CN112124303A - Parking space fusion method and system - Google Patents
Parking space fusion method and system Download PDFInfo
- Publication number
- CN112124303A CN112124303A CN202011029534.9A CN202011029534A CN112124303A CN 112124303 A CN112124303 A CN 112124303A CN 202011029534 A CN202011029534 A CN 202011029534A CN 112124303 A CN112124303 A CN 112124303A
- Authority
- CN
- China
- Prior art keywords
- parking
- space
- parking space
- line
- spaces
- 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
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
- B60W30/06—Automatic manoeuvring for parking
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
- B60W60/0011—Planning or execution of driving tasks involving control alternatives for a single driving scenario, e.g. planning several paths to avoid obstacles
Abstract
The invention discloses a parking space fusion method and a system, wherein the method comprises the following steps: the method comprises the steps of obtaining parking place types, parking place types and position information of the obtained parking places, wherein the parking place types comprise space parking places or linear parking places, and the parking place types comprise parallel parking places or vertical parking places; and judging whether the parking space has an obstacle or not, if not, determining the type of the output parking space and the position information thereof according to the type of the parking space and the relative positions of the space parking space and the line parking space when the parking space type comprises the space parking space and the line parking space. When the parking space is identified, the parking space and the barrier are fused, and the parking space are fused to obtain the final parking space. Through the implementation of this scheme, can improve parking stall discernment rate of accuracy. Meanwhile, the scheme has low requirement on the SOC processor, the algorithm is relatively simple, the algorithm is developed on the basis of a low-cost hardware platform, and the method is beneficial to mass production and popularization of the platform.
Description
Technical Field
The invention belongs to the technical field of intelligent automobiles, and particularly relates to a parking space fusion method and system.
Background
Parking space fusion is a key technology of intelligent parking, and directly influences parking path planning, success rate of parking and parking safety.
At present mainly detect and reconstruct the output through ultrasonic sensor and camera are synthesized to this scheme, though can realize normal parking stall and merge, because parking stall discernment has certain error, the parking stall that leads to fusing out can deviate from actual parking stall. For example, the parking spaces on the ground are regular rectangles or parallelograms, but the parking spaces output after the actual collected data is processed and reconstructed may be trapezoids, as shown by the vertical line parking spaces in fig. 1. For example, a reference vehicle used as a reference of a space parking space is not necessarily placed neatly, and if a parked vehicle body has a drift angle with the edge of a standard parking space, a final space parking space also has a certain deviation.
Another existing parking space fusion method is to fuse parking spaces by using a linear parking space, a spatial parking space and the relative positions of obstacles in the parking spaces respectively and combining a parking planning scheme in the parking process. Although the posture accuracy of the controlled vehicle finally entering the parking space is improved to a certain extent, the wrong parking space identification and the like are caused without considering the type diversity of the parking space and the position detection error of the barrier in the parking space, and finally the accurate parking is realized through the SOC processor with more enhanced performance and a more complex algorithm, so that the hardware cost is inevitably increased greatly.
Disclosure of Invention
The technical problem to be solved by the embodiment of the invention is that the problem of parking stall missing report or false report caused by the parking stall type diversity and the position detection error of the obstacle in the parking stall is not considered in the existing parking stall fusion. In order to solve the technical problem, the invention provides a parking space fusion method, which comprises the following steps:
step S1, acquiring parking space types, parking space types and position information of the acquired parking spaces, wherein the parking space types comprise at least one of space parking spaces and linear parking spaces, and the parking space types are parallel parking spaces or vertical parking spaces;
step S2, judging whether an obstacle exists in the parking space, if not, determining the relative position of the space parking space and the line parking space according to the position information of the space parking space and the position information of the line parking space when the parking space types simultaneously include space parking spaces and line parking spaces; and determining the type and the position information of the output parking space according to the parking space type and the relative position.
Further, the step S2 specifically includes:
when the space parking spaces and the line parking spaces are parallel parking spaces, comparing the relative position relation of the space parking spaces and the line parking spaces on first boundaries of the vehicle head and the vehicle tail;
when the two first boundaries of the line parking space are both located within the first boundaries of the space parking spaces, determining to output the line parking space and the position information thereof;
and when at least one first boundary of the line parking spaces is positioned outside the first boundary corresponding to the space parking spaces, determining to output the space parking spaces and the position information thereof.
Further, the step S2 specifically includes:
when the space parking space and the line parking space are both vertical parking spaces, judging whether the vertical parking spaces of the space parking space and the line parking space are the same in type; the vertical parking space types include: the parking spaces comprise vertical rectangular line parking spaces, forward parallel inclined parking spaces, reverse parallel inclined parking spaces, forward sawtooth inclined parking spaces and reverse sawtooth inclined parking spaces;
when the vertical parking spaces of the space parking space and the line parking space are the same in type, comparing the relative position relation of the space parking space and the line parking space on second boundaries at two sides of the vehicle;
when the two second boundaries of the line parking space are both located within the second boundaries of the space parking spaces, determining to output the line parking space and the position information thereof;
and when at least one second boundary of the line parking space is positioned outside the second boundary corresponding to the space parking space, determining to output the space parking space and the position information thereof.
Further, the step S2 specifically includes:
when the space parking stall with the perpendicular parking stall type of line parking stall is inequality, just the line parking stall is when any one of forward parallel strabismus parking stall, reverse parallel strabismus parking stall, forward sawtooth strabismus parking stall and reverse sawtooth strabismus parking stall, then confirms to export line parking stall and positional information.
Further, the step S2 further includes:
when the vehicle starts to park in the line parking space, the position information of the space parking space is updated;
and outputting the updated position information of the space parking spaces or the position information of the line parking spaces according to the relative positions of the line parking spaces and the updated space parking spaces.
Further, the outputting the updated position information of the space parking space or the position information of the line parking space according to the line parking space and the updated relative position of the space parking space specifically includes:
comparing the relative position relation of the updated space parking spaces and the second boundaries of the line parking spaces at the two sides of the vehicle;
when the two second boundaries of the line parking space are both located within the second boundaries of the updated space parking space, determining to output the line parking space and the position information thereof;
and when at least one second boundary of the line parking space is positioned outside the second boundary corresponding to the updated space parking space, determining to output the updated space parking space and the position information thereof.
Further, the parking space fusion method further comprises the following steps:
and step S3, when the parking space type only includes one of a space parking space and a line parking space, determining to output the currently acquired space parking space and the position information thereof, or determining to output the currently acquired line parking space and the position information thereof.
Further, the parking space fusion method further comprises the following steps:
and step S4, when the parking space type only includes one of a space parking space and a linear parking space, and the area of the parking space simultaneously meets the area requirement of a parallel parking space and the area requirement of a vertical parking space, outputting the position information of the parallel parking space or the position information of the vertical parking space.
A parking spot fusion system, comprising:
the ultrasonic sensor is used for acquiring the parking place type and position information of the space parking place;
the camera sensor is used for acquiring the parking place type and position information of the line parking place;
the parking space type is a parallel parking space or a vertical parking space;
the ultrasonic sensor and the camera sensor are also used for acquiring the information of the obstacles in the parking space;
the parking space fusion processing unit is used for judging whether an obstacle exists in the parking space or not, if the obstacle does not exist in the parking space, and when the parking space types simultaneously comprise a space parking space and a line parking space, determining the relative positions of the space parking space and the line parking space according to the position information of the space parking space and the position information of the line parking space; and determining the type and the position information of the output parking space according to the parking space type and the relative position.
Further, the parking space fusion processing unit is also used for:
when the space parking spaces and the line parking spaces are parallel parking spaces, comparing the relative position relation of the space parking spaces and the line parking spaces on first boundaries of the vehicle head and the vehicle tail;
when the two first boundaries of the line parking space are both located within the first boundaries of the space parking spaces, determining to output the line parking space and the position information thereof;
and when at least one first boundary of the line parking spaces is positioned outside the first boundary corresponding to the space parking spaces, determining to output the space parking spaces and the position information thereof.
Further, the parking space fusion processing unit is also used for:
work as the space parking stall with when line parking stall is perpendicular parking stall, judge the space parking stall with whether the perpendicular parking stall type of line parking stall is the same, perpendicular parking stall type includes: the parking spaces comprise vertical rectangular line parking spaces, forward parallel inclined parking spaces, reverse parallel inclined parking spaces, forward sawtooth inclined parking spaces and reverse sawtooth inclined parking spaces;
when the vertical parking spaces of the space parking space and the line parking space are the same in type, comparing the relative position relation of the space parking space and the line parking space on second boundaries at two sides of the vehicle;
when the two second boundaries of the line parking space are both located within the second boundaries of the space parking spaces, determining to output the line parking space and the position information thereof;
and when at least one second boundary of the line parking space is positioned outside the second boundary corresponding to the space parking space, determining to output the space parking space and the position information thereof.
Further, the parking space fusion processing unit is also used for:
when the space parking stall with the perpendicular parking stall type of line parking stall is inequality, just the line parking stall is when any one of forward parallel strabismus parking stall, reverse parallel strabismus parking stall, forward sawtooth strabismus parking stall and reverse sawtooth strabismus parking stall, then confirms to export line parking stall and positional information.
Further, the parking space fusion processing unit is also used for:
when the vehicle starts to park in the line parking space, the position information of the space parking space is updated;
and outputting the updated position information of the space parking spaces or the position information of the line parking spaces according to the relative positions of the line parking spaces and the updated space parking spaces.
Further, the parking space fusion processing unit is further configured to determine to output the currently acquired space parking space and the position information thereof or determine to output the currently acquired line parking space and the position information thereof when the parking space type includes only one of the space parking space and the line parking space.
Further, the parking space fusion processing unit is also used for:
when the parking space type only comprises one of a space parking space and a linear parking space, and the area of the parking space simultaneously accords with the area requirement of a parallel parking space and the area requirement of a vertical parking space, the position information of the parallel parking space or the position information of the vertical parking space is output.
The embodiment of the invention has the following beneficial effects: according to the invention, when the parking space is identified, the obstacle condition is comprehensively considered, and the parking space type are combined, so that the parking space and the obstacle are fused, and the parking space are fused, and the final parking space is obtained. Due to the error of parking space detection and the diversity of parking space types, if the parking space fusion process is not fully considered, situations such as missed parking space or false parking space can be finally obtained through fusion, and a complex parking planning process needs to be processed for realization. Therefore, through the implementation of the scheme, the parking space identification accuracy can be improved. Meanwhile, the scheme has low requirement on the SOC processor, the algorithm is relatively simple, and the method is developed on the basis of a low-cost hardware platform, so that the method is beneficial to the mass production of the platform.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic diagram illustrating a difference between an online parking space acquired by the SOC and an actual online parking space.
Fig. 2 is a schematic flow chart of a parking space fusion method according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of the parking space types defined by the present invention.
Fig. 4 is a schematic view of the parking space shape defined by the present invention.
Fig. 5 is a schematic diagram of a space and parking space search and obstacle fusion process in the embodiment of the present invention.
Fig. 6 is a schematic diagram of a line-parking space search and a fusion process with obstacles according to an embodiment of the present invention.
Fig. 7 is a schematic view illustrating a combination of a space parking space and a linear parking space, in which parking spaces are parallel parking spaces according to an embodiment of the present invention.
Fig. 8 is a logic diagram of the fusion processing of parking spaces when the parking spaces are parallel in shape according to the embodiment of the present invention.
Fig. 9 is a schematic view illustrating a combination of a space parking space and a linear parking space in which the parking space is vertical in shape in the embodiment of the present invention.
Fig. 10 is a logic diagram of the fusion processing of parking spaces when the parking space is a vertical parking space according to the embodiment of the present invention.
Detailed Description
The following description of the embodiments refers to the accompanying drawings, which are included to illustrate specific embodiments in which the invention may be practiced.
Referring to fig. 2, an embodiment of the present invention provides a parking space fusion method, including steps S101 to S102:
step S101, a parking place type and position information of the acquired parking places are acquired, wherein the parking place type comprises at least one of a space parking place and a line parking place, and the parking place type is a parallel parking place or a vertical parking place.
Specifically, referring to fig. 3 and 4, the parking space types include a space parking space and a line parking space, which are defined by referring to different reference objects for the same parking space, the line parking space is a parking space line with reference to the ground, and the space parking space is generated by the system according to reference objects around the parking space, for example, the reference objects of the space parking space in fig. 3 are vehicles on two sides of the parking space, and the area of the space parking space is larger than the area of the line parking space as long as the vehicles on two sides are parked in a standard (not beyond the range of the line parking space). The parking spaces are of the type including parallel parking spaces and vertical parking spaces, the parallel parking spaces are approximately parallel to a wall (reference object) in the direction from the head to the tail of the vehicle, the vertical parking spaces are approximately perpendicular to the wall in the direction from the head to the tail of the vehicle, and the vertical parking spaces can be further divided into vertical rectangular line parking spaces, forward parallel inclined parking spaces, reverse parallel inclined parking spaces, forward sawtooth inclined parking spaces and reverse sawtooth inclined parking spaces according to actual conditions, as shown in fig. 4. Due to the error of parking space detection and the diversity of parking space types, if the parking space is not fully considered in the parking space fusion process, the situation that the parking space which is finally fused is missed or misreported can be caused. The parking stall type diversity has been considered comprehensively to this scheme, can carry out the parking stall based on low-cost hardware platform and merge.
Specifically, the parking space type and the parking space type can be identified by providing an ultrasonic sensor and a camera sensor in the vehicle. The ultrasonic sensor can be used for searching the space parking space, the space parking space searching needs to refer to a reference object beside, the reference object can be a single-side reference object or a double-side reference object, and the reference object can be an object which is easy to detect by ultrasonic waves, such as a vehicle, a wall and the like beside. When only a single-side reference object exists, the space parking space can be obtained through a software algorithm. The line parking spaces in various shapes can be detected through the camera sensor, even if the parking space lines are not clear enough, the line parking space detection can be realized through a software algorithm as long as the parking space vertex close to the driving direction of the controlled vehicle is scanned, and meanwhile, the camera sensor can also realize the detection of obstacles such as ground locks, ice cream cones, pedestrians and the like through a certain algorithm. After the parking space type and the parking space type are obtained, the position information of the parking space is recorded, for example, four vertex coordinates of the parking space are obtained.
Step S102, judging whether an obstacle exists in the parking space, if not, determining the relative position of the space parking space and the line parking space according to the position information of the space parking space and the position information of the line parking space when the parking space type simultaneously comprises the space parking space and the line parking space; and determining the type and the position information of the output parking space according to the parking space type and the relative position.
Specifically, after the parking place type, the parking place type and the position information of the parking place are obtained, whether obstacles exist in the parking place can be further judged through the ultrasonic sensor and the camera sensor, and whether obstacles such as a ground lock, an ice cream tube and a pedestrian are in the current space parking place or a line parking place can be judged through the cooperation of a software algorithm. If the obstacle is in the space parking space or the line parking space, for example, a ground lock, an ice cream tube and the like exist in the parking space, the corresponding line parking space or the space parking space is cancelled, namely no parking space information is output. If do not have when the barrier in the parking stall, further include only the space parking stall according to current parking stall kind, only include the line parking stall to and including space parking stall and three kinds of circumstances of line parking stall simultaneously and handle, three kinds of circumstances are respectively: (1) the detected current parking space is only a wired parking space, and the fact that the vehicle is not parked beside the wired parking space is shown; (2) the detected current parking space is only a space parking space, which indicates that a parked vehicle is arranged beside the parking space, and the ground has no parking space line and can belong to a temporary parking space; (3) the current parking stall that detects includes two kinds of parking stalls, means that at least one adjacent parking stall of current line parking stall has stopped the vehicle, and the sensor has generated the space parking stall simultaneously on the basis of the online parking stall of thing according to this moment according to the reference, needs to do further processing to the line parking stall that detects and space parking stall this moment.
Specifically, when the parking space includes only one of a space parking space and a line parking space, that is, the sensor only recognizes the space parking space, or only recognizes the line parking space, the position information of the space parking space currently acquired or the position information of the line parking space is directly output, for example, four vertex coordinates of the parking space pattern are output. In this embodiment, when only a space parking space is identified, the process of searching the space parking space and merging the space parking space with the obstacle is shown in fig. 5. The flow of searching for line parking space and merging with obstacles when only line parking space is identified is shown in fig. 6.
When the current parking stall that detects includes space parking stall and line parking stall two kinds, need divide the condition to merge the processing to two kinds of parking stalls according to the type of parking stall. Firstly, defining the direction: the direction of movement which is consistent with the direction of the head of the vehicle is taken as the longitudinal direction, and the direction far away from the head of the vehicle is taken as the front direction. Conversely, the direction opposite to the direction of the head of the vehicle and far away from the head of the vehicle is defined as the rear direction.
(1) When the space slot and the line slot are parallel slots, as shown in fig. 7, the relative positional relationship of the boundaries (first boundaries) of the space slot (MNQP) and the line slot (M 'N' Q 'P') at the head and tail, that is, the relative positional relationship of MN, M 'N', and the relative positional relationship of PQ and P 'Q', are compared. If the MN is in front of the M 'N' and the PQ is behind the P 'Q', the line parking space is judged to be effective, and the parking space coordinate of the line parking space is taken as the current parallel parking space for fusion output. If not, namely MN is behind M 'N' or PQ is in front of P 'Q', for safety requirement, the linear parking space is invalid at this time, and the parking space coordinates of the spatial parking space are taken as the current parallel parking space to be fused and output, and the processing logic diagram is shown in fig. 8.
(2) When the spatial parking space and the linear parking space are vertical parking spaces, whether the types of the vertical parking spaces are consistent or not needs to be judged, when the shapes of the vertical parking spaces are consistent, the boundaries (second boundaries) of the spatial parking space (MNQP) and the linear parking space (M 'N' Q 'P') on the two sides of a vehicle (in a state after parking in the parking space) are compared, namely the relative position relationship of MN and M 'N' in the graph 9 and the relative position relationship of PQ and P 'Q', if MN is in front of M 'N' and PQ is behind P 'Q', the linear parking space is judged to be effective, and the parking space coordinate of the linear parking space is taken as the current parallel parking space to be fused and output. If not, namely MN is behind M 'N' or PQ is in front of P 'Q', for safety requirement, the linear parking space is invalid, and the parking space coordinate of the space parking space is taken as the current parallel parking space for fusion output.
(3) When the space parking space and the line parking space are vertical parking spaces and the types of the vertical parking spaces are inconsistent, and the line parking space is any one of a forward parallel inclined-row parking space, a reverse parallel inclined-row parking space, a forward sawtooth inclined-row parking space and a reverse sawtooth inclined-row parking space, namely, the line parking space is not a vertical rectangular parking space, because the automobile moves along the longitudinal direction, the ultrasonic sensor can only detect the vertical rectangular space parking space, and the rectangular parking space can meet the requirements of the parking spaces and can not be met to be cancelled, therefore, the line parking space is used as the standard at the moment, and the position information of the line parking space is output. Fig. 10 shows the processing logic diagrams of the cases (2) and (3).
Further, after the line parking space is determined as the standard for the situation (3), when the vehicle starts to park in the line parking space, the position information of the space parking space is obtained again, the space parking space which is the same as the vertical parking space of the line parking space in type can be obtained at the moment, the execution step of the situation (2) is repeated at the moment, the final parking space type can be obtained, and the corresponding parking space position is output.
Aiming at some special conditions, the detected parking space only comprises one of a space parking space and a linear parking space, the area of the parking space is large enough, so that when the area requirements of the parallel parking spaces and the area requirements of the vertical parking spaces are met simultaneously, the position information of the parallel parking spaces or the position information of the vertical parking spaces is output at the moment, and the vehicle can park according to the parallel parking spaces or the vertical parking spaces.
As can be seen from the above description, compared with the prior art, the beneficial effects of the present invention are: according to the invention, when the parking space is identified, the obstacle condition is comprehensively considered, and the parking space type are combined, so that the parking space and the obstacle are fused, and the parking space are fused, and the final parking space is obtained. Due to the error of parking space detection and the diversity of parking space types, if the parking space fusion process is not fully considered, situations such as missed parking space or false parking space can be finally obtained through fusion, and a complex parking planning process needs to be processed for realization. Therefore, through the implementation of the scheme, the parking space identification accuracy can be improved. Meanwhile, the scheme has low requirement on the SOC processor, the algorithm is relatively simple, and the method is developed on the basis of a low-cost hardware platform, so that the method is beneficial to the mass production of the platform.
Based on the above embodiment, the present invention provides an embodiment of a parking space fusion system, which includes:
the ultrasonic sensor is used for acquiring the parking place type and position information of the space parking place;
the camera sensor is used for acquiring the parking place type and position information of the line parking place;
the parking space type is a parallel parking space or a vertical parking space;
the ultrasonic sensor and the camera sensor are also used for acquiring the information of the obstacles in the parking space;
the parking space fusion processing unit is used for judging whether an obstacle exists in the parking space or not, if the obstacle does not exist in the parking space, and when the parking space types simultaneously comprise a space parking space and a line parking space, determining the relative positions of the space parking space and the line parking space according to the position information of the space parking space and the position information of the line parking space; and determining the type and the position information of the output parking space according to the parking space type and the relative position.
Further, the parking stall fuses the processing unit and can also be used for, the parking stall fuses the processing unit, still is used for: when the space parking spaces and the line parking spaces are parallel parking spaces, comparing the relative position relation of the space parking spaces and the line parking spaces on first boundaries of the vehicle head and the vehicle tail;
when the two first boundaries of the line parking space are both located within the first boundaries of the space parking spaces, determining to output the line parking space and the position information thereof;
and when at least one first boundary of the line parking spaces is positioned outside the first boundary corresponding to the space parking spaces, determining to output the space parking spaces and the position information thereof.
Further, the parking space fusion processing unit is also used for: work as the space parking stall with when line parking stall is perpendicular parking stall, judge the space parking stall with whether the perpendicular parking stall type of line parking stall is the same, perpendicular parking stall type includes: the parking spaces comprise vertical rectangular line parking spaces, forward parallel inclined parking spaces, reverse parallel inclined parking spaces, forward sawtooth inclined parking spaces and reverse sawtooth inclined parking spaces;
when the vertical parking spaces of the space parking space and the line parking space are the same in type, comparing the relative position relation of the space parking space and the line parking space on second boundaries at two sides of the vehicle;
when the two second boundaries of the line parking space are both located within the second boundaries of the space parking spaces, determining to output the line parking space and the position information thereof;
and when at least one second boundary of the line parking space is positioned outside the second boundary corresponding to the space parking space, determining to output the space parking space and the position information thereof.
Further, the parking space fusion processing unit is also used for:
when the space parking stall with the perpendicular parking stall type of line parking stall is inequality, just the line parking stall is when any one of forward parallel strabismus parking stall, reverse parallel strabismus parking stall, forward sawtooth strabismus parking stall and reverse sawtooth strabismus parking stall, then confirms to export line parking stall and positional information.
Further, the parking space fusion processing unit is further configured to determine to output the currently acquired space parking space and the position information thereof or determine to output the currently acquired line parking space and the position information thereof when the parking space type includes only one of the space parking space and the line parking space.
Further, the parking space fusion processing unit is also used for: when the parking space type only comprises one of a space parking space and a linear parking space, and the area of the parking space simultaneously accords with the area requirement of a parallel parking space and the area requirement of a vertical parking space, the position information of the parallel parking space or the position information of the vertical parking space is output.
For the working principle and process of the parking space fusion system of this embodiment, refer to the description of the first embodiment of the present invention, which is not further described herein.
As can be seen from the above description, compared with the prior art, the beneficial effects of the present invention are: according to the invention, when the parking space is identified, the obstacle condition is comprehensively considered, and the parking space type are combined, so that the parking space and the obstacle are fused, and the parking space are fused, and the final parking space is obtained. Through the implementation of this scheme, can improve parking stall discernment rate of accuracy. Meanwhile, the scheme has low requirement on the SOC processor, the algorithm is relatively simple, and the method is developed on the basis of a low-cost hardware platform, so that the method is beneficial to the mass production of the platform.
The above disclosure is only for the purpose of illustrating the preferred embodiments of the present invention, and it is therefore to be understood that the invention is not limited by the scope of the appended claims.
Claims (15)
1. The parking space fusion method is characterized by comprising the following steps:
step S1, acquiring parking space types, parking space types and position information of the acquired parking spaces, wherein the parking space types comprise at least one of space parking spaces and linear parking spaces, and the parking space types are parallel parking spaces or vertical parking spaces;
step S2, judging whether an obstacle exists in the parking space, if not, determining the relative position of the space parking space and the line parking space according to the position information of the space parking space and the position information of the line parking space when the parking space types simultaneously include space parking spaces and line parking spaces; and determining the type and the position information of the output parking space according to the parking space type and the relative position.
2. The parking space fusion method according to claim 1, wherein the step S2 specifically comprises:
when the space parking spaces and the line parking spaces are parallel parking spaces, comparing the relative position relation of the space parking spaces and the line parking spaces on first boundaries of the vehicle head and the vehicle tail;
when the two first boundaries of the line parking space are both located within the first boundaries of the space parking spaces, determining to output the line parking space and the position information thereof;
and when at least one first boundary of the line parking spaces is positioned outside the first boundary corresponding to the space parking spaces, determining to output the space parking spaces and the position information thereof.
3. The parking space fusion method according to claim 1, wherein the step S2 specifically comprises:
when the space parking space and the line parking space are both vertical parking spaces, judging whether the vertical parking spaces of the space parking space and the line parking space are the same in type; the vertical parking space types include: the parking spaces comprise vertical rectangular line parking spaces, forward parallel inclined parking spaces, reverse parallel inclined parking spaces, forward sawtooth inclined parking spaces and reverse sawtooth inclined parking spaces;
when the vertical parking spaces of the space parking space and the line parking space are the same in type, comparing the relative position relation of the space parking space and the line parking space on second boundaries at two sides of the vehicle;
when the two second boundaries of the line parking space are both located within the second boundaries of the space parking spaces, determining to output the line parking space and the position information thereof;
and when at least one second boundary of the line parking space is positioned outside the second boundary corresponding to the space parking space, determining to output the space parking space and the position information thereof.
4. The parking space fusion method according to claim 3, wherein the step S2 specifically comprises:
when the space parking stall with the perpendicular parking stall type of line parking stall is inequality, just the line parking stall is when any one of forward parallel strabismus parking stall, reverse parallel strabismus parking stall, forward sawtooth strabismus parking stall and reverse sawtooth strabismus parking stall, then confirms to export line parking stall and positional information.
5. The parking space fusion method according to claim 4, wherein the step S2 further comprises:
when the vehicle starts to park in the line parking space, the position information of the space parking space is updated;
and outputting the updated position information of the space parking spaces or the position information of the line parking spaces according to the relative positions of the line parking spaces and the updated space parking spaces.
6. The parking space fusion method according to claim 5, wherein outputting the updated position information of the space parking space or the updated position information of the line parking space according to the relative position of the line parking space and the updated space parking space specifically comprises:
comparing the relative position relation of the updated space parking spaces and the second boundaries of the line parking spaces at the two sides of the vehicle;
when the two second boundaries of the line parking space are both located within the second boundaries of the updated space parking space, determining to output the line parking space and the position information thereof;
and when at least one second boundary of the line parking space is positioned outside the second boundary corresponding to the updated space parking space, determining to output the updated space parking space and the position information thereof.
7. The parking space fusion method according to any one of claims 1 to 6, further comprising:
and step S3, when the parking space type only includes one of a space parking space and a line parking space, determining to output the currently acquired space parking space and the position information thereof, or determining to output the currently acquired line parking space and the position information thereof.
8. The parking space fusion method according to any one of claims 1 to 6, further comprising:
and step S4, when the parking space type only includes one of a space parking space and a linear parking space, and the area of the parking space simultaneously meets the area requirement of a parallel parking space and the area requirement of a vertical parking space, outputting the position information of the parallel parking space or the position information of the vertical parking space.
9. The utility model provides a parking stall fusion system which characterized in that includes:
the ultrasonic sensor is used for acquiring the parking place type and position information of the space parking place;
the camera sensor is used for acquiring the parking place type and position information of the line parking place;
the parking space type is a parallel parking space or a vertical parking space;
the ultrasonic sensor and the camera sensor are also used for acquiring the information of the obstacles in the parking space;
the parking space fusion processing unit is used for judging whether an obstacle exists in the parking space or not, if the obstacle does not exist in the parking space, and when the parking space types simultaneously comprise a space parking space and a line parking space, determining the relative positions of the space parking space and the line parking space according to the position information of the space parking space and the position information of the line parking space; and determining the type and the position information of the output parking space according to the parking space type and the relative position.
10. The parking space fusion system of claim 9, wherein the parking space fusion processing unit is further configured to:
when the space parking spaces and the line parking spaces are parallel parking spaces, comparing the relative position relation of the space parking spaces and the line parking spaces on first boundaries of the vehicle head and the vehicle tail;
when the two first boundaries of the line parking space are both located within the first boundaries of the space parking spaces, determining to output the line parking space and the position information thereof;
and when at least one first boundary of the line parking spaces is positioned outside the first boundary corresponding to the space parking spaces, determining to output the space parking spaces and the position information thereof.
11. The parking space fusion system of claim 9, wherein the parking space fusion processing unit is further configured to:
work as the space parking stall with when line parking stall is perpendicular parking stall, judge the space parking stall with whether the perpendicular parking stall type of line parking stall is the same, perpendicular parking stall type includes: the parking spaces comprise vertical rectangular line parking spaces, forward parallel inclined parking spaces, reverse parallel inclined parking spaces, forward sawtooth inclined parking spaces and reverse sawtooth inclined parking spaces;
when the vertical parking spaces of the space parking space and the line parking space are the same in type, comparing the relative position relation of the space parking space and the line parking space on second boundaries at two sides of the vehicle;
when the two second boundaries of the line parking space are both located within the second boundaries of the space parking spaces, determining to output the line parking space and the position information thereof;
and when at least one second boundary of the line parking space is positioned outside the second boundary corresponding to the space parking space, determining to output the space parking space and the position information thereof.
12. The parking space fusion system of claim 11, wherein the parking space fusion processing unit is further configured to:
when the space parking stall with the perpendicular parking stall type of line parking stall is inequality, just the line parking stall is when any one of forward parallel strabismus parking stall, reverse parallel strabismus parking stall, forward sawtooth strabismus parking stall and reverse sawtooth strabismus parking stall, then confirms to export line parking stall and positional information.
13. The parking space fusion system of claim 12, wherein the parking space fusion processing unit is further configured to:
when the vehicle starts to park in the line parking space, the position information of the space parking space is updated;
and outputting the updated position information of the space parking spaces or the position information of the line parking spaces according to the relative positions of the line parking spaces and the updated space parking spaces.
14. The parking space fusion system of claim 9, wherein the parking space fusion processing unit is further configured to determine to output the currently acquired space parking space and the position information thereof or determine to output the currently acquired line parking space and the position information thereof when the parking space type includes only one of a space parking space and a line parking space.
15. The parking space fusion system of claim 9, wherein the parking space fusion processing unit is further configured to:
when the parking space type only comprises one of a space parking space and a linear parking space, and the area of the parking space simultaneously accords with the area requirement of a parallel parking space and the area requirement of a vertical parking space, the position information of the parallel parking space or the position information of the vertical parking space is output.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011029534.9A CN112124303A (en) | 2020-09-27 | 2020-09-27 | Parking space fusion method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011029534.9A CN112124303A (en) | 2020-09-27 | 2020-09-27 | Parking space fusion method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112124303A true CN112124303A (en) | 2020-12-25 |
Family
ID=73840384
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011029534.9A Pending CN112124303A (en) | 2020-09-27 | 2020-09-27 | Parking space fusion method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112124303A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113112846A (en) * | 2021-05-20 | 2021-07-13 | 中国第一汽车股份有限公司 | Parking navigation method, device, equipment and storage medium |
| CN114111815A (en) * | 2021-11-01 | 2022-03-01 | 广州小鹏自动驾驶科技有限公司 | Map data processing method and device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20120130449A (en) * | 2011-05-23 | 2012-12-03 | 아진산업(주) | Method for providing of vehicle parking assistant image and system for providing thereof |
| CN106494395A (en) * | 2016-09-30 | 2017-03-15 | 惠州华阳通用电子有限公司 | A kind of automatic parking control method and device based on data fusion |
| CN108806308A (en) * | 2018-04-29 | 2018-11-13 | 惠州市德赛西威汽车电子股份有限公司 | A kind of parking stall recognition methods and method of parking |
| CN110293964A (en) * | 2019-06-25 | 2019-10-01 | 重庆长安汽车股份有限公司 | Automatic parking merges parking stall judgment method, system, computer readable storage medium and vehicle |
| CN110889974A (en) * | 2018-09-11 | 2020-03-17 | 广州汽车集团股份有限公司 | Intelligent parking space identification method and device and automobile |
| CN111191485A (en) * | 2018-11-14 | 2020-05-22 | 广州汽车集团股份有限公司 | Parking space detection method and system and automobile |
| CN111624610A (en) * | 2020-04-29 | 2020-09-04 | 东风汽车集团有限公司 | Parking space angle-based self-adaptive parking ultrasonic radar adjusting method |
-
2020
- 2020-09-27 CN CN202011029534.9A patent/CN112124303A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20120130449A (en) * | 2011-05-23 | 2012-12-03 | 아진산업(주) | Method for providing of vehicle parking assistant image and system for providing thereof |
| CN106494395A (en) * | 2016-09-30 | 2017-03-15 | 惠州华阳通用电子有限公司 | A kind of automatic parking control method and device based on data fusion |
| CN108806308A (en) * | 2018-04-29 | 2018-11-13 | 惠州市德赛西威汽车电子股份有限公司 | A kind of parking stall recognition methods and method of parking |
| CN110889974A (en) * | 2018-09-11 | 2020-03-17 | 广州汽车集团股份有限公司 | Intelligent parking space identification method and device and automobile |
| CN111191485A (en) * | 2018-11-14 | 2020-05-22 | 广州汽车集团股份有限公司 | Parking space detection method and system and automobile |
| CN110293964A (en) * | 2019-06-25 | 2019-10-01 | 重庆长安汽车股份有限公司 | Automatic parking merges parking stall judgment method, system, computer readable storage medium and vehicle |
| CN111624610A (en) * | 2020-04-29 | 2020-09-04 | 东风汽车集团有限公司 | Parking space angle-based self-adaptive parking ultrasonic radar adjusting method |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113112846A (en) * | 2021-05-20 | 2021-07-13 | 中国第一汽车股份有限公司 | Parking navigation method, device, equipment and storage medium |
| CN114111815A (en) * | 2021-11-01 | 2022-03-01 | 广州小鹏自动驾驶科技有限公司 | Map data processing method and device |
| CN114111815B (en) * | 2021-11-01 | 2023-02-03 | 广州小鹏自动驾驶科技有限公司 | Map data processing method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109649384B (en) | Parking assisting method | |
| JP6231345B2 (en) | Vehicle start support device | |
| EP1361543B1 (en) | Determining object motion from optical flow analysis | |
| CN110293964B (en) | Automatic parking fusion parking space judgment method and system, computer readable storage medium and vehicle | |
| JP3866328B2 (en) | Vehicle peripheral three-dimensional object recognition device | |
| JP7088135B2 (en) | Signal display estimation system | |
| JP3516856B2 (en) | Outside monitoring device | |
| CN109131317A (en) | Automatic vertical parking system and method based on multisection type planning and machine learning | |
| CN112455430B (en) | Method for detecting inclined parking places without parking place lines, parking method and parking system | |
| US8233663B2 (en) | Method for object formation | |
| TW201704067A (en) | Collision avoidance method, computer program product for said collision avoidance method and collision avoidance system | |
| CN104933409A (en) | Parking space identification method based on point and line features of panoramic image | |
| CN112124303A (en) | Parking space fusion method and system | |
| US10885356B2 (en) | Parking assisting apparatus and control unit | |
| CN112776797A (en) | Original parking space parking establishment method and system, vehicle and storage medium | |
| CN104417550A (en) | Back-sideways alarming system for vehicle and alarming control method thereof | |
| CN114056324B (en) | Parking space recognition method and system based on data fusion | |
| CN112009462A (en) | Forward automatic parking method and device | |
| CN113386736B (en) | Automatic parking control system and control method for new energy automobile | |
| Jung et al. | Isrss: Integrated side/rear safety system | |
| CN113954822A (en) | Method for automatically parking vehicle in side direction | |
| JP2018165945A (en) | Obstacle detection device | |
| Li et al. | LiDAR-based high-accuracy parking slot search, detection, and tracking | |
| CN113655486B (en) | Automatic parking method based on single rearview camera and multiple radars | |
| Choi et al. | Optimal Moving Windows for Real‐Time Road Image Processing |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201225 |