CN112489427B - Vehicle trajectory tracking method, device, equipment and storage medium - Google Patents
Vehicle trajectory tracking method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN112489427B CN112489427B CN202011348538.3A CN202011348538A CN112489427B CN 112489427 B CN112489427 B CN 112489427B CN 202011348538 A CN202011348538 A CN 202011348538A CN 112489427 B CN112489427 B CN 112489427B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- parking area
- parking
- point cloud
- image data
- 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
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration by the use of histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/586—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of parking space
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07B—TICKET-ISSUING APPARATUS; FARE-REGISTERING APPARATUS; FRANKING APPARATUS
- G07B15/00—Arrangements or apparatus for collecting fares, tolls or entrance fees at one or more control points
- G07B15/02—Arrangements or apparatus for collecting fares, tolls or entrance fees at one or more control points taking into account a variable factor such as distance or time, e.g. for passenger transport, parking systems or car rental systems
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
-
- 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
- G08G1/147—Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas where the parking area is within an open public zone, e.g. city centre
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a vehicle track tracking method, a device, equipment and a storage medium, wherein the method comprises the following steps: when the fact that the vehicle enters a parking area on the road side is detected, acquiring multiframe image data shot by a camera on the vehicle and multiframe point cloud data detected by a millimeter wave radar on the vehicle; in multi-frame image data, fusing a color histogram of a vehicle with particle filtering to calculate a first driving track of the vehicle moving in a parking area; calculating a second driving track of the vehicle moving in the parking area based on multi-frame point cloud data by referring to a coordinate conversion relation between the camera and the millimeter wave radar; splicing the first driving track and the second driving track to determine a target driving track of the vehicle moving in the parking area; the target travel trajectory is compared with a parking space in the parking area to perform parking-related business operations on vehicles entering or leaving the parking space. The scheme can detect the vehicle behaviors in the parking area in real time and provide a certificate for business operation.
Description
Technical Field
The embodiment of the invention relates to a vehicle management technology, in particular to a vehicle track tracking method, a vehicle track tracking device, vehicle track tracking equipment and a storage medium.
Background
At present, the open parking area at the urban road side mainly adopts geomagnetism, video piles, parking meters and manual mode charging.
However, geomagnetic installation has certain destructiveness on roads, the maintenance of batteries is troublesome, and when a vehicle stops for a long time or other vehicles run, a geomagnetic signal may be triggered by mistake; the video pile has limited control capacity on the parking space, is easily shielded and damaged by people, needs to invest too much and has higher cost; the parking meters are applied generally, but the construction difficulty is high, the urban image is easily influenced when a large number of parking meters are built, the equipment is also easily damaged, and the maintenance cost is high; the efficiency of manual mode charging is the lowest, and the human cost consumes highly, and there is the condition of artifical maloperation. The roadside charging mode still needs manual intervention, cannot realize automatic calculation of parking time and automatic provision of parking evidence while realizing payment of parking fees, is easy to generate parking bill disputes, and has serious phenomena of leakage and leakage during parking fee running and difficulty in obtaining evidence of vehicles in charge of pursuing and evasion afterwards.
Disclosure of Invention
The invention provides a vehicle track tracking method, a vehicle track tracking device, vehicle track tracking equipment and a storage medium, which are used for solving the problems of higher cost, high fee evasion rate and difficulty in fee evasion evidence collection in the conventional parking charging mode.
In a first aspect, an embodiment of the present invention provides a vehicle trajectory tracking method, where a camera and a millimeter wave radar are arranged on a road side, a monitoring range of the camera covers a part of a parking area on the road side, and a monitoring range of the millimeter wave radar covers all of the parking area on the road side, the method including:
when a vehicle is detected to enter a parking area on the road side, acquiring multi-frame image data shot by the camera on the vehicle and multi-frame point cloud data detected by the millimeter wave radar on the vehicle;
in a plurality of frames of the image data, calculating a first driving track of the vehicle moving in the parking area by fusing a color histogram of the vehicle with particle filtering;
calculating a second driving track of the vehicle moving in the parking area based on the multi-frame point cloud data by referring to a coordinate conversion relation between the camera and the millimeter wave radar;
splicing the first driving track and the second driving track to determine a target driving track of the vehicle moving in the parking area;
comparing the target driving trajectory with a parking space in the parking area to perform parking-related business operations on the vehicle entering or leaving the parking space.
In a second aspect, an embodiment of the present invention further provides a vehicle trajectory tracking device, where a camera and a millimeter wave radar are arranged on a road side, a monitoring range of the camera covers a part of a parking area on the road side, and a monitoring range of the millimeter wave radar covers all of the parking area on the road side, the device including:
the data acquisition module is used for acquiring multiframe image data shot by the camera on the vehicle and multiframe point cloud data detected by the millimeter wave radar on the vehicle when the vehicle is detected to enter a parking area on the road side;
the first driving track calculation module is used for calculating a first driving track of the vehicle moving in the parking area by fusing a color histogram of the vehicle with particle filtering in the image data of a plurality of frames;
the second driving track calculation module is used for calculating a second driving track of the vehicle moving in the parking area based on the multi-frame point cloud data by referring to a coordinate conversion relation between the camera and the millimeter wave radar;
the target running track determining module is used for splicing the first running track and the second running track to determine a target running track of the vehicle moving in the parking area;
and the service execution module is used for comparing the target driving track with the parking space in the parking area so as to execute service operation related to parking on the vehicle entering or leaving the parking space.
In a third aspect, an embodiment of the present invention further provides a computer device, where the computer device includes:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the vehicle trajectory tracking method according to the first aspect.
In a fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the vehicle trajectory tracking method according to the first aspect.
When the vehicle is detected to enter a parking area on the road side, multi-frame image data shot by a camera on the vehicle and multi-frame point cloud data detected by a millimeter wave radar on the vehicle are acquired; in multi-frame image data, fusing a color histogram of a vehicle with particle filtering to calculate a first driving track of the vehicle moving in a parking area; calculating a second driving track of the vehicle moving in the parking area based on multi-frame point cloud data by referring to a coordinate conversion relation between the camera and the millimeter wave radar; splicing the first driving track and the second driving track to determine a target driving track of the vehicle moving in the parking area; the target driving track is compared with the parking space in the parking area so as to execute parking related business operation on vehicles entering or leaving the parking space, the millimeter wave radar and the camera are combined, the camera can provide reference for marking the vehicles by the millimeter wave radar so that the millimeter wave radar can track the vehicles, the millimeter wave radar can make up for a short plate with a small camera shooting range and a limited distance, the millimeter wave radar and the camera can make up for the shortages, the problems that a video pile is limited in control capability and easy to be shielded are solved, excessive monitoring equipment is not required, the cost is saved, moreover, the precision of the millimeter wave radar and the camera is high, the difference of the driving tracks obtained by respective resolving of the millimeter wave radar and the camera is small, the target driving track is obtained by splicing the first driving track and the second driving track, the fused track is more accurate, and the precision requirement of tracking the vehicles can be met, meanwhile, the spliced target driving track is the whole driving track of the vehicle in the whole range from the parking area to the parking area, the parking time length can be automatically calculated for the vehicle and the parking evidence can be automatically provided while the vehicle collects the parking fee based on the target driving track, the parking bill dispute is avoided, the occurrence frequency of the phenomenon of parking fee leakage is reduced, and the evasion vehicle is easily subjected to responsibility tracing and evidence obtaining.
Drawings
Fig. 1 is a flowchart of a vehicle trajectory tracking method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a vehicle trajectory tracking device according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of a computer device according to a third embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of a vehicle trajectory tracking method according to an embodiment of the present invention, where the embodiment is applicable to monitoring vehicle behaviors in a road-side open parking area and recording a driving trajectory to trigger a parking-related business operation, and the method may be executed by a vehicle trajectory tracking device, where the vehicle trajectory tracking device may be implemented by software and/or hardware and may be configured in a computer device, such as a server, a workstation, a personal computer, and the like, and the method specifically includes the following steps:
s101, when the fact that the vehicle enters a parking area on the road side is detected, multi-frame image data shot by a camera on the vehicle and multi-frame point cloud data detected by a millimeter wave radar on the vehicle are obtained.
In this embodiment, a camera and a millimeter wave radar are distributed on the road side, the monitoring range of the camera covers a part of the parking area on the road side, the monitoring range of the millimeter wave radar covers the whole parking area on the road side, and the camera and the millimeter wave radar can be installed on a portal or a lamp pole facing the open parking area on the city road side.
The camera can be a camera set integrated with a license plate recognition function, generally speaking, the effective distance of the license plate recognition camera for recognizing the license plate of the vehicle is 25m-60m, the distance for tracking the track of the vehicle is 150m, and generally only 2 lanes can be monitored. And the vehicle target in the open parking area is tracked by computer vision alone, and the target is easily influenced by illumination change, shielding and background interference and is easily lost in practical application.
The detection distance of the millimeter wave radar is far (at least the detection distance can cover a lane within 300 m), the coverage range is wide, and therefore only one millimeter wave radar device needs to be installed on a door frame or a lamp post at a parking area at a road side to monitor the running track of each vehicle in the parking area.
In this embodiment, the camera mainly defines a vehicle detection area based on all lanes in the parking area, a parking space electronic area based on the real position of a parking space, the millimeter wave radar and the camera can detect vehicles entering the parking space electronic area, when it is detected that the vehicles enter the parking area which belongs to the parking space electronic area on the road side, the camera identifies license plates of the vehicles entering the parking area and captures the license plates, multi-frame image data can be obtained, the millimeter wave radar detects the vehicles in real time to obtain reflection signals, and multi-frame point cloud data are generated.
In one embodiment of the present invention, toll antennas are disposed at the ascending and descending gates and each of the turnouts in the parking area on the road side, and when the vehicle is driven away, ETC fee deduction can be performed. The antenna can be arranged on the portal frames of the ascending passageway, the descending passageway and the fork road, and the direction of the antenna needs to be opposite to the driving direction of the vehicle. The roadside parking area management system may be a Toll Collection system based on ETC (Electronic Toll Collection), and may be composed of three major parts: the system comprises a vehicle information acquisition terminal, a roadside core processing terminal and an ETC cloud platform.
The vehicle information acquisition terminal is mainly a camera, a millimeter wave radar and an antenna which are arranged at an entrance and an exit of a road side parking area and other turnouts, and is used for finishing vehicle license plate recognition, driving track recognition, ETC label information recognition and ETC fee deduction.
The roadside core processing terminal is deployed at the front end of a road side parking area and used for uniformly controlling license plate recognition, radar and antennas, and the specific functions comprise vehicle track fitting, license plate picture processing, equipment monitoring, ETC data analysis, parking time and cost calculation and communication with an ETC cloud platform. Generally, one is arranged upstream and downstream of one road segment.
The ETC cloud platform is deployed at the cloud end and used for carrying out background management on the whole system, converging the parking fee deduction bill to the central clearing and settlement system and carrying out clearing and settlement on the ETC bill. The functions of the system also comprise vehicle information management, user management, rate management, parameter management, equipment access management and the like, and the system supports various terminal queries.
And S102, in the multi-frame image data, fusing the color histogram of the vehicle with particle filtering to calculate a first running track of the vehicle moving in the parking area.
In this embodiment, for the acquired multiple frames of image data, the color features characterizing the vehicle in each frame of image data are extracted, a color histogram is generated, the color histogram is incorporated into a particle filter algorithm as a similarity metric value according to the distribution of the particle weights in the particle filter, and the first driving trajectory of the vehicle moving in the parking area is calculated by using the update iteration of the particle swarm.
As an example, the color histogram related to the vehicle in each frame of image data may be obtained by determining a color distribution model of a plurality of frames of image data containing vehicle information, quantizing the image data according to the color distribution model to determine color components in the image data, counting the total number of pixels in the image data for each color component, and calculating the ratio of the total number of pixels to the total number of pixels in the image data. For example, for image I, the color histogram is calculated as
Where P is the pixel interval for calculating the color histogram, v is the variable within the pixel interval, I (x, y) is the pixel value of the coordinates (x, y) in the image I, δ (·) is the kronecker function, and H is the color histogram of the vehicle in the single frame image data. It should be noted that the method for extracting the color histogram of the vehicle is not limited in any way in this embodiment.
In one implementation, S102 may include the following specific steps:
and S1021, determining a color histogram of the vehicle in single-frame image data representing the parking area in the multi-frame image data as a target feature.
And S1022, putting a first particle swarm in the single-frame image data representing the parking area.
And S1023, calculating a color histogram of each first particle in the first particle swarm to serve as a candidate feature.
The first particles are used for representing the estimated position of the vehicle in the parking area.
And S1024, calculating the similarity between the candidate characteristic and the target characteristic of each first particle.
For example, the similarity between the candidate feature and the target feature of each first particle may be calculated by using distance, cosine value, histogram feature statistics, and other calculation methods.
And S1025, putting a second particle swarm again in the single-frame image data according to the estimated position based on the similarity so as to calculate a first driving track of the vehicle moving in the parking area.
In one particular example, a first population of particles in a single frame of image data may be screened based on similarity; calculating a first weight of each first particle according to the similarity of each first particle in the screened first particle swarm, wherein the first weight is used for representing the accuracy of the estimated position; re-putting a second particle swarm in the single-frame image data according to the first weight and the estimated position, for example, summing the squares of the first weight to obtain a first value, taking the reciprocal of the first value as the measurement value of the particle degradation degree, comparing the measurement value with a preset threshold, and if the measurement value is smaller than the preset threshold, re-putting the second particle swarm in the single-frame image data according to the first weight and the estimated position; determining an estimated position of each second particle in the second particle swarm in the parking area, for example, in the second particle swarm, a second weight may be assigned to each second particle, a pixel position of each second particle in the image data is calculated, and the products of the pixel position and the second weight are summed to obtain an estimated position of each second particle in the parking area; updating the second particle swarm based on the estimated position of the second particle until the estimated position of the second particle meets a preset convergence condition, and determining the estimated position of the second particle as the first position of the vehicle in the parking area; and counting the first position of the vehicle in the parking area for all the frame image data to obtain a first running track of the vehicle moving in the parking area.
In order to make the above technical steps better understood by those skilled in the art, the following further explains a specific process of tracking a vehicle by using particle filtering.
In the multi-frame image data, for each frame of image data, the first particle swarm is uniformly distributed around the vehicle position in the current frame of image data, and the initial weight of each particle can be uniformly set according to the total number of the particles of the first particle swarm, for example, X first particles are uniformly distributed at the vehicle position
The initial weight of each particle may be initially set to
Particle: for a stationary random process, assume time k-1, the posterior probability density of the particle tracking system is P (X)k-1|Zk-1)，Xk-1The position state of the particle at time k-1, Zk-1The observed state (measured value) of the system for the particle is time k-1. Selecting n random sample points (particles) according to a certain principle, obtaining measurement information at the moment k, and after the state and time updating process, the posterior probability density of the n particles can be approximate to P (X)k|Zk). In the whole process of particle filtering, along with the increase of the number of particles, the probability density function of the particles gradually approaches to the probability density function of the state, and the particle filtering estimation achieves the effect of optimal Bayes estimation. Bayesian estimation is a theoretical basis of a particle filter method, is an estimation method by combining objective information and subjective information, considers the objective information of a sample and artificial subjective factors, and can well process the condition of the observed sample when the sample is abnormal. For the parameter to be estimated, Bayesian estimation gives prior distribution of the parameter before sampling, and posterior distribution information of the parameter can be obtained by combining sample information.
Let k be the ordinal number of the frame of image data. The particle state calculated by combining the last image data frame with the vehicle state transition equation L (k) ═ AL (k-1) + N (A is a state transition matrix and N is noise)
To predict the state of particles in the image data frame at the current moment
It will be appreciated that the particle states indicate the estimated position of the particles in the parking area, and can substantially represent a position of the vehicle within the parking area in the corresponding frame of image data, based on the Pasteur systemThe number (Bhattacharyya Coefficient, babysitter Coefficient) can calculate the similarity of tracking particles in two frames of image data before and after, the higher the similarity of the particles is, the more likely the first position of the vehicle is to be concentrated on the position of the particles with high similarity, the weight of the particles can be determined according to the similarity of the particles, and the normalization operation is performed on the weight, the size of the weight can represent the height of the similarity, which is an importance sampling principle of particle filtering, the resampling of the particles can be realized according to the weight and the particle state at the last moment, namely, the second particle swarm is thrown again after the first particle swarm is thrown again until the second particle swarm converges, the total number of the particles changes and the weight value also changes each time the particle swarm is thrown again, for example, the particles are resampled according to the weight of the particles and the weight is distributed
Calculating the position state of the vehicle may be expressed as
In order to prevent the particle degradation problem in particle filtering, after several iterations, all the particles except one have only a small weight. The basic idea of resampling is to exclude which particles have small weights, thereby concentrating the particles on particles with large weights. But resampling may ignore particles with higher weight of the implied weight, resulting in filter divergence. It is therefore desirable to introduce an effective ion number as a measure of the degree of particle degradation, i.e.
The method is in NeffLess than a predetermined threshold value NthResampling is performed. The resampling depends only on the normalized weights, and is independent of the dimension of the particle.
In the embodiment, a color histogram of a vehicle is used as a measure of similarity between particles, the weight of particle placement is redistributed based on the feature similarity between the particles, the particles are updated and iterated to track the position of the vehicle in multi-frame image data, a first driving track of the vehicle moving in a parking area is obtained, the tracking efficiency can be guaranteed, the track positioning accuracy is improved, the particle placement is random, the importance of each particle is calculated according to the feature similarity, then the particles are scattered in important places, the particles are scattered in unimportant places in small places, the calculation amount is smaller than that of Monte Carlo filtering.
S103, calculating a second driving track of the vehicle moving in the parking area based on multi-frame point cloud data by referring to a coordinate conversion relation between the camera and the millimeter wave radar.
In this embodiment, a particle swarm is put in the multi-frame image data obtained from the camera, the camera and the millimeter wave radar are calibrated jointly, the coordinate conversion relationship between the camera and the millimeter wave radar can be obtained, extracting point cloud data representing vehicles from each frame of point cloud data to obtain multiple frames of first candidate point cloud data, converting the multiple frames of first candidate point cloud data into a camera coordinate system according to a coordinate conversion relation to obtain multiple frames of second candidate point cloud data, in the multiple frames of second candidate point cloud data, projecting each frame of second candidate point cloud data to the corresponding single frame of image data representing the parking area to obtain multiple frames of third candidate point cloud data, matching the multiple frames of third candidate point cloud data with the particle swarm in the multiple frames of image data, and calculating a second driving track of the vehicle moving in the parking area based on the matching result.
And S104, splicing the first driving track and the second driving track to determine a target driving track of the vehicle moving in the parking area.
Because the camera has a limited vehicle identification range in the parking area, the camera cannot monitor all moving tracks of the vehicle in the parking area only by associating and binding license plate information identified by the camera with a target vehicle to be tracked due to shielding in the sight of the camera and limitation of effective identification range, namely, a first moving track calculated according to multi-frame image data may have missing and cannot be used as a proof of all behaviors of the vehicle in the road side parking area, and because the millimeter wave radar can complement the defect of small monitoring range of the camera, a second moving track calculated based on point cloud data acquired by the millimeter wave radar can monitor the moving track of the vehicle in the whole parking area, but the millimeter wave radar cannot identify the vehicle in a parking state (stationary) because the millimeter wave radar and the camera need to be linked, after the license plate of the vehicle is recognized and the identity of the vehicle is authenticated by the camera, the millimeter wave radar can share the collected data in the camera, so that the identity of the vehicle entering the parking area can be identified, and the corresponding second running track of the monitored vehicle can be distinguished.
The first running track and the second running track are spliced, the overlapped parts of the two tracks in a certain time range can be subjected to position fusion, more accurate vehicle running tracks can be obtained, the two tracks are spliced for the part with the gap in the single running track, the complete running track of the vehicle moving in the parking area can be recovered, and all behavior certificates of parking charging can be provided for the vehicle when parking business operation is triggered.
The first driving track comprises a plurality of first positions and first time points corresponding to the first positions, and the second driving track comprises a plurality of second positions and second time points corresponding to the second positions.
In one particular implementation, a first time point in the first travel trajectory and a second time point in the second travel trajectory are traversed; if the first time point is the same as the second time point, performing linear fusion on a first position corresponding to the first time point and a second position corresponding to the second time point to obtain a target position of the vehicle in the parking area; if the first time point is different from the second time point, generating a new position between a first position corresponding to the first time point and a second position corresponding to the second time point by adopting an interpolation method, and taking the new position as a target position of the vehicle in the parking area; and fitting all the target positions to obtain a target running track of the vehicle moving in the parking area. The embodiment does not limit the specific manner of splicing the first travel track and the second travel track.
In the embodiment, the first driving track and the second driving track are calculated without manual intervention, the target driving track is obtained based on the first driving track and the second driving track, the whole monitoring process of the whole vehicle driving track is an intelligent process, the staying time of the vehicle in the parking space can be calculated based on a plurality of time points in the target driving track, the target driving track can be uploaded to the cloud, the roadside core processing terminal in the roadside parking area management system can charge the parking state of the vehicle according to the target driving track, and an antenna is called to automatically deduct fees of the vehicle after the vehicle leaves the parking space, so that the congestion caused by fee paying and queuing at the entrance and the exit of the parking area is avoided, and the parking space turnover rate is improved.
And S105, comparing the target driving track with the parking space in the parking area so as to execute parking-related business operation on the vehicle entering or leaving the parking space.
In the specific implementation, if the direction of the target driving track is a parking space driven into a parking area and the target driving track passes through a parking line of the parking space, a camera is called to capture the vehicle, and the service operations of license plate recognition, license plate association, identity verification and parking timing are executed on the vehicle;
if the direction of the target running track is the direction of exiting from a parking space in the parking area and the target running track passes through a parking line of the parking space, calling a camera to capture the vehicle, uploading parking information of the vehicle to a cloud end, finishing parking timing of the vehicle, and triggering the cloud end to execute parking charging business operation on the vehicle.
The method comprises the steps of acquiring multiframe image data shot by a camera on the vehicle and multiframe point cloud data detected by a millimeter wave radar on the vehicle when the vehicle is detected to enter a parking area on the road side; in multi-frame image data, fusing a color histogram of a vehicle with particle filtering to calculate a first driving track of the vehicle moving in a parking area; calculating a second driving track of the vehicle moving in the parking area based on multi-frame point cloud data by referring to a coordinate conversion relation between the camera and the millimeter wave radar; splicing the first driving track and the second driving track to determine a target driving track of the vehicle moving in the parking area; the target driving track is compared with the parking space in the parking area so as to execute parking related business operation on vehicles entering or leaving the parking space, the millimeter wave radar and the camera are combined, the camera can provide reference for marking the vehicles by the millimeter wave radar so that the millimeter wave radar can track the vehicles, the millimeter wave radar can make up for a short plate with a small camera shooting range and a limited distance, the millimeter wave radar and the camera can make up for the shortages, the problems that a video pile is limited in control capability and easy to be shielded are solved, excessive monitoring equipment is not required, the cost is saved, moreover, the precision of the millimeter wave radar and the camera is high, the difference of the driving tracks obtained by respective resolving of the millimeter wave radar and the camera is small, the target driving track is obtained by splicing the first driving track and the second driving track, the fused track is more accurate, and the precision requirement of tracking the vehicles can be met, meanwhile, the spliced target driving track is the whole driving track of the vehicle in the whole range from the parking area to the parking area, the parking time length can be automatically calculated for the vehicle and the parking evidence can be automatically provided while the vehicle collects the parking fee based on the target driving track, the parking bill dispute is avoided, the occurrence frequency of the phenomenon of parking fee leakage is reduced, and the evasion vehicle is easily subjected to responsibility tracing and evidence obtaining.
Example two
Fig. 2 is a schematic structural diagram of a vehicle trajectory tracking device according to a second embodiment of the present invention, in this embodiment, a camera and a millimeter wave radar are arranged on a road side, a monitoring range of the camera covers a part of parking areas on the road side, and a monitoring range of the millimeter wave radar covers all parking areas on the road side, where the device may specifically include the following modules:
the data acquisition module 201 is configured to acquire, when it is detected that a vehicle enters a parking area on a road side, multi-frame image data of the vehicle shot by the camera and multi-frame point cloud data of the vehicle detected by the millimeter wave radar;
a first driving track calculation module 202, configured to calculate, in multiple frames of the image data, a first driving track of the vehicle moving in the parking area by using a color histogram fusion particle filter of the vehicle;
a second driving track calculation module 203, configured to calculate a second driving track of the vehicle moving in the parking area based on the multiple frames of point cloud data with reference to a coordinate conversion relationship between the camera and the millimeter wave radar;
a target driving track determining module 204, configured to splice the first driving track and the second driving track to determine a target driving track of the vehicle moving in the parking area;
a service execution module 205, configured to compare the target driving trajectory with a parking space in the parking area, so as to execute a service operation related to parking for the vehicle entering or leaving the parking space.
In one embodiment, the first travel track calculation module 202 includes:
the target feature confirming submodule is used for confirming a color histogram of the vehicle in a single frame of image data representing the parking area in a plurality of frames of image data to serve as a target feature;
the particle swarm throwing submodule is used for throwing a first particle swarm in the single frame of image data representing the parking area;
a candidate feature calculation submodule, configured to calculate a color histogram of each first particle in the first particle swarm as a candidate feature, where the first particle is used to represent an estimated position of the vehicle in the parking area;
a similarity operator module for calculating a similarity between the candidate feature and the target feature of each of the first particles;
and the first driving track confirming submodule is used for re-throwing a second particle swarm in the image data of the single frame according to the estimated position based on the similarity so as to calculate the first driving track of the vehicle moving in the parking area.
In one embodiment, the first travel track confirmation sub-module includes:
a particle swarm screening unit for screening the first particle swarm in the single frame of the image data based on the similarity;
a weight calculation unit, configured to calculate a first weight of each first particle in the first particle swarm after being screened, where the first weight is used to indicate accuracy of the estimated position;
the particle swarm throwing unit is used for throwing a second particle swarm again in the image data of the single frame according to the first weight and the estimated position;
the estimated position determining unit is used for determining the estimated position of each second particle in the second particle swarm in the parking area;
a particle swarm updating unit, configured to update the second particle swarm based on the estimated position of the second particle, and determine that the estimated position of the second particle is a first position of the vehicle in the parking area until the estimated position of the second particle meets a preset convergence condition;
and the position counting unit is used for counting the first position of the vehicle in the parking area for all the frame image data to obtain a first running track of the vehicle moving in the parking area.
In one embodiment, the particle swarm unit comprises:
the first numerical value calculating subunit is used for summing the squares of the first weights to obtain a first numerical value;
the second numerical value operator unit is used for taking the reciprocal of the first numerical value as a second numerical value for measuring the degradation degree of the particles;
a value comparison subunit, configured to compare the second value with a preset threshold;
the particle swarm re-throwing subunit is used for re-throwing a second particle swarm in the image data of the single frame according to the estimated position according to the first weight if the metric value is smaller than the preset threshold value;
in one embodiment, the predicted position determination unit includes:
a weight calculation subunit configured to assign a second weight to each of the second particles in the second particle group;
a pixel position calculating subunit configured to calculate a pixel position of each of the second particles in the image data;
and the estimated position confirming subunit is used for summing the products of the pixel positions and the second weights to obtain the estimated position of each second particle in the parking area.
In one embodiment, a particle swarm is put in the image data; the second travel track calculation module 203 includes:
the coordinate conversion relation calculation submodule is used for carrying out combined calibration on the camera and the millimeter wave radar to obtain a coordinate conversion relation between the camera and the millimeter wave radar;
the first candidate point cloud data confirmation submodule is used for extracting point cloud data representing the vehicle for each frame of the point cloud data in a plurality of frames of the point cloud data to obtain a plurality of frames of first candidate point cloud data;
the second candidate point cloud data confirmation submodule is used for converting a plurality of frames of the first candidate point cloud data into the camera coordinate system according to the coordinate conversion relation to obtain a plurality of frames of second candidate point cloud data;
the third candidate point cloud data confirmation submodule is used for projecting each frame of the second candidate point cloud data to a corresponding single frame of the image data representing the parking area in multiple frames of the second candidate point cloud data to obtain multiple frames of third candidate point cloud data;
the matching submodule is used for matching a plurality of frames of the third candidate point cloud data with a plurality of frames of the particle swarm in the image data;
and a second travel track confirmation submodule for calculating a second travel track along which the vehicle moves in the parking area based on a result of the matching.
In one embodiment, the first travel track comprises a plurality of first positions, a first point in time corresponding to the first positions, and the second travel track comprises a plurality of second positions, a second point in time corresponding to the second positions; the target travel track determination module 204 includes:
a traversing submodule for traversing a first time point in the first travel trajectory and a second time point in the second travel trajectory;
the first target position confirming submodule is used for carrying out linear fusion on a first position corresponding to the first time point and a second position corresponding to the second time point to obtain a target position of the vehicle in the parking area if the first time point is the same as the second time point;
a second target position confirmation submodule, configured to, if the first time point is different from the second time point, generate a new position between a first position corresponding to the first time point and a second position corresponding to the second time point by using an interpolation method, where the new position is used as a target position of the vehicle in the parking area;
and the target running track confirming submodule is used for fitting all the target positions to obtain a target running track of the vehicle moving in the parking area.
In one embodiment, the service execution module 205 comprises:
the first business operation sub-module is used for calling the camera to capture the vehicle and executing business operations of license plate recognition, license plate association, identity verification and parking timing on the vehicle if the orientation of the target driving track is the parking space driven into the parking area and the target driving track passes through a parking line of the parking space;
and the second business operation submodule is used for calling the camera to capture the vehicle if the direction of the target running track is that the vehicle is driven out of a parking space in the parking area and the target running track passes through a parking line of the parking space, uploading parking information of the vehicle to a cloud end, finishing parking timing of the vehicle and triggering the cloud end to execute parking charging business operation on the vehicle.
The vehicle track tracking device provided by the embodiment of the invention can execute the vehicle track tracking method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.
EXAMPLE III
Fig. 3 is a schematic structural diagram of a computer device according to a third embodiment of the present invention, as shown in fig. 3, the computer device includes a processor 300, a memory 301, a communication module 302, an input device 303, and an output device 304; the number of processors 300 in the computer device may be one or more, and one processor 300 is taken as an example in fig. 3; the processor 300, the memory 301, the communication module 302, the input device 303 and the output device 304 in the computer apparatus may be connected by a bus or other means, and fig. 3 illustrates the connection by a bus as an example.
The memory 301, as a computer-readable storage medium, may be used for storing software programs, computer-executable programs, and modules, such as modules corresponding to the vehicle trajectory tracking method in the embodiment of the present invention (for example, the data acquisition module 201, the first travel trajectory calculation module 202, the second travel trajectory calculation module 203, the target travel trajectory determination module 204, and the business execution module 205 in the vehicle trajectory tracking device shown in fig. 2). The processor 300 executes various functional applications and data processing of the computer device by executing software programs, instructions and modules stored in the memory 301, that is, implements the vehicle trajectory tracking method described above.
The memory 301 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 301 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, memory 301 may further include memory located remotely from processor 300, which may be connected to a computer device through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
And the communication module 302 is used for establishing connection with the display screen and realizing data interaction with the display screen.
The input device 303 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the computer apparatus.
The output means 304 may comprise a display device such as a display screen.
It should be noted that the specific composition of the input device 303 and the output device 304 can be set according to actual situations.
The computer device provided by the embodiment can execute the vehicle track tracking method provided by any embodiment of the invention, and has corresponding functions and beneficial effects.
Example four
The fourth embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the vehicle trajectory tracking method according to any one of the embodiments.
In the embodiment of the invention, a camera and a millimeter wave radar are distributed on the road side, the monitoring range of the camera covers part of the parking area on the road side, and the monitoring range of the millimeter wave radar covers the whole parking area on the road side, and the vehicle track tracking method comprises the following steps:
when a vehicle is detected to enter a parking area on the road side, acquiring multi-frame image data shot by the camera on the vehicle and multi-frame point cloud data detected by the millimeter wave radar on the vehicle;
in a plurality of frames of the image data, calculating a first driving track of the vehicle moving in the parking area by fusing a color histogram of the vehicle with particle filtering;
calculating a second driving track of the vehicle moving in the parking area based on the multi-frame point cloud data by referring to a coordinate conversion relation between the camera and the millimeter wave radar;
splicing the first driving track and the second driving track to determine a target driving track of the vehicle moving in the parking area;
comparing the target driving trajectory with a parking space in the parking area to perform parking-related business operations on the vehicle entering or leaving the parking space.
Of course, the computer-readable storage medium provided by the embodiments of the present invention is not limited to the method operations described above, and may also perform related operations in the vehicle trajectory tracking method provided by any embodiments of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.
It should be noted that, in the embodiment of the vehicle trajectory tracking device, the included units and modules are only divided according to the functional logic, but are not limited to the above division as long as the corresponding functions can be realized; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (9)
1. A vehicle track tracking method is characterized in that a camera and a millimeter wave radar are distributed on a road side, the monitoring range of the camera covers a part of parking areas on the road side, and the monitoring range of the millimeter wave radar covers all parking areas on the road side, and the method comprises the following steps:
when a vehicle is detected to enter a parking area on the road side, acquiring multi-frame image data shot by the camera on the vehicle and multi-frame point cloud data detected by the millimeter wave radar on the vehicle;
in a plurality of frames of the image data, calculating a first driving track of the vehicle moving in the parking area by fusing a color histogram of the vehicle with particle filtering;
calculating a second driving track of the vehicle moving in the parking area based on the multi-frame point cloud data by referring to a coordinate conversion relation between the camera and the millimeter wave radar;
splicing the first driving track and the second driving track to determine a target driving track of the vehicle moving in the parking area;
comparing the target driving trajectory with a parking space in the parking area to perform parking-related business operations on the vehicle entering or leaving the parking space;
a particle swarm is put in the image data;
the calculating a second travel track of the vehicle moving in the parking area based on the plurality of frames of point cloud data with reference to a coordinate conversion relationship between the camera and the millimeter wave radar includes:
carrying out combined calibration on the camera and the millimeter wave radar to obtain a coordinate conversion relation between the camera and the millimeter wave radar;
extracting point cloud data representing the vehicle from a plurality of frames of point cloud data to obtain a plurality of frames of first candidate point cloud data;
converting multiple frames of the first candidate point cloud data into the camera coordinate system according to the coordinate conversion relation to obtain multiple frames of second candidate point cloud data;
in a plurality of frames of the second candidate point cloud data, projecting each frame of the second candidate point cloud data to a corresponding single frame of the image data representing the parking area to obtain a plurality of frames of third candidate point cloud data;
matching a plurality of frames of the third candidate point cloud data with the plurality of frames of the particle swarm in the image data;
calculating a second travel track of the vehicle moving in the parking area based on a result of the matching.
2. The method according to claim 1, wherein the calculating a first driving track of the vehicle moving in the parking area by using a color histogram fusion particle filter of the vehicle in a plurality of frames of the image data comprises:
determining a color histogram of the vehicle in a single frame of the image data representing the parking area in a plurality of frames of the image data as a target feature;
putting a first particle swarm in the single-frame image data representing the parking area;
calculating a color histogram of each first particle in the first particle swarm as a candidate feature, wherein the first particles are used for representing the estimated position of the vehicle in the parking area;
calculating a similarity between the candidate feature and the target feature for each of the first particles;
and re-throwing a second particle swarm in the image data of a single frame according to the estimated position based on the similarity so as to calculate a first driving track of the vehicle moving in the parking area.
3. The method of claim 2, wherein the re-launching a second particle swarm in a single frame of the image data according to the estimated position based on the similarity to calculate a first driving trajectory of the vehicle moving in the parking area comprises:
screening the first particle swarm in the single frame of the image data based on the similarity;
calculating a first weight of each first particle according to the similarity of each first particle in the first particle swarm after screening, wherein the first weight is used for representing the accuracy of the estimated position;
putting a second particle swarm again in the image data of the single frame according to the first weight and the estimated position;
determining an estimated location of each second particle in the second population of particles in the parking area;
updating the second particle swarm based on the estimated position of the second particle, and determining the estimated position of the second particle as a first position of the vehicle in the parking area until the estimated position of the second particle meets a preset convergence condition;
and counting the first position of the vehicle in the parking area for all the frame image data to obtain a first driving track of the vehicle moving in the parking area.
4. The method of claim 3, wherein said re-delivering a second particle population in said estimated location in a single frame of said image data based on said first weight comprises:
summing the squares of the first weights to obtain a first value;
taking the reciprocal of the first value as a metric value for measuring the degradation degree of the particles;
comparing the metric value with a preset threshold value;
if the metric value is smaller than the preset threshold value, a second particle swarm is put in the image data of the single frame again according to the estimated position according to the first weight;
the determining an estimated location of each second particle of the second population of particles in the parking area comprises:
assigning a second weight to each of the second particles in the second population of particles;
calculating a pixel location of each of the second particles in the image data;
and summing the products of the pixel positions and the second weights to obtain the estimated position of each second particle in the parking area.
5. The method according to claim 1 or 2 or 3 or 4, characterized in that the first travel profile comprises a plurality of first positions, a first point in time corresponding to the first positions, and the second travel profile comprises a plurality of second positions, a second point in time corresponding to the second positions;
the stitching the first travel track and the second travel track to determine a target travel track for the vehicle to move in the parking area includes:
traversing a first time point in the first travel trajectory and a second time point in the second travel trajectory;
if the first time point is the same as the second time point, performing linear fusion on a first position corresponding to the first time point and a second position corresponding to the second time point to obtain a target position of the vehicle in the parking area;
if the first time point is different from the second time point, generating a new position between a first position corresponding to the first time point and a second position corresponding to the second time point by adopting an interpolation method, and using the new position as a target position of the vehicle in the parking area;
and fitting all the target positions to obtain a target running track of the vehicle moving in the parking area.
6. The method of claim 5, wherein said comparing said target travel trajectory to a parking space in said parking area to perform parking-related business operations on said vehicle entering or leaving said parking space comprises:
if the orientation of the target driving track is the parking space driven into the parking area and the target driving track passes through a parking line of the parking space, calling the camera to capture the vehicle, and performing service operations of license plate recognition, license plate association, identity verification and parking timing on the vehicle;
if the direction of the target driving track is that the vehicle is driven out of a parking space in the parking area and the target driving track passes through a parking line of the parking space, the camera is called to capture the vehicle, the parking information of the vehicle is uploaded to a cloud end, parking timing of the vehicle is finished, and the cloud end is triggered to execute parking charging business operation on the vehicle.
7. A vehicle track tracking device is characterized in that a camera and a millimeter wave radar are distributed on the road side, the monitoring range of the camera covers part of the parking area on the road side, and the monitoring range of the millimeter wave radar covers the whole parking area on the road side, and the device comprises:
the data acquisition module is used for acquiring multiframe image data shot by the camera on the vehicle and multiframe point cloud data detected by the millimeter wave radar on the vehicle when the vehicle is detected to enter a parking area on the road side;
the first driving track calculation module is used for calculating a first driving track of the vehicle moving in the parking area by fusing a color histogram of the vehicle with particle filtering in the image data of a plurality of frames;
the second driving track calculation module is used for calculating a second driving track of the vehicle moving in the parking area based on the multi-frame point cloud data by referring to a coordinate conversion relation between the camera and the millimeter wave radar;
the target running track determining module is used for splicing the first running track and the second running track to determine a target running track of the vehicle moving in the parking area;
the service execution module is used for comparing the target driving track with a parking space in the parking area so as to execute service operation related to parking on the vehicle entering or leaving the parking space;
the second driving trajectory calculation module includes:
the coordinate conversion relation calculation submodule is used for carrying out combined calibration on the camera and the millimeter wave radar to obtain a coordinate conversion relation between the camera and the millimeter wave radar;
the first candidate point cloud data confirmation submodule is used for extracting point cloud data representing the vehicle for each frame of the point cloud data in a plurality of frames of the point cloud data to obtain a plurality of frames of first candidate point cloud data;
the second candidate point cloud data confirmation submodule is used for converting a plurality of frames of the first candidate point cloud data into the camera coordinate system according to the coordinate conversion relation to obtain a plurality of frames of second candidate point cloud data;
the third candidate point cloud data confirmation submodule is used for projecting each frame of the second candidate point cloud data to a corresponding single frame of the image data representing the parking area in multiple frames of the second candidate point cloud data to obtain multiple frames of third candidate point cloud data;
the matching submodule is used for matching a plurality of frames of the third candidate point cloud data with a plurality of frames of the particle swarm in the image data;
and a second travel track confirmation submodule for calculating a second travel track along which the vehicle moves in the parking area based on a result of the matching.
8. A computer device, characterized in that the computer device comprises:
one or more processors;
a memory for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the vehicle trajectory tracking method of any one of claims 1-6.
9. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out a vehicle trajectory tracking method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011348538.3A CN112489427B (en) | 2020-11-26 | 2020-11-26 | Vehicle trajectory tracking method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011348538.3A CN112489427B (en) | 2020-11-26 | 2020-11-26 | Vehicle trajectory tracking method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112489427A CN112489427A (en) | 2021-03-12 |
| CN112489427B true CN112489427B (en) | 2022-04-15 |
Family
ID=74935833
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011348538.3A Active CN112489427B (en) | 2020-11-26 | 2020-11-26 | Vehicle trajectory tracking method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112489427B (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113240939B (en) * | 2021-03-31 | 2023-03-28 | 浙江吉利控股集团有限公司 | Vehicle early warning method, device, equipment and storage medium |
| CN113137963B (en) * | 2021-04-06 | 2023-05-05 | 上海电科智能系统股份有限公司 | High-precision comprehensive positioning and navigation method for passive indoor people and objects |
| CN113223326B (en) * | 2021-04-28 | 2022-11-11 | 上海电科智能系统股份有限公司 | Multi-vehicle multi-control multi-source low-speed auxiliary parking system based on road side |
| CN113177504B (en) * | 2021-05-13 | 2022-07-29 | 中移(上海)信息通信科技有限公司 | Vehicle queuing information detection method and device, electronic equipment and storage medium |
| CN113419244A (en) * | 2021-05-28 | 2021-09-21 | 同济大学 | Vehicle track splicing method based on millimeter wave radar data |
| CN113516852B (en) * | 2021-07-22 | 2022-09-09 | 珠海小可乐科技有限公司 | Multi-parking-space multi-target vehicle parking identification method and system |
| CN113888900A (en) * | 2021-09-10 | 2022-01-04 | 海信集团控股股份有限公司 | Vehicle early warning method and device |
| CN114475650B (en) * | 2021-12-01 | 2022-11-01 | 中铁十九局集团矿业投资有限公司 | Vehicle driving behavior determination method, device, equipment and medium |
| CN114463984B (en) * | 2022-03-02 | 2024-02-27 | 智道网联科技(北京)有限公司 | Vehicle track display method and related equipment |
| CN115223357A (en) * | 2022-04-07 | 2022-10-21 | 港珠澳大桥管理局 | Traffic information processing system, method, device and computer equipment |
| CN115762143B (en) * | 2022-11-02 | 2024-05-03 | 宁波云弧科技有限公司 | Vehicle track processing method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102012208025A1 (en) * | 2012-05-14 | 2013-11-14 | Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V. | Method for computer-aided segmentation of grey value image for purpose of computer-aided optical text character recognition, involves utilizing coordinate as search parameter for swarm optimization and function as objective function |
| CN105511266A (en) * | 2016-01-07 | 2016-04-20 | 无锡信捷电气股份有限公司 | Delta robot locus programming method based on gravitation searching particle swarm algorithm |
| CN110379178A (en) * | 2019-07-25 | 2019-10-25 | 电子科技大学 | Pilotless automobile intelligent parking method based on millimetre-wave radar imaging |
| CN110533923A (en) * | 2019-08-29 | 2019-12-03 | 北京精英路通科技有限公司 | Parking management method, device, computer equipment and storage medium |
| CN110853393A (en) * | 2019-11-26 | 2020-02-28 | 清华大学 | Intelligent network vehicle test field data acquisition and fusion method and system |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5472026B2 (en) * | 2010-06-29 | 2014-04-16 | トヨタ自動車株式会社 | Parking assistance device |
| CN105679043A (en) * | 2016-04-14 | 2016-06-15 | 中国电子科技集团公司第三十八研究所 | 3D radar intelligent bayonet system and processing method thereof |
| DE102016219698A1 (en) * | 2016-10-11 | 2018-04-12 | Robert Bosch Gmbh | Parking management system |
| CN209297496U (en) * | 2018-11-23 | 2019-08-23 | 北京猎户智芯科技有限公司 | A kind of vehicle identification system of radar and video camera linkage |
| CN110930753B (en) * | 2019-11-27 | 2021-07-02 | 江苏集萃智能传感技术研究所有限公司 | Parking space searching navigation system and parking space searching navigation method |
| CN111578957B (en) * | 2020-05-07 | 2022-05-10 | 泉州装备制造研究所 | Intelligent pure vehicle tracking method based on three-dimensional point cloud map positioning |
-
2020
- 2020-11-26 CN CN202011348538.3A patent/CN112489427B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102012208025A1 (en) * | 2012-05-14 | 2013-11-14 | Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V. | Method for computer-aided segmentation of grey value image for purpose of computer-aided optical text character recognition, involves utilizing coordinate as search parameter for swarm optimization and function as objective function |
| CN105511266A (en) * | 2016-01-07 | 2016-04-20 | 无锡信捷电气股份有限公司 | Delta robot locus programming method based on gravitation searching particle swarm algorithm |
| CN110379178A (en) * | 2019-07-25 | 2019-10-25 | 电子科技大学 | Pilotless automobile intelligent parking method based on millimetre-wave radar imaging |
| CN110533923A (en) * | 2019-08-29 | 2019-12-03 | 北京精英路通科技有限公司 | Parking management method, device, computer equipment and storage medium |
| CN110853393A (en) * | 2019-11-26 | 2020-02-28 | 清华大学 | Intelligent network vehicle test field data acquisition and fusion method and system |
Non-Patent Citations (1)
| Title |
|---|
| 基于视频的复杂条件下移动目标追踪方法研究;赵豪;《中国优秀硕士学位论文全文数据库 信息科技辑》;20190115;正文第37页倒数第2段-42页第1段 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112489427A (en) | 2021-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112489427B (en) | Vehicle trajectory tracking method, device, equipment and storage medium | |
| CN108986064B (en) | People flow statistical method, equipment and system | |
| CN110942625B (en) | Dynamic OD estimation method and device based on real path flow backtracking adjustment | |
| CN108765975B (en) | Roadside vertical parking lot management system and method | |
| CN103985250A (en) | Light-weight holographic road traffic state visual inspection device | |
| CN113671480A (en) | Radar and video fusion traffic target tracking method, system, equipment and terminal | |
| CN103235933A (en) | Vehicle abnormal behavior detection method based on Hidden Markov Model | |
| CN107885795A (en) | A kind of data verification method, system and the device of bayonet socket data | |
| CN113326719A (en) | Method, equipment and system for target tracking | |
| CN109727458B (en) | Method for realizing interval parking charging through dynamic and static traffic linkage | |
| CN109979197B (en) | Method and system for constructing highway traffic time map based on fusion data | |
| CN108629982B (en) | Road section vehicle number estimation method based on travel time distribution rule | |
| CN113487877A (en) | Road vehicle illegal parking monitoring method | |
| EP4020428A1 (en) | Method and apparatus for recognizing lane, and computing device | |
| CN114495520B (en) | Counting method and device for vehicles, terminal and storage medium | |
| CN110111582B (en) | Multi-lane free flow vehicle detection method and system based on TOF camera | |
| CN111429723B (en) | Communication and perception data fusion method based on road side equipment | |
| CN110880205B (en) | Parking charging method and device | |
| CN114783181B (en) | Traffic flow statistics method and device based on road side perception | |
| CN110021174A (en) | A kind of vehicle flowrate calculation method for being applicable in more scenes based on video image | |
| Rashid et al. | Automated traffic measurement system based on FCD and image processing | |
| Garvanov et al. | Detection and parameters estimation of moving objects via video surveillance | |
| CN111741267B (en) | Method, device, equipment and medium for determining vehicle delay | |
| Špaňhel et al. | Detection of traffic violations of road users based on convolutional neural networks | |
| Gregor et al. | Design and implementation of a counting and differentiation system for vehicles through video processing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |