CN117475669A - Parking space identification method and device - Google Patents
Parking space identification method and device Download PDFInfo
- Publication number
- CN117475669A CN117475669A CN202311566947.4A CN202311566947A CN117475669A CN 117475669 A CN117475669 A CN 117475669A CN 202311566947 A CN202311566947 A CN 202311566947A CN 117475669 A CN117475669 A CN 117475669A
- Authority
- CN
- China
- Prior art keywords
- value
- distance
- parking space
- target
- distance measurement
- 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 73
- 238000001914 filtration Methods 0.000 claims abstract description 27
- 230000008569 process Effects 0.000 claims abstract description 20
- 238000005259 measurement Methods 0.000 claims description 132
- 238000001514 detection method Methods 0.000 claims description 27
- 230000000630 rising effect Effects 0.000 claims description 23
- 238000003708 edge detection Methods 0.000 claims description 21
- 238000012545 processing Methods 0.000 claims description 7
- 238000012417 linear regression Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 9
- 230000001419 dependent effect Effects 0.000 description 6
- 230000009471 action Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000002592 echocardiography Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
- G08G1/145—Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas
- G08G1/146—Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas where the parking area is a limited parking space, e.g. parking garage, restricted space
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/04—Detecting movement of traffic to be counted or controlled using optical or ultrasonic detectors
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
- G08G1/149—Traffic control systems for road vehicles indicating individual free spaces in parking areas coupled to means for restricting the access to the parking space, e.g. authorization, access barriers, indicative lights
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Measurement Of Velocity Or Position Using Acoustic Or Ultrasonic Waves (AREA)
Abstract
The invention provides a parking space identification method and a device, which relate to the technical field of parking space identification, and the method comprises the following steps: in the process of detecting the obstacle distance of a vehicle aiming at a target parking space through an ultrasonic radar, filtering all distance measured values detected by the ultrasonic radar based on a weighted recursive average filtering method to obtain filtered data; the target parking space is a parking space in which obstacle vehicles are parked in the parking spaces at the two sides; and carrying out parking space identification by using the filtered data. The method and the device can improve the accuracy of the parking space identification result.
Description
Technical Field
The invention relates to the technical field of parking space recognition, in particular to a parking space recognition method and device.
Background
In a scene that an intelligent driving vehicle searches for a parking space in a parking lot, the identification of the parking space is a precondition for realizing automatic parking. Since the ultrasonic radar can detect the position, distance, and speed of a target object by transmitting an ultrasonic signal, parking space recognition can be performed using the ultrasonic radar.
The propagation speed of the ultrasonic signal is affected by the ambient temperature, so that the accuracy of the parking space recognition result is reduced, and therefore, the temperature compensation module is added in the parking space recognition device for intelligently driving the vehicle to improve the accuracy of the parking space recognition result, but noise data is introduced into the detection data of the ultrasonic radar, so that the instability and inaccuracy of the detection data are increased, and the accuracy of the parking space recognition result is lower.
Based on the above, how to improve the accuracy of the parking space recognition result becomes a technical problem to be solved urgently.
Disclosure of Invention
The invention provides a parking space identification method and device for solving the problem of low accuracy of a parking space identification result in the prior art.
The technical scheme of the invention is as follows:
the invention provides a parking space identification method, which comprises the following steps:
in the process of detecting obstacle distance by an ultrasonic radar for a target parking space, filtering all distance measured values detected by the ultrasonic radar based on a weighted recursive average filtering method to obtain filtered data; the target parking spaces are parking spaces in which obstacle vehicles are parked in the parking spaces at the two sides of the target parking space;
and carrying out parking space identification by using the filtered data.
Optionally, filtering all distance measurement values detected by the ultrasonic radar based on a weighted recursive average filtering method specifically includes:
initializing preset parameters, wherein the preset parameters comprise an initial distance estimated value and initial weights;
when the distance measured value detected by the ultrasonic radar is obtained each time, the following steps are executed for the distance measured value until the ultrasonic radar finishes the current obstacle distance detection:
when the distance measured value is the first distance measured value detected by the ultrasonic radar in the current obstacle distance detection, calculating a distance estimated value corresponding to the distance measured value according to the distance measured value, the initial distance estimated value and the initial weight;
and when the distance measured value is not the first distance measured value detected by the ultrasonic radar in the current obstacle distance detection, calculating a distance estimated value corresponding to the distance measured value according to the distance measured value and the distance estimated value corresponding to the last distance measured value of the distance measured value.
Optionally, calculating the distance estimation value corresponding to the distance measurement value according to the distance measurement value and the distance estimation value corresponding to the distance measurement value last to the distance measurement value specifically includes:
determining a target weight according to the distance measurement value and the difference value between the distance measurement value and the distance estimation value corresponding to the last distance measurement value of the distance measurement value;
multiplying the target weight by a distance estimated value corresponding to the last distance measurement value of the distance measurement values to obtain a first calculated value;
multiplying the distance measurement value by the difference between 1 and the target weight to obtain a second calculated value;
and adding the second calculated value to the first calculated value to obtain a distance estimated value corresponding to the distance measured value.
Optionally, determining the target weight according to the difference between the distance measurement value and the distance estimation value corresponding to the last distance measurement value of the distance measurement value specifically includes:
calculating the absolute value of the difference between the distance measurement value and the distance estimation value corresponding to the last distance measurement value of the distance measurement value;
judging whether the absolute value of the difference value is larger than a preset threshold value or not;
if the absolute value of the difference value is larger than a preset threshold value, enabling the target weight to be equal to one value in a first preset value range;
if the absolute value of the difference value is not greater than a preset threshold value, enabling the target weight to be equal to one value in a second preset value range; any one of the first preset numerical value range is larger than any one of the second preset numerical value range.
Optionally, the target weight is made to be equal to one value in a first preset value range, which specifically includes:
enabling the target weight to be equal to a first preset numerical value, wherein the first preset numerical value is located in the first preset numerical value range;
the target weight is enabled to be equal to one value in a second preset value range, and the method specifically comprises the following steps:
and enabling the target weight to be equal to a second preset numerical value, wherein the second preset numerical value is located in the second preset numerical value range.
Optionally, the target weight is made to be equal to one value in a first preset value range, which specifically includes:
randomly selecting a value from the first preset value range as the target weight;
the target weight is enabled to be equal to one value in a second preset value range, and the method specifically comprises the following steps:
randomly selecting a value from the second preset value range as the target weight.
Optionally, in the process that the vehicle detects the obstacle distance by the ultrasonic radar for the target parking space, the vehicle keeps a constant-speed running state;
the method for identifying the parking space by using the filtered data specifically comprises the following steps:
performing jump edge detection by using the filtered data to obtain a jump edge detection result; the jump edge detection result at least comprises a middle edge, and at least one of the rising edge and the falling edge; the middle edge is an edge between the end point of the rising edge and the start point of the falling edge;
and calculating the length and the width of the target parking space according to the jump edge detection result.
Optionally, calculating the length and width of the target parking space according to the jump edge detection result specifically includes:
calculating the vertical distance from the starting point of the rising edge to the middle edge to obtain the width of the target parking space;
multiplying the speed of the vehicle by the detection duration corresponding to the middle edge to obtain a first length;
dividing the width by the slope of the rising edge to obtain a second length;
and calculating the sum of the first length and the second length which is 2 times of the first length to obtain the length of the target parking space.
Optionally, determining the rising edge or the falling edge using the filtered data specifically includes:
determining all distance measurement values corresponding to a target edge as target distance measurement values, wherein the target edge is the rising edge or the falling edge;
the filtered data is used to determine a slope of the target edge based on a linear regression model.
The invention also provides a parking space recognition device, which comprises:
the data acquisition module is used for carrying out filtering processing on all distance measured values detected by the ultrasonic radar based on a weighted recursive average filtering method in the process of carrying out obstacle distance detection on a target parking space by the vehicle through the ultrasonic radar to obtain filtered data; the target parking spaces are parking spaces in which obstacle vehicles are parked in the parking spaces at the two sides of the target parking space;
and the parking space identification module is used for identifying the parking space by using the filtered data.
The invention adopts the technical scheme and has the following beneficial effects:
a parking space recognition method, comprising: in the process of detecting the obstacle distance of a vehicle aiming at a target parking space through an ultrasonic radar, filtering all distance measured values detected by the ultrasonic radar based on a weighted recursive average filtering method to obtain filtered data; the target parking space is a parking space in which obstacle vehicles are parked in the parking spaces at the two sides; and carrying out parking space identification by using the filtered data. Based on the method, the filtering processing is carried out on all distance measurement values detected by the ultrasonic radar based on the weighted recursive average filtering method, so that the stability and the accuracy of detection data of the ultrasonic radar can be improved, and the accuracy of a parking space recognition result can be improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of the theoretical change of distance measurement values during parking space recognition by using an ultrasonic radar;
FIG. 2 is a schematic view corresponding to FIG. 1 showing actual changes in distance measurement values during parking space recognition by ultrasonic radar;
fig. 3 is a schematic flow chart of a parking space recognition method according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a calculation principle of each side length of a parking space corresponding to fig. 2 according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a target edge determination principle provided by an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a parking space recognition device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In order to make the technical scheme of the present invention easier to understand, some technical terms possibly related to the technical scheme of the present invention are explained below.
Ultrasonic radar: a radar system for detecting and measuring the position, distance and velocity of a target object using ultrasonic technology acquires information about the target object by transmitting ultrasonic signals and receiving echoes thereof.
