance data according to the acquisition time, so as to obtain the time-series distance data.
In step 102, an incremental jump distance and a decremental jump distance are determined in the time series distance data by a preset parking space finding algorithm.
For example, in a possible predetermined parking space searching algorithm, if a distance increment point appears in the time series distance data, the distance data corresponding to the distance increment point may be determined as the incremental jumping distance, if a distance decrement point appears in the time series distance data, the distance data corresponding to the distance decrement point may be determined as the decremental jumping distance, but considering that if a distance increment point appears in the time series distance data, the distance data corresponding to the distance increment point may be determined as the incremental jumping distance (or, if a distance decrement point appears, the distance data corresponding to the distance decrement point may be determined as the decremental jumping distance), the accuracy of the target size data of the target parking space calculated based on the corresponding predetermined parking space searching algorithm may be poor, therefore, in the preset vehicle-locating algorithm provided by the present disclosure, the manner of determining the incremental jump distance and the decremental jump distance in the time-series distance data can be optimized as follows: determining distance data to be processed from the time series distance data in sequence according to the acquisition time; if the distance data to be processed is nth continuously increasing data and the difference value between the distance data to be processed and the distance data acquired at the previous moment is greater than or equal to a preset distance threshold, determining the distance data acquired at the previous moment as the increasing jump distance; if the distance data to be processed is nth continuously decreasing distance data, and in the continuously decreasing distance data, the difference value between the first continuously decreasing distance data and the first distance data is greater than or equal to the preset distance threshold value, determining that the first continuously decreasing distance data is the decreasing jump distance, the first distance data being the distance data acquired at the previous moment of acquiring the first continuously decreasing distance data, and n being a preset positive integer greater than 1.
In step 103, target size data of the target parking space is determined according to the incremental jump distance and the incremental jump distance.
Wherein the target size data may include a length or a width of the target parking space.
Considering that an actual obstacle detecting device can detect obstacle information within a preset detection angle, in most cases, an incremental jump point corresponding to the incremental jump distance and a decremental jump point corresponding to the decremental jump distance are not boundary points of the target parking space, and thus, in order to improve accuracy of detected size data of the target parking space, in one possible implementation of the present disclosure, the preset detection angle (the preset detection angle being a maximum detection angle of the obstacle detecting device for acquiring the distance data), a first wheel speed pulse of the vehicle acquired at an incremental time, a second wheel speed pulse of the vehicle acquired at a decremental time, and a first preset distance corresponding to a single wheel speed pulse of the vehicle may be acquired, where the incremental time is an acquisition time corresponding to the incremental jump distance, the descending moment is the collecting moment corresponding to the descending jump distance, so that a first size can be calculated according to the ascending jump distance and the preset detection angle, and a second size can be calculated according to the descending jump distance and the preset detection angle; calculating a third size according to the first wheel speed pulse, the second wheel speed pulse and the first preset distance; and taking the sum of the first size, the second size and the third size as target size data of the target parking space.
By adopting the method, the distance data with the increasing amplitude larger than or equal to the preset distance threshold value in the time series distance data can be determined as the increasing jump distance, the distance data with the continuous preset number of increasing data before the distance data exists is determined as the distance data with the decreasing amplitude larger than or equal to the preset distance threshold value, the distance data with the continuous preset number of decreasing data after the distance data exists is determined as the decreasing jump distance, and therefore the target size data of the target parking space is determined according to the increasing jump distance and the decreasing jump distance. Therefore, the target size data of the target parking space determined according to the jump distance is more accurate, the reliability of the detected parking space data is ensured, and the automatic parking path can be more accurately planned.
Fig. 2 is a flow chart illustrating a method of detecting a parking space, which may be applied to a vehicle, according to an exemplary embodiment, as shown in fig. 2, the method including the steps of:
in step 201, distance data between the vehicle and the target obstacle is collected according to a preset period, and time series distance data is obtained according to the collection time.
The vehicle is a vehicle which performs automatic parking through an automatic parking system, the target obstacle is an obstacle within a preset range of a target parking space, and the preset range can include areas on the left side and the right side of the target parking space or in second preset distances on the front side and the rear side of the target parking space.
In a possible implementation manner, the target obstacle may be detected by an obstacle detection device (e.g., an ultrasonic sensor) installed on the vehicle according to the preset period (e.g., once every 1 second is acquired), and the detected obstacle information is converted into the distance data, in addition, the automatic parking system in the present disclosure may include an upper computer acquisition module, so that after a start instruction for the automatic parking system of the vehicle is obtained, the obstacle detection device on the vehicle starts to detect the target obstacle according to the preset period, then the distance data between the vehicle and the target obstacle is acquired, and then the upper computer acquisition module may record and store the distance data according to the acquisition time, so as to obtain the time-series distance data.
It should be noted that, in a possible implementation manner, in order to improve the accuracy of detecting the target parking space size data, the obstacle detection devices may be respectively arranged at the head position and/or the tail position of the vehicle on the same side (left side or right side) of the vehicle, so that a plurality of sets of the time series distance data may be obtained based on the obstacle detection devices arranged at different positions of the vehicle, and thus, in the verification and optimization process of the parking space searching algorithm, the plurality of sets of the time series distance data may be mutually referred to and mutually supplemented, so that the accuracy of detecting the target parking space size data is improved, and further, the optimization efficiency of the algorithm is improved.
Fig. 3 is a schematic diagram illustrating a distribution of ultrasonic sensors on a vehicle according to an exemplary embodiment, and as shown in fig. 3, four of the ultrasonic sensors are provided on the vehicle, namely an ultrasonic sensor LIN0 provided at the left rear of the vehicle, an ultrasonic sensor LIN1 provided at the left front of the vehicle, an ultrasonic sensor LIN2 provided at the right front of the vehicle, and an ultrasonic sensor LIN3 provided at the right rear of the vehicle, so that the ultrasonic sensors LIN1 and LIN0 at the left of the vehicle can be grouped to provide obstacle information and distance data of a target parking space at the left of the vehicle, and the ultrasonic sensors LIN2 and LIN3 at the right of the vehicle can be grouped to provide obstacle information and distance data of a target parking space at the right of the vehicle, which is merely an example and is not limited by the present disclosure.
In addition, it should be further noted that after the time series distance data is obtained, the time series distance data may be stored by the upper computer acquisition module, and the distance data is dynamically displayed in real time in the upper computer acquisition module software interface, in one possible implementation manner, after an operation of obtaining the stored data triggered by the user in the upper computer acquisition module software interface is obtained, the time series distance data is stored according to a preset storage path and a preset storage frame number (the storage frame number may include the number of the distance data in the time series distance data, and the time series distance data may be stored in multiple forms, for example, in two storage manners of an image and a table.
For example, fig. 4 is a schematic diagram illustrating that the time-series distance data is stored in the form of an image, as shown in fig. 4, when the time-series distance data is stored in the form of an image, the time-series distance data can be plotted in a preset coordinate system, wherein the abscissa of the preset coordinate system is a time series (which can be understood as the acquisition time of each distance data) and the ordinate is the distance data, it should be noted that fig. 4 only illustrates an image storage form of a set of time-series distance data formed by the distance data acquired by one obstacle detecting device (such as the ultrasonic sensor LIN2 distributed at the right front of the vehicle in fig. 3) at one side of the vehicle, and the distance data acquired by other sensors on the vehicle can also be simultaneously stored in the preset coordinate system, for example, for convenience of distinguishing, the distance data collected by the obstacle detecting devices in different directions may be represented by distance variation curves in different colors, and assuming that the time-series distance data shown in fig. 4 is the distance data collected by the ultrasonic sensor LIN2 distributed at the right front of the vehicle shown in fig. 3, the detected target parking space shown in the dotted square frame in fig. 4 is one of the parking spaces at the right side of the vehicle, so that the user can visually and clearly see the overall state information (e.g., the approximate size of the parking space) of the detected parking space based on the time-series distance data displayed by the image, which is merely an example and is not limited by the present disclosure.
In addition, the time series distance data can be stored in a form of a table, and all detected distance data can be stored in the form, so that the size data of the detected target parking space can be comprehensively analyzed based on all the distance data, and a more specific data basis is provided for the optimization of the preset vehicle-searching algorithm.
In step 202, an incremental jump distance and a decremental jump distance are determined in the time series distance data by a preset parking space finding algorithm.
For example, in a possible preset parking space finding algorithm, if a distance increment point appears in the time series distance data, the distance data corresponding to the distance increment point can be determined as the incremental jumping distance, and if a distance decrement point appears in the time series distance data, the distance data corresponding to the distance decrement point can be determined as the decremental jumping distance.
For example, it is assumed that the time-series distance data is d1, d2, d3, d4, d5, d6, d7, and d8, where di (i ═ 1, 2.., 8) represents the distance data acquired at the i-th acquisition time, and the magnitude relationship of the time-series distance data is d1 ═ d2 ═ d3< d4< d5 ═ d6> d7> d8, in the time-series distance data, d4 is the distance increasing point which first appears, d7 is the distance decreasing point which first appears, so that d4 may be determined as the increasing jump distance, and d7 is the decreasing jump distance, which is only an example and is not limited by the present disclosure.
However, considering that if, in the time series distance data, a distance data corresponding to a distance increment point is determined to be the increment jump distance (or a distance data corresponding to a distance decrement point is determined to be the decrement jump distance) when the distance increment point occurs, the accuracy of the target size data of the target parking space calculated based on the corresponding preset parking space searching algorithm is poor, in the preset parking space searching algorithm provided by the present disclosure, the manner of determining the increment jump distance and the decrement jump distance in the time series distance data may be optimized as follows: determining distance data to be processed from the time series distance data in sequence according to the acquisition time; if the distance data to be processed is nth continuously increasing data and the difference value between the distance data to be processed and the distance data acquired at the previous moment is greater than or equal to a preset distance threshold, determining the distance data acquired at the previous moment as the increasing jump distance; if the distance data to be processed is nth continuously decreasing distance data, and in the continuously decreasing distance data, the difference value between the first continuously decreasing distance data and the first distance data is greater than or equal to the preset distance threshold value, determining that the first continuously decreasing distance data is the decreasing jump distance, the first distance data being the distance data acquired at the previous moment of acquiring the first continuously decreasing distance data, and n being a preset positive integer greater than 1.
For example, taking n as 3 and the preset distance variation threshold as 150cm as an example, it is assumed that the time-series distance data is:
d (1), d (2), d (3), d (4), d (5),. the.. d, d (k-2), d (k), wherein d (i) (1, 2.. the.. k) represents the distance data acquired at the ith acquisition time, the distance data to be processed can be determined from the time series distance data according to the acquisition time, wherein the distance data to be processed can be any other data except the distance data d (1) acquired at the 1 st acquisition time in the time series distance data, so that the determined 1 st distance data to be processed is d (2), whether d (2) is larger than d (1) is judged, if d (2) > d (1), d (2) is determined to be the data of the 1 st increment, and whether d (3) is larger than d (2) is continuously judged, if d (3) > d (2), determining that d (3) is 2 nd continuously increasing data, continuously judging whether d (4) is larger than d (3), if d (4) > d (3), determining that d (4) is 3 rd continuously increasing data, because preset n is 3, determining that the distance data d (4) to be processed is nth continuously increasing data, at this time, further judging whether the difference value between the distance data d (4) to be processed and the distance data d (3) acquired at the last moment is larger than or equal to a preset distance threshold value 150cm, and if the difference value between d (4) and d (3) is determined to be larger than or equal to the preset distance threshold value 150cm, determining that d (3) is the increasing jump distance.
Similarly, in the process of determining the decreasing jump distance, distance data to be processed is also determined from the time-series distance data in sequence according to the acquisition time, assuming that the distance data to be processed determined at the current time is d (i), and there is no distance data satisfying a condition of n (in this example, n is 3) th continuously decreasing distance data in the distance data before d (i) in the time-series distance data, if it is determined in the subsequent determination step that d (i) < d (i +1) < d (i +2) < d (i +3), it may be determined that d (i +3) is the 3 rd continuously decreasing distance data, and then it is further determined whether a difference between the first continuously decreasing distance data d (i +1) and the first distance data d (i +3) in the continuously decreasing distance data d (i +1), d (i +2), and d (i +3) is greater than or equal to the preset distance threshold value of 150cm, if the difference between d (i +1) and d (i) is greater than or equal to 150cm, the first continuously decreasing distance data d (i +1) may be determined as the decreasing jump distance, and the above example is only an example, and the disclosure does not limit this.
After the incremental jump distance and the decremental jump distance are obtained, target size data (length or width) of the detected target parking space may be further determined based on the incremental jump distance and the decremental jump distance.
In step 203, a preset detection angle is acquired.
Wherein the preset detection angle is a maximum detection angle of an obstacle detection device (such as an ultrasonic sensor) for acquiring the distance data.
In step 204, a first wheel speed pulse of the vehicle acquired at the increasing time, a second wheel speed pulse of the vehicle acquired at the decreasing time, and a first preset distance corresponding to a single wheel speed pulse of the vehicle are acquired.
The increasing moment is the collecting moment corresponding to the increasing jump distance, and the decreasing moment is the collecting moment corresponding to the decreasing jump distance.
In step 205, a first size is calculated according to the incremental jump distance and the preset detection angle, and a second size is calculated according to the incremental jump distance and the preset detection angle.
In step 206, a third dimension is calculated according to the first wheel speed pulse, the second wheel speed pulse and the first predetermined distance.
In step 207, the sum of the first size, the second size and the third size is used as the target size data of the target parking space.
Wherein the target size data may include a length or a width of the target parking space.
The following describes specific embodiments of steps 203 to 207 by taking the detection scene schematic diagrams of parking spaces shown in fig. 5 and 6 as examples:
for example, fig. 5 is a schematic view of a detection scene of a first type of parking space shown according to an exemplary embodiment, fig. 6 is a schematic view of a detection scene of a second type of parking space shown according to an exemplary embodiment, and as shown in fig. 5, assuming that there is one target parking space (i.e., space 3 shown in fig. 5) on the right side of the vehicle and that there are obstacle vehicles parked in the parking spaces (i.e., space 2 and space 4) on the left and right sides of the target parking space (i.e., the obstacle vehicles parked in space 2 and space 4 can be regarded as the target obstacle), in the process of detecting the size data of the target parking space, the vehicle can enter from the a port, then enter from the a segment (located in the same horizontal direction as space 4) into the B segment (located in the same horizontal direction as the target parking space), and then enter from the B segment into the C segment (located in the same horizontal direction as space 2), and during the vehicle is running in section a, the distance data acquired by the ultrasonic sensor LIN2 at the front right of the vehicle according to the preset period are the distance data between the vehicle and the obstacle vehicle parked in parking space 4, and the acquired distance data are not much different before the vehicle runs to the boundary between parking space 3 and parking space 4, because the ultrasonic sensor has a preset detection angle (such as α in fig. 6), the ultrasonic sensor LIN2 can acquire the distance data between the obstacle located in the preset detection angle range and the vehicle, so that, during the vehicle head of the vehicle enters section B from section a, the obstacle vehicle parked in parking space 4 is still located within the preset detection angle of the ultrasonic sensor, and the ultrasonic sensor can also continue to acquire the distance data between the vehicle and the obstacle vehicle parked in parking space 4, but the size of the distance data is in an increasing state, until the obstacle vehicle parked in parking space 4 exceeds the preset detection angle of the ultrasonic sensor, the ultrasonic sensor cannot acquire the distance data between the vehicle and the obstacle vehicle parked in parking space 4, and at this time, the target parking space enters the preset detection angle range, but no obstacle exists in the target parking space, at this time, the distance data between the vehicle and the target obstacle can be set as the maximum detection distance (such as 400cm) of the ultrasonic sensor, and in a later period of time, the distance data acquired by the ultrasonic sensor are the maximum detection distances, as the vehicle continues to move forward, the obstacle vehicle in parking space 2 starts to enter the preset detection angle of the ultrasonic sensor, at this time, the acquired distance data is the distance data between the vehicle and the obstacle vehicle in parking space 2, and the size of the distance data is in a decreasing state until the head of the vehicle enters the range of the parking space 2 in the horizontal direction.
As can be seen from the specific process of parking space detection described in the above example, the incremental jump distance may be regarded as the distance data between the vehicle and the obstacle vehicle located on the parking space 4 (e.g., d3 in fig. 6) acquired last time by the ultrasonic sensor, and the incremental jump distance may be regarded as the distance data between the vehicle and the obstacle vehicle located on the parking space 2 (e.g., d4 in fig. 6) acquired first time by the ultrasonic sensor, so that, as shown in fig. 6, in the process of calculating the target size data of the target parking space, the target size data L may be divided into three segments L1, L2, and L3, and specifically, the first size L1, L1 ═ d3 α sin α may be calculated according to the following formulas in combination with a trigonometric function according to the incremental jump distance and the preset detection angle1And calculating a second dimension L3 according to the descending jump distance and the preset detection angle and the following formula, wherein L3 is d4 sin alpha2Wherein d3 represents the incremental jump distance, d4 represents the decremental jump distance,and alpha is the preset detection angle, and in addition, the third ruler is calculatedAt size L2, a third size L2 may be calculated from the first wheel speed pulse, the second wheel speed pulse, and the first predetermined distance according to the following formula:
l2 (end-start pulse) × (PPL), where endpulse represents the second wheel speed pulse, startpulse represents the first wheel speed pulse, and PPL represents the first preset distance corresponding to a single wheel speed pulse of the vehicle, so that the target size data L of the target parking space is L1+ L2+ L3, which is only an example and is not limited by the disclosure.
It should be noted that, the above-mentioned process of calculating the target size data of the target parking space is calculated based on the time-series distance data acquired by the ultrasonic sensor LIN2 located at the front right of the vehicle, if the ultrasonic sensor (i.e. LIN3 in fig. 3) is also provided at the rear right of the vehicle, another target size data of the target parking space may also be calculated based on one set of the time-series distance data acquired by LIN3 according to the above-mentioned method, at this time, the target size data of the target parking space respectively calculated based on two sets of the time-series distance data acquired by the two ultrasonic sensors (i.e. LIN2 and LIN3) may be mutually referred to and complemented with each other, for example, if the two target size data are equal, any one may be selected as the target size data of the target parking space, if the two target size data are not equal, the average value of the two target size data can be taken as the target size data of the target parking space, so that the accuracy of detecting the target parking space size data can be improved.
It should be further noted that, for a vehicle to be parked, the target parking space may be a horizontal parking space or a vertical parking space, in general, minimum size data of the horizontal parking space (or referred to as a horizontal parking space) and the vertical parking space (or referred to as a longitudinal parking space) may be respectively set, then, based on a size relationship between the target size data and the minimum size data, it is determined whether the target parking space is the horizontal parking space or the vertical parking space, and if it is determined that the target parking space is the horizontal parking space, the calculated target size data is a length of the target parking space, and if it is determined that the target parking space is the vertical parking space, the calculated target size data is a width of the target parking space.
For example, the minimum size data of the horizontal parking space may be Lmin ═ vehicle length +60cm, the minimum size data of the vertical parking space may be Wmin ═ vehicle width +50cm, assuming that the calculated target size data of the target parking space is L, if Wmin < L <2 × Wmin, it is determined that the target parking space is a vertical parking space, and the target size data is the width of the target parking space; if L > Lmin, it is determined that the target parking space is a horizontal parking space, and the target size data is the length of the target parking space.
After the target size data is calculated, it can be verified whether the preset parking space searching algorithm is the optimal parking space searching algorithm by executing steps 208 to 211 according to the target size data and the actual size data of the target parking space.
In step 208, step 201 to step 207 are executed in a loop until the number of times of loop execution reaches a preset number of times, so as to obtain a plurality of target size data.
In step 209, an error of each of the target dimensional data relative to the actual dimensional data is calculated.
In this step, the error can be calculated according to the following formula:
where ε represents the error, LR represents the actual size data, and LT represents the target size data.
In step 210, the ratio of the number of target size data with the error within the preset error range to all the target size data is obtained.
In step 211, if the ratio is greater than or equal to a preset ratio threshold, it is determined that the preset parking space searching algorithm is the optimal parking space searching algorithm.
The following describes, by way of example, embodiments of steps 208 through 211:
for example, table 1 records target size data of N groups of target parking spaces and an error of each target size data with respect to an actual size data of the target parking space, and then counts a ratio of the number of target size data with the error within a preset error range (e.g. 5%) to all target size data, where P is N1/N, where N1 is the number of target size data with the error within a preset error range, and N is the number of all target size data, if the error is within the preset error range, it may be determined that the accuracy of the preset parking space searching algorithm is higher, further, if the ratio P of the number of target size data with the error within a preset error range (e.g. 5%) to all target size data is greater than or equal to a preset ratio threshold (e.g. 90%), it may be determined that the accuracy and stability of the preset parking space searching algorithm are better, therefore, the preset car-finding algorithm may be determined as the optimal car-finding algorithm, and the above examples are only illustrative and the disclosure is not limited thereto.
Target size data | Actual size data | Error of the measurement | |
First group | LT1 | LR | Error 1 |
Second group | LT2 | LR | Error 2 |
Third group | LT3 | LR | Error 3 |
Fourth group | LT4 | LR | Error 4 |
........... | ........... | ........... | ........... |
Group N | LTn | LR | Error n |
TABLE 1
Whether the preset parking space searching algorithm is the optimal parking space searching algorithm can be verified from the aspects of accuracy and stability by executing the steps 208 to 211, and compared with the conventional parking space searching algorithm, the optimal parking space searching algorithm has a better filtering effect, reduces the interference of the surrounding environment of the parking space on the parking space searching algorithm, and improves the accuracy and stability of the detection of the parking space searching algorithm.
In addition, in the process of verifying the preset parking space searching algorithm, only the accuracy of the parking space searching algorithm can be verified according to different service requirements, specifically, the error of the target size data relative to the actual size data can be calculated, if the error is within a preset error range, the accuracy of the preset parking space searching algorithm is determined to be better, and then the preset parking space searching algorithm can be determined to be the optimal parking space searching algorithm.
In step 212, if the ratio is smaller than the preset ratio threshold, it is determined that the preset parking space searching algorithm is not the optimal parking space searching algorithm, and the preset parking space searching algorithm is optimized.
In this step, if it is determined that the ratio is smaller than the preset ratio threshold, it is determined that the preset parking space searching algorithm does not meet the preset requirements for accuracy and stability, and it is determined that the preset parking space searching algorithm is not the optimal parking space searching algorithm.
In a possible optimization manner, the n value in the preset parking space searching algorithm and/or the preset distance threshold may be updated according to a preset updating range (for example, a new n value may be obtained by adding 1 to the n value, and/or the preset distance threshold is increased from 150cm to 200cm), so as to obtain a new preset parking space searching algorithm, and then new target size data of the target parking space is recalculated through the new preset parking space searching algorithm (the specific implementation manner is as described in steps 201 to 207, which is not described herein again), and then it may be verified whether the new preset parking space searching algorithm is the optimal parking space searching algorithm according to the new target size data and the actual size data of the target parking space according to the implementation manners described in steps 208 to 211 until the optimal parking space searching algorithm is determined, so as to determine the more accurate target size data through the optimal parking space searching algorithm, to ensure the reliability of the detected parking space size data.
It should be further noted that the time series distance data provided in the disclosure provides a data basis for optimization of the parking space searching algorithm, so that blindness of algorithm optimization is reduced, and efficiency of parking space searching algorithm optimization is improved.
By adopting the method, the distance data with the increasing amplitude larger than or equal to the preset distance threshold value in the time series distance data can be determined as the increasing jump distance, the distance data with the continuous preset number of increasing data before the distance data exists is determined as the distance data with the decreasing amplitude larger than or equal to the preset distance threshold value, the distance data with the continuous preset number of decreasing data after the distance data exists is determined as the decreasing jump distance, and therefore the target size data of the target parking space is determined according to the increasing jump distance and the decreasing jump distance. Therefore, the target size data of the target parking space determined according to the jump distance is more accurate, the reliability of the detected parking space data is ensured, and the automatic parking path can be more accurately planned.
Fig. 7 is a block diagram illustrating a parking space detection apparatus according to an exemplary embodiment, as shown in fig. 7, the apparatus including:
the upper computer acquisition module 701 is used for acquiring distance data between a vehicle and a target obstacle according to a preset period and obtaining time series distance data according to acquisition moments, wherein the target obstacle is an obstacle in a preset range of a target parking space;
a first determining module 702, configured to determine an increasing jump distance and a decreasing jump distance in the time series distance data through a preset parking space searching algorithm;
a second determining module 703, configured to determine target size data of the target parking space according to the incremental jump distance and the incremental jump distance;
the preset parking space searching algorithm comprises the following steps: determining distance data to be processed from the time series distance data in sequence according to the acquisition time; if the distance data to be processed is nth continuously increasing data and the difference value between the distance data to be processed and the distance data acquired at the previous moment is greater than or equal to a preset distance threshold, determining the distance data acquired at the previous moment as the increasing jump distance; if the distance data to be processed is nth continuously decreasing distance data, and in the continuously decreasing distance data, the difference value between the first continuously decreasing distance data and the first distance data is greater than or equal to the preset distance threshold value, determining that the first continuously decreasing distance data is the decreasing jump distance, the first distance data being the distance data acquired at the previous moment of acquiring the first continuously decreasing distance data, and n being a preset positive integer greater than 1.
Optionally, fig. 8 is a block diagram of a parking space detection apparatus according to the embodiment shown in fig. 7, and as shown in fig. 8, the apparatus further includes:
a first obtaining module 704, configured to obtain a preset detection angle, where the preset detection angle is a maximum detection angle of the obstacle detecting device for acquiring the distance data;
a second obtaining module 705, configured to obtain a first wheel speed pulse of the vehicle collected at an increasing time, a second wheel speed pulse of the vehicle collected at a decreasing time, and a first preset distance corresponding to a single wheel speed pulse of the vehicle; the increasing moment is the collecting moment corresponding to the increasing jump distance, and the decreasing moment is the collecting moment corresponding to the decreasing jump distance;
the second determining module 703 is configured to calculate a first size according to the incremental jump distance and the preset detection angle, and calculate a second size according to the incremental jump distance and the preset detection angle; calculating a third size according to the first wheel speed pulse, the second wheel speed pulse and the first preset distance; and taking the sum of the first size, the second size and the third size as target size data of the target parking space.
Optionally, fig. 9 is a block diagram of a parking space detection apparatus according to the embodiment shown in fig. 8, and as shown in fig. 9, the apparatus further includes:
the algorithm verification module 706 is configured to verify whether the preset parking space searching algorithm is the optimal parking space searching algorithm according to the target size data and the actual size data of the target parking space;
and an algorithm optimization module 707, configured to optimize the preset parking space searching algorithm if the preset parking space searching algorithm is not the optimal parking space searching algorithm.
Optionally, the algorithm verification module 706 is configured to calculate an error of the target dimension data relative to the actual dimension data; and if the error is within the preset error range, determining the preset parking space searching algorithm as an optimal parking space searching algorithm.
Optionally, fig. 10 is a block diagram of a parking space detection apparatus according to the embodiment shown in fig. 9, and as shown in fig. 10, the apparatus further includes:
a cycle execution module 708, configured to cyclically execute the step of acquiring distance data between the vehicle and the target obstacle according to the preset period, and obtaining time-series distance data according to the acquisition time, and determining target size data of the target parking space according to the incremental jump distance and the incremental jump distance until the number of times of cyclic execution reaches a preset number of times, so as to obtain a plurality of target size data;
the algorithm verification module 706 is used for calculating the error of each target dimension data relative to the actual dimension data; acquiring the proportion of the number of the target size data with the error within a preset error range in all the target size data; and if the ratio is greater than or equal to a preset ratio threshold value, determining that the preset parking space searching algorithm is the optimal parking space searching algorithm.
Optionally, the algorithm optimizing module 707 is configured to update the n value and/or the preset distance threshold according to a preset update amplitude.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
By adopting the device, the distance data with the increasing amplitude larger than or equal to the preset distance threshold value in the time series distance data can be determined as the increasing jump distance, the distance data with the continuous preset number of increasing data before the distance data exists is determined as the distance data with the decreasing amplitude larger than or equal to the preset distance threshold value, the distance data with the continuous preset number of decreasing data after the distance data exists is determined as the decreasing jump distance, and therefore the target size data of the target parking space is determined according to the increasing jump distance and the decreasing jump distance. Therefore, the target size data of the target parking space determined according to the jump distance is more accurate, the reliability of the detected parking space data is ensured, and the automatic parking path can be more accurately planned.
As shown in fig. 11, the present disclosure further provides a vehicle including the parking space detection apparatus 700 described above.
In another exemplary embodiment, a computer-readable storage medium is also provided, which comprises program instructions, which when executed by a processor, implement the steps of the parking test method described above.
In a further exemplary embodiment, a computer program product is also provided, which contains a computer program that can be executed by a programmable device, the computer program having code sections for performing the parking test method described above when the computer program is executed by the programmable device.
The preferred embodiments of the present disclosure are described in detail with reference to the accompanying drawings, however, the present disclosure is not limited to the specific details of the above embodiments, and various simple modifications may be made to the technical solution of the present disclosure within the technical idea of the present disclosure, and these simple modifications all belong to the protection scope of the present disclosure.
It should be noted that, in the foregoing embodiments, various features described in the above embodiments may be combined in any suitable manner, and in order to avoid unnecessary repetition, various combinations that are possible in the present disclosure are not described again.
In addition, any combination of various embodiments of the present disclosure may be made, and the same should be considered as the disclosure of the present disclosure, as long as it does not depart from the spirit of the present disclosure.
Claims (14)
1. A method of detecting a parking space, the method comprising:
acquiring distance data between a vehicle and a target obstacle according to a preset period, and acquiring time series distance data according to acquisition moments, wherein the target obstacle is an obstacle in a preset range of a target parking space;
determining an increasing jump distance and a decreasing jump distance in the time sequence distance data through a preset vehicle position searching algorithm;
determining target size data of the target parking space according to the incremental jumping distance and the incremental jumping distance;
the preset parking space searching algorithm comprises the following steps:
determining distance data to be processed from the time series distance data in sequence according to the acquisition time;
if the distance data to be processed is nth continuously increasing data and the difference value between the distance data to be processed and the distance data acquired at the previous moment is greater than or equal to a preset distance threshold, determining the distance data acquired at the previous moment as the increasing jump distance;
if the distance data to be processed is nth continuously decreasing distance data, and in the continuously decreasing distance data, the difference value between the first continuously decreasing distance data and the first distance data is greater than or equal to the preset distance threshold value, determining that the first continuously decreasing distance data is the decreasing jump distance, where the first distance data is distance data acquired at a previous time of acquiring the first continuously decreasing distance data, and n is a preset positive integer greater than 1.
2. The method of claim 1, wherein prior to said determining target size data for said target parking space based on said incremental jump distance and said decremental jump distance, said method further comprises:
acquiring a preset detection angle, wherein the preset detection angle is the maximum detection angle of the obstacle detection device for acquiring the distance data;
acquiring a first wheel speed pulse of the vehicle acquired at an increasing moment, a second wheel speed pulse of the vehicle acquired at a decreasing moment, and a first preset distance corresponding to a single wheel speed pulse of the vehicle; the increasing moment is the collecting moment corresponding to the increasing jump distance, and the decreasing moment is the collecting moment corresponding to the decreasing jump distance;
the determining the target size data of the target parking space according to the incremental jump distance and the incremental jump distance comprises:
calculating to obtain a first size according to the increasing jump distance and the preset detection angle, and calculating to obtain a second size according to the decreasing jump distance and the preset detection angle;
calculating to obtain a third size according to the first wheel speed pulse, the second wheel speed pulse and the first preset distance;
and taking the sum of the first size, the second size and the third size as target size data of the target parking space.
