CN114038228A - Parking space guiding method and device - Google Patents
Parking space guiding method and device Download PDFInfo
- Publication number
- CN114038228A CN114038228A CN202111220286.0A CN202111220286A CN114038228A CN 114038228 A CN114038228 A CN 114038228A CN 202111220286 A CN202111220286 A CN 202111220286A CN 114038228 A CN114038228 A CN 114038228A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- parking space
- detection model
- license plate
- frames
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000001514 detection method Methods 0.000 claims abstract description 247
- 230000008859 change Effects 0.000 claims abstract description 49
- 230000002159 abnormal effect Effects 0.000 abstract description 7
- 230000008569 process Effects 0.000 description 11
- 238000013527 convolutional neural network Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 239000003086 colorant Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 208000005809 status epilepticus Diseases 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
- G08G1/141—Traffic control systems for road vehicles indicating individual free spaces in parking areas with means giving the indication of available parking spaces
- G08G1/142—Traffic control systems for road vehicles indicating individual free spaces in parking areas with means giving the indication of available parking spaces external to the vehicles
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
- G08G1/145—Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The application discloses a parking space guiding method and device, which are used for reducing abnormal display conditions of parking space lamps. The method comprises the following steps: the method comprises the steps of obtaining a parking space lamp state and a parking space image of a target parking space, wherein the parking space lamp state comprises a vehicle state and a vehicle-free state; detecting the parking space image by using a vehicle detection model and a license plate detection model to obtain a detection result, wherein the vehicle detection model is used for detecting a vehicle, the vehicle comprises a vehicle head, a vehicle tail or a vehicle body, and the license plate detection model is used for detecting a license plate; judging whether the detection result reaches a preset change condition or not; and if so, changing the state of the parking spot lamp.
Description
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a method and an apparatus for guiding a parking space.
Background
With the continuous development of society, the automobile constantly increases, and in order to manage the vehicle, many parking lots utilize the parking stall lamp to remind the parking stall that the user corresponds whether have the car or not.
In the prior art, whether a car is in a parking space is generally judged through a vehicle head and tail detection model. When the vehicle head or the vehicle tail is detected through the vehicle head and vehicle tail detection model, the parking space is judged to be in a vehicle-available state, and the parking space lamp is adjusted to be in a color corresponding to the vehicle-available state so as to remind a user that the parking space is occupied and the vehicle cannot be parked; when the vehicle head or the vehicle tail cannot be detected through the vehicle head and vehicle tail detection model, the parking space is judged to be in a vehicle-free state, and the parking space lamp is adjusted to be in a color corresponding to the vehicle-free state, so that the user is reminded that the parking space is unoccupied, and the vehicle can be parked.
However, when a vehicle is blocked, the front and rear detection model easily determines the parking space as a vehicle-free state, so that the parking space guidance system changes the status of the parking space lights of the parking space into a vehicle-free state, which causes abnormal display of the parking space lights.
Disclosure of Invention
The application provides a parking space guiding method and device, which are beneficial to reducing the abnormal display condition of parking space lamps.
The application provides a parking space guiding method in a first aspect, which includes:
the method comprises the steps of obtaining a parking space lamp state and a parking space image of a target parking space, wherein the parking space lamp state comprises a vehicle state and a vehicle-free state;
detecting the parking space image by using a vehicle detection model and a license plate detection model to obtain a detection result, wherein the vehicle detection model is used for detecting a vehicle, the vehicle comprises a vehicle head, a vehicle tail or a vehicle body, and the license plate detection model is used for detecting a license plate;
judging whether the detection result reaches a preset change condition or not;
and if so, changing the state of the parking spot lamp.
Optionally, when the parking space lamp state is a no-vehicle state, the determining whether the detection result reaches a preset change condition includes:
judging whether at least M frames in the continuous N frames detect the vehicle head or the vehicle tail or at least M frames in the continuous N frames detect the vehicle license plate or at least P frames detect the vehicle head or the vehicle tail or at least P frames detect the vehicle license plate in the continuous N frames;
and if so, determining that the detection result reaches the preset change condition.
Optionally, the detecting the parking space image by using a vehicle detection model and a license plate detection model includes:
randomly selecting a vehicle detection model or a license plate detection model to detect the current frame parking space image;
if the vehicle is not detected by using the vehicle detection model, detecting the next frame of parking space image by using the license plate detection model;
if the license plate is not detected by using the license plate detection model, detecting the next frame of parking space image by using the vehicle detection model;
if the vehicle head or the vehicle tail is detected by using the vehicle detection model, detecting the next frame of parking space image by using the vehicle detection model;
and if the license plate detection model is used for detecting the license plate, the license plate detection model is used for detecting the next frame of parking space image.
Optionally, after the randomly selecting the vehicle detection model or the license plate detection model to detect the current frame parking space image, the method further includes:
and if the vehicle detection model is used for detecting the vehicle body, the vehicle detection model is used for detecting the next frame of parking space image, and when the vehicle body is detected in continuous Q frames but the vehicle head and the vehicle tail cannot be detected, the license plate detection model is used for detecting the next frame of parking space image.
Optionally, when the parking space lamp state is a vehicle state, the determining whether the detection result reaches a preset change condition includes:
judging whether at least Y frames in the continuous X frames do not detect the vehicle head, the vehicle tail or the license plate and do not detect the vehicle body or the continuous Z frames do not detect the vehicle head, the vehicle tail or the license plate and do not detect the vehicle body;
and if so, determining that the detection result reaches the preset change condition.
Optionally, the detecting the parking space image by using a vehicle detection model and a license plate detection model includes:
randomly selecting a vehicle detection model or a license plate detection model to detect the current frame parking space image;
if the license plate detection model is used for detection, the vehicle detection model is used for detecting the next frame of parking space image;
and if the vehicle detection model is used for detection, the license plate detection model is used for detecting the next frame of parking space image.
This application second aspect provides a parking stall guiding device, includes:
the system comprises an acquisition unit, a display unit and a display unit, wherein the acquisition unit is used for acquiring a parking space lamp state and a parking space image of a target parking space, and the parking space lamp state comprises a vehicle state and a vehicle-free state;
the detection unit is used for detecting the parking space image by using a vehicle detection model and a license plate detection model to obtain a detection result, the vehicle detection model is used for detecting a vehicle, the vehicle comprises a vehicle head, a vehicle tail or a vehicle body, and the license plate detection model is used for detecting a license plate;
the judging unit is used for judging whether the detection result reaches a preset change condition or not;
and the changing unit is used for changing the state of the parking space lamp when the judging unit determines that the detection result reaches the preset changing condition.
Optionally, the determining unit includes a first determining module, and the first determining module is configured to:
judging whether at least M frames in the continuous N frames detect the vehicle head or the vehicle tail or at least M frames in the continuous N frames detect the vehicle license plate or at least P frames detect the vehicle head or the vehicle tail or at least P frames detect the vehicle license plate in the continuous N frames;
and if so, determining that the detection result reaches the preset change condition.
Optionally, the determining unit includes a second determining module, and the second determining module is configured to:
judging whether at least Y frames in the continuous X frames do not detect the vehicle head, the vehicle tail or the license plate and do not detect the vehicle body or the continuous Z frames do not detect the vehicle head, the vehicle tail or the license plate and do not detect the vehicle body;
and if so, determining that the detection result reaches the preset change condition.
The third aspect of the present application provides a parking space guidance apparatus, including:
the device comprises a processor, a memory, an input and output unit and a bus;
the processor is connected with the memory, the input and output unit and the bus;
the memory stores a program, and the processor calls the program to execute the method according to the first aspect and any one of the possible implementation manners of the first aspect.
The processor is further configured to perform the method of the first aspect and the alternatives of the first aspect.
A fourth aspect of the present application provides a computer-readable storage medium having a program stored thereon, where the program is to make a computer perform the method of the first aspect and any one of the possible implementation manners of the first aspect when the program is executed on the computer.
According to the technical scheme, the method has the following advantages:
according to the method, the parking space lamp state and the parking space image of the target parking space are firstly obtained, then the parking space image is detected through the vehicle detection model and the license plate detection model, wherein the vehicle detection model is used for detecting the vehicle, and the license plate detection model is used for detecting the license plate.
Drawings
Fig. 1 is a schematic flowchart of an embodiment of a parking space guidance method according to the present application;
fig. 2 is a schematic flowchart of another embodiment of a parking space guidance method according to the present application;
fig. 3 is a schematic flowchart of another embodiment of a parking space guidance method according to the present application;
fig. 4 is a schematic structural diagram of an embodiment of a parking space guidance apparatus according to the present application;
fig. 5 is a schematic structural diagram of another embodiment of the parking space guidance device in the present application;
fig. 6 is a schematic structural diagram of another embodiment of the parking space guidance device in the present application;
fig. 7 is a schematic structural diagram of another embodiment of the parking space guidance device in the present application.
Detailed Description
The application provides a parking space guiding method and device, which are used for reducing abnormal display conditions of parking space lamps.
The method of the present application may be applied to a system, a server, a terminal, or other devices with logic processing capability, and the present application is not limited thereto. For convenience of description, the following description will be given taking the execution subject as an example of the system.
Embodiments in the present application will be described below with reference to the accompanying drawings.
Referring to fig. 1, an embodiment of a parking space guidance method in the present application includes:
101. the system acquires the parking space lamp state and the parking space image of the target parking space.
The system can acquire the parking space lamp state and the parking space image of a target parking space, the parking space lamp state comprises a vehicle state and a vehicle-free state, the vehicle state and the vehicle-free state are respectively represented by different colors, the parking space image is the image of the target parking space, and the system can acquire the parking space image in a real-time acquisition mode. In practical application, the camera is arranged to shoot a target parking space at a fixed angle, and the system can acquire a parking space image of the target parking space through the camera. The system acquires the parking space images, and aims to determine whether a target parking space is occupied or not through continuous multiframes of the parking space images, so that whether the state of a parking space lamp needs to be changed or not is determined.
In this embodiment, the system may be composed of an intelligent camera with logic processing capability alone, or may be composed of a front-end camera and a background server together, which is not limited herein.
It should be noted that, for the first frame of parking space image, a vehicle detection model or a license plate detection model may be preset for detection, or any one of the vehicle detection model or the license plate detection model may be randomly selected for detection, which is not limited herein.
102. The system detects the parking space image by using a vehicle detection model and a license plate detection model to obtain a detection result.
After the parking space lamp state and the parking space image of the target parking space are obtained, the system can detect the parking space image by using a vehicle detection model and a license plate detection model so as to obtain a detection result. The vehicle detection model is based on the convolutional neural network and used for detecting the vehicles in the image, and the license plate detection model is based on the convolutional neural network and used for detecting the license plates in the image. Therefore, when any frame of parking space image is detected by using the vehicle detection model, the detection results of the frame of parking space image comprise four conditions of detecting a vehicle head, detecting a vehicle tail, detecting a vehicle body and not detecting a vehicle; when the license plate detection model is used for detecting any frame of parking space image, the detection result of the frame of parking space image comprises two conditions of detecting the license plate and not detecting the license plate.
In this embodiment, the vehicle detection model can identify the vehicle head, the vehicle tail or the vehicle body, and the vehicle body in this embodiment refers to the vehicle head, the vehicle tail and the vehicle side face, which are partially shielded. In the process of training the vehicle detection model, the classifier defining the vehicle detection model comprises at least 3 categories, wherein the 3 categories are a vehicle head category, a vehicle tail category and a vehicle body category respectively. When the sample marking is carried out, a marking rectangular frame containing a complete and non-shielded vehicle head is used as a positive sample of the vehicle head category; taking a labeling rectangular frame containing the complete and unobstructed vehicle tail as a positive sample of the vehicle tail category; regarding the marked rectangular frames of the vehicle head containing a part of the blocked vehicle head, taking the marked rectangular frames of which the parts of the vehicle head which are not blocked are greater than or equal to a preset vehicle body threshold value as positive samples of the vehicle body category, and taking the marked rectangular frames of which the parts of the vehicle head which are not blocked are less than the preset vehicle body threshold value as training negative samples; regarding the marked rectangular frame of the vehicle tail containing the blocked part, taking the marked rectangular frame of which the unblocked part of the vehicle tail is greater than or equal to a preset vehicle body threshold value as a positive sample of the vehicle body category, and taking the marked rectangular frame of which the unblocked part of the vehicle tail is less than the preset vehicle body threshold value as a training negative sample; the marked rectangle containing the side of the vehicle is used as a positive sample of the vehicle body category. It should be noted that the vehicle detection model may be based on an SSD model, or may be based on models such as R-CNN, Fast R-CNN, or Mask R-CNN, and is not limited herein.
103. The system determines whether the detection result reaches a preset change condition, if so, executes step 104, and if not, ends the process.
After obtaining the detection result, the system may determine whether the detection result reaches a preset change condition, if it is determined that the detection result reaches the preset change condition, step 104 may be executed, otherwise, the process may be ended.
104. The system changes the state of the parking spot lamp.
If the system determines that the detection result reaches the preset change condition, the color of the parking spot lamp can be correspondingly adjusted to complete the change of the state of the parking spot lamp. For example, when the acquired parking spot light state is a vehicle-presence state, the system may change the parking spot light state into a vehicle-absence state; when the acquired parking spot light state is the no-vehicle state, the system can change the parking spot light state into the vehicle state.
In the implementation, the system firstly acquires the parking space lamp state and the parking space image of a target parking space, and then uses the vehicle detection model and the license plate detection model to detect the parking space image, wherein the vehicle detection model is used for detecting a vehicle, and the license plate detection model is used for detecting a license plate.
In this application, the system can judge whether the testing result reaches and predetermines the change condition through the mode of difference according to the difference of parking stall lamp state, describes respectively below:
when the parking space lamp state is a no-vehicle state, the system judges whether at least M frames in continuous N frames detect the vehicle head or the vehicle tail, or at least M frames in continuous N frames detect the vehicle license plate, or continuous P frames detect the vehicle head or the vehicle tail, or continuous P frames detect the vehicle license plate, so as to judge whether the detection result reaches a preset change condition.
Referring to fig. 2, another embodiment of a parking space guidance method in the present application includes:
201. the system acquires the parking space lamp state and the parking space image of the target parking space.
In this embodiment, step 201 is similar to step 101 in the previous embodiment, and is not described herein again.
202. The system randomly selects a vehicle detection model or a license plate detection model to detect the current frame parking space image.
The system can randomly select any one of the vehicle detection model or the license plate detection model, and the current frame parking space image is detected through the selected model.
203. And if the vehicle is not detected by using the vehicle detection model, detecting the next frame of parking space image by using the license plate detection model.
The system can randomly select any one of a vehicle detection model or a license plate detection model to detect the current frame parking space image, and the method comprises the following conditions:
1. if the system uses the vehicle detection model to detect the current frame parking space image and does not detect the vehicle, namely any one of the vehicle head, the vehicle tail and the vehicle body is not detected, then the license plate detection model is needed to detect the next frame parking space image;
2. if the system detects the current frame parking space image by using the license plate detection model and does not detect the license plate, the system needs to detect the next frame parking space image by using the vehicle detection model;
3. if the system detects the current frame parking space image by using the vehicle detection model and detects the vehicle head or the vehicle tail, the system needs to continuously detect the next frame parking space image by using the vehicle detection model;
4. if the system detects the current frame parking space image by using the license plate detection model and detects the license plate, the system needs to continuously use the license plate detection model to detect the next frame parking space image;
5. if the system detects the current frame parking space image by using the vehicle detection model and detects the vehicle body, the vehicle detection model is required to be continuously used for detecting the next frame parking space image, and when the vehicle body is detected in continuous Q frames but the vehicle head or the vehicle tail cannot be detected, the vehicle plate detection model is required to be used for detecting the next frame parking space image. Wherein Q is a positive integer, the value of Q is preset, for example, when the value of Q is set to be 5, the system uses the vehicle detection model to continuously detect the vehicle body for 5 times, and the vehicle plate detection model is used for detection.
Optionally, when the vehicle detection model detects the vehicle body, the system may generate a "hold" signal, and keep the current status of the parking space lights unchanged according to the "hold" signal, so as to further improve the abnormal status of the status change of the parking space lights. For example, when the vehicle is driven into a target parking space in a reverse mode or a forward mode, the system detects the vehicle body but cannot detect the vehicle head, the vehicle tail or a license plate, and the system generates a signal of 'keeping' and keeps the state of a parking space lamp unchanged according to the signal. The frequent change of the status of the parking space lights generally occurs when the road is busy, for example, the vehicle has partially entered the target parking space but needs to exit the target parking space for adjustment, at this time, if there is a pedestrian or other vehicle in front of the vehicle, the vehicle needs to wait, and at this time, the traditional parking guidance system may frequently change the status of the parking space lights. In the embodiment, the system can detect the vehicle body, then generate a signal of 'hold' and keep the state of the parking spot lamp unchanged according to the signal. Therefore, in the process that the vehicle drives into the target parking space, if the system determines that the target parking space is occupied, the parking space lamp state is kept in the parking space lamp state in the vehicle adjusting process, and the situation that other vehicle owners see that the parking space lamp state of the target parking space appears in the vehicle state and jumps from the vehicle state to the vehicle state without the vehicle state can be effectively reduced; in the process that the vehicle exits the target parking space, if the vehicle does not completely exit the target parking space, the system can detect the vehicle body, the state of the parking space lamp is kept to be a vehicle-existing state, and the system cannot detect the vehicle head, the vehicle tail, the vehicle body and the license plate until the vehicle completely exits the target parking space, so that the state of the parking space lamp is changed into a vehicle-free state, and the situation that other vehicle owners see that the state of the parking space lamp of the target parking space jumps from the vehicle-existing state to the vehicle-free state and make wrong judgment is effectively reduced.
The system detects continuous multi-frame parking space images through the vehicle detection model and the license plate detection model to obtain a detection result.
204. The system judges whether at least M frames in the continuous N frames detect the vehicle head or the vehicle tail, or at least M frames in the continuous N frames detect the vehicle license plate, or the continuous P frames detect the vehicle head or the vehicle tail, or the continuous P frames detect the vehicle license plate, if so, the step 205 is executed, and if not, the process is ended.
The system may determine whether there is a situation in the detection result that at least M frames in the consecutive N frames detect the vehicle head or the vehicle tail, or at least M frames in the consecutive N frames detect the vehicle license plate, or consecutive P frames detect the vehicle head or the vehicle tail, or consecutive P frames detect the vehicle license plate, and if such a situation exists, the system may perform step 205; if such a condition does not exist, the system may end the flow. M, N, P are positive integers, a value of M, N, P is preset, for example, when M is 10, N is 7, and P is 5, if any one of the detection results includes that a license plate is detected in 5 consecutive frames, a vehicle head or a vehicle tail is detected in 5 consecutive frames, a license plate is detected in at least 7 consecutive frames, and a vehicle head or a vehicle tail is detected in at least 7 consecutive frames, the system may execute step 205. Otherwise, the system may end the flow.
205. And the system determines that the detection result reaches a preset change condition.
If the system determines that at least M frames in the continuous N frames detect the vehicle head or the vehicle tail, or at least M frames in the continuous N frames detect the vehicle license plate, or the continuous P frames detect the vehicle head or the vehicle tail, or the continuous P frames detect the vehicle license plate, the system can determine that the detection result reaches the preset change condition.
206. The system changes the state of the parking spot lamp.
In this embodiment, after determining that the detection result meets the preset change condition, the system may change the status of the parking spot light, specifically, by changing the color of the parking spot light correspondingly, the status of the parking spot light is changed from the no-vehicle status to the vehicle status.
In this embodiment, when the parking space lamp state is the no-vehicle state, the system determines that the parking space lamp state needs to be changed to the vehicle-presence state only when the system determines that at least M frames in the consecutive N frames detect the vehicle head or the vehicle tail, or at least M frames in the consecutive N frames detect the vehicle license plates, or at least M frames in the consecutive P frames detect the vehicle head or the vehicle tail, or the consecutive P frames detect the vehicle license plates, so that the accuracy of changing the parking space lamp state from the no-vehicle state to the vehicle-presence state is improved.
And secondly, when the parking spot lamp state is a vehicle state, the system judges whether at least Y frames in continuous X frames exist in the detection result, the vehicle head, the vehicle tail or the license plate is not detected, and the vehicle body is not detected, or the vehicle head, the vehicle tail or the license plate is not detected in continuous Z frames, so that whether the detection result reaches a preset change condition or not is judged.
Referring to fig. 3, another embodiment of a parking space guidance method in the present application includes:
301. the system acquires the parking space lamp state and the parking space image of the target parking space.
302. The system randomly selects a vehicle detection model or a license plate detection model to detect the current frame parking space image.
In this embodiment, steps 301 to 302 are similar to steps 201 to 202 in the previous embodiment, and are not described again here.
303. And if the license plate detection model is used for detection, the system uses the vehicle detection model to detect the next frame of parking space image.
The system can randomly select any one of a vehicle detection model or a license plate detection model to detect the current frame parking space image, and the method comprises the following conditions:
1. if the system uses the vehicle detection model to detect the current frame parking space image, the license plate detection model is needed to detect the next frame parking space image.
2. If the system uses the license plate detection model to detect the current frame parking space image, the vehicle detection model is needed to detect the next frame parking space image.
Optionally, when the vehicle detection model detects the vehicle body, the system may generate a "hold" signal, and keep the current status of the parking space lights unchanged according to the "hold" signal, so as to further improve the abnormal status of the status change of the parking space lights. For example, when a vehicle exits a parking space, a part of the vehicle leaves the parking space, but at the moment, a pedestrian or a vehicle blocks the vehicle, the system can detect the vehicle body but cannot detect the vehicle head, the vehicle tail or a license plate, the system generates a 'keep' signal and keeps the state of the parking space lamp unchanged according to the signal, and when the vehicle leaves, the system cannot detect the vehicle or the license plate, the state of the parking space lamp is changed, so that the situation that the state of the parking space lamp is frequently changed is reduced.
The system detects continuous multi-frame parking space images through the vehicle detection model and the license plate detection model to obtain a detection result.
304. The system judges whether Y frames in the continuous X frames do not detect the vehicle head, the vehicle tail or the license plate and do not detect the vehicle body or the continuous Z frames do not detect the vehicle head, the vehicle tail or the license plate and do not detect the vehicle body, if yes, step 305 is executed, and if not, the process is ended.
The system may determine whether there are at least Y frames in the consecutive X frames that do not detect the vehicle head, the vehicle tail, or the license plate and do not detect the vehicle body, or consecutive Z frames that do not detect the vehicle head, the vehicle tail, or the license plate and do not detect the vehicle body, if so, the system may perform step 305; if this is not the case, the system may end the flow. Wherein X, Y, Z are all positive integers, a value of X, Y, Z is preset, for example, when X is 10, Y is 7, and Z is 5, if there is any one of 5 consecutive frames in which no vehicle head or tail or license plate is detected and no vehicle body is detected, and at least 7 consecutive frames in 10 frames in which no vehicle head or tail or license plate is detected and no vehicle body is detected, the system may execute step 305, otherwise the system may end the process.
305. And the system determines that the detection result reaches a preset change condition.
If the system determines that at least Y frames in the continuous X frames do not detect the vehicle head, the vehicle tail or the license plate and does not detect the vehicle body, or the continuous Z frames do not detect the vehicle head, the vehicle tail or the license plate and does not detect the vehicle body, the system can determine that the detection result reaches the preset change condition.
306. The system changes the state of the parking spot lamp.
In this embodiment, after determining that the detection result meets the preset change condition, the system may change the status of the parking spot light, specifically, by changing the color of the parking spot light correspondingly, the status of the parking spot light is changed from the vehicle-presence status to the vehicle-absence status.
In this embodiment, when the parking space lamp state is the vehicle-presence state, the system determines that the parking space lamp state needs to be changed to the vehicle-absence state only when at least Y frames of the continuous X frames do not detect the vehicle head, the vehicle tail or the license plate and do not detect the vehicle body, or the continuous Z frames do not detect the vehicle head, the vehicle tail or the license plate and do not detect the vehicle body, in the detection result, which is favorable for improving the accuracy of changing the parking space lamp state from the vehicle-presence state to the vehicle-absence state.
Referring to fig. 4, an embodiment of a parking space guidance apparatus in the present application includes:
the acquiring unit 401 is configured to acquire a parking space lamp state and a parking space image of a target parking space, where the parking space lamp state includes a vehicle-presence state and a vehicle-absence state;
the detection unit 402 is configured to detect the parking space image by using a vehicle detection model and a license plate detection model to obtain a detection result, where the vehicle detection model is used to detect a vehicle and the license plate detection model is used to detect a license plate;
a determining unit 403, configured to determine whether the detection result reaches a preset change condition;
a changing unit 404, configured to change the status of the parking space lights when the determining unit 403 determines that the detection result reaches the preset changing condition.
In this embodiment, the obtaining unit 401 first obtains the parking space light state and the parking space image of the target parking space, and then the detecting unit 402 detects the parking space image by using a vehicle detecting model and a license plate detecting model, where the vehicle detecting model is used to detect a vehicle and the license plate detecting model is used to detect a license plate, and if a detection result reaches a preset change condition, the changing unit 404 changes the parking space light state, which is beneficial to reducing the abnormal display condition of the parking space light.
Referring to fig. 5, another embodiment of the parking space guidance apparatus of the present application includes:
the acquiring unit 501 is configured to acquire a parking space lamp state and a parking space image of a target parking space, where the parking space lamp state includes a vehicle-presence state and a vehicle-absence state;
the detection unit 502 is used for detecting the parking space image by using a vehicle detection model and a license plate detection model to obtain a detection result, wherein the vehicle detection model is used for detecting a vehicle, and the license plate detection model is used for detecting a license plate;
a determining unit 503, configured to determine whether the detection result reaches a preset change condition;
a changing unit 504, configured to change the status of the parking space lights when the determining unit 503 determines that the detection result reaches the preset changing condition.
In this embodiment, the determining unit 503 includes a first determining module 5031.
The first determining module 5031 is configured to:
judging whether at least M frames in the continuous N frames detect the vehicle head or the vehicle tail or at least M frames in the continuous N frames detect the vehicle license plate or at least P frames detect the vehicle head or the vehicle tail or at least P frames detect the vehicle license plate in the continuous N frames;
and if so, determining that the detection result reaches the preset change condition.
The detection unit 502 is specifically configured to:
randomly selecting a vehicle detection model or a license plate detection model to detect the current frame parking space image;
if the vehicle is not detected by using the vehicle detection model, detecting the next frame of parking space image by using the license plate detection model;
if the license plate is not detected by using the license plate detection model, detecting the next frame of parking space image by using the vehicle detection model;
if the vehicle head or the vehicle tail is detected by using the vehicle detection model, detecting the next frame of parking space image by using the vehicle detection model;
if the license plate detection model is used for detecting the license plate, the license plate detection model is used for detecting the next frame of parking space image;
if the vehicle body is detected by using the vehicle detection model, detecting the next frame of parking space image by using the vehicle detection model, and when the vehicle body is detected by using the continuous Q frames but the vehicle head or the vehicle tail can not be detected, detecting the next frame of parking space image by using the license plate detection model.
Referring to fig. 6, another embodiment of the parking space guidance apparatus of the present application includes:
the acquisition unit 601 is configured to acquire a parking space lamp state and a parking space image of a target parking space, where the parking space lamp state includes a vehicle-presence state and a vehicle-absence state;
the detection unit 602 is configured to detect a parking space image by using a vehicle detection model and a license plate detection model to obtain a detection result, where the vehicle detection model is used to detect a vehicle and the license plate detection model is used to detect a license plate;
a determining unit 603, configured to determine whether the detection result meets a preset change condition;
a changing unit 604, configured to change the status of the parking space lights when the determining unit 603 determines that the detection result reaches the preset changing condition.
In this embodiment, the determining unit 603 includes a second determining module 6031.
The second judging module is used for:
judging whether at least Y frames in the continuous X frames do not detect the vehicle head, the vehicle tail or the license plate and do not detect the vehicle body or the continuous Z frames do not detect the vehicle head, the vehicle tail or the license plate and do not detect the vehicle body;
and if so, determining that the detection result reaches the preset change condition.
The detecting unit 602 is specifically configured to:
randomly selecting a vehicle detection model or a license plate detection model to detect the current frame parking space image;
if the license plate detection model is used for detection, the vehicle detection model is used for detecting the next frame of parking space image;
and if the vehicle detection model is used for detection, detecting the next frame of parking space image by using the license plate detection model.
Referring to fig. 7, another embodiment of the parking space guidance apparatus of the present application includes:
the device comprises a processor, a memory, an input and output unit and a bus;
the processor is connected with the memory, the input and output unit and the bus;
the processor specifically performs the following operations:
acquiring a parking space lamp state and a parking space image of a target parking space, wherein the parking space lamp state comprises a vehicle state and a vehicle-free state;
detecting the parking space image by using a vehicle detection model and a license plate detection model to obtain a detection result, wherein the vehicle detection model is used for detecting a vehicle, and the license plate detection model is used for detecting a license plate;
judging whether the detection result reaches a preset change condition or not;
if so, changing the state of the parking spot lamp.
In this embodiment, the functions of the processor correspond to the steps in the embodiments shown in fig. 1 to fig. 3, and are not described herein again.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and the like.
Claims (10)
1. A method of parking space guidance, comprising:
the method comprises the steps of obtaining a parking space lamp state and a parking space image of a target parking space, wherein the parking space lamp state comprises a vehicle state and a vehicle-free state;
detecting the parking space image by using a vehicle detection model and a license plate detection model to obtain a detection result, wherein the vehicle detection model is used for detecting a vehicle, the vehicle comprises a vehicle head, a vehicle tail or a vehicle body, and the license plate detection model is used for detecting a license plate;
judging whether the detection result reaches a preset change condition or not;
and if so, changing the state of the parking spot lamp.
2. The method of claim 1, wherein when the parking spot light status is a no-vehicle status, the determining whether the detection result meets a preset change condition comprises:
judging whether at least M frames in the continuous N frames detect the vehicle head or the vehicle tail or at least M frames in the continuous N frames detect the vehicle license plate or at least P frames detect the vehicle head or the vehicle tail or at least P frames detect the vehicle license plate in the continuous N frames;
and if so, determining that the detection result reaches the preset change condition.
3. The method of claim 2, wherein the detecting the parking space image using a vehicle detection model and a license plate detection model comprises:
randomly selecting a vehicle detection model or a license plate detection model to detect the current frame parking space image;
if the vehicle is not detected by using the vehicle detection model, detecting the next frame of parking space image by using the license plate detection model;
if the license plate is not detected by using the license plate detection model, detecting the next frame of parking space image by using the vehicle detection model;
if the vehicle head or the vehicle tail is detected by using the vehicle detection model, detecting the next frame of parking space image by using the vehicle detection model;
and if the license plate detection model is used for detecting the license plate, the license plate detection model is used for detecting the next frame of parking space image.
4. The method of claim 3, wherein after the randomly selecting the vehicle detection model or the license plate detection model to detect the current frame parking space image, the method further comprises:
and if the vehicle detection model is used for detecting the vehicle body, the vehicle detection model is used for detecting the next frame of parking space image, and when the vehicle body is detected in continuous Q frames but the vehicle head or the vehicle tail cannot be detected, the license plate detection model is used for detecting the next frame of parking space image.
5. The method according to claim 1, wherein when the parking spot light state is a vehicle-in state, the determining whether the detection result meets a preset change condition comprises:
judging whether at least Y frames in the continuous X frames do not detect the vehicle head, the vehicle tail or the license plate and do not detect the vehicle body or the continuous Z frames do not detect the vehicle head, the vehicle tail or the license plate and do not detect the vehicle body;
and if so, determining that the detection result reaches the preset change condition.
6. The method of claim 5, wherein the detecting the parking space image using a vehicle detection model and a license plate detection model comprises:
randomly selecting a vehicle detection model or a license plate detection model to detect the current frame parking space image;
if the license plate detection model is used for detection, the vehicle detection model is used for detecting the next frame of parking space image;
and if the vehicle detection model is used for detection, the license plate detection model is used for detecting the next frame of parking space image.
7. A parking space guidance apparatus, comprising:
the system comprises an acquisition unit, a display unit and a display unit, wherein the acquisition unit is used for acquiring a parking space lamp state and a parking space image of a target parking space, and the parking space lamp state comprises a vehicle state and a vehicle-free state;
the detection unit is used for detecting the parking space image by using a vehicle detection model and a license plate detection model to obtain a detection result, the vehicle detection model is used for detecting a vehicle, the vehicle comprises a vehicle head, a vehicle tail or a vehicle body, and the license plate detection model is used for detecting a license plate;
the judging unit is used for judging whether the detection result reaches a preset change condition or not;
and the changing unit is used for changing the state of the parking space lamp when the judging unit determines that the detection result reaches the preset changing condition.
8. The apparatus according to claim 7, wherein the determining unit comprises a first determining module configured to:
judging whether at least M frames in the continuous N frames detect the vehicle head or the vehicle tail or at least M frames in the continuous N frames detect the vehicle license plate or at least P frames detect the vehicle head or the vehicle tail or at least P frames detect the vehicle license plate in the continuous N frames;
and if so, determining that the detection result reaches the preset change condition.
9. The apparatus according to claim 7, wherein the determining unit comprises a second determining module configured to:
judging whether at least Y frames in the continuous X frames do not detect the vehicle head, the vehicle tail or the license plate and do not detect the vehicle body or the continuous Z frames do not detect the vehicle head, the vehicle tail or the license plate and do not detect the vehicle body;
and if so, determining that the detection result reaches the preset change condition.
10. A parking space guidance apparatus, comprising:
the device comprises a processor, a memory, an input and output unit and a bus;
the processor is connected with the memory, the input and output unit and the bus;
a program stored in the memory, the program being called by the processor to perform the method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111220286.0A CN114038228A (en) | 2021-10-20 | 2021-10-20 | Parking space guiding method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111220286.0A CN114038228A (en) | 2021-10-20 | 2021-10-20 | Parking space guiding method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114038228A true CN114038228A (en) | 2022-02-11 |
Family
ID=80142179
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111220286.0A Pending CN114038228A (en) | 2021-10-20 | 2021-10-20 | Parking space guiding method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114038228A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114582163A (en) * | 2022-03-14 | 2022-06-03 | 深圳市捷顺科技实业股份有限公司 | Parking space management and control method, device, equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106599921A (en) * | 2016-12-14 | 2017-04-26 | 深圳市捷顺科技实业股份有限公司 | Parking stall guiding method and device |
| CN110245544A (en) * | 2018-09-26 | 2019-09-17 | 浙江大华技术股份有限公司 | A kind of method and device of determining dead ship condition |
| CN110245673A (en) * | 2018-03-09 | 2019-09-17 | 浙江宇视科技有限公司 | Method for detecting parking stalls and device |
| CN111145555A (en) * | 2019-12-09 | 2020-05-12 | 浙江大华技术股份有限公司 | Method and device for detecting vehicle violation |
| CN111784857A (en) * | 2020-06-22 | 2020-10-16 | 浙江大华技术股份有限公司 | Parking space management method and device and computer storage medium |
| CN111898485A (en) * | 2020-07-14 | 2020-11-06 | 浙江大华技术股份有限公司 | Parking space vehicle detection processing method and device |
| CN113408364A (en) * | 2021-05-26 | 2021-09-17 | 深圳市捷顺科技实业股份有限公司 | Temporary license plate recognition method, system, device and storage medium |
-
2021
- 2021-10-20 CN CN202111220286.0A patent/CN114038228A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106599921A (en) * | 2016-12-14 | 2017-04-26 | 深圳市捷顺科技实业股份有限公司 | Parking stall guiding method and device |
| CN110245673A (en) * | 2018-03-09 | 2019-09-17 | 浙江宇视科技有限公司 | Method for detecting parking stalls and device |
| CN110245544A (en) * | 2018-09-26 | 2019-09-17 | 浙江大华技术股份有限公司 | A kind of method and device of determining dead ship condition |
| CN111145555A (en) * | 2019-12-09 | 2020-05-12 | 浙江大华技术股份有限公司 | Method and device for detecting vehicle violation |
| CN111784857A (en) * | 2020-06-22 | 2020-10-16 | 浙江大华技术股份有限公司 | Parking space management method and device and computer storage medium |
| CN111898485A (en) * | 2020-07-14 | 2020-11-06 | 浙江大华技术股份有限公司 | Parking space vehicle detection processing method and device |
| CN113408364A (en) * | 2021-05-26 | 2021-09-17 | 深圳市捷顺科技实业股份有限公司 | Temporary license plate recognition method, system, device and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114582163A (en) * | 2022-03-14 | 2022-06-03 | 深圳市捷顺科技实业股份有限公司 | Parking space management and control method, device, equipment and storage medium |
| CN114582163B (en) * | 2022-03-14 | 2023-05-16 | 深圳市捷顺科技实业股份有限公司 | Parking space management and control method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| DE102007000420B4 (en) | In-vehicle device for detecting vehicles and device for controlling headlamps by using the device | |
| US7957559B2 (en) | Apparatus and system for recognizing environment surrounding vehicle | |
| CN111815959B (en) | Vehicle violation detection method and device and computer readable storage medium | |
| CN109318799B (en) | Automobile, automobile ADAS system and control method thereof | |
| CN114038228A (en) | Parking space guiding method and device | |
| CN114475429B (en) | Traffic light reminding method and system combined with user driving intention and automobile | |
| CN115257527A (en) | Tail lamp display control method and device and vehicle | |
| CN112699862B (en) | Image data processing method, device, equipment and storage medium | |
| CN111959417B (en) | Automobile panoramic image display control method, device, equipment and storage medium | |
| CN115416574B (en) | Strong light early warning method, device and equipment in automobile driving and storage medium | |
| US20230368545A1 (en) | Method for processing images | |
| CN115965636A (en) | Vehicle side view generating method and device and terminal equipment | |
| CN110789449A (en) | Overtaking avoidance reminding method and system based on image recognition technology and vehicle-mounted terminal | |
| CN113581180B (en) | Congestion road condition lane change decision method, storage medium and electronic equipment | |
| CN114078212A (en) | Accurate vehicle type identification method and device based on ETC portal | |
| CN107331181A (en) | A kind of vehicle is with car intelligent prompt method and its system | |
| CN112164221A (en) | Image data mining method, device and equipment and road side equipment | |
| CN111098780A (en) | Traffic signal display system, vehicle and method | |
| CN110596415A (en) | Method and device for detecting speed of adjacent vehicle based on monocular distance measurement | |
| CN117068176A (en) | Method, device, equipment and storage medium for determining vehicle distance | |
| CN113657427B (en) | In-vehicle multi-source image fusion recognition method and device | |
| CN111762090B (en) | High beam real-time reminding platform, method and storage medium | |
| CN116039631A (en) | Driving control method and device for vehicle, vehicle and storage medium | |
| CN116513054A (en) | Vehicle driving assisting method and device, vehicle and storage medium | |
| CN116985816A (en) | Front vehicle sliding monitoring method, system, vehicle and computer storage medium |
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: 20220211 |