Method, device, equipment and readable storage medium for searching effective parking spaces
The sensing sensor detects whether there are motion obstacles in the parking spaces with reference obstacles, which solves the problem of wrong release of parking spaces during automatic parking, and improves the accuracy and safety of automatic parking.
Patent Information
- Application Number
- CN202210332489.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-03-30
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2042-03-30
AI Technical Summary
During automatic parking, parking space search is prone to error release of parking spaces, especially the space-type parking spaces may be locked by other vehicles and not detected, resulting in errors in parking space release.
Data is collected by sensing sensors to determine the parking space, detect whether there is a motion obstacle corresponding to the parking space. If it exists, return and search again. If it does not exist, release the parking space. This method combines data from vision, radar sensors and millimeter wave radar sensors to improve the accuracy of dynamic obstacle detection and avoid the misreleasing of parking spaces.
It effectively reduces the probability of parking space being released incorrectly, avoids parking failures and vehicle collisions, and improves the accuracy and safety of automatic parking.
Smart Images

Figure CN114655193B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of intelligent driving, and in particular to a method, device, equipment and readable storage medium for searching an effective parking space. Background Art
[0002] With the development of intelligent driving, drivers have a growing demand for automatic parking systems, and more and more models are equipped with automatic parking systems. From the initial automatic parking system that relied on pure ultrasound to achieve spatial parking, to the current automatic parking system that uses ultrasound and visual fusion to achieve spatial parking and linear parking. Although the addition of visual fusion has increased the use scenarios of automatic parking.
[0003] However, the problem of incorrect release of parking spaces has not been solved, especially for the scenario where customers search for parking spaces. When a parking space is found, it will be released, but it may have been locked by other vehicles, that is, the parking space is incorrectly released. Summary of the invention
[0004] The main purpose of the present invention is to provide a method, device, equipment and readable storage medium for searching for an effective parking space, aiming to solve the technical problem that a parking space may be released erroneously when searching for a parking space during automatic parking.
[0005] In a first aspect, the present invention provides a method for searching for an effective parking space, the method comprising the following steps:
[0006] Determine a parking space based on perception data collected by a perception sensor;
[0007] When the parking space is a space-type parking space, detecting whether there is at least one moving obstacle among the reference obstacles corresponding to the space-type parking space;
[0008] If there is at least one moving obstacle, returning to the step of determining the parking space based on the sensing data collected by the sensing sensor;
[0009] If there is no moving obstacle, the spatial parking space is released.
[0010] Optionally, the step of detecting whether there is at least one moving obstacle among the reference obstacles corresponding to the spatial parking space includes:
[0011] Obtaining a relative speed between a reference obstacle corresponding to the spatial parking space and the vehicle;
[0012] Calculate whether there is a reference obstacle whose absolute value of the sum of the relative speed and the own vehicle speed is greater than a preset threshold;
[0013] If so, it is determined that there is at least one moving obstacle among the reference obstacles corresponding to the spatial parking space.
[0014] Optionally, the step of determining a parking space based on the perception data collected by the perception sensor includes:
[0015] When the parking space is a linear parking space, detect whether there is an obstacle in the linear parking space;
[0016] If yes, returning to the step of determining the parking space based on the perception data collected by the perception sensor;
[0017] If not, the linear parking space is released.
[0018] Optionally, the step of determining a parking space based on the perception data collected by the perception sensor includes:
[0019] Determine whether there is a linear parking space based on the road surface image collected by the visual sensor;
[0020] If there is a linear parking space, executing the step of detecting whether there is an obstacle in the linear parking space when the parking space is a linear parking space;
[0021] If there is no linear parking space, determine whether there is a spatial parking space based on the echo signal collected by the radar sensor;
[0022] If there is a spatial parking space, the step of detecting whether there is at least one moving obstacle among the reference obstacles corresponding to the spatial parking space when the parking space is a spatial parking space is performed.
[0023] Optionally, the step of determining whether there is a linear parking space based on the road surface image collected by the visual sensor includes:
[0024] Acquire a road surface image collected by a visual sensor, and perform binarization processing on the road surface image to obtain a binary image;
[0025] Identify the binary image based on an edge detection algorithm to obtain edge lines in the binary image;
[0026] If it is determined that there are at least two linear parking space corner points in the binary image based on the intersection points between the edge lines, it is determined that there is a linear parking space.
[0027] Optionally, the step of determining whether there is a spatial parking space based on the echo signal collected by the radar sensor includes:
[0028] Establish the vehicle coordinate system with the center of the rear wheel of the vehicle as the origin;
[0029] Based on the vehicle's own parameter information, the radar sensor collects the echo signal of the obstacle, as well as the wheel pulse signal, wheel driving direction signal and steering wheel angle signal obtained by the on-board sensor to determine the coordinate relationship between the reference obstacle and the vehicle;
[0030] Based on the coordinate relationship between the reference obstacles and the ego vehicle, determine whether there is a spatial parking space between the reference obstacles.
[0031] In a second aspect, the present invention further provides a device for searching for an effective parking space, the device for searching for an effective parking space comprising:
[0032] A determination module, used to determine a parking space based on the perception data collected by the perception sensor;
[0033] a detection module, for detecting, when the parking space is a spatial parking space, whether there is at least one moving obstacle among the reference obstacles corresponding to the spatial parking space;
[0034] A control module, configured to return to the step of determining a parking space based on the sensing data collected by the sensing sensor if at least one moving obstacle exists;
[0035] If there is no moving obstacle, the spatial parking space is released.
[0036] Optionally, the detection module is specifically used to:
[0037] Obtaining a relative speed between a reference obstacle corresponding to the spatial parking space and the vehicle;
[0038] Calculate whether there is a reference obstacle whose absolute value of the sum of the relative speed and the own vehicle speed is greater than a preset threshold;
[0039] If so, it is determined that there is at least one moving obstacle among the reference obstacles corresponding to the spatial parking space.
[0040] Optionally, the effective parking space search device further includes a first control module, which is used to:
[0041] When the parking space is a linear parking space, detect whether there is an obstacle in the linear parking space;
[0042] If yes, return to the step of determining the parking space based on the perception data collected by the perception sensor;
[0043] If not, the linear parking space is released.
[0044] Optionally, the determining module is specifically used to:
[0045] Determine whether there is a linear parking space based on the road surface image collected by the visual sensor;
[0046] If there is a linear parking space, executing the step of detecting whether there is an obstacle in the linear parking space when the parking space is a linear parking space;
[0047] If there is no linear parking space, determine whether there is a spatial parking space based on the echo signal collected by the radar sensor;
[0048] If there is a spatial parking space, the step of detecting whether there is at least one moving obstacle among the reference obstacles corresponding to the spatial parking space when the parking space is a spatial parking space is performed.
[0049] Optionally, the determining module is further specifically configured to:
[0050] Acquire a road surface image collected by a visual sensor, and perform binarization processing on the road surface image to obtain a binary image;
[0051] Identify the binary image based on an edge detection algorithm to obtain edge lines in the binary image;
[0052] If it is determined that there are at least two linear parking space corner points in the binary image based on the intersection points between the edge lines, it is determined that there is a linear parking space.
[0053] Optionally, the determining module is further specifically configured to:
[0054] Establish the vehicle coordinate system with the center of the rear wheel of the vehicle as the origin;
[0055] Based on the vehicle's own parameter information, the radar sensor collects the echo signal of the obstacle, as well as the wheel pulse signal, wheel driving direction signal and steering wheel angle signal obtained by the on-board sensor to determine the coordinate relationship between the reference obstacle and the vehicle;
[0056] Based on the coordinate relationship between the reference obstacles and the ego vehicle, determine whether there is a spatial parking space between the reference obstacles.
[0057] In a third aspect, the present invention further provides a device for searching for valid parking spaces, the device comprising a processor, a memory, and a search program for valid parking spaces stored in the memory and executable by the processor, wherein when the search program for valid parking spaces is executed by the processor, the steps of the method for searching for valid parking spaces as described above are implemented.
[0058] In a fourth aspect, the present invention further provides a readable storage medium, on which a valid parking space search program is stored, wherein when the valid parking space search program is executed by a processor, the steps of the valid parking space search method as described above are implemented.
[0059] The method for searching for an effective parking space in the present invention includes: determining a parking space based on the sensing data collected by the sensing sensor; when the parking space is a spatial parking space, detecting whether there is at least one moving obstacle in the reference obstacles corresponding to the spatial parking space; if there is at least one moving obstacle, returning to the step of determining the parking space based on the sensing data collected by the sensing sensor; if there is no moving obstacle, releasing the spatial parking space. The present invention can solve the problem of mistakenly releasing a parking space when searching for a parking space during automatic parking. BRIEF DESCRIPTION OF THE DRAWINGS
[0060] Figure 1 A schematic diagram of the hardware structure of a valid parking space search device involved in an embodiment of the present invention;
[0061] Figure 2 A schematic diagram of a flow chart of an embodiment of a method for searching for an effective parking space according to the present invention;
[0062] Figure 3 Schematic diagram of functional modules of an embodiment of a device for searching for effective parking spaces according to the present invention.
[0063] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0064] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.
[0065] In a first aspect, an embodiment of the present invention provides a device for searching for an effective parking space.
[0066] Reference Figure 1 , Figure 1The hardware structure diagram of the effective parking space search device involved in the embodiment of the present invention. In the embodiment of the present invention, the effective parking space search device may include a processor 1001 (such as a central processing unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components; the user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard); the network interface 1004 may optionally include a standard wired interface, a wireless interface (such as a wireless fidelity WIreless-FIdelity, WI-FI interface); the memory 1005 may be a high-speed random access memory (random access memory, RAM), or a stable memory (non-volatile memory), such as a disk storage, and the memory 1005 may optionally be a storage device independent of the aforementioned processor 1001. Those skilled in the art will understand that Figure 1 The hardware structure shown in the figure does not constitute a limitation of the present invention, and may include more or less components than those shown in the figure, or combine certain components, or arrange the components differently.
[0067] Continue to refer to Figure 1 , Figure 1 The memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a valid parking space search program. The processor 1001 may call the valid parking space search program stored in the memory 1005 and execute the valid parking space search method provided in the embodiment of the present invention.
[0068] In a second aspect, an embodiment of the present invention provides a method for searching for an effective parking space.
[0069] Reference Figure 2 , Figure 2 Schematic diagram of a flow chart of an embodiment of a method for searching for an effective parking space according to the present invention.
[0070] In an embodiment of a method for searching for an effective parking space of the present invention, the method for searching for an effective parking space includes:
[0071] Step S10, determining a parking space based on the perception data collected by the perception sensor;
[0072] In this embodiment, when the vehicle is performing automatic parking, it must first determine the parking space situation based on the perception data collected by the perception sensors, including using visual sensors such as surround cameras to collect images of the surroundings of the vehicle, the images including road images, based on which the parking lines and other information in the parking area with parking lines can be identified; using radar sensors such as ultrasonic radars to collect the relative position relationship of the surrounding obstacles of the vehicle after the vehicle enters the parking function, based on which it can be identified whether there is a parking space in the parking area without parking lines, that is, whether there is a space-type parking space. Using the perception data collected by the above-mentioned multiple perception sensors, the vehicle can detect different parking spaces in a variety of scenarios when searching for parking spaces in automatic parking, so as to find parking spaces more conveniently.
[0073] Step S20, when the parking space is a spatial parking space, detecting whether there is at least one moving obstacle among the reference obstacles corresponding to the spatial parking space;
[0074] In this embodiment, in the existing scheme, when searching for a spatial parking space, the automatic parking controller controls the ultrasonic wave to emit the ultrasonic wave and receive the echo. According to the time t between the emission and the echo, combined with the propagation speed v of the ultrasonic wave in the air, the distance s between the obstacle and the vehicle is obtained, which is (v*t) / 2. Therefore, based on the distance between the obstacle and the vehicle corresponding to a number of echo points, it is judged whether there is a parking space, that is, a spatial parking space. However, the ultrasonic radar for detecting whether there is a spatial parking space in the existing scheme cannot distinguish whether the obstacle is a moving obstacle or a stationary obstacle, and the visual sensor such as a camera has a relatively poor detection capability for moving objects. Therefore, in this case, when the ultrasonic radar detects the corresponding spatial parking space, the reference obstacle will be in a state where the above-mentioned spatial parking space has been locked and moved to the above-mentioned spatial parking space at a low speed. That is, at this time, the automatic parking controller will mistakenly believe that the above-mentioned spatial parking space is valid, and release the parking space, resulting in the wrong release of the parking space.
[0075] Therefore, when determining that a parking space is a spatial parking space based on the perception data collected by the perception sensor, it is necessary to determine whether the spatial parking space found above is valid, so as to reduce the probability of erroneous release of the parking space. That is, when determining that the parking space searched is a spatial parking space, it is detected whether there is at least one moving obstacle in the reference obstacle corresponding to the spatial parking space. Among them, since the millimeter-wave radar sensor is superior to the obstacle detection on the adjacent lane of the vehicle trajectory, the detection accuracy of dynamic obstacles is higher than that of the existing traditional ultrasonic radar sensor, and the obstacle distance that can be detected is farther, the millimeter-wave radar sensor can be used in the above-mentioned process of detecting whether there are moving obstacles, and the perception results of the millimeter-wave radar sensor are fused with the perception results of the ultrasonic radar sensor and the visual sensor, and the wrong parking space is eliminated according to the perception information of the millimeter-wave radar sensor, so as to reduce the probability of erroneous release of the parking space, thereby avoiding parking failures and vehicle collisions due to erroneous release of the parking space during the parking process.
[0076] Step S31: if there is at least one moving obstacle, return to the step of determining the parking space based on the sensing data collected by the sensing sensor;
[0077] In this embodiment, since there is more than one obstacle referenced when searching for a spatial parking space, if it is detected that there is at least one moving obstacle in the searched spatial parking space, it means that the searched spatial parking space is locked by other vehicles, i.e., the moving reference obstacle. In order to avoid parking failure and vehicle collision, it can be determined that the searched spatial parking space is invalid, the above-mentioned spatial parking space is abandoned, and other parking spaces are searched again for automatic parking, that is, returning to the step of determining the parking space based on the perception data collected by the perception sensor.
[0078] Step S32: if there is no moving obstacle, the spatial parking space is released.
[0079] In this embodiment, if it is detected that there is no moving obstacle in the searched spatial parking space, it means that the searched spatial parking space is not locked by a static reference obstacle at this time, and the searched spatial parking space is determined to be valid, and the spatial parking space is released, so that the automatic parking operation is performed on the released spatial parking space.
[0080] Furthermore, in one embodiment, the step of detecting whether there is at least one moving obstacle in the reference obstacles corresponding to the spatial parking space includes:
[0081] Obtaining a relative speed between a reference obstacle corresponding to the spatial parking space and the vehicle;
[0082] Calculate whether there is a reference obstacle whose absolute value of the sum of the relative speed and the own vehicle speed is greater than a preset threshold;
[0083] If so, it is determined that there is at least one moving obstacle among the reference obstacles corresponding to the spatial parking space.
[0084] In this embodiment, the step of detecting whether there is at least one moving obstacle in the reference obstacles corresponding to the searched spatial parking space may specifically include: obtaining the relative speed, relative position relationship, etc. between the reference obstacle corresponding to the spatial parking space and the self-vehicle, so as to determine whether there is a moving obstacle in the reference obstacle by calculation. Among them, the above relative speed and relative position relationship can be obtained by millimeter wave radar. Specifically, according to the frequency difference Δf, time difference ΔT, wave frequency f, electromagnetic wave transmission speed C in space, the relative speed V1=(C / 2f)*Δf and the relative distance s=(C*ΔT) / 2 between the reference obstacle and the self-vehicle can be obtained by the Doppler effect principle, and the obstacle azimuth β can be located according to the phase difference of the received echo, so as to obtain the position relationship between the obstacle and the self-vehicle.
[0085] After obtaining the relative speed and relative position relationship between the reference obstacle corresponding to the spatial parking space and the vehicle, it can be calculated whether there is a reference obstacle whose absolute value of the sum of the relative speed and the vehicle speed is greater than the preset threshold. If it is calculated that there is a reference obstacle whose absolute value of the sum of the relative speed and the vehicle speed is greater than the preset threshold, it can be judged that there is at least one moving obstacle in the reference obstacles corresponding to the spatial parking space. Among them, taking the vehicle speed V2 as positive, when the reference obstacle is far away from the vehicle, the relative speed V1 is positive; when the reference obstacle is close to the vehicle, the relative speed V1 is negative as an example. For example, when the vehicle is driving forward at 10km / h, the absolute value of the sum of the relative speed and the vehicle speed is 5km / h, that is, the vehicle reference obstacle may be driving in the same direction as the vehicle at 5km / h, and the relative speed is -5km / h; or the vehicle reference obstacle is driving in the opposite direction of the vehicle at 5km / h, that is, the relative speed is -15km / h, and the obstacle is a moving obstacle. When the vehicle is moving forward at 10km / h, the absolute value of the sum of the relative speed and the vehicle speed is 0km / h, that is, the vehicle reference obstacle is stationary, and the relative speed is -10km / h. Since the vehicle speed and the speed of other reference obstacles will not be fast during the search for parking spaces, and a certain error in the speed data is allowed, taking the preset threshold of 0.5km / h as an example, when |V1+V2|≤0.5km / h is detected, it is judged as a stationary obstacle; when |V1+V2|>0.5km / h is detected, it is judged as a moving obstacle.
[0086] Furthermore, in one embodiment, the step of determining a parking space based on the perception data collected by the perception sensor includes:
[0087] When the parking space is a linear parking space, detect whether there is an obstacle in the linear parking space;
[0088] If yes, return to the step of determining the parking space based on the perception data collected by the perception sensor;
[0089] If not, the linear parking space is released.
[0090] In this embodiment, since the linear parking space is determined based on the corner points of the parking line, when it is determined that there is a linear parking space, it is only necessary to determine whether there is an obstacle in the linear parking space to determine whether the linear parking space is valid. Therefore, when the parking space is determined to be a linear parking space based on the perception data collected by the perception sensor, it is necessary to detect whether there is an obstacle in the linear parking space. If it is detected that there is an obstacle in the linear parking space, it is determined that the linear parking space searched above is invalid, the linear parking space is abandoned, and other parking spaces are searched again for automatic parking, that is, the step of determining the parking space based on the perception data collected by the perception sensor is returned. If it is detected that there is no obstacle in the linear parking space, it is determined that the linear parking space searched above is valid, and the linear parking space is released, so that the automatic parking operation is performed on the released linear parking space.
[0091] Furthermore, in one embodiment, the step of determining a parking space based on the perception data collected by the perception sensor includes:
[0092] Determine whether there is a linear parking space based on the road surface image collected by the visual sensor;
[0093] If there is a linear parking space, executing the step of detecting whether there is an obstacle in the linear parking space when the parking space is a linear parking space;
[0094] If there is no linear parking space, determine whether there is a spatial parking space based on the echo signal collected by the radar sensor;
[0095] If there is a spatial parking space, the step of detecting whether there is at least one moving obstacle among the reference obstacles corresponding to the spatial parking space when the parking space is a spatial parking space is performed.
[0096] In this embodiment, since there are two types of parking spaces, linear parking spaces and spatial parking spaces, in the actual parking search scene, the linear parking spaces have higher recognition accuracy than spatial parking spaces, and in order to avoid encroaching on other people's parking spaces, the parking strategy requires that the vehicle be parked within the parking space line as much as possible, so the priority of the linear parking spaces is higher than that of the spatial parking spaces. When the linear parking spaces and the spatial parking spaces are found, it is necessary to first determine whether the linear parking spaces are valid. When it is determined that the linear parking spaces are invalid or there are no linear parking spaces, it is then determined whether the searched spatial parking spaces are valid. That is, the step of determining the parking spaces based on the perception data collected by the perception sensor includes: determining whether there are linear parking spaces based on the road surface image collected by the visual sensor. If there are linear parking spaces, the step of detecting whether there are obstacles in the linear parking spaces when the parking spaces are linear parking spaces is executed. If there are no linear parking spaces, it is determined whether there are spatial parking spaces based on the echo signals collected by the radar sensor. If there is a spatial parking space, the step of detecting whether there is at least one moving obstacle among the reference obstacles corresponding to the spatial parking space when the parking space is a spatial parking space is performed.
[0097] Furthermore, in one embodiment, the step of determining whether there is a linear parking space based on the road surface image collected by the visual sensor includes:
[0098] Acquire a road surface image collected by a visual sensor, and perform binarization processing on the road surface image to obtain a binary image;
[0099] Identify the binary image based on an edge detection algorithm to obtain edge lines in the binary image;
[0100] If it is determined that there are at least two linear parking space corner points in the binary image based on the intersection points between the edge lines, it is determined that there is a linear parking space.
[0101] In this embodiment, a plurality of surround view cameras collect road images of different perspectives, and splice the road images of different perspectives into a panoramic surround view image, which includes road information around the vehicle at a preset distance from the edge of the vehicle body. Therefore, the road image collected by the visual sensor can be obtained, and the road image can be detected for corner points to determine whether there is a linear parking space. Specifically, the acquired road image can be binarized to obtain a binarized image, and then the binarized image is imported into the canny edge detection algorithm. The edge line in the binarized image is identified based on the canny edge detection algorithm, and after the edge line is obtained, the linear parking space corner point and the position coordinates of the corner point are determined based on the obtained edge line and the intersection between the edge lines. If it is determined based on the intersection between the edge line and the edge line that there are at least two linear parking space corner points in the binary image, it is determined that there is a linear parking space.
[0102] Further, in one embodiment, the step of determining whether there is a spatial parking space based on the echo signal collected by the radar sensor includes:
[0103] Establish the vehicle coordinate system with the center of the rear wheel of the vehicle as the origin;
[0104] Based on the vehicle's own parameter information, the radar sensor collects the echo signal of the obstacle, as well as the wheel pulse signal, wheel driving direction signal and steering wheel angle signal obtained by the on-board sensor to determine the coordinate relationship between the reference obstacle and the vehicle;
[0105] Based on the coordinate relationship between the reference obstacles and the ego vehicle, determine whether there is a spatial parking space between the reference obstacles.
[0106] In this embodiment, the step of determining whether there is a spatial parking space based on the echo signal collected by the radar sensor includes: a vehicle coordinate system can be established with the center of the rear wheel of the vehicle as the origin. Based on the vehicle's own parameter information, the radar sensor collects the echo signal of the obstacle, as well as the wheel pulse signal, wheel driving direction signal and steering wheel angle signal of the vehicle acquired by the on-board sensor, and determines the coordinate relationship between the reference obstacle corresponding to the echo point and the vehicle. Based on the coordinate relationship between different reference obstacles and the vehicle, the coordinate relationship between the reference obstacles is obtained, so as to determine whether there is a parking space between the reference obstacles, that is, a spatial parking space.
[0107] In this embodiment, the search method for an effective parking space includes: determining a parking space based on the sensing data collected by the sensing sensor; when the parking space is a spatial parking space, detecting whether there is at least one moving obstacle among the reference obstacles corresponding to the spatial parking space; if there is at least one moving obstacle, returning to the step of determining the parking space based on the sensing data collected by the sensing sensor; if there is no moving obstacle, releasing the spatial parking space. The search method for an effective parking space can solve the problem of mistakenly releasing a parking space when searching for a parking space during automatic parking.
[0108] In a third aspect, an embodiment of the present invention further provides a device for searching for an effective parking space.
[0109] Reference Figure 3 , a schematic diagram of functional modules of an embodiment of a device for searching for effective parking spaces.
[0110] In this embodiment, the effective parking space search device includes:
[0111] A determination module 10, for determining a parking space based on the perception data collected by the perception sensor;
[0112] A detection module 20, for detecting, when the parking space is a spatial parking space, whether there is at least one moving obstacle in the reference obstacles corresponding to the spatial parking space;
[0113] The control module 30 is configured to return to the step of determining the parking space based on the sensing data collected by the sensing sensor if there is at least one moving obstacle;
[0114] If there is no moving obstacle, the spatial parking space is released.
[0115] Furthermore, in one embodiment, the detection module 20 is specifically used for:
[0116] Obtaining a relative speed between a reference obstacle corresponding to the spatial parking space and the vehicle;
[0117] Calculate whether there is a reference obstacle whose absolute value of the sum of the relative speed and the own vehicle speed is greater than a preset threshold;
[0118] If so, it is determined that there is at least one moving obstacle among the reference obstacles corresponding to the spatial parking space.
[0119] Furthermore, in one embodiment, the effective parking space search device further includes a first control module, which is used to:
[0120] When the parking space is a linear parking space, detect whether there is an obstacle in the linear parking space;
[0121] If yes, returning to the step of determining the parking space based on the perception data collected by the perception sensor;
[0122] If not, the linear parking space is released.
[0123] Further, in one embodiment, the determining module 10 is specifically configured to:
[0124] Determine whether there is a linear parking space based on the road surface image collected by the visual sensor;
[0125] If there is a linear parking space, executing the step of detecting whether there is an obstacle in the linear parking space when the parking space is a linear parking space;
[0126] If there is no linear parking space, determine whether there is a spatial parking space based on the echo signal collected by the radar sensor;
[0127] If there is a spatial parking space, the step of detecting whether there is at least one moving obstacle among the reference obstacles corresponding to the spatial parking space when the parking space is a spatial parking space is performed.
[0128] Furthermore, in one embodiment, the determining module 10 is further specifically configured to:
[0129] Acquire a road surface image collected by a visual sensor, and perform binarization processing on the road surface image to obtain a binary image;
[0130] Identify the binary image based on an edge detection algorithm to obtain edge lines in the binary image;
[0131] If it is determined that there are at least two linear parking space corner points in the binary image based on the intersection points between the edge lines, it is determined that there is a linear parking space.
[0132] Furthermore, in one embodiment, the determining module 10 is further specifically configured to:
[0133] Establish the vehicle coordinate system with the center of the rear wheel of the vehicle as the origin;
[0134] Based on the vehicle's own parameter information, the radar sensor collects the echo signal of the obstacle, as well as the wheel pulse signal, wheel driving direction signal and steering wheel angle signal obtained by the on-board sensor to determine the coordinate relationship between the reference obstacle and the vehicle;
[0135] Based on the coordinate relationship between the reference obstacles and the ego vehicle, determine whether there is a spatial parking space between the reference obstacles.
[0136] Among them, the functional implementation of each module in the above-mentioned effective parking space search device corresponds to the various steps in the above-mentioned effective parking space search method embodiment, and its functions and implementation processes are no longer repeated here one by one.
[0137] In a fourth aspect, an embodiment of the present invention further provides a readable storage medium.
[0138] The readable storage medium of the present invention stores a valid parking space search program, wherein when the valid parking space search program is executed by a processor, the steps of the valid parking space search method described above are implemented.
[0139] Among them, the method implemented when the effective parking space search program is executed can refer to the various embodiments of the effective parking space search method of the present invention, and will not be repeated here.
[0140] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.
[0141] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.
[0142] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for a terminal device to execute the methods described in each embodiment of the present invention.
[0143] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.
Claims
1. A method for searching for an effective parking space, characterized in that: The method for searching for an effective parking space includes: Determine a parking space based on perception data collected by a perception sensor; When the parking space is a space-type parking space, detecting whether there is at least one moving obstacle among the reference obstacles corresponding to the space-type parking space; If there is at least one moving obstacle, returning to the step of determining the parking space based on the sensing data collected by the sensing sensor; If there is no moving obstacle, releasing the spatial parking space; The step of detecting whether there is at least one moving obstacle among the reference obstacles corresponding to the spatial parking space comprises: Obtaining a relative speed between a reference obstacle corresponding to the spatial parking space and the vehicle; Calculate whether there is a reference obstacle whose absolute value of the sum of the relative speed and the own vehicle speed is greater than a preset threshold; If so, it is determined that there is at least one moving obstacle among the reference obstacles corresponding to the spatial parking space.
2. The method for searching for an effective parking space according to claim 1, characterized in that: The step of determining a parking space based on the perception data collected by the perception sensor includes: When the parking space is a linear parking space, detect whether there is an obstacle in the linear parking space; If yes, returning to the step of determining the parking space based on the perception data collected by the perception sensor; If not, the linear parking space is released.
3. The method for searching for an effective parking space according to claim 2, characterized in that: The step of determining a parking space based on the perception data collected by the perception sensor includes: Determine whether there is a linear parking space based on the road surface image collected by the visual sensor; If there is a linear parking space, executing the step of detecting whether there is an obstacle in the linear parking space when the parking space is a linear parking space; If there is no linear parking space, determine whether there is a spatial parking space based on the echo signal collected by the radar sensor; If there is a spatial parking space, the step of detecting whether there is at least one moving obstacle among the reference obstacles corresponding to the spatial parking space when the parking space is a spatial parking space is performed.
4. The method for searching for an effective parking space according to claim 3, characterized in that: The step of determining whether there is a linear parking space based on the road surface image collected by the visual sensor includes: Acquire a road surface image collected by a visual sensor, and perform binarization processing on the road surface image to obtain a binary image; Identify the binary image based on an edge detection algorithm to obtain edge lines in the binary image; If it is determined that there are at least two linear parking space corner points in the binary image based on the intersection points between the edge lines, it is determined that there is a linear parking space.
5. The method for searching for an effective parking space according to claim 3, characterized in that: The step of determining whether there is a spatial parking space based on the echo signal collected by the radar sensor includes: Establish the vehicle coordinate system with the center of the rear wheel of the vehicle as the origin; Based on the vehicle's own parameter information, the radar sensor collects the echo signal of the obstacle, as well as the wheel pulse signal, wheel driving direction signal and steering wheel angle signal obtained by the on-board sensor to determine the coordinate relationship between the reference obstacle and the vehicle; Based on the coordinate relationship between the reference obstacles and the ego vehicle, determine whether there is a spatial parking space between the reference obstacles.
6. A device for searching for an effective parking space, characterized in that: The effective parking space search device comprises: A determination module, used to determine a parking space based on the perception data collected by the perception sensor; a detection module, for detecting, when the parking space is a spatial parking space, whether there is at least one moving obstacle among the reference obstacles corresponding to the spatial parking space; A control module, configured to return to the step of determining a parking space based on the sensing data collected by the sensing sensor if at least one moving obstacle exists; If there is no moving obstacle, releasing the spatial parking space; The detection module is used for: Obtaining a relative speed between a reference obstacle corresponding to the spatial parking space and the vehicle; Calculate whether there is a reference obstacle whose absolute value of the sum of the relative speed and the own vehicle speed is greater than a preset threshold; If so, it is determined that there is at least one moving obstacle among the reference obstacles corresponding to the spatial parking space.
7. A device for searching for effective parking spaces, characterized in that: The valid parking space search device includes a processor, a memory, and a valid parking space search program stored in the memory and executable by the processor, wherein when the valid parking space search program is executed by the processor, the steps of the valid parking space search method as described in any one of claims 1 to 5 are implemented.
8. A readable storage medium, characterized in that: The readable storage medium stores a valid parking space search program, wherein when the valid parking space search program is executed by a processor, the steps of the valid parking space search method according to any one of claims 1 to 5 are implemented.
Citation Information
Patent Citations
Parking space identification method based on point and line features of panoramic image
CN104933409A
Automatic parking method
CN111231944A
Automatic parking space mistaken release prevention method
CN114063086A
Method and system for automatically finding parking space and automatically parking vehicle
CN114220290A
Automatic parking system, automatic parking control device, and automatic parking control method
WO2017168754A1