Wheel speed sensor: an apparatus for measuring the rotational speed of each wheel of a vehicle is capable of monitoring the movement of the vehicle and transmitting speed information of the vehicle to an electronic control system of the vehicle.
Beam-emittance: sound waves emitted from a sound source propagate in a certain direction (the other direction is very weak), and are called beam emission, and the quality of the beam-emittance of ultrasonic waves is generally measured by the size of a divergence angle.
Linear regression: a statistical method for establishing a relationship between a dependent variable and one or more independent variables is generally used to predict or interpret the value of the dependent variable.
Weighted recursive average filtering: from the previous measurement, the next measurement is estimated by a weighted calculation.
In a scene that the intelligent driving vehicle searches for a parking space in a parking lot, the parking space identification is a first link for realizing automatic parking, is a key for success or failure of parking, and can perform next operations such as parking path planning only after detecting a proper parking space. Since the ultrasonic radar can detect the position, distance, and speed of a target object by transmitting an ultrasonic signal, parking space recognition can be performed using the ultrasonic radar. Fig. 1 is a schematic diagram of a theoretical change of distance measurement values when parking space recognition is performed by using an ultrasonic radar. As shown in fig. 1, the number 1 obstacle vehicles and the number 2 obstacle vehicles are respectively parked in the parking spaces at the two sides of the target parking space. When the host vehicle starts parking, it runs at a constant speed V, wherein the running speed of the vehicle can be detected by a wheel speed sensor in the vehicle. When the target ultrasonic radar of the vehicle detects the tail of the No. 1 obstacle vehicle during the running process of the vehicle, the distance measured value at the moment is recorded as d1, and the target ultrasonic radar can be an ultrasonic radar arranged on the right front side of the vehicle; when the vehicle drives away from the head of the No. 1 obstacle vehicle, the corresponding distance measurement value jumps, the distance measurement value is recorded as d2, and meanwhile, the vehicle starts to time; when the target ultrasonic radar detects the tail of the No. 2 obstacle vehicle, the corresponding distance measurement value jumps again, and meanwhile, the vehicle stops timing, and the timing duration of the vehicle is recorded as delta t. Thus, it can be determined that the length L of the target parking space is equal to the vehicle speed V times the timer period Δt, i.e., l=v×Δt, and that the width W of the target parking space is equal to the distance measurement value jump amplitude, i.e., w=d2-d 1.
However, in the practical application process, for some reasons, the distance measurement value of the target ultrasonic radar often shakes, even is abnormal, so that the whole distance measurement value curve presents a saw tooth shape. For example, the propagation speed of the ultrasonic signal may be affected by the ambient temperature, so that the accuracy of the parking space recognition result is reduced, and therefore, a temperature compensation module is added to the parking space recognition device for intelligently driving the vehicle to improve the accuracy of the parking space recognition result, but at the same time, noise data is introduced into the detection data of the ultrasonic radar, so that the instability and inaccuracy of the detection data are increased, and further, the accuracy of the parking space recognition result is lower. Fig. 2 is a schematic diagram showing actual changes in distance measurement values at the time of parking space recognition by the ultrasonic radar corresponding to fig. 1. As shown in fig. 2, the actual curve 21 of the distance measurement d exhibits a saw-tooth shape.
Therefore, in order to improve the accuracy of the parking space identification result, the invention provides a parking space identification method and device. The technical scheme of the invention is described in detail below with reference to the accompanying drawings.
Fig. 3 is a flow chart of a parking space recognition method according to an embodiment of the present invention. As shown in fig. 3, the present process includes:
step 301: in the process of detecting the obstacle distance of a vehicle aiming at a target parking space through an ultrasonic radar, filtering all distance measured values detected by the ultrasonic radar based on a weighted recursive average filtering method to obtain filtered data; the target parking space is a parking space in which obstacle vehicles are arranged in the parking spaces at the two sides of the target parking space.
Step 302: and carrying out parking space identification by using the filtered data.
According to the technical scheme, the filtering processing is carried out on all distance measurement values detected by the ultrasonic radar based on the weighted recursive average filtering method, so that the stability, accuracy and anti-interference performance of detection data of the ultrasonic radar can be improved, the influence of abnormal values in all the distance measurement values on a parking space recognition result is reduced or even eliminated, and the accuracy of the parking space recognition result can be improved.
In the embodiment of the invention, filtering processing is performed on all distance measurement values detected by an ultrasonic radar based on a weighted recursive average filtering method, which specifically comprises the following steps:
(1) Initializing preset parameters, wherein the preset parameters comprise an initial distance estimated value and an initial weight.
Specifically, the values of the initial distance estimation value and the initial weight may be set by those skilled in the art according to actual needs, for example, the initial distance estimation value and the initial weight are set to be equal to 0, and in this case, when the computer initializes the preset parameters, the values of the initial distance estimation value and the initial weight are made to be equal to 0.
(2) When the distance measured value detected by the ultrasonic radar is obtained each time, the following steps are executed for the distance measured value until the ultrasonic radar finishes the detection of the distance of the obstacle:
(a) When the distance measurement value is the first distance measurement value detected by the ultrasonic radar in the obstacle distance detection, calculating a distance estimation value corresponding to the distance measurement value according to the distance measurement value, the initial distance estimation value and the initial weight.
Specifically, for any distance measurement value, the calculation formula of the distance estimation value is as follows:
E new ＝E old * α+distance measurement (1- α.). The term (1)
Wherein E is new Distance estimation value, E, being a distance measurement value old And alpha is the weight corresponding to the distance measurement value.
Therefore, for the first distance measurement value D1 detected by the ultrasonic radar in the current obstacle distance detection, E is calculated when the distance estimation value old And α takes initialization parameters, namely:
distance estimation value of D1 = initial distance estimation value × initial weight + D1 × (1- α).
When the initial distance estimation value and the initial weight value are equal to 0, the distance estimation value of D1 is equal to itself, namely: distance estimate of D1 = D1.
(b) When the distance measurement value is not the first distance measurement value detected by the ultrasonic radar in the current obstacle distance detection, calculating a distance estimation value corresponding to the distance measurement value according to the distance measurement value and the distance estimation value corresponding to the last distance measurement value of the distance measurement value.
In the embodiment of the present invention, based on formula (1), when the distance measurement value is not the first distance measurement value detected by the ultrasonic radar in the current obstacle distance detection, calculating a distance estimation value corresponding to the distance measurement value according to the distance measurement value and a distance estimation value corresponding to the last distance measurement value of the distance measurement value, may specifically include:
(1) And determining the target weight according to the difference value between the distance measurement value and the distance estimation value corresponding to the last distance measurement value of the distance measurement value.
Specifically, when the phase difference between the distance measurement value obtained at this time and the distance estimation value corresponding to the last distance measurement value is larger, the jitter of the distance measurement value obtained at this time is larger, so in order to reduce the jitter of the distance measurement value, α may be made to take a larger value, whereas when the phase difference between the distance measurement value obtained at this time and the distance estimation value corresponding to the last distance measurement value is smaller, α may be made to take a smaller value.
In a specific example, the value range of α may be (0, 1).
(2) Multiplying the distance estimated value corresponding to the last distance measurement value of the distance measurement value by the target weight to obtain a first calculated value, namely:
first calculated value = distance estimate value corresponding to the last distance measurement value of the distance measurement value.
It can be seen that the first calculated value is E in the above formula (1) old * Alpha part.
(3) Multiplying the distance measurement by the difference between 1 and the target weight to obtain a second calculated value, namely:
second calculation = distance measurement (1-target weight).
It can be seen that the second calculated value is the distance measurement value (1- α) in the above formula (1).
(4) And adding the second calculated value to the first calculated value to obtain a distance estimated value corresponding to the distance measured value.
In the embodiment of the present invention, determining the target weight according to the difference between the distance measurement value and the distance estimation value corresponding to the last distance measurement value of the distance measurement value may specifically include:
(1) And calculating the absolute value delta S of the difference between the distance measurement value and the distance estimation value corresponding to the last distance measurement value of the distance measurement value.
(2) And judging whether the absolute value delta S of the difference value is larger than a preset threshold value T.
Specifically, the preset threshold T may be freely set by a person skilled in the art according to practical situations, and the embodiment of the present invention is not specifically limited herein.
(3) If the absolute value DeltaS of the difference value is larger than a preset threshold value T, enabling the target weight to be equal to one value in a first preset value range; and if the absolute value DeltaS of the difference value is not greater than the preset threshold value T, enabling the target weight to be equal to one value in a second preset value range; any one of the first predetermined range of values is greater than any one of the second predetermined range of values.
In a specific example, the first preset value range is (0.8,1), and the second preset value range is (0,0.2), namely:
in the embodiment of the present invention, when the absolute value Δs of the difference is greater than the preset threshold T, the target weight is made to be equal to a value in the first preset value range, which specifically may include:
the target weight is equal to a first preset value, and the first preset value is located in a first preset value range.
And when the absolute value Δs of the difference is not greater than the preset threshold T, making the target weight equal to one value in the second preset value range, specifically may include:
the target weight is equal to a second preset value, and the second preset value is located in a second preset value range.
Specifically, the first preset value and the second preset value may be preset by those skilled in the art according to the actual situation, for example, the first preset value is set to 0.9, and the second preset value is set to 0.1, in which case, when the computer determines that the absolute value Δs of the difference is greater than the preset threshold T, the target weight is set to 0.9, and when the computer determines that the absolute value Δs of the difference is not greater than the preset threshold T, the target weight is set to 0.1.
In the embodiment of the present invention, when the absolute value Δs of the difference is greater than the preset threshold T, the target weight is made to be equal to a value in the first preset value range, which specifically may include:
randomly selecting a value from a first preset value range as a target weight.
And when the absolute value Δs of the difference is not greater than the preset threshold T, making the target weight equal to one value in the second preset value range, specifically may include:
randomly selecting a value from the second preset value range as a target weight.
Specifically, when the computer determines that the absolute value Δs of the difference is greater than the preset threshold T, a value is randomly selected from the first preset numerical range as the target weight, and when the computer determines that the absolute value Δs of the difference is not greater than the preset threshold T, a value is randomly selected from the second preset numerical range as the target weight.
Referring to fig. 2, in the practical application process, the inventor finds that, because the ultrasonic radar has a certain divergence angle when transmitting data, when the vehicle starts to drive away from the head of the obstacle No. 1 vehicle, the corresponding distance measurement value does not jump instantaneously but gradually increases until the vehicle becomes stable, and similarly, when the target ultrasonic radar just detects the tail of the obstacle No. 2 vehicle, the corresponding distance measurement value does not jump instantaneously but gradually decreases until the vehicle becomes stable. The length of the parking space calculated by the current parking space recognition method is smaller than the actual length of the parking space, so that the accuracy of the parking space recognition result is lower.
Based on this, fig. 4 is a schematic diagram of a calculation principle of each side length of the parking space corresponding to fig. 2 according to an embodiment of the present invention. Step 302 of the present invention is described in detail below in conjunction with FIG. 4: and carrying out parking space identification by using the filtered data.
In the embodiment of the invention, the vehicle keeps a constant-speed running state in the process of detecting the obstacle distance by the ultrasonic radar aiming at the target parking space.
Step 302: the parking space identification using the filtered data may specifically include:
(1) Performing jump edge detection by using the filtered data to obtain a jump edge detection result; the jump edge detection result at least comprises an intermediate edge EF, and at least one of a rising edge BE and a falling edge FG; the intermediate edge EF is the edge between the end of the rising edge BE (i.e., point E) and the start of the falling edge FG (i.e., point F).
The distance measurement value corresponding to the line segment AB and the line segment GH is d1, and the distance measurement value corresponding to the line segment EF is d2.
(2) And calculating the length and the width of the target parking space according to the jump edge detection result.
In the embodiment of the present invention, calculating the length and width of the target parking space according to the jump edge detection result may specifically include:
(1) And calculating the vertical distance from the starting point B of the rising edge BE to the middle edge EF to obtain the width W of the target parking space.
Specifically, the vertical distance from point B to the intermediate edge EF is equal to d2-d1, and thus the width W of the target parking space is equal to the difference of d2 minus d1, i.e., w=d2-d 1.
(2) The detection duration corresponding to the intermediate edge EF is multiplied by the speed V of the vehicle to obtain a first length L1.
Specifically, referring to fig. 1 and 4, during the running of the vehicle, from when the vehicle starts to drive off the head of the obstacle 1 vehicle, when the distance measurement value increases to d2, the time at which t1 is recorded, that is, the time corresponding to the point E is t1, and next, when the distance measurement value starts to decrease from d2 to d1, the time at which t2 is recorded, that is, the time corresponding to the point F is t2. Thus, it can be derived that l1= (t 2-t 1) ×v.
(3) Dividing the width by the slope K of the rising edge gives a second length L2, i.e. l2= (d 2-d 1)/K.
It should BE noted that, the line segments BE and FG have symmetry, that is, the sum of the slope of the line segment BE and the slope of the line segment FG is 0, so that the compensation length L2 corresponding to the line segment BE is equal to the compensation length L3 corresponding to the line segment FG, and further, in the practical application process, one of the two is calculated, while the embodiment of the invention is described by calculating the compensation length L2 corresponding to the line segment BE, a person skilled in the art may select to calculate the compensation length L3 corresponding to the line segment FG according to the practical requirement, and calculate the length of the target parking space according to L3, or calculate that the compensation length L2 corresponding to the line segment BE is equal to the compensation length L3 corresponding to the line segment FG, and calculate the length of the target parking space according to L2 and L3.
(4) Calculating the sum of the first length L1 and the second length L2 which is 2 times to obtain the length L of the target parking space, namely: l=l1+l2.
In the embodiment of the present invention, determining the rising edge BE or the falling edge FG by using the filtered data may specifically include:
(1) And determining all the distance measured values corresponding to the target edge as target distance measured values, wherein the target edge is a rising edge BE or a falling edge FG.
(2) The slope of the target edge is determined using the filtered data based on a linear regression model.
Fig. 5 is a schematic diagram of a target edge determination principle according to an embodiment of the present invention. As shown in fig. 5, the scattered points in the graph are target distance measurement values, and the best-fit straight line BE of the scattered points (i.e., all target distance measurement values) can BE obtained based on a linear regression model, which is generally expressed as: y=kx+b. Where y is a dependent variable (i.e., the variable to be predicted); x is an independent variable (i.e., a variable used to predict the dependent variable); k is a slope, which represents the degree of influence of the independent variable x on the dependent variable y; b is the intercept, representing the value of the dependent variable y when the argument x is equal to zero.
In the process of obtaining the best-fit straight line BE, the slope K of the straight line BE is determined using the least square method, that is:
where n is the total number of target distance measurements, (x) i ,y i ) Is the coordinates of the target distance measurement.
In summary, according to the embodiment of the invention, the compensation length L2 corresponding to the line segment BE and the compensation length L3 corresponding to the line segment FG are added into the calculation result of the length L of the target parking space, so that the accuracy of the identification result of the parking space can BE further improved.
Based on a general inventive concept, the invention also provides a parking space recognition device. Fig. 6 is a schematic structural diagram of a parking space recognition device according to an embodiment of the present invention. As shown in fig. 6, the present apparatus includes:
the data acquisition module 61 is configured to perform filtering processing on all distance measurement values detected by the ultrasonic radar based on a weighted recursive average filtering method in a process that the vehicle detects the obstacle distance by the ultrasonic radar for the target parking space, so as to obtain filtered data; the target parking space is a parking space in which obstacle vehicles are arranged in the parking spaces at the two sides of the target parking space.
The parking space identification module 62 is configured to use the filtered data to identify a parking space.
Optionally, the data acquisition module 61 may specifically include:
the initialization unit is used for initializing preset parameters, wherein the preset parameters comprise an initial distance estimated value and an initial weight.
The distance estimation unit is used for executing the following steps aiming at the distance measured value when the distance measured value detected by the ultrasonic radar is obtained each time until the ultrasonic radar finishes the distance detection of the obstacle:
(1) When the distance measurement value is the first distance measurement value detected by the ultrasonic radar in the obstacle distance detection, calculating a distance estimation value corresponding to the distance measurement value according to the distance measurement value, the initial distance estimation value and the initial weight.
(2) When the distance measurement value is not the first distance measurement value detected by the ultrasonic radar in the current obstacle distance detection, calculating a distance estimation value corresponding to the distance measurement value according to the distance measurement value and the distance estimation value corresponding to the last distance measurement value of the distance measurement value.
Optionally, the distance estimation unit includes:
and the target weight determining subunit is used for determining the target weight according to the distance measurement value and the difference value between the distance measurement value and the distance estimation value corresponding to the last distance measurement value of the distance measurement value.
And the first calculating subunit is used for multiplying the distance estimated value corresponding to the last distance measurement value of the distance measurement value by the target weight to obtain a first calculated value.
And the second calculating subunit is used for multiplying the distance measurement value by the difference between 1 and the target weight to obtain a second calculated value.
And the third calculation subunit is used for adding the second calculation value to the first calculation value to obtain a distance estimation value corresponding to the distance measurement value.
Optionally, the determining the target weight subunit may be specifically configured to:
(1) And calculating the absolute value of the difference between the distance measurement value and the distance estimation value corresponding to the last distance measurement value of the distance measurement value.
(2) And judging whether the absolute value of the difference value is larger than a preset threshold value.
(3) If the absolute value of the difference is greater than the preset threshold, the target weight is made to be equal to one value in the first preset value range.
(4) If the absolute value of the difference value is not greater than the preset threshold value, enabling the target weight to be equal to one value in a second preset value range; any one of the first predetermined range of values is greater than any one of the second predetermined range of values.
Wherein, the target weight is equal to one value in the first preset value range, which specifically may include:
the target weight is equal to a first preset value, and the first preset value is located in a first preset value range.
The making the target weight equal to one value in the second preset value range may specifically include:
the target weight is equal to a second preset value, and the second preset value is located in a second preset value range.
Secondly, making the target weight equal to one value in the first preset value range, and specifically further including:
randomly selecting a value from a first preset value range as a target weight.
The making the target weight equal to one value in the second preset value range may specifically further include:
randomly selecting a value from the second preset value range as a target weight.
Optionally, in the process that the vehicle detects the obstacle distance by the ultrasonic radar for the target parking space, the vehicle keeps a constant-speed running state.
Parking space identification module 62 may specifically include:
the jump edge detection unit is used for carrying out jump edge detection by using the filtered data to obtain a jump edge detection result; the jump edge detection result at least comprises a middle edge, and at least one of a rising edge and a falling edge; the middle edge is the edge between the end of the rising edge and the start of the falling edge.
And the parking space identification unit is used for calculating the length and the width of the target parking space according to the jump edge detection result.
Optionally, the parking space identifying unit may specifically be configured to:
(1) And calculating the vertical distance from the starting point of the rising edge to the middle edge to obtain the width of the target parking space.
(2) And multiplying the speed of the vehicle by the detection duration corresponding to the middle edge to obtain a first length.
(3) Dividing the width by the slope of the rising edge to obtain a second length.
(4) And calculating the sum of the first length and the second length which is 2 times of the first length to obtain the length of the target parking space.
Optionally, the jump edge detection unit may be specifically configured to:
(1) And determining all the distance measured values corresponding to the target edge as target distance measured values, wherein the target edge is a rising edge or a falling edge.
(2) The slope of the target edge is determined using the filtered data based on a linear regression model.
For the foregoing method embodiments, for simplicity of explanation, the methodologies are shown as a series of acts, but one of ordinary skill in the art will appreciate that the present invention is not limited by the order of acts, as some steps may, in accordance with the present invention, occur in other orders or concurrently. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required for the present invention.
It should be noted that, in the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described as different from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other. For the apparatus class embodiments, the description is relatively simple as it is substantially similar to the method embodiments, and reference is made to the description of the method embodiments for relevant points.
The steps in the method of each embodiment of the invention can be sequentially adjusted, combined and deleted according to actual needs, and the technical features described in each embodiment can be replaced or combined.
The modules and the submodules in the device and the terminal of the embodiments of the invention can be combined, divided and deleted according to actual needs.
In the embodiments provided in the present invention, it should be understood that the disclosed terminal, apparatus and method may be implemented in other manners. For example, the above-described terminal embodiments are merely illustrative, and for example, the division of modules or sub-modules is merely a logical function division, and there may be other manners of division in actual implementation, for example, multiple sub-modules or modules may be combined or integrated into another module, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or modules, which may be in electrical, mechanical, or other forms.
The modules or sub-modules illustrated as separate components may or may not be physically separate, and components that are modules or sub-modules may or may not be physical modules or sub-modules, i.e., may be located in one place, or may be distributed over multiple network modules or sub-modules. Some or all of the modules or sub-modules may be selected according to actual needs to achieve the purpose of the embodiment.
In addition, each functional module or sub-module in the embodiments of the present invention may be integrated in one processing module, or each module or sub-module may exist alone physically, or two or more modules or sub-modules may be integrated in one module. The integrated modules or sub-modules may be implemented in hardware or in software functional modules or sub-modules.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of functionality in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software unit executed by a processor, or in a combination of the two. The software elements may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A parking space recognition method, characterized by comprising:
in the process of detecting obstacle distance by an ultrasonic radar for a target parking space, filtering all distance measured values detected by the ultrasonic radar based on a weighted recursive average filtering method to obtain filtered data; the target parking spaces are parking spaces in which obstacle vehicles are parked in the parking spaces at the two sides of the target parking space;
and carrying out parking space identification by using the filtered data.
2. The parking space recognition method according to claim 1, wherein filtering all distance measurement values detected by the ultrasonic radar based on a weighted recursive average filtering method, specifically comprises:
initializing preset parameters, wherein the preset parameters comprise an initial distance estimated value and initial weights;
when the distance measured value detected by the ultrasonic radar is obtained each time, the following steps are executed for the distance measured value until the ultrasonic radar finishes the current obstacle distance detection:
when the distance measured value is the first distance measured value detected by the ultrasonic radar in the current obstacle distance detection, calculating a distance estimated value corresponding to the distance measured value according to the distance measured value, the initial distance estimated value and the initial weight;
and when the distance measured value is not the first distance measured value detected by the ultrasonic radar in the current obstacle distance detection, calculating a distance estimated value corresponding to the distance measured value according to the distance measured value and the distance estimated value corresponding to the last distance measured value of the distance measured value.
3. The parking space recognition method according to claim 2, wherein calculating the distance estimation value corresponding to the distance measurement value according to the distance measurement value and the distance estimation value corresponding to the distance measurement value last to the distance measurement value, specifically comprises:
determining a target weight according to the distance measurement value and the difference value between the distance measurement value and the distance estimation value corresponding to the last distance measurement value of the distance measurement value;
multiplying the target weight by a distance estimated value corresponding to the last distance measurement value of the distance measurement values to obtain a first calculated value;
multiplying the distance measurement value by the difference between 1 and the target weight to obtain a second calculated value;
and adding the second calculated value to the first calculated value to obtain a distance estimated value corresponding to the distance measured value.
4. A parking space recognition method according to claim 3, wherein determining the target weight based on the difference between the distance measurement value and the distance estimation value corresponding to the last distance measurement value of the distance measurement value, specifically comprises:
calculating the absolute value of the difference between the distance measurement value and the distance estimation value corresponding to the last distance measurement value of the distance measurement value;
judging whether the absolute value of the difference value is larger than a preset threshold value or not;
if the absolute value of the difference value is larger than a preset threshold value, enabling the target weight to be equal to one value in a first preset value range;
if the absolute value of the difference value is not greater than a preset threshold value, enabling the target weight to be equal to one value in a second preset value range; any one of the first preset numerical value range is larger than any one of the second preset numerical value range.
5. The parking space recognition method according to claim 4, wherein the target weight is made equal to one value in a first preset value range, specifically comprising:
enabling the target weight to be equal to a first preset numerical value, wherein the first preset numerical value is located in the first preset numerical value range;
the target weight is enabled to be equal to one value in a second preset value range, and the method specifically comprises the following steps:
and enabling the target weight to be equal to a second preset numerical value, wherein the second preset numerical value is located in the second preset numerical value range.
6. The parking space recognition method according to claim 4, wherein the target weight is made equal to one value in a first preset value range, specifically comprising:
randomly selecting a value from the first preset value range as the target weight;
the target weight is enabled to be equal to one value in a second preset value range, and the method specifically comprises the following steps:
randomly selecting a value from the second preset value range as the target weight.
7. The parking space recognition method according to claim 1, wherein the vehicle maintains a constant speed driving state during obstacle distance detection by an ultrasonic radar with respect to a target parking space;
the method for identifying the parking space by using the filtered data specifically comprises the following steps:
performing jump edge detection by using the filtered data to obtain a jump edge detection result; the jump edge detection result at least comprises a middle edge, and at least one of the rising edge and the falling edge; the middle edge is an edge between the end point of the rising edge and the start point of the falling edge;
and calculating the length and the width of the target parking space according to the jump edge detection result.
8. The parking space recognition method according to claim 7, wherein calculating the length and width of the target parking space according to the jump edge detection result specifically comprises:
calculating the vertical distance from the starting point of the rising edge to the middle edge to obtain the width of the target parking space;
multiplying the speed of the vehicle by the detection duration corresponding to the middle edge to obtain a first length;
dividing the width by the slope of the rising edge to obtain a second length;
and calculating the sum of the first length and the second length which is 2 times of the first length to obtain the length of the target parking space.
9. The parking space identification method according to claim 7, wherein determining the rising edge or the falling edge using the filtered data, in particular comprises:
determining all distance measurement values corresponding to a target edge as target distance measurement values, wherein the target edge is the rising edge or the falling edge;
the filtered data is used to determine a slope of the target edge based on a linear regression model.
10. A parking space recognition apparatus, characterized by comprising:
the data acquisition module is used for carrying out filtering processing on all distance measured values detected by the ultrasonic radar based on a weighted recursive average filtering method in the process of carrying out obstacle distance detection on a target parking space by the vehicle through the ultrasonic radar to obtain filtered data; the target parking spaces are parking spaces in which obstacle vehicles are parked in the parking spaces at the two sides of the target parking space;
and the parking space identification module is used for identifying the parking space by using the filtered data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311566947.4A CN117475669A (en) | 2023-11-22 | 2023-11-22 | Parking space identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311566947.4A CN117475669A (en) | 2023-11-22 | 2023-11-22 | Parking space identification method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117475669A true CN117475669A (en) | 2024-01-30 |
Family
ID=89637865
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311566947.4A Pending CN117475669A (en) | 2023-11-22 | 2023-11-22 | Parking space identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117475669A (en) |
-
2023
- 2023-11-22 CN CN202311566947.4A patent/CN117475669A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7385550B2 (en) | Method for measuring distances and speeds of several objects by means of an FMCW radar | |
| JP5627240B2 (en) | Dynamic obstacle judgment device | |
| JP6788388B2 (en) | Radar device and control method of radar device | |
| US20200124716A1 (en) | Radar track initialization | |
| US9689975B2 (en) | Radar apparatus | |
| JP2019158814A (en) | Radar system and method for controlling radar system | |
| CN109196374A (en) | Object detecting device | |
| US11815596B2 (en) | Object detection device | |
| JP2012194039A (en) | In-vehicle radar system | |
| JP2012146024A (en) | Parking space detection device | |
| KR101017590B1 (en) | Method and apparatus for measuring range gate pull-off | |
| JP2010002396A (en) | Object detection device | |
| CN117475669A (en) | Parking space identification method and device | |
| US10114108B2 (en) | Positioning apparatus | |
| CN113805180A (en) | Object detection device | |
| JP5682711B2 (en) | Lane judgment device, lane judgment method, and computer program for lane judgment | |
| JP2002006040A (en) | Object sensing device | |
| US20200301009A1 (en) | Object detection apparatus | |
| EP4369040A1 (en) | Object detecting device, and object detecting method | |
| JP7257628B2 (en) | rangefinder | |
| JP7261988B2 (en) | rangefinder | |
| US11860274B2 (en) | Object detection device | |
| JP7261987B2 (en) | rangefinder | |
| JP2738875B2 (en) | Target tracking method | |
| WO2024013839A1 (en) | Object recognition device and object recognition method |
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 |