CN115222767A - Space parking stall-based tracking method and system - Google Patents
Space parking stall-based tracking method and system Download PDFInfo
- Publication number
- CN115222767A CN115222767A CN202210379055.2A CN202210379055A CN115222767A CN 115222767 A CN115222767 A CN 115222767A CN 202210379055 A CN202210379055 A CN 202210379055A CN 115222767 A CN115222767 A CN 115222767A
- Authority
- CN
- China
- Prior art keywords
- parking space
- space
- parking
- candidate
- point cloud
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000012545 processing Methods 0.000 claims abstract description 30
- 238000004364 calculation method Methods 0.000 claims abstract description 14
- 239000002245 particle Substances 0.000 claims description 34
- 238000000605 extraction Methods 0.000 claims description 31
- 238000012163 sequencing technique Methods 0.000 claims description 13
- 238000000342 Monte Carlo simulation Methods 0.000 claims description 9
- 238000011176 pooling Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 7
- 238000005065 mining Methods 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 5
- 238000007418 data mining Methods 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 description 14
- 238000010586 diagram Methods 0.000 description 11
- 238000004590 computer program Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000009528 severe injury Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
- G06T2207/30264—Parking
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Multimedia (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a space parking stall-based tracking method, which comprises the following steps: acquiring information of each space parking space detected at the current moment, and projecting the information to a grid map of the vehicle; acquiring point cloud information around each space parking space; acquiring parking space characteristics corresponding to the parking spaces in each space based on the point cloud information of the parking spaces in each space; generating at least one candidate parking space in a vehicle grid map according to the parking space characteristics corresponding to each space parking space; and carrying out characteristic matching processing on the parking space characteristics corresponding to each candidate parking space and the parking space characteristics of each detected parking space in the parking space tracking result obtained at the last moment, and obtaining the parking space tracking result at the current moment according to the matching result. The invention also discloses a corresponding system. The parking space tracking method and the parking space tracking device can track the parking space based on the space parking space, have the characteristics of low calculation cost and quick and accurate calculation, and improve the driving experience of a user.
Description
Technical Field
The invention relates to the field of intelligent driving perception, in particular to a space parking space-based tracking method and system.
Background
For the automatic driving function in the scenes of the parking lot such as automatic parking, the sensing capability of the vehicle on the parking places around the parking lot is very important, and the success rate and the accuracy rate of the parking are directly determined.
The parking spaces can be classified into linear parking spaces and space parking spaces on the whole, wherein the linear parking spaces refer to the parking spaces containing the parking space lines, and the space parking spaces refer to the parking spaces without the parking spaces or the parking spaces with the heavily blurred or damaged parking space lines. To many domestic parking lots, because the earlier stage construction planning is not enough, later maintenance cost is higher scheduling problem, a lot of parking stalls all belong to the space parking stall. Because the traditional parking space tracking algorithm based on the camera to acquire images very depends on the characteristics of parking space lines, the algorithm can not be effectively applied to the tracking of space parking spaces. Compared with a camera, the millimeter wave radar is used for parking space tracking, so that the influence of serious blurring or damage of a parking space line on a tracking algorithm can be effectively avoided, the quality of a parking space tracking result is guaranteed, but the commonly used tracking algorithm is carried out based on parking space visual characteristics, so that corresponding characteristic extraction and model updating need higher calculation force support, and the generalization capability is poor.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a space parking stall-based tracking method and system, which can track parking stalls based on space parking stalls, have the characteristics of low calculation cost and quick and accurate calculation, and can improve the driving experience.
In order to solve the above technical problems, an aspect of the present invention provides a space-based parking space tracking method, which includes the following steps:
step S10, acquiring information of each space parking space detected at the current moment in a vehicle driving path, and projecting the information to a grid map of the vehicle;
s11, acquiring point cloud information around each space parking space according to the acquired space parking space information;
s12, acquiring parking space characteristics corresponding to the parking spaces in each space based on the point cloud information of the parking spaces in each space, wherein the parking space characteristics at least comprise first type characteristics and second type characteristics;
step S13, generating at least one candidate parking space in a vehicle grid map according to the parking space characteristics corresponding to the parking spaces in each space;
and S14, performing feature matching processing on the parking space feature corresponding to each candidate parking space and the parking space feature of each detected parking space in the parking space tracking result obtained at the previous moment, and obtaining the parking space tracking result at the current moment according to the matching result.
Wherein the step S10 further includes:
acquiring information of each space parking space detected at the current moment in a vehicle driving path;
projecting the information of each space parking space to a grid map of the vehicle, and forming corresponding rectangular frames under a vehicle grid map coordinate system, wherein each rectangular frame comprises coordinates of four vertexes;
and calculating the distance from the space parking spaces to the vehicle according to the coordinates of each rectangular frame, and sequencing the space parking spaces from near to far according to the length of the distance.
Wherein the step S11 further includes:
acquiring all point cloud information in a vehicle grid map range by using a millimeter wave radar;
and mining and storing the point cloud data of the corresponding parking space area in the grid map according to the acquired coordinates of the rectangular frames corresponding to the parking spaces in each space.
Wherein the step S12 further includes:
calculating first type characteristics corresponding to the space parking spaces according to the point cloud data corresponding to the space parking spaces, wherein the first type characteristics comprise the length-width ratio and the inclination ratio of the space parking spaces;
inputting the point cloud data corresponding to each space parking space into a pre-trained feature extraction network to obtain a plurality of second-class features corresponding to each space parking space; the feature extraction network comprises 3 convolution layers, 3 pooling layers and 1 full-connection layer, the output layer of the feature extraction network is a softmax layer, and each second-class feature output is a numerical value between 0 and 1.
Wherein, before inputting the point cloud data that each space parking stall corresponds to a feature extraction network trained in advance, further include:
down-sampling the point cloud data of each space parking space according to a preset rule;
and cutting and sequencing the down-sampled data obtained in the last step to finally obtain a two-dimensional point cloud array with the size of 128 x 128, wherein the two-dimensional point cloud array is used as the input of the feature extraction network.
Wherein the step S13 further includes:
inputting each first class of characteristics and each second class of characteristics corresponding to all parking space spaces into a particle filter, generating Gaussian distribution random numbers by using a Monte Carlo method according to the state and weight of a particle swarm at the last moment, forming the position and state of a new particle swarm, carrying out KNN clustering processing, and obtaining the position and state of a candidate parking space, wherein the position comprises four vertex coordinates of the candidate parking space under a vehicle grid map, and the state represents the confidence degree of the candidate parking space;
and acquiring a first class characteristic and a second class characteristic corresponding to each candidate parking space.
Wherein the step S14 further comprises:
matching the parking space characteristics corresponding to each candidate parking space with the parking space characteristics of each detected parking space in the parking space tracking result obtained at the last moment in pairs, calculating the sum of variances between the corresponding parking space characteristics, and if the sum is greater than a preset matching threshold, judging that the matching is successful;
for the same detected parking space, if two or more waiting parking spaces successfully matched exist, selecting one with the highest matching calculation result as the tracking result of the detected parking space; if only one candidate parking space which is successfully paired exists, directly selecting the candidate parking space as a tracking result of the detected parking space; if the candidate parking space is not successfully matched, the detected parking space is considered to be absent at the current moment so that the parking operation cannot be carried out;
and obtaining the parking space tracking result at the current moment and displaying the parking space tracking result in the vehicle.
In another aspect of the present invention, a space-based parking space tracking system is further provided, which includes:
the system comprises a spatial parking space information acquisition unit, a grid map acquisition unit and a grid map display unit, wherein the spatial parking space information acquisition unit is used for acquiring information of each spatial parking space detected at the current moment in a vehicle driving path and projecting the information into the grid map of the vehicle;
the point cloud information acquisition unit is used for acquiring point cloud information around each space parking space according to the acquired space parking space information;
the parking space feature acquisition unit is used for acquiring parking space features corresponding to the parking spaces in each space based on the point cloud information of the parking spaces in each space, and the parking space features at least comprise first-class features and second-class features;
the candidate parking space acquisition unit is used for generating at least one candidate parking space in the vehicle grid map according to the parking space characteristics corresponding to each space parking space;
and the parking space tracking result acquisition unit is used for performing characteristic matching processing on the parking space characteristics corresponding to each candidate parking space and the parking space characteristics of each detected parking space in the parking space tracking results acquired at the previous moment, and acquiring the parking space tracking result at the current moment according to the matching result.
Wherein, space parking stall information acquisition unit further includes:
the first acquisition unit is used for acquiring the information of each space parking space detected at the current moment in the driving path of the vehicle;
the projection processing unit is used for projecting the information of each space parking space to a grid map of the vehicle, and corresponding rectangular frames are formed under a vehicle grid map coordinate system, wherein each rectangular frame comprises coordinates of four vertexes;
and the sequencing unit is used for calculating the distance from the space parking space to the vehicle according to the coordinates of each rectangular frame and sequencing the space parking spaces from near to far according to the length of the distance.
Wherein the point cloud information acquiring unit further includes:
the second acquisition unit is used for acquiring all point cloud information in the vehicle grid map range by using the millimeter wave radar;
and the data mining unit is used for mining and storing the point cloud data of the corresponding parking space area in the grid map according to the acquired coordinates of the rectangular frame corresponding to each space parking space.
Wherein, parking stall characteristic acquisition unit further includes:
the system comprises a first type feature acquisition unit, a first type feature acquisition unit and a second type feature acquisition unit, wherein the first type feature acquisition unit is used for calculating a first type feature corresponding to each space parking space according to point cloud data corresponding to each space parking space, and the first type feature comprises an aspect ratio and an inclination ratio of the space parking spaces;
the system comprises a preprocessing unit, a data processing unit and a data processing unit, wherein the preprocessing unit is used for performing down-sampling on the point cloud data of each space parking space according to a preset rule, and cutting and sequencing the down-sampled data to finally obtain a two-dimensional point cloud array with the size of 128 × 128;
the second-class feature acquisition unit is used for inputting the result of the point cloud data corresponding to each space parking space after being processed by the preprocessing unit into a pre-trained feature extraction network to obtain a plurality of second-class features corresponding to each space parking space; the feature extraction network comprises 3 convolution layers, 3 pooling layers and 1 full-connection layer, the output layer of the feature extraction network is a softmax layer, and each second-class feature output is a numerical value between 0 and 1.
Wherein, the candidate parking space obtaining unit further comprises:
the filtering processing unit is used for inputting each first type of characteristic and each second type of characteristic corresponding to all parking space spaces into a particle filter, generating Gaussian distribution random numbers by using a Monte Carlo method according to the state and the weight of the particle swarm at the last moment, and forming the position and the state of a new particle swarm;
the clustering processing unit is used for carrying out KNN clustering processing on the result of the filtering processing unit to obtain the position and the state of the candidate parking space, wherein the position comprises four vertex coordinates of the candidate parking space under a vehicle grid map, and the state represents the confidence degree of the candidate parking space;
and the characteristic calling unit is used for calling the first class characteristic and the second class characteristic corresponding to each candidate parking space obtained by the parking space characteristic obtaining unit.
Wherein, the parking stall is tracked the result and is obtained the unit and further includes:
the matching comparison unit is used for matching the parking space characteristics corresponding to each candidate parking space with the parking space characteristics of each detected parking space in the parking space tracking result obtained at the last moment in pairs, calculating the sum of variances between the corresponding parking space characteristics, and if the sum is greater than a preset matching threshold value, judging that the matching is successful;
the tracking result acquisition unit is used for selecting one of the waiting parking spaces with the highest matching calculation result as the tracking result of the detected parking space if two or more than two successfully paired waiting parking spaces exist in the results of the matching comparison unit; if only one candidate parking space which is successfully paired exists, directly selecting the candidate parking space as a tracking result of the detected parking space; if the candidate parking space is not successfully matched, the detected parking space is considered to be absent at the current moment so that the parking operation cannot be carried out;
and the display unit is used for obtaining the parking space tracking result at the current moment and displaying the parking space tracking result in the vehicle.
The embodiment of the invention has the following beneficial effects:
the invention discloses a space-based parking space tracking method and a system, wherein the method comprises the steps of acquiring the position information of each parking space at the current moment in a driving path of a driver, projecting the position information to a 2D grid map of a vehicle, collecting point cloud information of a target frame of each parking space based on a millimeter wave radar, and extracting characteristics; and based on a preset rule and a particle filter algorithm, generating a certain number of candidate parking space samples in a vehicle grid map, matching the candidate parking space samples with all the parking spaces detected at the last moment, and finally obtaining a tracking result of the corresponding parking space. The invention relates to advanced automatic driving functions such as a remote control parking system and an auxiliary parking system, can accurately track spatial parking spaces around a driving vehicle, has higher accuracy, can adapt to the parking space tracking requirements under complex scenes such as no parking space or serious damage of a vehicle line and the like, and is suitable for most parking scenes in China;
in the embodiment of the invention, the millimeter wave radar is used for providing the point cloud information of the parking space, the calculation resources required by the whole tracking algorithm can be reduced through the first class of feature extraction based on manual design and the second class of feature extraction based on the optimized neural network model, the operation cost of the tracking algorithm is effectively reduced, and the parking space candidate sample is generated through the particle filter based on the Monte Carlo method and the KNN clustering algorithm, so that the accuracy of the tracking result is improved while the calculated amount of parking space matching is reduced, the requirement of parking space tracking instantaneity is better met, and the driving feeling of a driver is improved. The invention can effectively track the space parking space in a special scene by tracking the parking space in the process of searching the space parking space.
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 introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is within the scope of the present invention for those skilled in the art to obtain other drawings based on the drawings without inventive exercise.
Fig. 1 is a schematic main flow chart of an embodiment of a space-based parking space tracking method according to the present invention;
FIG. 2 is a schematic view of a grid coordinate system of a vehicle according to the present invention;
fig. 3 is a schematic structural diagram of an embodiment of a space-based parking space tracking system provided in the present invention;
fig. 4 is a schematic structural diagram of the space information acquiring unit in fig. 3;
fig. 5 is a schematic structural diagram of a point cloud information acquiring unit in fig. 3;
FIG. 6 is a schematic structural diagram of the parking space characteristic acquiring unit in FIG. 3;
fig. 7 is a schematic structural diagram of the candidate parking space acquisition unit in fig. 3;
fig. 8 is a schematic structural diagram of the parking space tracking result obtaining unit in fig. 3.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings.
Fig. 1 shows a main flow chart of an embodiment of a space-based parking space tracking method according to the present invention. Referring to fig. 2 together, in this embodiment, the method includes the following steps:
step S10, acquiring information of each space parking space detected at the current moment in a vehicle driving path, and projecting the information to a grid map of the vehicle;
in a specific example, the step S10 further includes:
acquiring information of each space parking space detected at the current moment in a vehicle driving path; the sources of the space parking space information can be parking space detection results obtained through cameras or other sensors and related target detection algorithms, or tracking results obtained through calculation based on the parking space characteristics at the previous moment, or certain parking spaces selected by a driver in a human-vehicle interaction system;
projecting the information of each space parking space to a grid map of the vehicle, and forming corresponding rectangular frames under a vehicle grid map coordinate system, wherein each rectangular frame comprises coordinates of four vertexes;
and calculating the distance from the space parking spaces to the vehicle according to the coordinates of each rectangular frame, and sequencing the space parking spaces from near to far according to the length of the distance.
S11, acquiring point cloud information around each space parking space according to the acquired space parking space information;
in a specific example, the step S11 further includes:
acquiring all point cloud information in a vehicle grid map range by using a millimeter wave radar;
and mining and storing the point cloud data of the corresponding parking space area in the grid map according to the acquired coordinates of the rectangular frames corresponding to the parking spaces in each space.
S12, acquiring parking space characteristics corresponding to the parking spaces in each space based on the point cloud information of the parking spaces in each space, wherein the parking space characteristics at least comprise first type characteristics and second type characteristics; it is to be understood that in embodiments of the present invention, the first type of feature may be an explicit feature; the second type of feature may be an implicit feature.
In a specific example, the step S12 further includes:
calculating first-class features corresponding to the space parking spaces according to the point cloud data corresponding to the space parking spaces, wherein the first-class features (namely dominant features) are artificially designed features, and the first-class features are two features in the embodiment and comprise the length-width ratio and the inclination ratio of the space parking spaces; specifically, as shown in fig. 2, in the vehicle grid coordinate system, the origin of coordinates is the center of the rear axle of the vehicle, the X-axis is the vertical movement direction of the vehicle, and the Y-axis is the vertical movement direction of the vehicle. The length-width ratio is obtained by calculating the length and width of the space parking space; the inclination ratio refers to the inclination degree of the space parking space, and specifically is an included angle between a connecting line of the parking space vertexes P1 and P2 and a connecting line of the parking space vertexes P2 and P3;
inputting the point cloud data corresponding to each space parking space into a pre-trained feature extraction network to obtain a plurality of second-class features (namely recessive features) corresponding to each space parking space; the feature extraction network comprises 3 convolutional layers, 3 pooling layers and 1 full-connection layer, the output layer of the feature extraction network is a softmax layer, and each second-class feature output is a numerical value between 0 and 1. It can be understood that the second-class features are depth features learned through a large number of training samples, and 5 second-class features are output in the present embodiment;
wherein, before inputting the point cloud data that each space parking stall corresponds to a feature extraction network trained in advance, further include:
down-sampling the point cloud data of each space parking space according to a preset rule;
and cutting and sequencing the down-sampled data obtained in the last step to finally obtain a two-dimensional point cloud array with the size of 128 x 128, wherein the two-dimensional point cloud array is used as the input of the feature extraction network.
More specifically, in the present embodiment, the following table lists the network structure and parameters of an employed feature extraction network:
parameter map for table-feature extraction network
| Network layer | Dimension of input | Convolution kernel size | Step size | Output dimension |
| First convolution layer (CONV 1) | 128*128 | 7*7 | 1 | 122*122 |
| First pooling layer (POOL 1) | 122*122 | 2*2 | 2 | 64*64 |
| Second convolution layer (CONV 2) | 64*64 | 3*3 | 1 | 62*62 |
| Second pooling layer (POOL 2) | 62*62 | 2*2 | 2 | 32*32 |
| Third convolution layer (CONV 3) | 32*32 | 1*1 | 1 | 32*32 |
| Third pooling layer (POOL 4) | 32*32 | 2*2 | 2 | 16*16 |
| Full connecting layer (FC 1) | 16*16 | 1*1 | 1 | 256*1 |
| Output layer (Softmax) | 256*1 | \ | \ | 5*1 |
Step S13, generating at least one candidate parking space in a vehicle grid map through particle filtering processing according to the parking space characteristics corresponding to the parking spaces in each space;
in a specific example, the step S13 further includes:
inputting each first-class feature (2) and second-class feature (5) corresponding to all parking space spaces into a particle filter, generating Gaussian distribution random numbers by using a Monte Carlo method according to the state and weight of a particle swarm at the last moment, forming the position and state of a new particle swarm, performing KNN clustering processing to obtain the position and state of a candidate parking space, wherein the position comprises four vertex coordinates of the candidate parking space under a vehicle grid map, and the state represents the confidence level of the candidate parking space;
and acquiring a first class of characteristics and a second class of characteristics corresponding to each candidate parking space.
It is understood that, in the embodiment of the present invention, the particle filter algorithm is a sequential bayesian inference method, and the implicit state of the target is inferred in a recursive manner. The process of generating the candidate parking space sample generally requires initializing a particle filter, including the number of particles and the weight of each particle. Considering the characteristics of a parking scene and the characteristics of a millimeter wave radar sensor, the number of particles at each moment is fixed to 100, and a method for initializing the weight adopts a xavier Gaussian initialization; then updating the particle weight, namely generating a Gaussian distribution random number by using a Monte Carlo method according to the state and the weight of the particle swarm at the last moment, and further generating the position and the state of a new particle swarm; and finally, generating a candidate parking space sample based on the particle swarm, namely performing KNN clustering on the newly generated particle swarm, so as to further update and obtain the positions and states of the plurality of particle swarms, namely the positions and states of the candidate parking spaces, wherein the positions comprise 4 vertex coordinates (shown in FIG. 2) of the candidate parking spaces under a vehicle grid map, and the states represent the confidence degree of the candidate parking spaces.
And S14, performing characteristic matching processing on the parking space characteristics corresponding to each candidate parking space and the parking space characteristics of each detected parking space in the parking space tracking result obtained at the previous moment, and obtaining the parking space tracking result at the current moment according to the matching result.
In a specific example, the step S14 further includes:
matching the parking space characteristics corresponding to each candidate parking space with the parking space characteristics of each detected parking space in the parking space tracking result obtained at the last moment in pairs, calculating the sum of variances between the corresponding parking space characteristics, and if the sum is greater than a preset matching threshold, determining that the matching is successful, wherein the matching threshold is obtained by pre-calibration;
for the same detected parking space, if two or more waiting parking spaces successfully matched exist, selecting one with the highest matching calculation result as the tracking result of the detected parking space; if only one candidate parking space which is successfully paired exists, directly selecting the candidate parking space as a tracking result of the detected parking space; if the candidate parking space is not successfully matched, the detected parking space is considered to be absent at the current moment so that the parking operation cannot be carried out;
and obtaining the parking space tracking result at the current moment and displaying the parking space tracking result in the vehicle.
As shown in fig. 3, a schematic structural diagram of an embodiment of a space-based parking space tracking system provided by the present invention is shown; referring to fig. 4 to 8 together, in this embodiment, the space-based parking space tracking system 1 at least includes:
the spatial parking space information acquiring unit 10 is configured to acquire spatial parking space information detected at the current time in a vehicle driving path, and project the spatial parking space information to a grid map of a vehicle;
the point cloud information acquisition unit 11 is used for acquiring point cloud information around each space parking space according to the acquired space parking space information;
the parking space feature acquiring unit 12 is configured to acquire a parking space feature corresponding to each spatial parking space based on the point cloud information of the spatial parking spaces, where the parking space feature at least includes a first type of feature and a second type of feature;
the candidate parking space obtaining unit 3 is used for generating at least one candidate parking space in the vehicle grid map according to the parking space characteristics corresponding to the parking spaces in each space;
and the parking space tracking result obtaining unit 14 is configured to perform feature matching processing on the parking space feature corresponding to each candidate parking space and the parking space feature of each detected parking space in the parking space tracking result obtained at the previous time, and obtain the parking space tracking result at the current time according to the matching result.
As shown in fig. 4, in a specific example, the space and parking space information obtaining unit 10 further includes:
a first obtaining unit 100, configured to obtain information of each space parking space detected at a current time in a vehicle driving path;
the projection processing unit 101 is used for projecting the information of each space parking space to a grid map of the vehicle, and forming corresponding rectangular frames under a vehicle grid map coordinate system, wherein each rectangular frame comprises coordinates of four vertexes;
and the sequencing unit 102 is configured to calculate a distance from the space parking space to the vehicle according to the coordinates of each rectangular frame, and sequence the space parking spaces from near to far according to the length of the distance.
As shown in fig. 5, in a specific example, the point cloud information obtaining unit 11 further includes:
a second obtaining unit 110, configured to obtain all point cloud information within a grid map of a vehicle by using a millimeter wave radar;
and the data mining unit 111 is used for mining and storing the point cloud data of the corresponding parking space area in the grid map according to the acquired coordinates of the rectangular frame corresponding to each space parking space.
As shown in fig. 6, in a specific example, the parking space characteristic obtaining unit 12 further includes:
the first-class feature obtaining unit 120 is configured to calculate, according to the point cloud data corresponding to each space parking space, a first-class feature corresponding to each space parking space, where the first-class feature includes an aspect ratio and an inclination ratio of the space parking space;
the preprocessing unit 121 is configured to perform downsampling on the point cloud data of each space parking space according to a predetermined rule, cut and sort the downsampled data, and finally obtain a two-dimensional point cloud array with a size of 128 × 128;
the second-class feature acquisition unit 122 is configured to input a result of the point cloud data corresponding to each space parking space processed by the preprocessing unit to a pre-trained feature extraction network, and obtain a plurality of second-class features corresponding to each space parking space; the feature extraction network comprises 3 convolutional layers, 3 pooling layers and 1 full-connection layer, the output layer of the feature extraction network is a softmax layer, and each second-class feature output is a numerical value between 0 and 1.
As shown in fig. 7, in a specific example, the candidate space acquiring unit 13 further includes:
the filtering processing unit 130 is configured to input each first type of feature and each second type of feature corresponding to all parking space spaces into a particle filter, generate a gaussian-distributed random number by using a monte carlo method according to the state and weight of a particle swarm at the previous time, and form a position and a state of a new particle swarm;
the clustering unit 131 is configured to perform KNN clustering on the result of the filtering unit to obtain a position and a state of the candidate parking space, where the position includes four vertex coordinates of the candidate parking space under the vehicle grid map, and the state represents a confidence level of the candidate parking space;
the feature retrieving unit 132 is configured to retrieve the first class feature and the second class feature corresponding to each candidate parking space obtained by the parking space feature obtaining unit.
As shown in fig. 8, in a specific example, the space tracking result obtaining unit 14 further includes:
the matching comparison unit 140 is configured to perform pairwise matching processing on the parking space characteristics corresponding to each candidate parking space and the parking space characteristics of each detected parking space in the parking space tracking result obtained at the previous time, calculate a sum of variances between corresponding parking space characteristics, and determine that matching is successful if the sum is greater than a predetermined matching threshold;
a tracking result obtaining unit 141, configured to select, for the same detected parking space, one parking space with the highest matching calculation result as a tracking result of the detected parking space if two or more waiting spaces successfully paired exist in the results of the matching comparison unit; if only one candidate parking space which is successfully paired exists, directly selecting the candidate parking space as a tracking result of the detected parking space; if the candidate parking space is not successfully matched, the detected parking space is considered to be absent at the current moment so that the parking operation cannot be carried out;
and the display unit 142 is configured to obtain a parking space tracking result at the current moment and display the parking space tracking result in the vehicle.
For more details, reference may be made to the preceding description of fig. 1-2, which is not to be recalled here.
The embodiment of the invention has the following beneficial effects:
the invention discloses a space-based parking space tracking method and a system, wherein the method comprises the steps of acquiring the position information of each parking space at the current moment in a driving path of a driver, projecting the position information to a 2D grid map of a vehicle, collecting point cloud information of a target frame of each parking space based on a millimeter wave radar, and extracting characteristics; and based on a preset rule and a particle filter algorithm, generating a certain number of candidate parking space samples in a vehicle grid map, matching the candidate parking space samples with all the parking spaces detected at the last moment, and finally obtaining a tracking result of the corresponding parking space. The invention relates to advanced automatic driving functions such as a remote control parking system and an auxiliary parking system, can accurately track space parking spots around a travelling crane, has higher accuracy, can adapt to parking spot tracking requirements under complex scenes such as severe damage of wireless parking spots or vehicle line and the like, and is suitable for most of domestic parking scenes;
in the embodiment of the invention, the millimeter wave radar is used for providing the point cloud information of the parking space, the calculation resources required by the whole tracking algorithm can be reduced through the first class of feature extraction based on manual design and the second class of feature extraction based on the optimized neural network model, the operation cost of the tracking algorithm is effectively reduced, and the parking space candidate sample is generated through the particle filter based on the Monte Carlo method and the KNN clustering algorithm, so that the accuracy of the tracking result is improved while the calculated amount of parking space matching is reduced, the requirement of parking space tracking instantaneity is better met, and the driving feeling of a driver is improved. The invention can effectively track the space parking space in a special scene by tracking the parking space in the process of searching the space parking space.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While the invention has been described in connection with what is presently considered to be the most practical and preferred embodiment, it is to be understood that the invention is not to be limited to the disclosed embodiment, but on the contrary, is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.
Claims (13)
1. The space parking space-based tracking method is characterized by comprising the following steps of:
step S10, acquiring information of each space parking space detected at the current moment in a vehicle driving path, and projecting the information to a grid map of the vehicle;
s11, acquiring point cloud information around each space parking space according to the acquired space parking space information;
s12, acquiring parking space characteristics corresponding to the parking spaces in each space based on the point cloud information of the parking spaces in each space, wherein the parking space characteristics at least comprise first type characteristics and second type characteristics;
s13, generating at least one candidate parking space in a vehicle grid map according to the parking space characteristics corresponding to the parking spaces in each space;
and S14, performing characteristic matching processing on the parking space characteristics corresponding to each candidate parking space and the parking space characteristics of each detected parking space in the parking space tracking result obtained at the previous moment, and obtaining the parking space tracking result at the current moment according to the matching result.
2. The space-based parking space tracking method according to claim 2, wherein the step S10 further comprises:
acquiring information of each space parking space detected at the current moment in a vehicle running path;
projecting the information of each space parking space to a grid map of the vehicle, and forming corresponding rectangular frames under a vehicle grid map coordinate system, wherein each rectangular frame comprises coordinates of four vertexes;
and calculating the distance from the space parking space to the vehicle according to the coordinates of each rectangular frame, and sequencing the space parking spaces from near to far according to the length of the distance.
3. The space-based parking space tracking method according to claim 2, wherein the step S11 further comprises:
acquiring all point cloud information in a vehicle grid map range by using a millimeter wave radar;
and mining and storing the point cloud data of the corresponding parking space area in the grid map according to the acquired coordinates of the rectangular frames corresponding to the parking spaces in each space.
4. The space-based parking space tracking method according to claim 3, wherein the step S12 further comprises:
calculating first type characteristics corresponding to the space parking places according to the point cloud data corresponding to the space parking places, wherein the first type characteristics comprise the length-width ratio and the inclination ratio of the space parking places;
inputting the point cloud data corresponding to each space parking space into a pre-trained feature extraction network to obtain a plurality of second-class features corresponding to each space parking space; the feature extraction network comprises 3 convolutional layers, 3 pooling layers and 1 full-connection layer, the output layer of the feature extraction network is a softmax layer, and each second-class feature output is a numerical value between 0 and 1.
5. The method as claimed in claim 4, wherein before inputting the point cloud data corresponding to each space and parking space into a pre-trained feature extraction network, the method further comprises:
down-sampling the point cloud data of each space parking space according to a preset rule;
and cutting and sequencing the down-sampled data obtained in the last step to finally obtain a two-dimensional point cloud array with the size of 128 x 128, wherein the two-dimensional point cloud array is used as the input of the feature extraction network.
6. The space-based parking space tracking method according to claim 2, wherein the step S13 further comprises:
inputting each first type of characteristic and each second type of characteristic corresponding to all parking space spaces into a particle filter, generating Gaussian distribution random numbers by using a Monte Carlo method according to the state and the weight of a particle swarm at the last moment, forming the position and the state of a new particle swarm, carrying out KNN clustering processing to obtain the position and the state of a candidate parking space, wherein the position comprises four vertex coordinates of the candidate parking space under a vehicle grid map, and the state represents the confidence degree of the candidate parking space;
and acquiring a first class characteristic and a second class characteristic corresponding to each candidate parking space.
7. The space-based parking space tracking method according to claim 7, wherein the step S14 further comprises:
matching the parking space characteristics corresponding to each candidate parking space with the parking space characteristics of each detected parking space in the parking space tracking result obtained at the last moment in pairs, calculating the sum of variances between the corresponding parking space characteristics, and if the sum is greater than a preset matching threshold, judging that the matching is successful;
if two or more waiting parking spaces successfully matched exist in the same detected parking space, selecting one parking space with the highest matching calculation result as the tracking result of the detected parking space; if only one candidate parking space which is successfully paired exists, directly selecting the candidate parking space as a tracking result of the detected parking space; if the candidate parking space is not successfully matched, the detected parking space is considered to be absent at the current moment so that the parking operation cannot be carried out;
and obtaining the parking space tracking result at the current moment and displaying the parking space tracking result in the vehicle.
8. The utility model provides a tracker based on space parking stall which characterized in that includes:
the system comprises a spatial parking space information acquisition unit, a grid map acquisition unit and a grid map display unit, wherein the spatial parking space information acquisition unit is used for acquiring information of each spatial parking space detected at the current moment in a vehicle driving path and projecting the information into the grid map of the vehicle;
the point cloud information acquisition unit is used for acquiring point cloud information around each space parking space according to the acquired space parking space information;
the parking space feature acquisition unit is used for acquiring parking space features corresponding to the parking spaces in each space based on the point cloud information of the parking spaces in each space, and the parking space features at least comprise first-class features and second-class features;
the candidate parking space acquisition unit is used for generating at least one candidate parking space in the vehicle grid map according to the parking space characteristics corresponding to the parking spaces in each space;
and the parking space tracking result acquisition unit is used for performing characteristic matching processing on the parking space characteristics corresponding to each candidate parking space and the parking space characteristics of each detected parking space in the parking space tracking results acquired at the previous moment, and acquiring the parking space tracking result at the current moment according to the matching result.
9. The space and parking space-based tracking system of claim 8, wherein the space and parking space information acquiring unit further comprises:
the first acquisition unit is used for acquiring the information of each space parking space detected at the current moment in the vehicle running path;
the projection processing unit is used for projecting the information of each space parking space to a grid map of the vehicle, and corresponding rectangular frames are formed under a vehicle grid map coordinate system, wherein each rectangular frame comprises coordinates of four vertexes;
and the sequencing unit is used for calculating the distance from the space parking space to the vehicle according to the coordinates of each rectangular frame and sequencing the space parking spaces from near to far according to the length of the distance.
10. The space-based parking space tracking system of claim 9, wherein the point cloud information obtaining unit further comprises:
the second acquisition unit is used for acquiring all point cloud information in the range of the vehicle grid map by using the millimeter wave radar;
and the data mining unit is used for mining and storing the point cloud data of the corresponding parking space area in the grid map according to the acquired coordinates of the rectangular frame corresponding to each space parking space.
11. The space-based parking space tracking system according to claim 10, wherein the parking space characteristic acquiring unit further comprises:
the system comprises a first-class feature acquisition unit, a first-class feature acquisition unit and a second-class feature acquisition unit, wherein the first-class feature acquisition unit is used for calculating first-class features corresponding to space parking places according to point cloud data corresponding to the space parking places, and the first-class features comprise the length-width ratio and the inclination ratio of the space parking places;
the system comprises a preprocessing unit, a data processing unit and a data processing unit, wherein the preprocessing unit is used for performing down-sampling on the point cloud data of each space parking space according to a preset rule, and cutting and sequencing the down-sampled data to finally obtain a two-dimensional point cloud array with the size of 128 × 128;
the second-class feature acquisition unit is used for inputting the result of the point cloud data corresponding to each space parking space after being processed by the preprocessing unit into a pre-trained feature extraction network to obtain a plurality of second-class features corresponding to each space parking space; the feature extraction network comprises 3 convolution layers, 3 pooling layers and 1 full-connection layer, the output layer of the feature extraction network is a softmax layer, and each second-class feature output is a numerical value between 0 and 1.
12. The spatial space based tracking system of claim 11, wherein said candidate space obtaining unit further comprises:
the filtering processing unit is used for inputting each first type of characteristic and each second type of characteristic corresponding to all parking space spaces into a particle filter, generating Gaussian distribution random numbers by using a Monte Carlo method according to the state and the weight of the particle swarm at the last moment, and forming the position and the state of a new particle swarm;
the clustering processing unit is used for carrying out KNN clustering processing on the result of the filtering processing unit to obtain the position and the state of the candidate parking space, wherein the position comprises four vertex coordinates of the candidate parking space under a vehicle grid map, and the state represents the confidence degree of the candidate parking space;
and the characteristic calling unit is used for calling the first class characteristic and the second class characteristic corresponding to each candidate parking space obtained by the parking space characteristic obtaining unit.
13. The space-based parking space tracking system according to claim 12, wherein the parking space tracking result obtaining unit further comprises:
the matching comparison unit is used for matching the parking space characteristics corresponding to each candidate parking space with the parking space characteristics of each detected parking space in the parking space tracking result obtained at the last moment in pairs, calculating the sum of variances between the corresponding parking space characteristics, and if the sum is greater than a preset matching threshold value, judging that the matching is successful;
the tracking result acquisition unit is used for selecting one of the waiting parking spaces with the highest matching calculation result as the tracking result of the detected parking space if two or more than two successfully paired waiting parking spaces exist in the results of the matching comparison unit; if only one candidate parking space which is successfully paired exists, directly selecting the candidate parking space as a tracking result of the detected parking space; if the matched candidate parking spaces do not exist, the detected parking space is considered to be unavailable at the current moment so that the parking operation cannot be carried out;
and the display unit is used for obtaining the parking space tracking result at the current moment and displaying the parking space tracking result in the vehicle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210379055.2A CN115222767B (en) | 2022-04-12 | 2022-04-12 | Tracking method and system based on space parking space |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210379055.2A CN115222767B (en) | 2022-04-12 | 2022-04-12 | Tracking method and system based on space parking space |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115222767A true CN115222767A (en) | 2022-10-21 |
| CN115222767B CN115222767B (en) | 2024-01-23 |
Family
ID=83605916
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210379055.2A Active CN115222767B (en) | 2022-04-12 | 2022-04-12 | Tracking method and system based on space parking space |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115222767B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117152258A (en) * | 2023-11-01 | 2023-12-01 | 中国电建集团山东电力管道工程有限公司 | Product positioning method and system for intelligent workshop of pipeline production |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| SE0004096D0 (en) * | 2000-11-08 | 2000-11-08 | Nira Automotive Ab | Positioning system |
| US20180183650A1 (en) * | 2012-12-05 | 2018-06-28 | Origin Wireless, Inc. | Method, apparatus, and system for object tracking and navigation |
| CN109031346A (en) * | 2018-07-09 | 2018-12-18 | 江苏大学 | A kind of periphery parking position aided detection method based on 3D laser radar |
| CN109829386A (en) * | 2019-01-04 | 2019-05-31 | 清华大学 | Intelligent vehicle based on Multi-source Information Fusion can traffic areas detection method |
| CN110888125A (en) * | 2019-12-05 | 2020-03-17 | 奥特酷智能科技(南京)有限公司 | Automatic driving vehicle positioning method based on millimeter wave radar |
| CN111272165A (en) * | 2020-02-27 | 2020-06-12 | 清华大学 | Intelligent vehicle positioning method based on characteristic point calibration |
| CN111814773A (en) * | 2020-09-07 | 2020-10-23 | 广州汽车集团股份有限公司 | Lineation parking space identification method and system |
| WO2021004077A1 (en) * | 2019-07-09 | 2021-01-14 | 华为技术有限公司 | Method and apparatus for detecting blind areas of vehicle |
| CN112612862A (en) * | 2020-12-24 | 2021-04-06 | 哈尔滨工业大学芜湖机器人产业技术研究院 | Grid map positioning method based on point cloud registration |
| CN113076824A (en) * | 2021-03-19 | 2021-07-06 | 上海欧菲智能车联科技有限公司 | Parking space acquisition method and device, vehicle-mounted terminal and storage medium |
-
2022
- 2022-04-12 CN CN202210379055.2A patent/CN115222767B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| SE0004096D0 (en) * | 2000-11-08 | 2000-11-08 | Nira Automotive Ab | Positioning system |
| US20180183650A1 (en) * | 2012-12-05 | 2018-06-28 | Origin Wireless, Inc. | Method, apparatus, and system for object tracking and navigation |
| CN109031346A (en) * | 2018-07-09 | 2018-12-18 | 江苏大学 | A kind of periphery parking position aided detection method based on 3D laser radar |
| CN109829386A (en) * | 2019-01-04 | 2019-05-31 | 清华大学 | Intelligent vehicle based on Multi-source Information Fusion can traffic areas detection method |
| WO2021004077A1 (en) * | 2019-07-09 | 2021-01-14 | 华为技术有限公司 | Method and apparatus for detecting blind areas of vehicle |
| CN110888125A (en) * | 2019-12-05 | 2020-03-17 | 奥特酷智能科技(南京)有限公司 | Automatic driving vehicle positioning method based on millimeter wave radar |
| CN111272165A (en) * | 2020-02-27 | 2020-06-12 | 清华大学 | Intelligent vehicle positioning method based on characteristic point calibration |
| CN111814773A (en) * | 2020-09-07 | 2020-10-23 | 广州汽车集团股份有限公司 | Lineation parking space identification method and system |
| CN112612862A (en) * | 2020-12-24 | 2021-04-06 | 哈尔滨工业大学芜湖机器人产业技术研究院 | Grid map positioning method based on point cloud registration |
| CN113076824A (en) * | 2021-03-19 | 2021-07-06 | 上海欧菲智能车联科技有限公司 | Parking space acquisition method and device, vehicle-mounted terminal and storage medium |
Non-Patent Citations (4)
| Title |
|---|
| HENGWANG ZHAO ET.AL.: ""Time-of-Flight Camera Based Indoor Parking Localization Leveraging Manhattan World Regulation"", 《2020 IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV)》 * |
| 何松;孙静;郭乐江;陈梁;: "基于激光SLAM和深度学习的语义地图构建", 计算机技术与发展, no. 09, pages 94 - 100 * |
| 唐娜: ""自主泊车场景的无人车辆定位与导航建图算法研究"", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》, vol. 2022, no. 01, pages 035 - 398 * |
| 郝岩: ""基于激光Slam的仓储搬运AGV定位技术研究"", 《中国优秀硕士学位论文全文数据库 经济与管理科学辑》, vol. 2018, no. 12, pages 157 - 492 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117152258A (en) * | 2023-11-01 | 2023-12-01 | 中国电建集团山东电力管道工程有限公司 | Product positioning method and system for intelligent workshop of pipeline production |
| CN117152258B (en) * | 2023-11-01 | 2024-01-30 | 中国电建集团山东电力管道工程有限公司 | Product positioning method and system for intelligent workshop of pipeline production |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115222767B (en) | 2024-01-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111666921B (en) | Vehicle control method, apparatus, computer device, and computer-readable storage medium | |
| CN109800689B (en) | Target tracking method based on space-time feature fusion learning | |
| Rummelhard et al. | Conditional monte carlo dense occupancy tracker | |
| WO2022188663A1 (en) | Target detection method and apparatus | |
| CN109977997B (en) | Image target detection and segmentation method based on convolutional neural network rapid robustness | |
| CN110879994A (en) | Three-dimensional visual inspection detection method, system and device based on shape attention mechanism | |
| CN111627050B (en) | Training method and device for target tracking model | |
| CN113483747A (en) | Improved AMCL (advanced metering library) positioning method based on semantic map with corner information and robot | |
| CN110599489A (en) | Target space positioning method | |
| CN113705655B (en) | Three-dimensional point cloud full-automatic classification method and deep neural network model | |
| CN111311663B (en) | Real-time large-scene three-dimensional semantic modeling method | |
| Han et al. | Parking Space Recognition for Autonomous Valet Parking Using Height and Salient‐Line Probability Maps | |
| Roberts | Attentive visual tracking and trajectory estimation for dynamic scene segmentation | |
| CN115222767A (en) | Space parking stall-based tracking method and system | |
| CN115620263A (en) | Intelligent vehicle obstacle detection method based on image fusion of camera and laser radar | |
| CN115482255A (en) | Obstacle tracking method, device, equipment and storage medium | |
| CN114091515A (en) | Obstacle detection method, obstacle detection device, electronic apparatus, and storage medium | |
| CN112700469A (en) | Visual target tracking method and device based on ECO algorithm and target detection | |
| CN110008838B (en) | Lane line detection method and system based on improved fitting algorithm | |
| CN116921932A (en) | Welding track recognition method, device, equipment and storage medium | |
| CN116740160A (en) | Millisecond level multi-plane real-time extraction method and device in complex traffic scene | |
| CN116052099A (en) | Small target detection method for unstructured road | |
| Yang et al. | A novel vision-based framework for real-time lane detection and tracking | |
| CN115273068A (en) | Laser point cloud dynamic obstacle removing method and device and electronic equipment | |
| CN115063760A (en) | Vehicle travelable area detection method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |