CN117671968A - Parking space detection method and device, storage medium and electronic equipment - Google Patents
Parking space detection method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN117671968A CN117671968A CN202311561577.5A CN202311561577A CN117671968A CN 117671968 A CN117671968 A CN 117671968A CN 202311561577 A CN202311561577 A CN 202311561577A CN 117671968 A CN117671968 A CN 117671968A
- Authority
- CN
- China
- Prior art keywords
- camera
- vehicle
- parking space
- determining
- detection result
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 154
- 238000012544 monitoring process Methods 0.000 claims abstract description 39
- 238000000034 method Methods 0.000 claims abstract description 23
- 238000004590 computer program Methods 0.000 claims description 8
- 238000013507 mapping Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 9
- 238000012545 processing Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 4
- 230000004397 blinking Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention discloses a parking space detection method, a device, a storage medium and electronic equipment, and relates to the technical field of information, wherein the method comprises the following steps: acquiring a video image shot by a camera in a parking lot, a camera rotation angle corresponding to the video image, and a detection result of an ultrasonic radar on whether the parking space is occupied or not; identifying a vehicle in the video image, and determining a vehicle center according to contour information of the vehicle; determining a detection result of whether the camera is occupied for the parking space according to the vehicle center and the rotation angle of the camera; determining a confidence coefficient region of the vehicle in a camera monitoring range according to the vehicle center; and comprehensively determining the occupation condition of the parking space according to the confidence coefficient region, the detection result of the ultrasonic radar and the detection result of the camera. The invention can detect the free parking space with precision.
Description
Technical Field
The present invention relates to the field of information technologies, and in particular, to a method and apparatus for detecting a parking space, a storage medium, and an electronic device.
Background
The parking lot parking space guiding device adopts the technology comprising a sensing technology, data communication and data processing, and in addition, the technology further comprises an LED/LCD display screen, a mobile application program, a voice prompt and cloud integration, and the development of the technology enables parking lot management to be more efficient, so that an owner can find available parking spaces more easily.
Currently, when detecting an idle parking space in a parking lot, a single sensor is generally adopted for detection. However, this detection method may be limited by the detection range of a single sensor, or the shielding of an obstacle, and it is difficult to accurately identify an empty parking space.
Disclosure of Invention
The invention provides a parking space detection method, a device, a storage medium and electronic equipment, which mainly aim to improve the detection precision of an idle parking space.
According to a first aspect of an embodiment of the present invention, there is provided a parking space detection method, applied to an edge computing device, including:
acquiring a video image shot by a camera in a parking lot, a camera rotation angle corresponding to the video image, and a detection result of an ultrasonic radar on whether the parking space is occupied or not;
identifying a vehicle in the video image, and determining a vehicle center according to contour information of the vehicle;
determining a detection result of whether the camera is occupied for the parking space according to the vehicle center and the rotation angle of the camera;
determining a confidence coefficient region of the vehicle in a camera monitoring range according to the vehicle center;
and comprehensively determining the occupation condition of the parking space according to the confidence coefficient region, the detection result of the ultrasonic radar and the detection result of the camera.
According to a second aspect of an embodiment of the present invention, there is provided a parking space detection apparatus including:
the device comprises an acquisition unit, a detection unit and a control unit, wherein the acquisition unit is used for acquiring video images shot by cameras in a parking lot, camera rotation angles corresponding to the video images and detection results of an ultrasonic radar aiming at whether the parking space is occupied or not;
an identification unit configured to identify a vehicle in the video image and determine a vehicle center according to contour information of the vehicle;
the first determining unit is used for determining whether the camera is occupied for the parking space or not according to the vehicle center and the rotation angle of the camera;
the second determining unit is used for determining a confidence coefficient region of the vehicle in the monitoring range of the camera according to the center of the vehicle;
and the third determining unit is used for comprehensively determining the parking space occupation condition according to the confidence coefficient region, the detection result of the ultrasonic radar and the detection result of the camera.
According to a third aspect of embodiments of the present invention, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:
acquiring a video image shot by a camera in a parking lot, a camera rotation angle corresponding to the video image, and a detection result of an ultrasonic radar on whether the parking space is occupied or not;
identifying a vehicle in the video image, and determining a vehicle center according to contour information of the vehicle;
determining a detection result of whether the camera is occupied for the parking space according to the vehicle center and the rotation angle of the camera;
determining a confidence coefficient region of the vehicle in a camera monitoring range according to the vehicle center;
and comprehensively determining the occupation condition of the parking space according to the confidence coefficient region, the detection result of the ultrasonic radar and the detection result of the camera.
According to a fourth aspect of embodiments of the present invention, there is provided an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the program:
acquiring a video image shot by a camera in a parking lot, a camera rotation angle corresponding to the video image, and a detection result of an ultrasonic radar on whether the parking space is occupied or not;
identifying a vehicle in the video image, and determining a vehicle center according to contour information of the vehicle;
determining a detection result of whether the camera is occupied for the parking space according to the vehicle center and the rotation angle of the camera;
determining a confidence coefficient region of the vehicle in a camera monitoring range according to the vehicle center;
and comprehensively determining the occupation condition of the parking space according to the confidence coefficient region, the detection result of the ultrasonic radar and the detection result of the camera.
The innovation point of the invention is as follows:
1. according to the invention, the monitoring camera and the ultrasonic radar are arranged in the parking lot, so that the situation that the parking space is occupied can be comprehensively judged according to the detection result of the camera and the detection result of the ultrasonic radar, the problem that the detection result of a single sensor is abnormal can be solved, and the detection precision of the idle parking space is improved.
2. The invention reduces the number of cameras, thereby reducing the equipment deployment cost of the parking lot.
3. According to the invention, the parking space guiding logic is optimized, the guiding devices are respectively installed in each area, and the guiding devices flash when a vehicle runs in the area, so that the guiding information is clearer and has pertinence.
4. According to the invention, a distributed computing architecture is adopted, and embedded computing units with lower cost are arranged in each area of the parking lot, the embedded computing units in each area are responsible for sensor data processing in the area, and the processing results are communicated and transmitted between devices, so that the wiring harness is only required to be connected to the embedded computing devices in a small-range area, and the arrangement cost of the server and the wiring harness can be reduced.
Compared with the prior art, the parking space detection method, the device, the storage medium and the electronic equipment can acquire the video image shot by the camera in the parking lot, the camera rotation angle corresponding to the video image and the detection result of the ultrasonic radar on whether the parking space is occupied or not, identify the vehicle in the video image, determine the vehicle center according to the contour information of the vehicle, determine the detection result of the camera on whether the parking space is occupied or not according to the vehicle center and the camera rotation angle, determine the confidence coefficient region of the vehicle in the monitoring range of the camera according to the vehicle center, and finally comprehensively determine the parking space occupation condition according to the confidence coefficient region, the detection result of the ultrasonic radar and the detection result of the camera. Therefore, the invention can comprehensively judge the situation that the parking space is occupied according to the detection result of the camera and the detection result of the ultrasonic radar by arranging the monitoring camera and the ultrasonic radar in the parking lot, thereby solving the problem that the detection result of a single sensor is abnormal, improving the detection precision of the idle parking space, reducing the use quantity of the camera and reducing the equipment deployment cost of the parking lot. Furthermore, the invention adopts a distributed computing architecture, and the embedded computing units with lower cost are arranged in each area of the parking lot, so that the wiring harness is only required to be connected to the embedded computing equipment in a small-range area, and the arrangement cost of the server and the wiring harness can be reduced.
The foregoing description is only an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 shows a schematic flow chart of a parking space detection method according to an embodiment of the present invention;
fig. 2 shows a schematic diagram of an ultrasonic radar combined with a camera according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a distributed data processing framework provided by an embodiment of the present invention;
fig. 4 is a schematic diagram showing a sensing range of a camera at different rotation angles according to an embodiment of the present invention;
fig. 5 shows a schematic diagram of an arrangement position of an ultrasonic radar according to an embodiment of the present invention;
fig. 6 is a schematic diagram of different areas of a camera monitoring screen according to an embodiment of the present invention;
FIG. 7 shows a schematic diagram of path search provided by an embodiment of the present invention;
fig. 8 is a schematic structural diagram of a parking space detection device according to an embodiment of the present invention;
fig. 9 shows a schematic entity structure of an electronic device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without any inventive effort, are intended to be within the scope of the invention.
It should be noted that the terms "comprising" and "having" and any variations thereof in the embodiments of the present invention and the accompanying drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.
The existing detection mode can be limited by the detection range of a single sensor or the shielding of an obstacle, and the idle parking space is difficult to accurately identify.
In order to overcome the above-mentioned drawbacks, an embodiment of the present invention provides a parking space detection method applied to an edge computing device, as shown in fig. 1, the method includes:
step 101, acquiring a video image shot by a camera in a parking lot, a camera rotation angle corresponding to the video image, and a detection result of an ultrasonic radar on whether the parking space is occupied or not.
The embodiment of the invention is mainly suitable for detecting the scene of the idle parking space in the parking lot. The execution subject of the embodiment of the invention is a device or equipment capable of detecting an idle parking space in a parking lot, such as an edge computing equipment.
In order to improve the detection precision of an idle parking space in a parking lot, the embodiment of the invention simultaneously arranges a monitoring camera and an ultrasonic radar in the parking lot, as shown in fig. 2. In addition, in order to reduce the cost of the server and the cost of the wiring harness arrangement, the embodiment of the invention adopts a distributed computing architecture, namely, embedded computing devices with lower cost are arranged in different areas, as shown in fig. 3, the embedded computing devices in each area are responsible for processing sensor data in the area and communicating and transmitting processing results to other edge computing devices, so that the wiring harness is only required to be connected to an embedded computing unit in a small-range area, thereby not only reducing the cost of the server, but also reducing the cost of the wiring harness arrangement.
Further, the camera adopted in the embodiment of the invention is a camera with a rotation function, and through rotation at different angles, the information of the free parking spaces in 4 directions can be judged, as shown in fig. 4. For the ultrasonic radar sensor, the ultrasonic radar sensor may be disposed on the floor or ceiling right behind each parking space according to the actual space situation of the parking space, as shown in fig. 5, and the ultrasonic radar is disposed at an angle to the floor or ceiling.
Further, before formally detecting the free parking space, the parking space calibration is performed on the image collected by the camera in each direction, namely four vertex coordinates of the parking space in the image collected in each direction are recorded, then the vertex coordinates are stored in a csv file, and the rotation state bit information of the current camera is marked according to the rotation angle of the camera, for example, 0-0 °, 1-90 °, 2-180 °, and 3-270 °. The rotation state bit information indicates that only vertex coordinate information of a parking space corresponding to the rotation state bit information is effective under the direction of the current camera, so that the subsequent idle parking space judgment and use are convenient, and the finally generated preset parking space coordinate information is shown as follows:
TABLE 1
| Status bit | Parking space identification | Coordinate 1 | Coordinates 2 | Coordinates 3 | Coordinates 4 |
| 0 | 101 | (246,430) | (19,457) | (130,479) | (322,440) |
| ... | ... | ... | ... | ... | ... |
| 2 | 163 | (412,450) | (268,502) | (419,528) | (505,462) |
| 2 | 164 | (540,467) | (487,533) | (677,569) | (641,481) |
| ... | ... | ... | ... | ... | .... |
For the embodiment of the invention, when the detection of the free parking space is specifically performed, the camera records the currently shot picture data (video image in RGB format) and the current rotation angle of the camera, and sends the information to the edge computing equipment in the corresponding area for processing. At the same time, the ultrasonic radar sensor records whether the corresponding parking space is occupied or not, and sends the situation to edge computing equipment in the corresponding area for processing.
And 102, identifying the vehicle in the video image, and determining the center of the vehicle according to the contour information of the vehicle.
For the embodiment of the invention, after the edge computing device receives the sensor (camera and ultrasonic radar) data, the edge computing device can judge the parking space occupation condition of the corresponding management area according to the sensor data. For the camera, first, the vehicle in the video image is identified, and for this process, step 102 specifically includes: and inputting the video image into a preset target detection model to detect the vehicle, and outputting the vehicle and corresponding contour information in the video image. The preset target detection model can be a yolo model, an ssd model and the like, the contour information of the vehicle specifically comprises information such as the length, the width and the center of the contour, and the center of the contour is the center of the vehicle.
And step 103, determining a detection result of whether the camera is occupied for the parking space according to the vehicle center and the rotation angle of the camera.
For the embodiment of the present invention, in order to determine the detection result of whether the camera is occupied for the parking space, step 103 specifically includes: determining the rotation state bit information of the camera according to the rotation angle of the camera and the mapping relation between different rotation angles of the camera and different rotation state bit information; and determining a detection result of whether the camera is occupied for the parking space according to the vehicle center and the rotation state bit information.
Further, the determining, according to the vehicle center and the rotation status bit information, a detection result of whether the camera is occupied for the parking space, includes: inquiring a preset parking space coordinate information table according to the rotation state bit information, and determining vertex coordinates of corresponding parking spaces in the video image, wherein parking space identifiers and vertex coordinates corresponding to different rotation state bit information are recorded in the preset parking space coordinate information table; if the center of the vehicle is in a quadrilateral range enclosed by the vertex coordinates, determining that the detection result of the camera is that the corresponding parking space is occupied; if the center of the vehicle is not in the quadrilateral range enclosed by the vertex coordinates, determining that the detection result of the camera is that the corresponding parking space is unoccupied.
For example, assuming that the rotation frequency of the camera is rotated 90 ° per minute, that is, rotated once per 4 minutes, the current camera rotation angle is 180 °, the rotation state bit information of the camera can be determined to be 2 according to the mapping relationship between the different camera rotation angles and the different rotation state bit information, and then the preset parking space coordinate information table (table 1) is queried according to the rotation state bit information, and the vertex coordinates of the parking spaces 163 and 164 in the video image can be determined. Then, whether the center of the vehicle is in a quadrilateral range enclosed by the vertex coordinates of the parking space 163 is respectively judged, and if the center of the vehicle is in the quadrilateral range enclosed by the vertex coordinates of the parking space 163, the parking space 163 is occupied; if it is not within the quadrangular range enclosed by the vertex coordinates of the parking space 163, it is indicated that the parking space 163 is not occupied. And similarly, whether parking space 164 is occupied may be determined.
And 104, determining a confidence coefficient region of the vehicle in a camera monitoring range according to the vehicle center.
In the embodiment of the invention, the monitoring range of the camera is a curved surface, so that the confidence of different monitoring area ranges is different. If the vehicle center is in the first area range of the video image, determining a high confidence level area of the vehicle in the monitoring range of the camera; and if the center of the vehicle is in the second area range of the video image, determining a low confidence level area of the vehicle in the monitoring range of the camera.
The first area range and the second area range may be set according to actual service requirements, and the embodiment of the present invention does not specifically limit the division of the monitoring area range and the confidence area.
As shown in fig. 6, the 3/4 area range of the camera monitoring screen is a high confidence area of the camera, and the 1/4 area range of the periphery of the camera monitoring screen is a low confidence area of the camera. The proportion of the high confidence region is specifically selected to be correspondingly adjusted according to cameras with different optical characteristics.
And 105, comprehensively determining the parking space occupation condition according to the confidence coefficient region, the detection result of the ultrasonic radar and the detection result of the camera.
For the embodiment of the invention, the situation that the occupation condition of the parking space is detected by using the camera alone may generate false detection in the edge area of the visual field range of the camera, and in order to improve the detection precision of the idle parking space, the embodiment of the invention fuses the detection result of the camera with the detection result of the ultrasonic radar based on the confidence level area of the vehicle in the monitoring range of the camera, and aiming at the process, the method comprises the following steps: if the vehicle is in a high confidence coefficient area in the monitoring range of the camera, determining the parking space occupation condition according to the detection result of the ultrasonic radar and the detection result of the camera; if the vehicle is in a low confidence coefficient region in the camera monitoring range, estimating the proportioning condition of the number of vehicles and the number of parking spaces in the low confidence coefficient region, and determining the occupation condition of the parking spaces according to the proportioning condition, the detection result of the ultrasonic radar and the detection result of the camera.
Further, the estimating the ratio of the number of vehicles to the number of parking spaces in the low confidence region includes: counting the number of vehicles in the low confidence coefficient region and the number of parking spaces in the low confidence coefficient region; if the number of vehicles is greater than or equal to the number of parking spaces, determining that the proportioning condition is insufficient parking spaces; and if the number of vehicles is smaller than the number of parking spaces, determining that the proportioning condition is sufficient.
Specifically, when the vehicle is in the high confidence region within the monitoring range of the camera, the parking space occupation condition is determined directly according to the detection result of the ultrasonic radar and the detection result of the camera, for example, if the detection result of the ultrasonic radar is 1 (i.e. the parking space is occupied), and the detection result of the camera is 1, the parking space is occupied; if the detection result of the ultrasonic radar is 1 and the detection result of the camera is 0, the parking space is not occupied; if the detection result of the ultrasonic radar is 0 and the detection result of the camera is 1, the parking space is occupied; if the detection result of the ultrasonic radar is 0 and the detection result of the camera is 0, the parking space is not occupied.
Further, when the vehicle is in a low confidence coefficient region in the camera monitoring range, the parking space occupation condition is comprehensively determined according to the proportioning condition of the number of vehicles and the number of parking spaces in the low confidence coefficient region, the detection result of the ultrasonic radar and the detection result of the camera, specifically as shown in table 2, aiming at the confidence coefficient region, 1 represents a high confidence coefficient region, and 0 represents a low confidence coefficient region; aiming at the detection result of the camera and the detection result of the ultrasonic radar, 1 represents that the parking space is occupied, and 0 represents that the parking space is unoccupied; for the situation of the ratio of the parking spaces, 1 represents insufficient parking spaces, and 0 represents sufficient parking spaces; for whether a parking space is occupied, 1 represents that the parking space is occupied, and 0 represents that the parking space is unoccupied.
TABLE 2
In a specific application scenario, parking guidance may be further performed according to a parking space analysis result of each edge computing device, and for the process, the method further includes: receiving parking space occupation conditions broadcast by other nearby edge computing devices; generating a parking space topological graph related to each edge computing device according to the parking space occupation situation of the area which is responsible for the edge computing device and the parking space occupation situation of the area which is responsible for other edge computing devices; performing path searching based on the parking space topological graph, and determining a guide path with the largest number of idle parking spaces along the way; and issuing a guide instruction to the corresponding guide equipment according to the guide path.
Specifically, after the edge computing device detects whether the parking space is occupied, the number of free parking spaces may be broadcast to nearby edge computing devices. Each edge computing device can be regarded as a node, and the node comprises the number of idle parking spaces in the current area and the number of idle parking spaces in the adjacent area. Therefore, the parking lot can be regarded as a topological graph, a graph searching algorithm is executed, as shown in fig. 7, dijkstra, a, and other algorithms can be adopted to generate a guiding path with the largest number of idle parking spaces along the way, for example, the reciprocal of the number of idle parking spaces corresponding to each edge computing device node is taken, the reciprocal and the smallest guiding path of each node are searched, and then guiding instructions are issued to corresponding guiding devices according to the guiding paths.
Further, the issuing, according to the guiding path, a guiding instruction to a corresponding guiding device includes: according to the guiding path, vehicle running detection is carried out on the corresponding area, and a vehicle running detection result is obtained; and issuing a guiding instruction and a vehicle running detection result to corresponding guiding equipment according to the guiding path, wherein the guiding equipment is used for judging whether to perform flickering guiding according to the guiding instruction and the vehicle running detection result.
Specifically, after receiving the flicker signal, the guiding device needs to receive a detection result of whether the vehicle runs in the corresponding area or not in order to more accurately guide the vehicle, the detection result is obtained by the edge computing device of the current area through a target detection algorithm, and if the vehicle runs in the current area, the guiding device performs flicker guiding; if the vehicle is not running in the current area, the guidance apparatus does not perform blinking guidance.
When the edge computing device detects the vehicle running, a target detection algorithm may be adopted to identify the vehicles in the two adjacent video images and the corresponding contour information thereof, and determine whether the vehicle running is performed according to the change of the contour center of the vehicle.
According to the parking space detection method, the monitoring cameras and the ultrasonic radars are arranged in the parking lot, and the situation that the parking space is occupied can be comprehensively judged according to the detection results of the cameras and the detection results of the ultrasonic radars, so that the problem that the detection results of a single sensor are abnormal can be solved, the detection accuracy of the idle parking space is improved, meanwhile, the use quantity of the cameras can be reduced, and the equipment deployment cost of the parking lot is reduced. Furthermore, the embodiment of the invention adopts a distributed computing architecture, and the embedded computing units with lower cost are arranged in each area of the parking lot, so that the wiring harness is only required to be connected to the embedded computing equipment in a small-range area, and the arrangement cost of the server and the wiring harness can be reduced.
Further, as a specific implementation of fig. 1, an embodiment of the present invention provides a parking space detection device, as shown in fig. 8, where the device includes: an acquisition unit 31, an identification unit 32, a first determination unit 33, a second determination unit 34, and a third determination unit 35.
The obtaining unit 31 may be configured to obtain a video image captured by a camera in the parking lot, a camera rotation angle corresponding to the video image, and a detection result of whether the ultrasonic radar is occupied for the parking space.
The identifying unit 32 may be configured to identify a vehicle in the video image and determine a vehicle center based on profile information of the vehicle.
The first determining unit 33 may be configured to determine, according to the vehicle center and the rotation angle of the camera, a detection result of whether the camera is occupied for the parking space.
The second determining unit 34 may be configured to determine, according to the vehicle center, a confidence level region of the vehicle in a camera monitoring range.
The third determining unit 35 may be configured to comprehensively determine the parking space occupation condition according to the confidence level region, the detection result of the ultrasonic radar, and the detection result of the camera.
In a specific application scenario, the identifying unit 32 may be specifically configured to input the video image into a preset target detection model for vehicle detection, and output the vehicle in the video image and corresponding contour information thereof;
in a specific application scenario, the first determining unit 33 includes: a first determination module and a second determination module.
The first determining module may be configured to determine rotation state bit information of the camera according to the rotation angle of the camera and a mapping relationship between different rotation angles of the camera and different rotation state bit information.
The second determining module may be configured to determine, according to the vehicle center and the rotation status bit information, a detection result of whether the camera is occupied for the parking space.
The second determining module may be specifically configured to query a preset parking space coordinate information table according to the rotation state bit information, and determine vertex coordinates of the corresponding parking space in the video image, where the preset parking space coordinate information table records parking space identifiers and vertex coordinates corresponding to different rotation state bit information; if the center of the vehicle is in a quadrilateral range enclosed by the vertex coordinates, determining that the detection result of the camera is that the corresponding parking space is occupied; if the center of the vehicle is not in the quadrilateral range enclosed by the vertex coordinates, determining that the detection result of the camera is that the corresponding parking space is unoccupied.
In a specific application scenario, the second determining unit 34 may be specifically configured to determine, if the vehicle center is within the first area range of the video image, a high confidence level area of the vehicle within the camera monitoring range; if the vehicle center is in the second area range of the video image, determining a low confidence level area of the vehicle in a camera monitoring range;
in a specific application scenario, the third determining unit 35 includes a third determining module and a fourth determining module.
The third determining module may be configured to determine, if the vehicle is in a high confidence region within a monitoring range of the camera, the parking space occupation condition according to a detection result of the ultrasonic radar and a detection result of the camera;
the fourth determining module may be configured to estimate a ratio of the number of vehicles to the number of parking spaces in the low confidence region if the vehicle is in the low confidence region within the monitoring range of the camera, and determine the parking space occupation condition according to the ratio, the detection result of the ultrasonic radar, and the detection result of the camera.
Further, the fourth determining module may be specifically configured to count the number of vehicles in the low confidence region and the number of parking spaces in the low confidence region; if the number of vehicles is greater than or equal to the number of parking spaces, determining that the proportioning condition is insufficient parking spaces; and if the number of vehicles is smaller than the number of parking spaces, determining that the proportioning condition is sufficient.
In a specific application scenario, the apparatus further includes: a receiving unit 36, a generating unit 37 and a issuing unit 38.
The receiving unit 36 may be configured to receive parking space occupancy broadcast by other edge computing devices in the vicinity.
The generating unit 37 may be configured to generate a parking space topology map related to each edge computing device according to the parking space occupation situation of the area that the edge computing device is responsible for and the parking space occupation situation of the area that the other edge computing device is responsible for.
The first determining unit 33 may be further configured to perform a path search based on the parking space topology map, and determine a guidance path with the largest number of free parking spaces along the path.
The issuing unit 38 may be configured to issue a guidance instruction to a corresponding guidance device according to the guidance path.
Further, the issuing unit 38 may be specifically configured to perform vehicle running detection on the corresponding area according to the guiding path, so as to obtain a vehicle running detection result; and issuing a guiding instruction and a vehicle running detection result to corresponding guiding equipment according to the guiding path, wherein the guiding equipment is used for judging whether to perform flickering guiding according to the guiding instruction and the vehicle running detection result.
It should be noted that, other corresponding descriptions of each functional module related to the parking space detection device provided by the embodiment of the present invention may refer to corresponding descriptions of the method shown in fig. 1, and are not repeated herein.
Based on the above method as shown in fig. 1, correspondingly, the embodiment of the present invention further provides a computer readable storage medium, on which a computer program is stored, which when being executed by a processor, implements the following steps: acquiring a video image shot by a camera in a parking lot, a camera rotation angle corresponding to the video image, and a detection result of an ultrasonic radar on whether the parking space is occupied or not; identifying a vehicle in the video image, and determining a vehicle center according to contour information of the vehicle; determining a detection result of whether the camera is occupied for the parking space according to the vehicle center and the rotation angle of the camera; determining a confidence coefficient region of the vehicle in a camera monitoring range according to the vehicle center; and comprehensively determining the occupation condition of the parking space according to the confidence coefficient region, the detection result of the ultrasonic radar and the detection result of the camera.
Based on the embodiment of the method shown in fig. 1 and the device shown in fig. 8, the embodiment of the invention further provides a physical structure diagram of an electronic device, as shown in fig. 9, where the electronic device includes: a processor 41, a memory 42, and a computer program stored on the memory 42 and executable on the processor, wherein the memory 42 and the processor 41 are both arranged on a bus 43, the processor 41 implementing the following steps when executing the program: acquiring a video image shot by a camera in a parking lot, a camera rotation angle corresponding to the video image, and a detection result of an ultrasonic radar on whether the parking space is occupied or not; identifying a vehicle in the video image, and determining a vehicle center according to contour information of the vehicle; determining a detection result of whether the camera is occupied for the parking space according to the vehicle center and the rotation angle of the camera; determining a confidence coefficient region of the vehicle in a camera monitoring range according to the vehicle center; and comprehensively determining the occupation condition of the parking space according to the confidence coefficient region, the detection result of the ultrasonic radar and the detection result of the camera.
According to the embodiment of the invention, the monitoring cameras and the ultrasonic radars are arranged in the parking lot, so that the situation that the parking space is occupied can be comprehensively judged according to the detection results of the cameras and the detection results of the ultrasonic radars, the problem that the detection results of a single sensor are abnormal can be solved, the detection precision of the idle parking space is improved, meanwhile, the use quantity of the cameras can be reduced, and the equipment deployment cost of the parking lot is reduced. Furthermore, the embodiment of the invention adopts a distributed computing architecture, and the embedded computing units with lower cost are arranged in each area of the parking lot, so that the wiring harness is only required to be connected to the embedded computing equipment in a small-range area, and the arrangement cost of the server and the wiring harness can be reduced.
Those of ordinary skill in the art will appreciate that: the drawing is a schematic diagram of one embodiment and the modules or flows in the drawing are not necessarily required to practice the invention.
Those of ordinary skill in the art will appreciate that: the modules in the apparatus of the embodiments may be distributed in the apparatus of the embodiments according to the description of the embodiments, or may be located in one or more apparatuses different from the present embodiments with corresponding changes. The modules of the above embodiments may be combined into one module, or may be further split into a plurality of sub-modules.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A parking space detection method, applied to an edge computing device, comprising:
acquiring a video image shot by a camera in a parking lot, a camera rotation angle corresponding to the video image, and a detection result of an ultrasonic radar on whether the parking space is occupied or not;
identifying a vehicle in the video image, and determining a vehicle center according to contour information of the vehicle;
determining a detection result of whether the camera is occupied for the parking space according to the vehicle center and the rotation angle of the camera;
determining a confidence coefficient region of the vehicle in a camera monitoring range according to the vehicle center;
and comprehensively determining the occupation condition of the parking space according to the confidence coefficient region, the detection result of the ultrasonic radar and the detection result of the camera.
2. The method of claim 1, wherein the identifying the vehicle in the video image comprises:
inputting the video image into a preset target detection model for vehicle detection, and outputting the vehicle and corresponding contour information in the video image;
the determining, according to the vehicle center and the camera rotation angle, a detection result of whether the camera is occupied for the parking space, includes:
determining the rotation state bit information of the camera according to the rotation angle of the camera and the mapping relation between different rotation angles of the camera and different rotation state bit information;
and determining a detection result of whether the camera is occupied for the parking space according to the vehicle center and the rotation state bit information.
3. The method according to claim 2, wherein the determining, according to the vehicle center and the rotation status bit information, a detection result of whether the camera is occupied for a parking space, includes:
inquiring a preset parking space coordinate information table according to the rotation state bit information, and determining vertex coordinates of corresponding parking spaces in the video image, wherein parking space identifiers and vertex coordinates corresponding to different rotation state bit information are recorded in the preset parking space coordinate information table;
if the center of the vehicle is in a quadrilateral range enclosed by the vertex coordinates, determining that the detection result of the camera is that the corresponding parking space is occupied;
if the center of the vehicle is not in the quadrilateral range enclosed by the vertex coordinates, determining that the detection result of the camera is that the corresponding parking space is unoccupied.
4. The method of claim 1, wherein determining, based on the vehicle center, a confidence region in which the vehicle is within a monitoring range of the camera comprises:
if the vehicle center is in the first area range of the video image, determining a high confidence level area of the vehicle in a camera monitoring range;
if the vehicle center is in the second area range of the video image, determining a low confidence level area of the vehicle in a camera monitoring range;
the step of comprehensively determining the parking space occupation condition according to the confidence coefficient region, the detection result of the ultrasonic radar and the detection result of the camera comprises the following steps:
if the vehicle is in a high confidence coefficient area in the monitoring range of the camera, determining the parking space occupation condition according to the detection result of the ultrasonic radar and the detection result of the camera;
if the vehicle is in a low confidence coefficient region in the camera monitoring range, estimating the proportioning condition of the number of vehicles and the number of parking spaces in the low confidence coefficient region, and determining the occupation condition of the parking spaces according to the proportioning condition, the detection result of the ultrasonic radar and the detection result of the camera.
5. The method of claim 4, wherein estimating the ratio of the number of vehicles to the number of parking spaces in the low confidence region comprises:
counting the number of vehicles in the low confidence coefficient region and the number of parking spaces in the low confidence coefficient region;
if the number of vehicles is greater than or equal to the number of parking spaces, determining that the proportioning condition is insufficient parking spaces;
and if the number of vehicles is smaller than the number of parking spaces, determining that the proportioning condition is sufficient.
6. The method according to any one of claims 1-5, further comprising:
receiving parking space occupation conditions broadcast by other nearby edge computing devices;
generating a parking space topological graph related to each edge computing device according to the parking space occupation situation of the area which is responsible for the edge computing device and the parking space occupation situation of the area which is responsible for other edge computing devices;
performing path searching based on the parking space topological graph, and determining a guide path with the largest number of idle parking spaces along the way;
and issuing a guide instruction to the corresponding guide equipment according to the guide path.
7. The method of claim 6, wherein issuing a boot instruction to a corresponding boot device according to the boot path comprises:
according to the guiding path, vehicle running detection is carried out on the corresponding area, and a vehicle running detection result is obtained;
and issuing a guiding instruction and a vehicle running detection result to corresponding guiding equipment according to the guiding path, wherein the guiding equipment is used for judging whether to perform flickering guiding according to the guiding instruction and the vehicle running detection result.
8. A parking space detection device, characterized by comprising:
the device comprises an acquisition unit, a detection unit and a control unit, wherein the acquisition unit is used for acquiring video images shot by cameras in a parking lot, camera rotation angles corresponding to the video images and detection results of an ultrasonic radar aiming at whether the parking space is occupied or not;
an identification unit configured to identify a vehicle in the video image and determine a vehicle center according to contour information of the vehicle;
the first determining unit is used for determining whether the camera is occupied for the parking space or not according to the vehicle center and the rotation angle of the camera;
the second determining unit is used for determining a confidence coefficient region of the vehicle in the monitoring range of the camera according to the center of the vehicle;
and the third determining unit is used for comprehensively determining the parking space occupation condition according to the confidence coefficient region, the detection result of the ultrasonic radar and the detection result of the camera.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the computer program when executed by the processor implements the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311561577.5A CN117671968A (en) | 2023-11-22 | 2023-11-22 | Parking space detection method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311561577.5A CN117671968A (en) | 2023-11-22 | 2023-11-22 | Parking space detection method and device, storage medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117671968A true CN117671968A (en) | 2024-03-08 |
Family
ID=90070540
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311561577.5A Pending CN117671968A (en) | 2023-11-22 | 2023-11-22 | Parking space detection method and device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117671968A (en) |
-
2023
- 2023-11-22 CN CN202311561577.5A patent/CN117671968A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112014845B (en) | Vehicle obstacle positioning method, device, equipment and storage medium | |
| US9794519B2 (en) | Positioning apparatus and positioning method regarding a position of mobile object | |
| US20190164267A1 (en) | Failed vehicle estimation system, failed vehicle estimation method and computer-readable non-transitory storage medium | |
| US11334756B2 (en) | Homography through satellite image matching | |
| CN108629763B (en) | Disparity map judging method and device and terminal | |
| US11208100B2 (en) | Server device and vehicle | |
| US11410429B2 (en) | Image collection system, image collection method, image collection device, recording medium, and vehicle communication device | |
| CN113487759A (en) | Parking patrol method and device, mobile patrol equipment and patrol system | |
| JP2020077414A (en) | Scene detection device and method | |
| US20170025006A1 (en) | Direct vehicle to vehicle communications | |
| CN110992706A (en) | Vehicle detection method and device and vehicle-road cooperation system | |
| CN110837077B (en) | Sound source position verification method and device | |
| CN113240880A (en) | Fire detection method and device, electronic equipment and storage medium | |
| CN110705338A (en) | Vehicle detection method and device and monitoring equipment | |
| WO2021200038A1 (en) | Road deteriotation diagnosing device, road deterioration diagnosing method, and recording medium | |
| US10163345B2 (en) | Method and device for providing an event message indicative of an imminent event for a vehicle | |
| US20200250970A1 (en) | Information processing apparatus, information processing method and program | |
| CN111325088B (en) | Information processing system, recording medium, and information processing method | |
| CN113313110A (en) | License plate type recognition model construction and license plate type recognition method | |
| CN117671968A (en) | Parking space detection method and device, storage medium and electronic equipment | |
| KR101968983B1 (en) | Speed detection using OBD for vehicle and checking system for automatic vehicle-detecting device therewith | |
| CN113220805B (en) | Map generation device, recording medium, and map generation method | |
| US20210180985A1 (en) | Method for generating map and map generation device | |
| US11740079B2 (en) | Method, computer program and device for determining a vehicle spacing for an observation period | |
| CN115019511A (en) | Method and device for identifying illegal lane change of motor vehicle based on automatic driving vehicle |
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 |