3. The method of claim 1 or 2, wherein after said determining target size data for said target parking space based on said incremental jump distance and said decremental jump distance, said method further comprises:
verifying whether the preset parking space searching algorithm is the optimal parking space searching algorithm or not according to the target size data and the actual size data of the target parking space;
and if the preset parking space searching algorithm is not the optimal parking space searching algorithm, optimizing the preset parking space searching algorithm.
4. The method of claim 3, wherein the verifying whether the preset parking space searching algorithm is the optimal parking space searching algorithm according to the target size data and the actual size data of the target parking space comprises:
calculating an error of the target dimension data relative to the actual dimension data;
and if the error is within a preset error range, determining the preset vehicle-position searching algorithm as an optimal vehicle-position searching algorithm.
5. The method of claim 4, wherein before verifying whether the preset parking space-finding algorithm is the optimal parking space-finding algorithm according to the target size data and the actual size data of the target parking space, the method further comprises:
circularly executing the step of acquiring distance data between the vehicle and a target obstacle according to a preset period, acquiring time sequence distance data according to acquisition time, and determining target size data of the target parking space according to the incremental jumping distance and the decremental jumping distance until the number of times of circular execution reaches a preset number of times to obtain a plurality of target size data;
the verifying whether the preset parking space searching algorithm is the optimal parking space searching algorithm or not according to the target size data and the actual size data of the target parking space comprises the following steps:
calculating an error of each of the target dimensional data relative to the actual dimensional data;
acquiring the proportion of the number of the target size data with the error within a preset error range in all the target size data;
and if the ratio is greater than or equal to a preset ratio threshold value, determining that the preset parking space searching algorithm is the optimal parking space searching algorithm.
6. The method of claim 3, wherein the optimizing the predetermined slot-finding algorithm comprises:
and updating the n value and/or the preset distance threshold according to a preset updating amplitude.
7. A parking space detection device, the device comprising:
the upper computer acquisition module is used for acquiring distance data between the vehicle and a target obstacle according to a preset period and acquiring time series distance data according to acquisition moments, wherein the target obstacle is an obstacle in a preset range of a target parking space;
the first determining module is used for determining an increasing jump distance and a decreasing jump distance in the time sequence distance data through a preset vehicle-locating algorithm;
the second determination module is used for determining target size data of the target parking space according to the increasing jump distance and the decreasing jump distance;
the preset parking space searching algorithm comprises the following steps:
determining distance data to be processed from the time series distance data in sequence according to the acquisition time;
if the distance data to be processed is nth continuously increasing data and the difference value between the distance data to be processed and the distance data acquired at the previous moment is greater than or equal to a preset distance threshold, determining the distance data acquired at the previous moment as the increasing jump distance;
if the distance data to be processed is nth continuously decreasing distance data, and in the continuously decreasing distance data, the difference value between the first continuously decreasing distance data and the first distance data is greater than or equal to the preset distance threshold value, determining that the first continuously decreasing distance data is the decreasing jump distance, where the first distance data is distance data acquired at a previous time of acquiring the first continuously decreasing distance data, and n is a preset positive integer greater than 1.
8. The apparatus of claim 7, further comprising:
a first obtaining module, configured to obtain a preset detection angle, where the preset detection angle is a maximum detection angle of an obstacle detection device used for acquiring the distance data;
the second acquisition module is used for acquiring a first wheel speed pulse of the vehicle acquired at an increasing moment, a second wheel speed pulse of the vehicle acquired at a decreasing moment and a first preset distance corresponding to a single wheel speed pulse of the vehicle; the increasing moment is the collecting moment corresponding to the increasing jump distance, and the decreasing moment is the collecting moment corresponding to the decreasing jump distance;
the second determining module is configured to calculate a first size according to the incremental jump distance and the preset detection angle, and calculate a second size according to the incremental jump distance and the preset detection angle; calculating to obtain a third size according to the first wheel speed pulse, the second wheel speed pulse and the first preset distance; and taking the sum of the first size, the second size and the third size as target size data of the target parking space.
9. The apparatus of claim 7 or 8, further comprising:
the algorithm verification module is used for verifying whether the preset parking space searching algorithm is the optimal parking space searching algorithm or not according to the target size data and the actual size data of the target parking space;
and the algorithm optimization module is used for optimizing the preset parking space searching algorithm if the preset parking space searching algorithm is not the optimal parking space searching algorithm.
10. The apparatus of claim 9, wherein the algorithm validation module is configured to calculate an error of the target dimensional data relative to the actual dimensional data; and if the error is within a preset error range, determining the preset vehicle-position searching algorithm as an optimal vehicle-position searching algorithm.
11. The apparatus of claim 10, further comprising:
the cyclic execution module is used for cyclically executing the steps from acquiring distance data of a vehicle and a target obstacle according to a preset period, obtaining time sequence distance data according to acquisition time, determining target size data of the target parking space according to the increasing jump distance and the decreasing jump distance until the number of times of cyclic execution reaches a preset number of times, and obtaining a plurality of target size data;
the algorithm verification module is used for calculating the error of each target size data relative to the actual size data; acquiring the proportion of the number of the target size data with the error within a preset error range in all the target size data; and if the ratio is greater than or equal to a preset ratio threshold value, determining that the preset parking space searching algorithm is the optimal parking space searching algorithm.
12. The apparatus of claim 9, wherein the algorithm optimization module is configured to update the n value and/or the preset distance threshold according to a preset update amplitude.
13. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 6.
14. A vehicle comprising a parking space detection device as claimed in any one of claims 7 to 12.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910809746.XA CN112440980B (en) | 2019-08-29 | 2019-08-29 | Parking space detection method and device, storage medium and vehicle |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910809746.XA CN112440980B (en) | 2019-08-29 | 2019-08-29 | Parking space detection method and device, storage medium and vehicle |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112440980A true CN112440980A (en) | 2021-03-05 |
CN112440980B CN112440980B (en) | 2021-11-12 |
Family
ID=74741562
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910809746.XA Active CN112440980B (en) | 2019-08-29 | 2019-08-29 | Parking space detection method and device, storage medium and vehicle |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112440980B (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1713099A (en) * | 2004-06-23 | 2005-12-28 | 株式会社电装 | Parking assistance system |
CN102483457A (en) * | 2009-08-26 | 2012-05-30 | 三菱电机株式会社 | Parking support device |
US20130021171A1 (en) * | 2011-07-22 | 2013-01-24 | Automotive Research & Test Center | Parking space detection device and method thereof |
US20150185319A1 (en) * | 2012-07-06 | 2015-07-02 | Denso Corporation | Adjacent vehicle detection device |
CN105467394A (en) * | 2014-08-27 | 2016-04-06 | 现代摩比斯株式会社 | Device for detecting parking space and method thereof |
CN105608924A (en) * | 2016-02-18 | 2016-05-25 | 广州橙行智动汽车科技有限公司 | Parking space detection method based on ultrasonic radar |
CN109581389A (en) * | 2017-09-28 | 2019-04-05 | 上海汽车集团股份有限公司 | A kind of method and apparatus identifying parking space boundary |
CN110095769A (en) * | 2018-01-29 | 2019-08-06 | 杭州海康汽车技术有限公司 | A kind of method for detecting parking stalls, device and electronic equipment |
-
2019
- 2019-08-29 CN CN201910809746.XA patent/CN112440980B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1713099A (en) * | 2004-06-23 | 2005-12-28 | 株式会社电装 | Parking assistance system |
CN102483457A (en) * | 2009-08-26 | 2012-05-30 | 三菱电机株式会社 | Parking support device |
US20130021171A1 (en) * | 2011-07-22 | 2013-01-24 | Automotive Research & Test Center | Parking space detection device and method thereof |
US20150185319A1 (en) * | 2012-07-06 | 2015-07-02 | Denso Corporation | Adjacent vehicle detection device |
CN105467394A (en) * | 2014-08-27 | 2016-04-06 | 现代摩比斯株式会社 | Device for detecting parking space and method thereof |
CN105608924A (en) * | 2016-02-18 | 2016-05-25 | 广州橙行智动汽车科技有限公司 | Parking space detection method based on ultrasonic radar |
CN109581389A (en) * | 2017-09-28 | 2019-04-05 | 上海汽车集团股份有限公司 | A kind of method and apparatus identifying parking space boundary |
CN110095769A (en) * | 2018-01-29 | 2019-08-06 | 杭州海康汽车技术有限公司 | A kind of method for detecting parking stalls, device and electronic equipment |
Non-Patent Citations (1)
Title |
---|
苏松恺: "基于超声波传感器的车位边缘误差分析及补偿", 《上海汽车》 * |
Also Published As
Publication number | Publication date |
---|---|
CN112440980B (en) | 2021-11-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110632921B (en) | Robot path planning method and device, electronic equipment and storage medium | |
JP7059888B2 (en) | Assistance control system | |
CN113495272B (en) | Method for generating dynamic occupied grid | |
CN109795477A (en) | Eliminate the method, apparatus and storage medium of stable state lateral deviation | |
CN110550030B (en) | Lane changing control method and device for unmanned vehicle, computer equipment and storage medium | |
CN112068558A (en) | Shuttle vehicle walking positioning control method | |
US11080544B1 (en) | Method and device for calibrating pitch of camera on vehicle and method and device for continual learning of vanishing point estimation model to be used for calibrating the pitch | |
JP2019028665A (en) | Calibration apparatus and method for on-vehicle camera | |
GB2550485A (en) | Enhanced vehicle operation | |
US11922701B2 (en) | Method and system for creating a semantic representation of the environment of a vehicle | |
CN112440980B (en) | Parking space detection method and device, storage medium and vehicle | |
JP2015069287A (en) | Own vehicle position recognition device | |
JP5055691B2 (en) | Front object detection apparatus and front object detection method | |
JP5490633B2 (en) | Vehicle traveling path estimation device | |
CN116642481A (en) | Parking lot map generation method, device, storage medium and processor | |
KR102360466B1 (en) | Map matching method using reverse tracking map matching | |
JP4506163B2 (en) | Front object detection apparatus and front object detection method | |
US20050177336A1 (en) | Method for identifying object constellations using distance signals | |
KR101977479B1 (en) | Method and system for detecting location of moving vehicle | |
JP7344744B2 (en) | Roadside edge detection method and roadside edge detection device | |
JP7344743B2 (en) | Occupancy map creation method and occupancy map creation device | |
CN111091148B (en) | Vehicle-mounted radar target tracking method and device based on target prior information | |
KR20130136078A (en) | Appartus and method for controlling aotomatic parking | |
CN114549632A (en) | Vehicle positioning method and device | |
CN111025300B (en) | Method and device for measuring length of parking space |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |