CN108230705B - Method and device for planning path in parking lot - Google Patents
Method and device for planning path in parking lot Download PDFInfo
- Publication number
- CN108230705B CN108230705B CN201611190071.8A CN201611190071A CN108230705B CN 108230705 B CN108230705 B CN 108230705B CN 201611190071 A CN201611190071 A CN 201611190071A CN 108230705 B CN108230705 B CN 108230705B
- Authority
- CN
- China
- Prior art keywords
- target
- vehicle
- determining
- node
- path
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3407—Route searching; Route guidance specially adapted for specific applications
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the invention discloses a method and a device for planning a path in a parking lot, wherein the method comprises the following steps: for each path, determining state information of each node in the path; determining the busy level of the path according to the determined state information of each node; and selecting a target path according to the determined busy level of each path. That is to say, according to busy level, plan the route in the parking area, avoided the route to block up, shortened the parking time.
Description
Technical Field
The invention relates to the technical field of video monitoring, in particular to a method and a device for planning a path in a parking lot.
Background
With the continuous improvement of living standard, private cars have become more and more popular. And in addition, the parking spaces of the parking lot are more and more. The existing scheme can feed back the information of available parking spaces in the parking lot to a driver after a vehicle drives into the parking lot so as to shorten the time consumed in the parking process.
However, the scheme only feeds back the information of the available parking spaces to the driver, does not plan the driving path of the vehicle in the parking lot, and if a plurality of vehicles simultaneously appear in the same path, the path congestion is caused, and a lot of time is still consumed in the parking process.
Disclosure of Invention
An object of the embodiments of the present invention is to provide a method and an apparatus for planning a route in a parking lot, so as to shorten a parking time.
In order to achieve the purpose, the embodiment of the invention discloses a path planning method in a parking lot, which comprises the following steps:
for each path, determining state information of each node in the path;
determining the busy level of the path according to the determined state information of each node;
and selecting a target path according to the determined busy level of each path.
Optionally, before the step of determining the state information of each node in each path, the method may further include:
determining a current location of a target vehicle;
judging whether the current position is located in a parking space;
if yes, determining a path between the current position and the exit position of the parking lot;
and if not, determining a path between the current position and the available parking space.
Optionally, the step of determining the state information of each node in the path may include:
determining each target node contained in the path;
searching the state information of each target node in the stored state information of each node of the parking lot;
and determining the searched state information as the state information of each node in the path.
Optionally, the process of saving the state information of each node of the parking lot may include:
acquiring a current image group of each node in the parking lot every other preset period;
and analyzing the acquired current image group, and determining and storing the state information of each node in the parking lot according to the analysis result.
Optionally, the step of analyzing the acquired current image group and determining the state information of each node in the parking lot according to the analysis result may include:
aiming at each node, identifying images in the current image group of the node by using a target identification technology;
judging whether a target image exists in the current image group of the node or not according to the identification result, wherein a vehicle target exists in the target image;
if not, the state information of the node is unoccupied; if yes, the state information of the node is occupied;
the step of determining the busy level of the path according to the determined state information of each node comprises the following steps:
determining the number of busy nodes, wherein the state information of the busy nodes is occupied;
and determining the busy level of the path according to the preset corresponding relation between the busy level and the number of the busy nodes.
Optionally, the step of analyzing the acquired current image group and determining the state information of each node in the parking lot according to the analysis result may include:
aiming at each node, identifying images in the current image group of the node by using a target identification technology;
judging whether a target image exists in the current image group of the node or not according to the identification result, wherein a vehicle target exists in the target image;
if not, the state information of the node is unoccupied;
if yes, extracting a vehicle target in the target image, and determining the posture of the vehicle target;
determining the motion characteristics of each vehicle target corresponding to the node according to the determined posture of each vehicle target;
determining the time length of the vehicle target occupying the corresponding node according to the preset corresponding relation between the motion characteristics and the occupied time length;
determining state information of the corresponding node according to the determined duration, wherein the state information comprises an occupation grade corresponding to the duration;
the step of determining the busy level of the path according to the determined state information of each node comprises the following steps:
and determining the busy level of the path according to the determined occupation level contained in the state information of each node.
Optionally, the step of determining the motion characteristic of each vehicle target corresponding to the node according to the determined posture of each vehicle target may include:
determining the motion trail of each vehicle target extracted from the same image group by using a target tracking technology according to the determined posture of each vehicle target;
and determining the motion characteristics of the vehicle target according to the motion track.
Optionally, the step of determining the state information of the corresponding node according to the determined duration may include:
determining a number of the extracted different vehicle targets;
and determining the state information of the corresponding node according to the number of the different vehicle targets and the time length of each vehicle target occupying the corresponding node.
Optionally, the step of identifying an image in the current image group of the node by using the target identification technology may include:
and identifying the images in the current image group of the node by utilizing a moving object detection technology, a machine learning detection technology or a license plate identification technology.
Optionally, the step of selecting a target path according to the determined busy level of each path may include:
determining a path distance between a destination position in each path and a current position of a target vehicle, wherein the target vehicle is a vehicle of which the path is to be determined in a parking lot;
and combining the determined path distance and the busy level of each path to select the target path.
Optionally, after the step of selecting the target path, the method may further include:
determining a vehicle characteristic of the target vehicle;
when the fact that the driven vehicle exists in the target parking space corresponding to the target path is detected, whether the vehicle characteristics of the driven vehicle are consistent with the vehicle characteristics of the target vehicle is judged;
if not, returning to the step of determining the path distance between each path and the current position of the target vehicle.
In order to achieve the above object, an embodiment of the present invention further discloses a device for planning a path in a parking lot, including:
a first determining module, configured to determine, for each path, state information of each node in the path;
the second determining module is used for determining the busy level of the path according to the determined state information of each node;
and the selection module is used for selecting the target path according to the determined busy level of each path.
Optionally, the apparatus may further include:
a third determination module for determining a current location of the target vehicle;
the first judgment module is used for judging whether the current position is located in the parking space;
the fourth determining module is used for determining a path between the current position and the exit position of the parking lot when the first judging module judges that the current position is the exit position; and when the judgment result of the first judgment module is negative, determining a path between the current position and the available parking space.
Optionally, the first determining module may be specifically configured to:
determining each target node contained in the path;
searching the state information of each target node in the stored state information of each node of the parking lot;
and determining the searched state information as the state information of each node in the path.
Optionally, the apparatus may further include:
the first acquisition module is used for acquiring the current image group of each node in the parking lot every other preset period;
the fifth determining module is used for analyzing the acquired current image group and determining the state information of each node in the parking lot according to the analysis result;
and the storage module is used for storing the state information of each node in the parking lot.
Optionally, the fifth determining module may be specifically configured to:
aiming at each node, identifying images in the current image group of the node by using a target identification technology;
judging whether a target image exists in the current image group of the node or not according to the identification result, wherein a vehicle target exists in the target image;
if not, the state information of the node is unoccupied; if yes, the state information of the node is occupied;
the second determining module is specifically configured to:
determining the number of busy nodes, wherein the state information of the busy nodes is occupied;
and determining the busy level of the path according to the preset corresponding relation between the busy level and the number of the busy nodes.
Optionally, the fifth determining module may include:
the identification submodule is used for identifying the images in the current image group of each node by utilizing a target identification technology;
the judging submodule is used for judging whether a target image exists in the current image group of the node or not according to the identification result, and a vehicle target exists in the target image; if not, the state information of the node is unoccupied; if yes, triggering an extraction submodule;
the extraction submodule is used for extracting the vehicle target in the target image and determining the posture of the vehicle target;
the first determining submodule is used for determining the motion characteristics of each vehicle target corresponding to the node according to the determined posture of each vehicle target;
the second determining submodule is used for determining the time length of the vehicle target occupying the corresponding node according to the corresponding relation between the preset motion characteristic and the occupied time length;
a third determining submodule, configured to determine, according to the determined duration, state information of the corresponding node, where the state information includes an occupancy level corresponding to the duration;
the second determining module is specifically configured to:
and determining the busy level of the path according to the determined occupation level contained in the state information of each node.
Optionally, the first determining submodule may be specifically configured to:
determining the motion trail of each vehicle target extracted from the same image group by using a target tracking technology according to the determined posture of each vehicle target;
and determining the motion characteristics of the vehicle target according to the motion track.
Optionally, the third determining sub-module may be specifically configured to:
determining a number of the extracted different vehicle targets;
and determining the state information of the corresponding node according to the number of the different vehicle targets and the time length of each vehicle target occupying the corresponding node.
Optionally, the identification submodule may be specifically configured to:
and identifying the images in the current image group of the node by utilizing a moving object detection technology, a machine learning detection technology or a license plate identification technology.
Optionally, the selecting module may include:
the fourth determining submodule is used for determining a path distance between the end point position in each path and the current position of a target vehicle, and the target vehicle is a vehicle of which the path is to be determined in the parking lot;
and the selection submodule is used for combining the determined path distance and the busy level of each path to select a target path.
Optionally, the apparatus may further include:
a sixth determination module to determine a vehicle characteristic of the target vehicle;
the second judging module is used for judging whether the vehicle characteristics of the entering vehicle are consistent with the vehicle characteristics of the target vehicle or not when the entering vehicle is detected to exist in the target parking space corresponding to the target path; if not, triggering the fourth determination submodule.
By applying the embodiment of the invention, the busy level of each path is determined according to the state information of each node in the path; and selecting a target path according to the busy level of each path. That is to say, according to busy level, plan the route in the parking area, avoided the route to block up, shortened the parking time.
Of course, not all of the advantages described above need to be achieved at the same time in the practice of any one product or method of the invention.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a parking path determining method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a parking path determining apparatus according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to solve the above technical problems, embodiments of the present invention provide a method and an apparatus for planning a path in a parking lot, which may be applied to a server, a client and various electronic devices installed in the parking lot, and may also be applied to various electronic devices in a vehicle, and are not limited specifically.
To distinguish descriptions, if the electronic device executing the present scheme is an electronic device set in a parking lot, it is referred to as a first electronic device, and if the electronic device executing the present scheme is an electronic device in a vehicle, it is referred to as a second electronic device.
In addition, it should be noted that the scheme can be applied to route planning when a vehicle enters a parking lot or leaves the parking lot.
First, a method for planning a route in a parking lot according to an embodiment of the present invention will be described in detail.
Fig. 1 is a schematic flow chart of a method for planning a path in a parking lot according to an embodiment of the present invention, including:
s101: and determining the state information of each node in each path.
As described above, the present embodiment may be applied to various electronic devices (first electronic devices) provided in a parking lot, and the first electronic device may execute the present scheme when detecting a target vehicle or when receiving a path planning request transmitted by the target vehicle.
Specifically, the first electronic device may communicate with other devices provided in the parking lot, and therefore, when a vehicle enters the parking lot, the access control device of the parking lot may transmit a signal to the first electronic device, so that the first electronic device may detect the target vehicle, and at this time, the first electronic device may perform S101.
Or, when a vehicle entering the parking lot needs to perform path planning, a path planning request is sent to the first electronic device, and after receiving the request, the first electronic device may execute S101.
It can be understood that, if the application scenario of the scheme is that when a vehicle drives into a parking lot, the starting point of the path is the current position of the target vehicle, and the ending point is the position of the available parking space; if the application scene of the scheme is that the vehicle leaves the parking lot, the starting point of the path is the current position of the target vehicle, and the terminal point is the exit position of the parking lot.
In one embodiment, the first electronic device may be communicatively coupled to a locating device in the target vehicle so that the current location of the target vehicle may be determined.
Alternatively, the current position of the target vehicle may be determined in other manners, for example, a device for tracking the target vehicle is disposed in the parking lot, and the device sends the position information of the tracked vehicle to the first electronic device, and the like, which is not limited in detail.
The method comprises the steps that a first electronic device judges whether the current position of a target vehicle is located in a parking space, if yes, the target vehicle is indicated to be required to leave the parking space, and a path between the current position and an exit position of the parking space is determined; if not, the target vehicle is indicated to be required to drive into the parking space of the parking lot, and the first device can acquire the position of the available parking space in the parking lot and determine a path between the current position and the available parking space.
In addition, the present embodiment may also be applied to various electronic devices (second electronic devices) in a vehicle, and the second electronic device may execute the present scheme after a vehicle (target vehicle) to which the second electronic device belongs enters a parking lot or when a path planning request sent by a user is received.
The second electronic device may also determine a current location of the target vehicle; judging whether the current position is located in a parking space; if yes, determining a path between the current position and the exit position of the parking lot; and if not, determining a path between the current position and the available parking space.
Each node in the parking lot can be provided with acquisition equipment, and image acquisition is carried out on each parking space. Specifically, each parking space can be used as a node, and a preset number of parking spaces can also be used as a node. That is to say, one collection device may be arranged at each parking space, or one collection device may be arranged at intervals of a plurality of parking spaces, and the collection device is not limited specifically. One path includes several nodes.
The first electronic device, or the second electronic device, may determine each target node included in the path; searching the state information of each target node in the stored state information of each node of the parking lot; and determining the searched state information as the state information of each node in the path.
In this embodiment, the state information of each node in the parking lot may be stored in advance, and the state information may be stored in a database, a server, or the first electronic device in the parking lot, and the specific storage location is not limited. The first electronic device or the second electronic device may obtain the saved state information of each node.
Assuming that the state information is stored in the first electronic device, the process of the first electronic device storing the state information of each node of the parking lot may include:
acquiring a current image group of each node in the parking lot every other preset period;
and analyzing the acquired current image group, and determining and storing the state information of each node in the parking lot according to the analysis result.
The current image group can be understood as a multi-frame image in a video acquired by the acquisition equipment arranged at the node in the current time period. The images in the image group may carry time information, and the order of the images in the image group may be determined according to the time information.
The first electronic device can be in communication connection with each acquisition device arranged in the parking lot, so that the first electronic device can acquire the image group of each node in the parking lot.
Specifically, the first electronic device may acquire a current image group of each node in the parking lot every preset period;
and analyzing the acquired current image group, and determining and storing the state information of each node in the parking lot according to the analysis result.
The preset period can be set according to actual conditions, and the state information of each parking space in the parking lot is stored every other preset period, namely, the stored state information of each parking space is updated regularly, so that the accuracy of the state information of the parking spaces can be improved.
S102: and determining the busy level of the path according to the determined state information of each node.
As an embodiment, the step of analyzing the acquired current image group and determining the status information of each node in the parking lot according to the analysis result may include:
aiming at each node, identifying images in the current image group of the node by using a target identification technology;
judging whether a target image exists in the current image group of the node or not according to the identification result, wherein a vehicle target exists in the target image;
if not, the state information of the node is unoccupied; if yes, the state information of the node is occupied.
Specifically, there may be a plurality of schemes for identifying the images in the current image group of the node by using a target identification technology, for example, using a moving target detection technology, a machine learning detection technology, or a license plate identification technology to identify the images in the current image group of the node.
For example, the moving object detection technique may detect a moving object in an image, i.e., a vehicle object in the embodiment, by using background modeling and frame difference. In particular, a background model may be saved or adaptively updated in real time for each node, and a background model may be understood as a model of a node where no vehicle exists. When the image in the current image group is not matched with the corresponding background model, the image shows that a suspected moving object exists in the image. In this case, the image may be compared with a plurality of previous or subsequent frames of images by using a frame difference method to determine whether the suspected moving object is a moving object. If so, non-vehicle objects may be further filtered out by a priori knowledge (e.g., vehicle size, aspect ratio, etc.), such that vehicle objects in the image are identified.
The machine learning detection technology can be used for detecting the head of the vehicle on the image by using a head detection technology, or detecting the tail of the vehicle on the image by using a tail detection technology, or marking the driving direction of the vehicle, learning to obtain a vehicle driving direction classifier, and classifying the image by using the classifier so as to identify the vehicle target in the image.
The license plate recognition technology can recognize whether a license plate exists in the image or not, and if the license plate exists, the vehicle target exists in the image.
Assuming that there are 20 images in the current image group of the node a, and there are 16 images with vehicle targets, these 16 images are target images, there are target images in the current image group of the node a, and the status information of the node a is occupied.
If there are 20 images in the current image group of the node B and there is no vehicle target in the 20 images, the state information of the node B is unoccupied.
In this embodiment, S102 may include: determining the number of busy nodes, wherein the state information of the busy nodes is occupied; and determining the busy level of the path according to the preset corresponding relation between the busy level and the number of the busy nodes.
Here, a node whose state information is "occupied" is referred to as a busy node. It can be understood that if there is no busy node in a path, the busy level of the path is the lowest, and the target vehicle travels the most smoothly in the path; the more busy nodes contained in a route, the higher the busy level of the route, and the more serious the congestion condition when the target vehicle travels in the route.
Thus, the busy level is positively correlated with the number of busy nodes. For example, when the number of busy nodes is 0, the busy level is 0, when the number of busy nodes is 1 to 3, the busy level is 1, and when the number of busy nodes is greater than 3, the specific correspondence relationship of the busy level being 2 … … may be set according to actual conditions.
As another embodiment, the step of analyzing the acquired current image and determining the state information of each node in the parking lot according to the analysis result may include:
aiming at each node, identifying images in the current image group of the node by using a target identification technology;
judging whether a target image exists in the current image group of the node or not according to the identification result, wherein a vehicle target exists in the target image;
if not, the state information of the node is unoccupied;
if yes, extracting a vehicle target in the target image, and determining the posture of the vehicle target;
determining the motion characteristics of each vehicle target corresponding to the node according to the determined posture of each vehicle target;
determining the time length of the vehicle target occupying the corresponding node according to the preset corresponding relation between the motion characteristics and the occupied time length;
and determining the state information of the corresponding node according to the determined duration, wherein the state information comprises the occupancy level corresponding to the duration.
The foregoing has described the object recognition technology in detail, and the details are not repeated here.
In the present embodiment, when a vehicle object exists in an image, the vehicle object is extracted. Specifically, the moving object detection technology, the machine learning detection technology, or the license plate recognition technology is used to identify the vehicle object, and the identified vehicle object may be further extracted, and the posture of the extracted vehicle object may be determined. Determining the pose of the vehicle object is understood to mean determining the head position, tail position, etc. of the vehicle object in the image.
As an embodiment, the step of determining the motion characteristic of each vehicle target corresponding to the node according to the determined posture of each vehicle target may include:
determining the motion trail of each vehicle target extracted from the same image group by using a target tracking technology according to the determined posture of each vehicle target;
and determining the motion characteristics of the vehicle target according to the motion track.
Continuing with the above example, there are 16 object images in the current image group of node A, and it is assumed that there are 2 vehicle objects in the first 14 images and 1 vehicle object in the last 2 images of the 16 images. Each vehicle target in each image is tracked using target tracking techniques. There are various tracking methods, for example, a color-based method may be used to track the vehicle target at multiple scales by using a gaussian pyramid. This way multiple vehicle targets can be tracked simultaneously.
Assume that the tracking result indicates that 2 vehicle targets in the first 10 images are vehicle target X and vehicle target Y, and 2 vehicle targets in the last 4 images are vehicle target Y and vehicle target Z.
Determining the motion characteristics of the vehicle target X according to the posture of the vehicle target X in the first 10 images; determining the motion characteristics of the vehicle object Y according to the posture of the vehicle object Y in the 14 images; and determining the motion characteristics of the vehicle target X according to the posture of the vehicle target Z in the last 4 images.
Taking the vehicle target X as an example:
through the above steps, the posture of the vehicle target X, that is, the head position or the tail position of the vehicle target X in the image, or the like has been determined. According to the head position or the tail position of the vehicle target X in the 10 images, the motion track of the vehicle target X in the 10 images can be determined.
According to the motion trail, whether the motion characteristics of the vehicle target drive into a parking space, pass through a lane, reverse into a parking space or the like can be determined. Alternatively, the motion characteristics may include others, and are not particularly limited.
It is understood that for a typical driver, the duration of backing into a parking space > the duration of exiting a parking space > the duration of passing a lane. Therefore, if the motion characteristic of the vehicle object is passing through a lane, the vehicle object should occupy a node, or occupy a path for a short period of time; if the motion characteristic of the vehicle target is exiting from the parking space, the time length of the node occupied by the vehicle target or the time length of the path occupied by the vehicle target is longer; if the motion characteristic of the vehicle object is reverse parking, the vehicle object should occupy the node, or the path, for a longer period of time.
The corresponding relation between the motion characteristics and the occupation time can be set according to actual conditions, for example, the occupation time corresponding to passing through a lane can be within 5s, the occupation time corresponding to driving out a parking space can be 5s-10s, and the occupation time corresponding to backing into a parking space can be more than 10 s.
It will be appreciated that the longer the duration, the higher its corresponding occupancy level. Assuming that the occupancy level corresponding to "within 5 s" is 1 level, the occupancy level corresponding to "5 s-10 s" is 2 levels, and the occupancy level corresponding to "above 10 s" is 3 levels.
In the present embodiment, the state information of the node includes the occupancy level. That is, if the motion feature of the vehicle target in the current image corresponding to a node is "passing through the lane", the occupancy level included in the state information of the node is level 1; if the motion characteristic of the vehicle target in the current image corresponding to a certain node is 'exiting a parking space', the occupancy level contained in the state information of the node is 2 level; and if the motion characteristic of the vehicle target in the current image corresponding to a certain node is 'backing into position', the occupation level contained in the state information of the node is 3 level.
The more different vehicle targets a node corresponds to, the higher the occupancy level contained in the state information of the node (because the more vehicles in the node area, the more congested the route). In this embodiment, the occupancy level included in the state information of the node may be determined by comprehensively considering the occupancy duration and the number of different vehicle targets.
Thus, in determining the state information of the node, the number of different vehicle targets extracted may be determined; and determining the state information of the nodes according to the number of the different vehicle targets and the time length of each vehicle target occupying the corresponding node.
Specifically, the number of vehicle targets and the time length for occupying the node may be quantized, a weight may be assigned to the quantized number, and the occupancy level included in the state information of the node may be determined according to the final weight.
For example, assume that the quantitative score for the number of vehicle targets "1-2" is 1 and the quantitative score for the number of vehicle targets "3-4" is 2. Suppose that the quantization score corresponding to the time length within 5s of the occupied node is 1, the quantization score corresponding to the time length from 5s to 10s is 2, and the quantization score corresponding to the time length above 10s is 3. Assuming that the weight value corresponding to the number of the vehicle targets is 60%, and the weight value corresponding to the time length of occupying the node is 40%.
In the above example, node a corresponds to 3 different vehicle targets: vehicle object X, vehicle object Y, and vehicle object Z, and thus, the corresponding quantitative score is 2. Assume that the motion characteristic of the vehicle object X is a passing lane (corresponding to a quantized score of 1), the motion characteristic of the vehicle object Y is a driving out of a parking space (corresponding to a quantized score of 2), and the motion characteristic of the vehicle object Z is a reversing into a parking space (corresponding to a quantized score of 3). The occupancy level contained in the status information of node a may be 2 × 60% +1 × 40% +2 × 40% +3 × 40% — 3.6.
Or, other manners may also be adopted, the occupancy duration and the number of different vehicle targets are comprehensively considered, and the occupancy level included in the state information of the node is determined, which is not limited specifically.
In this embodiment, S102 may include: and determining the busy level of the path according to the determined occupation level contained in the state information of each node.
For example, assume that there are 4 nodes in the path, and the occupancy levels included in the state information of the 4 nodes are 1, 1.6, 2.4, and 3.2, respectively. As an embodiment, the sum of the 4 occupancy levels may be determined as the busy level of the path, i.e., 1+1.6+2.4+3.2 — 8.2. Alternatively, the average of the 4 occupancy levels may be determined as the busy level of the path, i.e., 8.2/4 — 2.05. Alternatively, other methods may be used, and are not particularly limited.
S103: and selecting a target path according to the determined busy level of each path.
As an embodiment, a path with a low busy level may be selected as the target path.
As another embodiment, a path distance between the end position in each path and the current position of a target vehicle, which is a vehicle of a parking lot whose path is to be determined, may be determined; and combining the determined path distance and the busy level of each path to select the target path.
Assume that there are 3 paths: the vehicle includes route 1, route 2, and route 3, where the end position of route 1 is a vehicle slot No. 51, the end position of route 2 is a vehicle slot No. 52, and the end position of route 3 is a vehicle slot No. 55.
Assume that the path distance between the vehicle slot with serial number 51 and the current position of the target vehicle is 510m, the path distance between the vehicle slot with serial number 52 and the current position of the target vehicle is 190m, and the path distance between the vehicle slot with serial number 55 and the current position of the target vehicle is 290 m.
Assume busy level for path 1 is 3.2, busy level for path 2 is 2.4, and busy level for path 3 is 1.8.
As an embodiment, each path may be sorted according to the path distance and the busy level, and specifically, weights may be assigned to the path distance and the busy level, for example, the weight corresponding to the path distance is 60%, and the weight corresponding to the busy level is 40%.
And quantizing the path distance and the busy level, such as: the corresponding score of the path distance within 0-100m is 5, the corresponding score of the path distance within 101-200m is 4, the corresponding score of the path distance within 201-300m is 3, the corresponding score of the path distance within 301-400m is 2, the corresponding score of the path distance within 401-500m is 1, and the corresponding score of the path distance above 500m is 0.
The score value corresponding to a busy level within 0-1 (excluding 1) is 3, the score value corresponding to a busy level within 1-2 (excluding 2) is 2, the score value corresponding to a busy level within 2-3 (excluding 3) is 1, and the score value corresponding to a busy level > -3 is 0.
Thus, the final score of route 1 is 0 × 60% +0 × 40% ═ 0, the final score of route 2 is 4 × 60% +1 × 40% ═ 2.8, the final score of route 3 is 3 × 60% +2 × 40% + 2.6, and the ranking for each route results in: route 2, route 3, route 1.
The path ranked at the first bit may be determined as the target path, and the paths ranked at the first several bits may also be determined as the target path, which is not limited specifically. It is assumed here that the path ranked first is determined as the target path.
And determining the path 2 as a target path, and sending the target path to the target vehicle, wherein the target vehicle can directly drive into the available parking space according to the determined path, and the target path is a planned preferred path, so that the path congestion can be avoided, and the parking time can be shortened.
By applying the embodiment shown in fig. 1 of the present invention, the busy level of each path is determined according to the state information of each node in the path; and selecting a target path according to the busy level of each path. Namely, the route is planned according to the busy level, so that the route congestion is avoided, and the parking time is shortened.
In the embodiment shown in fig. 1, if the target vehicle enters the parking lot, the target route is selected for the target vehicle by applying the scheme, and the end position of the target route is the available parking space. The target vehicle travels according to the target path, and in the traveling process, another vehicle suddenly occupies the available parking space, and in this case, the target path needs to be selected for the target vehicle again.
If the first electronic device executes the scheme, the first electronic device may determine the vehicle characteristic of the target vehicle after S103;
when the fact that the driven vehicle exists in the target parking space corresponding to the target path is detected, whether the vehicle characteristics of the driven vehicle are consistent with the vehicle characteristics of the target vehicle or not is determined;
if not, returning to the step of determining the path distance between each path and the current position of the target vehicle.
The vehicle characteristics may include a license plate, or include a color and a vehicle type, or may also include a license plate, a color and a vehicle type, and the like, which is not limited specifically.
It is understood that when a vehicle enters a parking lot, an access control device of the parking lot may acquire vehicle characteristics (license plate, color, model, etc.) of the vehicle. Therefore, after the first electronic device determines the path of the target vehicle, the vehicle characteristics of the target vehicle can be acquired from the access control device.
In addition, the first electronic device may acquire a current image of a target parking space corresponding to the path, and when it is detected that the entering vehicle exists in the target parking space, the first electronic device may acquire a vehicle feature of the entering vehicle from the current image of the parking space by using a target recognition technology. If the vehicle characteristic is consistent with the vehicle characteristic of the target vehicle, indicating that the target vehicle is parked completely; if the parking spaces are inconsistent, the parking spaces are occupied by other vehicles, the current positions of the target vehicles need to be determined again, and new target paths need to be selected again.
Specifically, the vehicle characteristics may only include a license plate, and in this case, a license plate recognition technology may be used to acquire a license plate of the entering vehicle from the current image of the parking space, and further determine whether the license plate of the entering vehicle is consistent with the license plate of the target vehicle. The vehicle characteristics may also include a color and a vehicle type, and in this case, it may be determined whether the color and the vehicle type of the incoming vehicle are consistent with those of the target vehicle using a target matching technique.
If the second electronic device executes the scheme, the scheme in fig. 1 may be executed again to reselect the target path when the second electronic device occupies the target parking space corresponding to the target path by another vehicle.
Corresponding to the embodiment of the method, the invention also provides a parking path determining device.
Fig. 2 is a schematic structural diagram of a parking path determining apparatus according to an embodiment of the present invention, including:
a first determining module 201, configured to determine, for each path, state information of each node in the path;
a second determining module 202, configured to determine, according to the determined state information of each node, a busy level of the path;
and the selection module 203 is used for selecting a target path according to the determined busy level of each path.
In this embodiment, the apparatus may further include: a third determining module, a first judging module and a fourth determining module (not shown in the figure), wherein,
a third determination module for determining a current location of the target vehicle;
the first judgment module is used for judging whether the current position is located in the parking space;
the fourth determining module is used for determining a path between the current position and the exit position of the parking lot when the first judging module judges that the current position is the exit position; and when the judgment result of the first judgment module is negative, determining a path between the current position and the available parking space.
In this embodiment, the first determining module 201 may be specifically configured to:
determining each target node contained in the path;
searching the state information of each target node in the stored state information of each node of the parking lot;
and determining the searched state information as the state information of each node in the path.
In this embodiment, the apparatus further includes: a first obtaining module, a fifth determining module and a saving module (not shown in the figure), wherein,
the first acquisition module is used for acquiring the current image group of each node in the parking lot every other preset period;
the fifth determining module is used for analyzing the acquired current image group and determining the state information of each node in the parking lot according to the analysis result;
and the storage module is used for storing the state information of each node in the parking lot.
In this embodiment, the fifth determining module may be specifically configured to:
aiming at each node, identifying images in the current image group of the node by using a target identification technology;
judging whether a target image exists in the current image group of the node or not according to the identification result, wherein a vehicle target exists in the target image;
if not, the state information of the node is unoccupied; if yes, the state information of the node is occupied;
the second determining module 202 may specifically be configured to:
determining the number of busy nodes, wherein the state information of the busy nodes is occupied;
and determining the busy level of the path according to the preset corresponding relation between the busy level and the number of the busy nodes.
In this embodiment, the fifth determining module may include:
the identification submodule is used for identifying the images in the current image group of each node by utilizing a target identification technology;
the judging submodule is used for judging whether a target image exists in the current image group of the node or not according to the identification result, and a vehicle target exists in the target image; if not, the state information of the node is unoccupied; if yes, triggering an extraction submodule;
the extraction submodule is used for extracting the vehicle target in the target image and determining the posture of the vehicle target;
the first determining submodule is used for determining the motion characteristics of each vehicle target corresponding to the node according to the determined posture of each vehicle target;
the second determining submodule is used for determining the time length of the vehicle target occupying the corresponding node according to the corresponding relation between the preset motion characteristic and the occupied time length;
a third determining submodule, configured to determine, according to the determined duration, state information of the corresponding node, where the state information includes an occupancy level corresponding to the duration;
the second determining module 202 may specifically be configured to:
and determining the busy level of the path according to the determined occupation level contained in the state information of each node.
In this embodiment, the first determining submodule may be specifically configured to:
determining the motion trail of each vehicle target extracted from the same image group by using a target tracking technology according to the determined posture of each vehicle target;
and determining the motion characteristics of the vehicle target according to the motion track.
In this embodiment, the third determining submodule may be specifically configured to:
determining a number of the extracted different vehicle targets;
and determining the state information of the corresponding node according to the number of the different vehicle targets and the time length of each vehicle target occupying the corresponding node.
In this embodiment, the identification submodule may be specifically configured to:
and identifying the images in the current image group of the node by utilizing a moving object detection technology, a machine learning detection technology or a license plate identification technology.
In this embodiment, the selecting module 203 may include: a fourth determination submodule and a selection submodule (not shown in the figure), wherein,
the fourth determining submodule is used for determining a path distance between the end point position in each path and the current position of a target vehicle, and the target vehicle is a vehicle of which the path is to be determined in the parking lot;
and the selection submodule is used for combining the determined path distance and the busy level of each path to select a target path.
In this embodiment, the apparatus may further include: a sixth determining module and a second judging module (not shown in the figure), wherein,
a sixth determination module to determine a vehicle characteristic of the target vehicle;
the second judging module is used for judging whether the vehicle characteristics of the entering vehicle are consistent with the vehicle characteristics of the target vehicle or not when the entering vehicle is detected to exist in the target parking space corresponding to the target path; if not, triggering the fourth determination submodule.
By applying the embodiment shown in fig. 2 of the present invention, the busy level of each path is determined according to the state information of each node in the path; and selecting a target path according to the busy level of each path. That is to say, according to busy level, plan the route in the parking area, avoided the route to block up, shortened the parking time.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
Those skilled in the art will appreciate that all or part of the steps in the above method embodiments may be implemented by a program to instruct relevant hardware to perform the steps, and the program may be stored in a computer-readable storage medium, which is referred to herein as a storage medium, such as: ROM/RAM, magnetic disk, optical disk, etc.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.
Claims (17)
1. A method for path planning in a parking lot, comprising:
for each path, determining state information of each node in the path;
determining the busy level of the path according to the determined state information of each node;
selecting a target path according to the determined busy level of each path;
the determining the state information of each node in each path includes:
for each node, judging whether a target image exists in the node or not, wherein a vehicle target exists in the target image;
if yes, extracting a vehicle target in the target image, and determining the posture of the vehicle target;
determining the motion characteristics of each vehicle target corresponding to the node according to the determined posture of each vehicle target;
determining the time length of the vehicle target occupying the corresponding node according to the preset corresponding relation between the motion characteristics and the occupied time length;
determining state information of the corresponding node according to the determined duration, wherein the state information comprises an occupation grade corresponding to the duration;
the step of determining the busy level of the path according to the determined state information of each node comprises the following steps:
and determining the busy level of the path according to the determined occupation level contained in the state information of each node.
2. The method of claim 1, further comprising, prior to the step of determining, for each path, state information for nodes in the path:
determining a current location of a target vehicle;
judging whether the current position is located in a parking space;
if yes, determining a path between the current position and the exit position of the parking lot;
and if not, determining a path between the current position and the available parking space.
3. The method of claim 1, wherein the step of determining the state information of each node in the path comprises:
determining each target node contained in the path;
searching the state information of each target node in the stored state information of each node of the parking lot;
and determining the searched state information as the state information of each node in the path.
4. The method of claim 3, wherein the step of maintaining the state information of the nodes of the parking lot comprises:
acquiring a current image group of each node in the parking lot every other preset period;
and analyzing the acquired current image group, and determining and storing the state information of each node in the parking lot according to the analysis result.
5. The method according to claim 4, wherein the step of analyzing the acquired current image group and determining the status information of each node in the parking lot according to the analysis result comprises:
aiming at each node, identifying images in the current image group of the node by using a target identification technology;
judging whether a target image exists in the current image group of the node or not according to the identification result, wherein a vehicle target exists in the target image;
if not, the state information of the node is unoccupied.
6. The method of claim 5, wherein determining the motion characteristics of each vehicle target corresponding to the node based on the determined pose of each vehicle target comprises:
determining the motion trail of each vehicle target extracted from the same image group by using a target tracking technology according to the determined posture of each vehicle target;
and determining the motion characteristics of the vehicle target according to the motion track.
7. The method of claim 5, wherein the step of determining the state information of the corresponding node according to the determined duration comprises:
determining a number of the extracted different vehicle targets;
and determining the state information of the corresponding node according to the number of the different vehicle targets and the time length of each vehicle target occupying the corresponding node.
8. The method according to any of claims 5-7, wherein said step of identifying the image in the current set of images for the node using object recognition techniques comprises:
and identifying the images in the current image group of the node by utilizing a moving object detection technology, a machine learning detection technology or a license plate identification technology.
9. The method of claim 1, wherein the step of selecting the target path based on the determined busy level for each path comprises:
determining a path distance between a destination position in each path and a current position of a target vehicle, wherein the target vehicle is a vehicle of which the path is to be determined in a parking lot;
and combining the determined path distance and the busy level of each path to select the target path.
10. The method of claim 9, further comprising, after the step of selecting a target path:
determining a vehicle characteristic of the target vehicle;
when the fact that the driven vehicle exists in the target parking space corresponding to the target path is detected, whether the vehicle characteristics of the driven vehicle are consistent with the vehicle characteristics of the target vehicle is judged;
if not, returning to the step of determining the path distance between each path and the current position of the target vehicle.
11. A path planning device in a parking lot, comprising:
a first determining module, configured to determine, for each path, each target node included in the path; searching the state information of each target node in the stored state information of each node of the parking lot; determining the searched state information as the state information of each node in the path;
the second determining module is used for determining the busy level of the path according to the determined state information of each node;
the selection module is used for selecting a target path according to the determined busy level of each path;
the device further comprises:
the first acquisition module is used for acquiring the current image group of each node in the parking lot every other preset period;
the fifth determining module is used for analyzing the acquired current image group and determining the state information of each node in the parking lot according to the analysis result;
the storage module is used for storing the state information of each node in the parking lot;
the fifth determining module includes:
the identification submodule is used for identifying the images in the current image group of each node by utilizing a target identification technology;
the judging submodule is used for judging whether a target image exists in the current image group of the node or not according to the identification result, and a vehicle target exists in the target image; if not, the state information of the node is unoccupied; if yes, triggering an extraction submodule;
the extraction submodule is used for extracting the vehicle target in the target image and determining the posture of the vehicle target;
the first determining submodule is used for determining the motion characteristics of each vehicle target corresponding to the node according to the determined posture of each vehicle target;
the second determining submodule is used for determining the time length of the vehicle target occupying the corresponding node according to the corresponding relation between the preset motion characteristic and the occupied time length;
a third determining submodule, configured to determine, according to the determined duration, state information of the corresponding node, where the state information includes an occupancy level corresponding to the duration;
the second determining module is specifically configured to:
and determining the busy level of the path according to the determined occupation level contained in the state information of each node.
12. The apparatus of claim 11, further comprising:
a third determination module for determining a current location of the target vehicle;
the first judgment module is used for judging whether the current position is located in the parking space;
the fourth determining module is used for determining a path between the current position and the exit position of the parking lot when the first judging module judges that the current position is the exit position; and when the judgment result of the first judgment module is negative, determining a path between the current position and the available parking space.
13. The apparatus according to claim 11, wherein the first determining submodule is specifically configured to:
determining the motion trail of each vehicle target extracted from the same image group by using a target tracking technology according to the determined posture of each vehicle target;
and determining the motion characteristics of the vehicle target according to the motion track.
14. The apparatus according to claim 11, wherein the third determining submodule is specifically configured to:
determining a number of the extracted different vehicle targets;
and determining the state information of the corresponding node according to the number of the different vehicle targets and the time length of each vehicle target occupying the corresponding node.
15. The apparatus according to claim 11, 13 or 14, wherein the identification submodule is configured to:
and identifying the images in the current image group of the node by utilizing a moving object detection technology, a machine learning detection technology or a license plate identification technology.
16. The apparatus of claim 11, wherein the selection module comprises:
the fourth determining submodule is used for determining a path distance between the end point position in each path and the current position of a target vehicle, and the target vehicle is a vehicle of which the path is to be determined in the parking lot;
and the selection submodule is used for combining the determined path distance and the busy level of each path to select a target path.
17. The apparatus of claim 16, further comprising:
a sixth determination module to determine a vehicle characteristic of the target vehicle;
the second judging module is used for judging whether the vehicle characteristics of the entering vehicle are consistent with the vehicle characteristics of the target vehicle or not when the entering vehicle is detected to exist in the target parking space corresponding to the target path; if not, triggering the fourth determination submodule.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611190071.8A CN108230705B (en) | 2016-12-21 | 2016-12-21 | Method and device for planning path in parking lot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611190071.8A CN108230705B (en) | 2016-12-21 | 2016-12-21 | Method and device for planning path in parking lot |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108230705A CN108230705A (en) | 2018-06-29 |
| CN108230705B true CN108230705B (en) | 2020-09-04 |
Family
ID=62651006
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611190071.8A Active CN108230705B (en) | 2016-12-21 | 2016-12-21 | Method and device for planning path in parking lot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108230705B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110246355B (en) * | 2019-06-13 | 2021-06-04 | 广州小鹏汽车科技有限公司 | Vehicle scheduling control method and device, computer equipment and storage medium |
| CN111739327B (en) * | 2020-07-29 | 2022-05-13 | 湖南汽车工程职业学院 | In-road parking planning system based on internet of things technology |
| CN113299102A (en) * | 2021-03-27 | 2021-08-24 | 宁波工程学院 | Underground parking lot navigation method, system and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102522002A (en) * | 2011-12-31 | 2012-06-27 | 南京九竹科技实业有限公司 | All-round intelligent guiding system and method for large parking lot |
| CN102779428A (en) * | 2012-07-31 | 2012-11-14 | 深圳市捷顺科技实业股份有限公司 | Guiding method and system of parking lot |
| CN105118325A (en) * | 2015-09-07 | 2015-12-02 | 广东欧珀移动通信有限公司 | Garage navigation method and terminal |
| CN105702083A (en) * | 2016-04-13 | 2016-06-22 | 重庆邮电大学 | Distributed vision-based parking lot-vehicle cooperative intelligent parking system and method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150170517A1 (en) * | 2013-12-12 | 2015-06-18 | Chen Yan | Vehicle parking management system with guidance for indicating floor vacant vehicular parking dock |
-
2016
- 2016-12-21 CN CN201611190071.8A patent/CN108230705B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102522002A (en) * | 2011-12-31 | 2012-06-27 | 南京九竹科技实业有限公司 | All-round intelligent guiding system and method for large parking lot |
| CN102779428A (en) * | 2012-07-31 | 2012-11-14 | 深圳市捷顺科技实业股份有限公司 | Guiding method and system of parking lot |
| CN105118325A (en) * | 2015-09-07 | 2015-12-02 | 广东欧珀移动通信有限公司 | Garage navigation method and terminal |
| CN105702083A (en) * | 2016-04-13 | 2016-06-22 | 重庆邮电大学 | Distributed vision-based parking lot-vehicle cooperative intelligent parking system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108230705A (en) | 2018-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109993969B (en) | Road condition judgment information acquisition method, device and equipment | |
| US9336450B2 (en) | Methods and systems for selecting target vehicles for occupancy detection | |
| CN111652912B (en) | Vehicle counting method and system, data processing equipment and intelligent shooting equipment | |
| CN111540201B (en) | Vehicle queuing length real-time estimation method and system based on roadside laser radar | |
| CN107292277B (en) | Trackable method for roadside double-parking-space parking | |
| CN109241938B (en) | Road congestion detection method and terminal | |
| CN106469518A (en) | The method of the intelligent parking guiding based on video tracking identification, server and system | |
| CN108230705B (en) | Method and device for planning path in parking lot | |
| CN108460968A (en) | A kind of method and device obtaining traffic information based on car networking | |
| CN108961825B (en) | Parking lot parking guiding method based on vehicle secondary identification | |
| CN103325245A (en) | Method for predicting space-time traveling track of blacklisted vehicle | |
| CN108168562B (en) | Method for extracting stop point of positioning track | |
| CN107590486B (en) | Moving object identification method and system, and bicycle flow statistical method and equipment | |
| US11010619B2 (en) | Device and a method for searching for a lane on which a vehicle can drive | |
| CN105528912A (en) | Indoor parking stall recommendation method and system | |
| CN108156406A (en) | The information processing method and device of automobile data recorder | |
| CN109446881A (en) | A kind of express highway section Traffic State Detection Method based on isomeric data | |
| CN115909224A (en) | Track detection method and track detection system | |
| CN110175654A (en) | A kind of update method and system of track road sign | |
| CN111301404A (en) | Vehicle control method and device, storage medium and processor | |
| CN111105619A (en) | Method and device for judging road side reverse parking | |
| CN114049610A (en) | Active discovery method for reverse and reverse illegal behaviors of motor vehicles on expressway | |
| CN109300313B (en) | Illegal behavior detection method, camera and server | |
| CN113407871A (en) | Boarding point recommendation method and device, electronic equipment and readable storage medium | |
| CN110696828B (en) | Forward target selection method and device and vehicle-mounted equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |