CN114723784A - Pedestrian motion trajectory prediction method based on domain adaptation technology - Google Patents

Pedestrian motion trajectory prediction method based on domain adaptation technology Download PDF

Info

Publication number
CN114723784A
CN114723784A CN202210364770.9A CN202210364770A CN114723784A CN 114723784 A CN114723784 A CN 114723784A CN 202210364770 A CN202210364770 A CN 202210364770A CN 114723784 A CN114723784 A CN 114723784A
Authority
CN
China
Prior art keywords
domain
training
matrix
pedestrian
input sample
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
Application number
CN202210364770.9A
Other languages
Chinese (zh)
Other versions
CN114723784B (en
Inventor
张小恒
刘书君
李勇明
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chongqing University
Original Assignee
Chongqing University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Chongqing University filed Critical Chongqing University
Priority to CN202210364770.9A priority Critical patent/CN114723784B/en
Publication of CN114723784A publication Critical patent/CN114723784A/en
Application granted granted Critical
Publication of CN114723784B publication Critical patent/CN114723784B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
    • 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
    • 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
    • G06T2207/30241—Trajectory
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computing Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Multimedia (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to the technical field of automatic driving, and particularly discloses a pedestrian motion trail prediction method based on a domain adaptation technology
Figure DDA0003586605130000011
Then based on
Figure DDA0003586605130000012
And X' constructing r time sequence convolution networks for training to obtain r prediction models, and then carrying out training on the r prediction models
Figure DDA0003586605130000013
Inputting the predicted path into r prediction models to predict r predicted paths of N pedestrians, and finally performing path fusion to obtain the optimal predicted track of each pedestrian. The invention enables the data distribution of the training scene and the actual application scene to be approximately consistent through the domain adaptation processing, enhances the generalization capability of the prediction model, and maps the observation track into the training input tracks with different scales through changing the domain adaptation parameters so as to utilize the deeper information of the observation track, thereby enabling the prediction track to be more accurate.

Description

Pedestrian motion trajectory prediction method based on domain adaptation technology
Technical Field
The invention relates to the technical field of automatic driving, in particular to a pedestrian motion trail prediction method based on a domain adaptation technology.
Background
With the popularization of intelligent transportation, predicting the motion trajectory of pedestrians becomes an increasingly important issue. In unmanned or assisted driving, accurate prediction of pedestrian trajectories facilitates a driving system to plan ahead the motion trajectory of a vehicle in a traffic environment. Currently, research results in the field mainly focus on the following aspects: firstly, modeling is carried out by using various social force models based on social attributes of pedestrian motion in the early stage; in recent years, modeling is performed by combining a deep learning method, such as Social long-short term memory network (Social LSTM), Social generation countermeasure network (Social GAN), graph neural network and other methods, but the following problems are faced:
(1) the construction of the social force model is subjective, and the complex actual motion rule of the pedestrian is difficult to accurately describe;
(2) the deep learning related method depends on massive training data, but the training data scene is not matched with the actual application scene, so that the model generalization capability is poor;
(3) the observation track generally adopts fixed time interval sampling, and the multi-scale and multi-resolution depth information of sampling points with different time intervals is difficult to utilize.
Therefore, the invention carries out the domain adaptation processing on the training scene and the testing scene to ensure that the distribution of the training scene and the testing scene is approximately consistent, and fuses the sequences of sampling points at different time intervals, thereby more accurately predicting the pedestrian track.
Disclosure of Invention
The invention provides a pedestrian motion trail prediction method based on a domain adaptation technology, which solves the technical problems that: how to more accurately predict pedestrian trajectories in crowded environments.
In order to solve the above technical problems, the present invention provides a method for predicting a pedestrian motion trajectory based on a domain adaptation technique, comprising the steps of:
s1, acquiring the motion trail of the pedestrian under a training scene and a testing scene to generate a corresponding training data set and a corresponding testing data set, preprocessing the training data set to generate a training input sample set X and a training output reference set X', and preprocessing the testing data set to generate a testing input sample set Y;
s2, based on r different domain adaptive parameters, carrying out domain adaptive processing on the training input sample set X and the test input sample set Y to obtain r different domain adaptive training input sample sets
Figure BDA0003586605110000022
Adapting a test input sample set to r different domains
Figure BDA0003586605110000023
S3 adaptive training input sample set based on r fields
Figure BDA0003586605110000024
Constructing r time series convolution networks for training by a training output reference set X' to obtain r corresponding different prediction models;
s4, fitting r fields into the test input sample set
Figure BDA0003586605110000025
The method comprises the steps of inputting the prediction information into r prediction models correspondingly for prediction to obtain r prediction paths of each pedestrian;
and S5, fusing the r predicted paths of each pedestrian to obtain the predicted track of each pedestrian.
Further, the step S2 specifically includes the steps of:
s21, inputting training into the abscissa component X of the sample set XxAnd testing the abscissa component Y of the input sample set YxExtracted and respectively regarded as a source domain and a target domain for domain adaptation processing, and r groups of domain adaptation abscissa source domain matrixes are obtained on the basis of r different main characteristic vector numbers d
Figure BDA0003586605110000026
Sum-domain adaptive abscissa target domain matrix
Figure BDA0003586605110000027
S22, inputting training into the ordinate component X of the sample set XyAnd testing the ordinate component Y of the input sample set YyExtracted and respectively regarded as a source domain and a target domain for domain adaptation processing, and r groups of domain adaptation ordinate source domain matrixes are obtained based on r different main characteristic vector numbers d
Figure BDA0003586605110000028
Dome adaptive ordinate object domain matrix
Figure BDA0003586605110000029
S23, adapting the fields of the same group to the source field matrix of abscissa
Figure BDA00035866051100000210
Dome-adaptive ordinate source domain matrix
Figure BDA00035866051100000211
Merging to obtain r field adaptive training input sample sets
Figure BDA00035866051100000213
Adapting the fields of the same group to the abscissa object field matrix
Figure BDA00035866051100000214
Dome adaptive ordinate object domain matrix
Figure BDA00035866051100000212
To carry out the combinationAnd, r groups of domain adaptation test input sample sets are obtained together
Figure BDA00035866051100000215
Step S21 does not have to be in the order of step S22.
The domain adaptation processing procedure in step S21 specifically includes the steps of:
s211, combining the source domain matrix XxAnd the target domain matrix YxSplicing to obtain a nuclear matrix
Figure BDA0003586605110000021
T at the upper right corner of the matrix represents matrix transposition;
s212, constructing a maximum mean difference measure matrix
Figure BDA00035866051100000316
MN + KN dimensional row vector
Figure BDA0003586605110000031
M is the number of samples in the training input sample set X, namely the training output reference set X', N is the total number of pedestrians, K is the number of samples in the test input sample set Y,
Figure BDA0003586605110000032
is a matrix
Figure BDA0003586605110000033
F norm of (d);
s213, constructing a central matrix
Figure BDA0003586605110000034
E is an MN + KN dimensional unit matrix, and 1 is an MN + KN dimensional all-1 row vector;
s214, matrix pair (KMK + mu E)-1KHK carries out eigenvalue decomposition, and extracts the first d main eigenvectors to construct a transfer matrix W, wherein mu is a balance factor;
s215, extracting WTMN column vectors before K form MN x d domain adaptive abscissa source domain matrix
Figure BDA0003586605110000035
Extraction of WTKN column vectors after K form a KN x d domain adaptive abscissa target domain matrix
Figure BDA0003586605110000036
S216, changing the main feature vector number d for r-1 times, reconstructing the transfer matrix W according to the steps S214 and S215 after each change, and constructing a new domain adaptive abscissa source domain matrix based on the reconstructed transfer matrix W
Figure BDA0003586605110000037
Sum-domain adaptive abscissa target domain matrix
Figure BDA0003586605110000038
Thereby obtaining r groups of different domain adaptive abscissa source domain matrixes aiming at r different main characteristic vector numbers d
Figure BDA0003586605110000039
Domain-adapted abscissa target domain matrix
Figure BDA00035866051100000310
The domain adaptation processing procedure in step S22 is the same as step S211 to step S216.
Further, in step S1, the training data set S includes F frame position coordinates obtained by sampling the motion trajectories of N pedestrians at equal time intervals for a long time, that is, the position coordinates are obtained
Figure BDA00035866051100000311
Wherein 1 frame data
Figure BDA00035866051100000312
The spatial positions of N pedestrians at a certain moment in time, i.e.
Figure BDA00035866051100000313
Wherein the pedestrian is nThe spatial position of the frame sequence f is marked as
Figure BDA00035866051100000314
F is more than or equal to 1 and less than or equal to F is a frame number, N is more than or equal to 1 and less than or equal to N is a pedestrian number, and (x, y) is a two-dimensional plane coordinate point of a pedestrian;
time period [ Delta T, T + Delta T]T comprising N pedestrians0+T1Frame sequential position coordinates, front T0The frame data can construct a multi-dimensional training input sample
Figure BDA00035866051100000315
Rear T1The frame data can construct a multi-dimensional training output reference sample
Figure BDA0003586605110000041
Wherein training input samples for the nth pedestrian
Figure BDA0003586605110000042
Training output reference sample of nth pedestrian
Figure BDA0003586605110000043
(xn,i,yn,i) The position coordinates of the nth pedestrian in the ith frame are shown, i is 1,2, …, T0+T1；
By varying the starting time Δ t, i.e. Δ t ═ mTfraM is more than or equal to 0 and less than or equal to (M-1), wherein TfraFor adjacent frame time intervals, obtaining M multi-dimensional training input samples to form a training input sample set
Figure BDA0003586605110000044
And M multi-dimensional training output reference samples form a training output reference set
Figure BDA0003586605110000045
Preprocessing a test data set to generate a test input sample set
Figure BDA0003586605110000046
To training dataThe same process is used for generating the training input sample set X by preprocessing the set S.
Further, in step S211, the abscissa component X of the input sample set X is trainedxI.e. the source domain matrix XxComprises the following steps:
Figure BDA0003586605110000047
testing the abscissa component Y of the input sample set YxI.e. the target domain matrix YxComprises the following steps:
Figure BDA0003586605110000048
in step S215, the corresponding domain is adapted to the abscissa source domain matrix
Figure BDA0003586605110000049
Comprises the following steps:
Figure BDA00035866051100000410
corresponding domain adaptation abscissa target domain matrix
Figure BDA0003586605110000051
Comprises the following steps:
Figure BDA0003586605110000052
similarly, the domain adaptation in step S22 is based on the vertical coordinate source domain matrix
Figure BDA0003586605110000053
Comprises the following steps:
Figure BDA0003586605110000054
corresponding field adaptation ordinate meshMark domain matrix
Figure BDA0003586605110000055
Comprises the following steps:
Figure BDA0003586605110000056
in step S23, merge
Figure BDA0003586605110000057
And
Figure BDA0003586605110000058
resulting set of domain-adapted training input samples
Figure BDA0003586605110000059
Sample of (1)
Figure BDA00035866051100000510
Comprises the following steps:
Figure BDA00035866051100000511
can be obtained by the same way, combined
Figure BDA00035866051100000512
And
Figure BDA00035866051100000513
resulting set of domain-adapted test input samples
Figure BDA00035866051100000514
Sample of (1)
Figure BDA00035866051100000515
Comprises the following steps:
Figure BDA00035866051100000516
further, the step S3 specifically includes the steps of:
s31, adapting the first domain to the training input sample set
Figure BDA00035866051100000517
Sample of (1)
Figure BDA00035866051100000518
Rearranging construct sets
Figure BDA0003586605110000061
Wherein the sample
Figure BDA0003586605110000062
S32, input
Figure BDA0003586605110000063
Training the L-layer time sequence convolution network, taking the average displacement error between the output of the L-layer time sequence convolution network and a training output reference set X' as a loss function for calculating a training error in the training process, learning a weight value by using a random gradient descent algorithm, and storing a trained prediction model when the training termination condition is that the maximum training period number is met; wherein the convolution process of the time series convolution network is described as follows:
Figure BDA0003586605110000064
in
Figure BDA0003586605110000065
Is a2 XN dimensional matrix, will
Figure BDA0003586605110000066
Inputting L-layer time sequence convolution network to obtain first-layer output
Figure BDA0003586605110000067
1≤t≤d,1≤t′≤T1I is more than or equal to 1 and less than or equal to 2, j is more than or equal to 1 and less than or equal to N and higher layer output
Figure BDA0003586605110000068
1≤t′＜T1L is more than or equal to 1 and less than L, and correspondingly obtained
Figure BDA0003586605110000069
First layer output of (2)
Figure BDA00035866051100000610
And higher layer output
Figure BDA00035866051100000611
The weights of the convolution kernels of the different layers, η the scale of the convolution kernel,
Figure BDA00035866051100000612
representing the input of the L-layer time series convolution network;
s33, remaining r-1 field adaptation training input sample set
Figure BDA00035866051100000613
And repeating the steps S31 to S32 to finally obtain r trained prediction models.
Further, the step S4 specifically includes the steps of:
s41, fitting r fields into the test input sample set
Figure BDA00035866051100000614
Sample of (1)
Figure BDA00035866051100000615
Rearranging r sets of structure
Figure BDA00035866051100000616
Wherein
Figure BDA00035866051100000617
S42, collecting r
Figure BDA00035866051100000618
The predicted paths are input into r prediction models trained in step S33, and r different predicted paths Tra (1), Tra (2), …, Tra (r) are obtained for each pedestrian.
Further, for r different predicted paths Tra (1), Tra (2), …, Tra (r) of the pedestrian n, the step S5 is performed according to Tra ═ α1Tra(1)+α2Tra(2)+…+αrTra (r) to obtain a predicted trajectory Tra of the pedestrian n,
Figure BDA00035866051100000619
αjdenotes the weight of the first predicted path tra (j), j being 1,2, …, r.
The invention provides a pedestrian motion trail prediction method based on a domain adaptation technology, which comprises the steps of firstly acquiring a training data set and a test data set, preprocessing the training data set and the test data set to obtain a training input sample set X, a training output reference set X' and a test input sample set Y, then performing domain adaptation on the two input sample sets X and Y based on r different domain adaptation parameters to obtain a domain adapted data set
Figure BDA0003586605110000071
Then based on
Figure BDA0003586605110000072
And X' constructing r time series convolution networks for training to obtain r prediction models, and then training the r prediction models
Figure BDA0003586605110000073
Inputting the prediction path into r prediction models for prediction to obtain r prediction paths of N pedestrians, and finally fusing the r prediction paths of each pedestrian to obtain the optimal prediction track of each pedestrian. In the invention, the training scene data and the actual application scene data do not meet the independent and same-distribution statistical characteristic, and the training scene data and the actual application scene data are approximately consistent through domain adaptation processing, so that the generalization capability of a prediction model is enhanced; the invention takes the multi-scale and multi-resolution depth information of the observation track into consideration, maps the observation track into different scale training input tracks by changing the domain adaptive parameters, thereby utilizingAnd the deeper information of the track is observed, so that the final predicted track is more accurate as a whole.
Drawings
Fig. 1 is a flowchart of a method for predicting a pedestrian motion trajectory based on a domain adaptation technology according to an embodiment of the present invention.
Detailed Description
The embodiments of the present invention will be described in detail below with reference to the accompanying drawings, which are given solely for the purpose of illustration and are not to be construed as limitations of the invention, including the drawings which are incorporated herein by reference and for illustration only and are not to be construed as limitations of the invention, since many variations thereof are possible without departing from the spirit and scope of the invention.
In order to predict the pedestrian trajectory more accurately, referring to the flowchart in fig. 1, an embodiment of the present invention provides a method for predicting a pedestrian motion trajectory based on a domain adaptation technique, which generally includes the steps of:
s1, acquiring the motion trail of the pedestrian under a training scene and a testing scene to generate a corresponding training data set and a corresponding testing data set, preprocessing the training data set to generate a training input sample set X and a training output reference set X', and preprocessing the testing data set to generate a testing input sample set Y;
s2, carrying out domain adaptation processing on the training input sample set X and the test input sample set Y to obtain r different domain adaptation training input sample sets
Figure BDA00035866051100000812
Adapting a test input sample set to r different domains
Figure BDA00035866051100000813
S3 adaptive training input sample set based on r fields
Figure BDA00035866051100000814
Constructing r time series convolution networks for training by a training output reference set X' to obtain r corresponding different prediction models;
s4, correspondingly inputting r field adaptation test input sample sets Y into r prediction models for prediction to obtain r prediction paths of each pedestrian;
and S5, fusing the r predicted paths of each pedestrian to obtain the predicted track of each pedestrian.
In detail, in step S1, the training data set S includes F-frame position coordinates obtained by sampling the motion trajectories of N pedestrians at equal time intervals over a long period of time, that is, the F-frame position coordinates
Figure BDA0003586605110000081
Wherein 1 frame data
Figure BDA0003586605110000082
The spatial positions of N pedestrians at a certain moment in time, i.e.
Figure BDA0003586605110000083
Wherein the spatial position of the pedestrian n in the frame sequence f is marked as
Figure BDA0003586605110000084
F is more than or equal to 1 and less than or equal to F is a frame number, N is more than or equal to 1 and less than or equal to N is a pedestrian number, and (x, y) is a two-dimensional plane coordinate point of a pedestrian;
time period [ Delta T, T + Delta T]T comprising N pedestrians0+T1Frame sequential position coordinates, front T0The frame data can construct a multi-dimensional training input sample
Figure BDA0003586605110000085
Rear T1The frame data can construct a multi-dimensional training output reference sample
Figure BDA0003586605110000086
Training input sample of nth pedestrian
Figure BDA0003586605110000087
Training output reference sample of nth pedestrian
Figure BDA0003586605110000088
(xn,i,yn,i) The position coordinates of the nth pedestrian in the ith frame are shown, i is 1,2, …, T0+T1；
By varying the starting time Δ t, i.e. Δ t ═ mTfraM is more than or equal to 0 and less than or equal to (M-1), wherein TfraFor adjacent frame time intervals, obtaining M multi-dimensional training input samples to form a training input sample set
Figure BDA0003586605110000089
And M multi-dimensional training output reference samples form a training output reference set
Figure BDA00035866051100000810
Preprocessing a test data set to generate a test input sample set
Figure BDA00035866051100000811
The process of (2) is the same as the process of preprocessing the training data set S to generate the training input sample set X.
Step S2 specifically includes the steps of:
s21, inputting training into the abscissa component X of the sample set XxAnd testing the abscissa component Y of the input sample set YxExtracted and respectively regarded as a source domain and a target domain for domain adaptation processing, and r groups of domain adaptation abscissa source domain matrixes are obtained on the basis of r different main characteristic vector numbers d
Figure BDA0003586605110000091
Sum-domain adaptive abscissa target domain matrix
Figure BDA0003586605110000092
S22, inputting training into the ordinate component X of the sample set XyAnd testing the ordinate component Y of the input sample set YyExtracted and respectively regarded as a source domain and a target domain for domain adaptation processing, and r groups of domain adaptation ordinate source domain matrixes are obtained based on r different main characteristic vector numbers d
Figure BDA0003586605110000093
Sum-domain adaptive ordinate object domain matrix
Figure BDA0003586605110000094
S23, adapting the domains of the same group to the abscissa source domain matrix
Figure BDA0003586605110000095
Dome-adaptive ordinate source domain matrix
Figure BDA0003586605110000096
Merging to obtain r field adaptive training input sample sets
Figure BDA0003586605110000097
Adapting the fields of the same group to the abscissa object field matrix
Figure BDA0003586605110000098
Dome adaptive ordinate object domain matrix
Figure BDA0003586605110000099
Merging to obtain r groups of domain adaptation test input sample sets
Figure BDA00035866051100000910
Step S21 does not have to be in the order of step S22.
The domain adaptation processing procedure in step S21 specifically includes the steps of:
s211, combining the source domain matrix XxAnd the target domain matrix YxSplicing to obtain a nuclear matrix
Figure BDA00035866051100000911
T at the upper right corner of the matrix represents matrix transposition;
s212, constructing a maximum mean difference measure matrix
Figure BDA00035866051100000912
MN + KN dimensional row vector
Figure BDA00035866051100000913
M is the number of samples in the training input sample set X, namely the training output reference set X', N is the total number of pedestrians, K is the number of samples in the test input sample set Y,
Figure BDA00035866051100000914
is a matrix
Figure BDA00035866051100000915
F norm of (d);
s213, constructing a central matrix
Figure BDA00035866051100000916
E is an MN + KN dimensional unit matrix, and 1 is an MN + KN dimensional all-1 row vector;
s214, matrix pair (KMK + μ E)-1KHK carries out eigenvalue decomposition, and extracts the first d main eigenvectors to construct a transfer matrix W, wherein mu is a balance factor;
s215, extracting WTMN column vectors before K form MN x d domain adaptive abscissa source domain matrix
Figure BDA0003586605110000101
Extraction of WTKN column vectors after K form a KN x d domain adaptive abscissa target domain matrix
Figure BDA0003586605110000102
S216, changing the main feature vector number d for r-1 times, reconstructing the transfer matrix W according to the steps S214 and S215 after each change, and constructing a new domain adaptive abscissa source domain matrix based on the reconstructed transfer matrix W
Figure BDA0003586605110000103
Sum-domain adaptive abscissa target domain matrix
Figure BDA0003586605110000104
Thereby aiming at r different main characteristicsVector number d obtains r groups of different domain adaptive abscissa source domain matrixes
Figure BDA0003586605110000105
Domain-adapted abscissa target domain matrix
Figure BDA0003586605110000106
The domain adaptation processing procedure in step S22 is the same as that of steps S211 to S216.
Further illustratively, in step S211, the abscissa component X of the input sample set X is trainedxI.e. the source domain matrix XxComprises the following steps:
Figure BDA0003586605110000107
testing the abscissa component Y of the input sample set YxI.e. the target domain matrix YxComprises the following steps:
Figure BDA0003586605110000108
in step S215, the corresponding domain is adapted to the abscissa source domain matrix
Figure BDA0003586605110000109
Comprises the following steps:
Figure BDA00035866051100001010
corresponding domain adaptation abscissa target domain matrix
Figure BDA00035866051100001011
Comprises the following steps:
Figure BDA0003586605110000111
similarly, the domain adaptation ordinate in step S22Source domain matrix
Figure BDA0003586605110000112
Comprises the following steps:
Figure BDA0003586605110000113
domain-adapted ordinate target domain matrix
Figure BDA0003586605110000114
Comprises the following steps:
Figure BDA0003586605110000115
in step S23, merge
Figure BDA0003586605110000116
And
Figure BDA0003586605110000117
resulting set of domain-adapted training input samples
Figure BDA0003586605110000118
Sample of (1)
Figure BDA0003586605110000119
Comprises the following steps:
Figure BDA00035866051100001110
can be obtained by the same way, combined
Figure BDA00035866051100001111
And
Figure BDA00035866051100001112
resulting set of domain-adapted test input samples
Figure BDA00035866051100001113
Sample of (1)
Figure BDA00035866051100001114
Comprises the following steps:
Figure BDA00035866051100001115
based on this, step S3 specifically includes the steps of:
s31, adapting the first domain to the training input sample set
Figure BDA00035866051100001116
Sample of (1)
Figure BDA00035866051100001117
Rearranging construct sets
Figure BDA0003586605110000121
In which the sample
Figure BDA0003586605110000122
S32, input
Figure BDA0003586605110000123
Training the L-layer time sequence convolution network, taking the average displacement error between the output of the L-layer time sequence convolution network and a training output reference set X' as a loss function for calculating a training error in the training process, learning a weight value by using a random gradient descent algorithm, and storing a trained prediction model when the training termination condition is that the maximum training period number is met; wherein the convolution process of the time series convolution network is described as follows:
Figure BDA0003586605110000124
in
Figure BDA0003586605110000125
Is a2 XN dimensional matrix, will
Figure BDA0003586605110000126
Inputting L layers of time sequence convolution network to obtain first layer output
Figure BDA0003586605110000127
1≤t≤d,1≤t′≤T1I is more than or equal to 1 and less than or equal to 2, j is more than or equal to 1 and less than or equal to N and higher layer output
Figure BDA0003586605110000128
1≤t′＜T1L is more than or equal to 1 and less than L, and correspondingly obtained
Figure BDA0003586605110000129
First layer output of (2)
Figure BDA00035866051100001210
And higher layer output
Figure BDA00035866051100001211
The weights of the convolution kernels of the different layers, η the scale of the convolution kernel,
Figure BDA00035866051100001212
representing the input of an L-layer time series convolutional network;
s33, remaining r-1 field adaptation training input sample set
Figure BDA00035866051100001213
And repeating the steps S31 to S32 to finally obtain r trained prediction models.
Step S4 specifically includes the steps of:
s41, fitting r fields into the test input sample set
Figure BDA00035866051100001214
Sample of (1)
Figure BDA00035866051100001215
Rearranging r sets of structure
Figure BDA00035866051100001216
Wherein
Figure BDA00035866051100001217
S42, collecting r
Figure BDA00035866051100001218
The predicted paths are input into r prediction models trained in step S33, and r different predicted paths Tra (1), Tra (2), …, Tra (r) are obtained for each pedestrian.
Then, r different predicted paths Tra (1), Tra (2), …, Tra (r) for the pedestrian n, step S5 is performed based on Tra ═ α1Tra(1)+α2Tra(2)+…+αrTra (r) to obtain a predicted trajectory Tra of the pedestrian n,
Figure BDA00035866051100001219
αjdenotes the weight of the first predicted path tra (j), j being 1,2, …, r. And obtaining the predicted tracks of the N pedestrians in the same way.
The embodiment of the invention provides a pedestrian motion trail prediction method based on a domain adaptation technology, which comprises the steps of firstly acquiring a training data set and a test data set, carrying out preprocessing to obtain a training input sample set X, a training output reference set X' and a test input sample set Y, then carrying out domain adaptation on the two input sample sets X and Y based on r different domain adaptation parameters to obtain a domain adapted data set
Figure BDA0003586605110000131
Then based on
Figure BDA0003586605110000132
And X' constructing r time series convolution networks for training to obtain r prediction models, and then training the r prediction models
Figure BDA0003586605110000133
Inputting the prediction into r prediction models for prediction to obtain r prediction paths of N pedestrians, and finally fusing the r prediction paths of each pedestrian to obtain the optimal prediction track of each pedestrian. In the invention, the training scene data and the actual application scene data do not meet the independent and identically distributed statistical characteristics, and the training scene data and the actual application scene data are approximately consistent through domain adaptive processing, so that the generalization capability of a prediction model is enhanced; the invention takes the multi-scale and multi-resolution depth information of the observation track into consideration, and maps the observation track into different-scale training input tracks by changing the domain adaptive parameters, thereby utilizing the deeper information of the observation track and integrally enabling the final predicted track to be more accurate.
In a specific experiment, the training data set in step S1 includes two data sets (eth, hotel) of eth and 3 data sets (univ, zara1, zara2) of UCY, which are 5 different scene data sets. Table 1 shows an example of a single-frame data segment, a training data set is composed of multi-frame data, each frame of data is marked with a pedestrian number, a frame number, a pedestrian x coordinate and a pedestrian y coordinate, the frame interval is 0.4 second, an observation sample is a pedestrian track of 3.2 seconds and corresponds to T0The next 4.8 seconds of trajectory is predicted, corresponding to T, for 8 frames of image112 frames of pictures.
Table 1 single frame data fragment example
Frame number Pedestrian numbering Pedestrian x coordinate Y coordinate of pedestrian
10 1.0 10.7867577985 3.67631555479
10 2.0 10.9587077931 3.15460523261
10 3.0 10.9993275592 2.64673717882
The balance factor μ in the domain adaptation algorithm in step S2 is 0.01, the first domain adaptation main feature vector number d is 12, the first time d is 10, and the third time d is 6, that is, the parameter is changed three times r is 3.
Activation function of time series convolutional network in step S3
Figure BDA0003586605110000134
Where a is 0.25, the convolution kernel scale is 2 × 2, and the total number of layers L is 5. The model implementation is based on a Pythrch library, each layer of convolution is realized by depending on a two-dimensional convolution function Conv2d, the loss function is the average displacement error ADE, each batch of training samples is 128, the model is trained for 100 cycles by using random gradient descent (SGD), and the learning rate is 0.01.
Fusion parameter α in step S41＝0.2，α2＝0.3，α3＝0.5。
In step S1, the test data set is also taken from scene 1 to scene 5, and 5 alternative training test modes are adopted to avoid overlapping of the training set and the test set. 1. Training set (hotel, univ, zara1, zara2), test set (eth); 2. training set (eth, univ, zara1, zara2), test set (hotel); 3. training set (eth, hotel, zara1, zara2), test set (univ); 4. training set (eth, hotel, univ, zara2), test set (zara 1); 5. training set (eth, hotel, univ, zara1), test set (zara 2).
And finally, calculating the average displacement error ADE and the final displacement error FDE value of the optimal planning track and the actual track in the test set for evaluating the classification effect. The expressions for the average displacement error ADE and the final displacement error FDE are as follows:
Figure BDA0003586605110000141
wherein
Figure BDA0003586605110000142
Figure BDA0003586605110000143
Respectively predicting coordinates and actual coordinates of the t frame of the pedestrian n,
Figure BDA0003586605110000144
the predicted coordinates and the actual coordinates are respectively the last frame of the trajectory of the pedestrian n.
The average ADE FDE values for 5 different scenes of the present invention were compared to other mainstream methods (Linear, S-LSTM, S-GAN-P, SoPhie) and the results are shown in Table 2.
TABLE 2 comparison of ADE/FDE measurements with existing mainstream results
eth hotel univ zara1 zara2 Average
Linear 1.33/2.94 0.39/0.72 0.82/1.59 0.62/1.21 0.77/1.48 0.79/1.59
S-LSTM 1.09/2.35 0.79/1.76 0.67/1.40 0.47/1.00 0.56/1.17 0.72/1.54
S-GAN-P 0.87/1.62 0.67/1.37 0.76/1.52 0.35/0.68 0.42/0.84 0.61/1.21
SoPhie 0.70/1.43 0.76/1.67 0.54/1.24 0.30/0.63 0.38/0.78 0.54/1.15
The invention 0.70/1.28 0.39/0.63 0.49/0.90 0.39/0.66 0.32/0.50 0.45/0.79
As can be seen from table 2, the average ADE value FDE values of the present invention are significantly better than the 4 main stream methods in 5 different scenes.
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and all such changes, modifications, substitutions, combinations, and simplifications are intended to be included in the scope of the present invention.

Claims (8)

1. A pedestrian motion trail prediction method based on a domain adaptation technology is characterized by comprising the following steps:
s1, acquiring the motion trail of the pedestrian under a training scene and a testing scene to generate a corresponding training data set and a corresponding testing data set, preprocessing the training data set to generate a training input sample set X and a training output reference set X', and preprocessing the testing data set to generate a testing input sample set Y;
s2, based on r different domain adaptive parameters, carrying out domain adaptive processing on the training input sample set X and the test input sample set Y to obtain r different domain adaptive training input sample sets
Figure FDA0003586605100000011
Adapting a test input sample set to r different domains
Figure FDA0003586605100000012
S3, training input sample set based on r field adaptation
Figure FDA0003586605100000013
R time series convolution networks are constructed by the training output reference set X' for training to obtain r corresponding different prediction models;
s4, fitting r fields into the test input sample set
Figure FDA0003586605100000014
The method comprises the steps of inputting the prediction information into r prediction models correspondingly for prediction to obtain r prediction paths of each pedestrian;
and S5, fusing the r predicted paths of each pedestrian to obtain the predicted track of each pedestrian.
2. The method for predicting the motion trail of the pedestrian based on the domain adaptation technology as claimed in claim 1, wherein the step S2 specifically comprises the steps of:
s21, inputting training into the abscissa component X of the sample set XxAnd testing the abscissa component Y of the input sample set YxExtracted and respectively regarded as a source domain and a target domain for domain adaptation processing, and r groups of domain adaptation abscissa source domain matrixes are obtained on the basis of r different main characteristic vector numbers d
Figure FDA0003586605100000015
Sum-domain adaptive abscissa target domain matrix
Figure FDA0003586605100000016
S22, inputting training into the ordinate component X of the sample set XyAnd testing the ordinate component Y of the input sample set YyExtracted and respectively regarded as a source domain and a target domain for domain adaptation processing, and r groups of domain adaptation ordinate source domain matrixes are obtained based on r different main characteristic vector numbers d
Figure FDA0003586605100000017
Dome adaptive ordinate object domain matrix
Figure FDA0003586605100000018
S23, adapting the fields of the same group to the source field matrix of abscissa
Figure FDA0003586605100000019
Dome-adaptive ordinate source domain matrix
Figure FDA00035866051000000110
Merging to obtain r field adaptive training input sample sets
Figure FDA00035866051000000111
Adapting the fields of the same group to the abscissa object field matrix
Figure FDA00035866051000000112
Dome adaptive ordinate object domain matrix
Figure FDA00035866051000000113
Merging to obtain r groups of domain adaptation test input sample sets
Figure FDA00035866051000000114
Step S21 does not have to be in the order of step S22.
3. The method for predicting the motion trail of the pedestrian based on the domain adaptation technology as claimed in claim 2, wherein the domain adaptation processing procedure in the step S21 specifically comprises the steps of:
s211, combining the source domain matrix XxAnd the target domain matrix YxSplicing to obtain a nuclear matrix
Figure FDA0003586605100000021
T at the upper right corner of the matrix represents matrix transposition;
s212, constructing a maximum mean difference measure matrix
Figure FDA0003586605100000022
MN + KN dimensional row vector
Figure FDA0003586605100000023
M is the number of samples in the training input sample set X, namely the training output reference set X', N is the total number of pedestrians, K is the number of samples in the test input sample set Y,
Figure FDA0003586605100000024
is a matrix
Figure FDA0003586605100000025
F norm of (d);
s213, constructing a central matrix
Figure FDA0003586605100000026
E is an MN + KN dimensional unit matrix, and 1 is an MN + KN dimensional all-1 row vector;
s214, matrix pair (KMK + mu E)-1KHK carries out eigenvalue decomposition, and extracts the first d main eigenvectors to construct a transfer matrix W, wherein mu is a balance factor;
s215, extracting WTMN column vectors before K form MN x d domain adaptive abscissa source domain matrix
Figure FDA0003586605100000027
Extraction of WTKN column vectors after K form a KN x d domain adaptive abscissa target domain matrix
Figure FDA0003586605100000028
S216, changing the main feature vector number d for r-1 times, reconstructing the transfer matrix W according to the steps S214 and S215 after each change, and constructing a new domain adaptive abscissa source domain matrix based on the reconstructed transfer matrix W
Figure FDA0003586605100000029
Sum-domain adaptive abscissa object domain matrix
Figure FDA00035866051000000210
Thereby obtaining r groups of different domain adaptive abscissa source domain matrixes aiming at r different main characteristic vector numbers d
Figure FDA00035866051000000211
Domain-adapted abscissa target domain matrix
Figure FDA00035866051000000212
The domain adaptation processing procedure in step S22 is the same as that of steps S211 to S216.
4. The method for predicting pedestrian motion trail according to claim 3, wherein in the step S1, the training data set S comprises F-frame position coordinates obtained by sampling N pedestrians 'motion trail at equal time intervals for a longer time, that is, N pedestrians' motion trail
Figure FDA0003586605100000031
Wherein 1 frame data
Figure FDA0003586605100000032
The spatial positions of N pedestrians at a certain moment in time, i.e.
Figure FDA0003586605100000033
Wherein the spatial position of the pedestrian n in the frame sequence f is identified as
Figure FDA0003586605100000034
F is more than or equal to 1 and less than or equal to F is a frame number, N is more than or equal to 1 and less than or equal to N is a pedestrian number, and (x, y) is a two-dimensional plane coordinate point of a pedestrian;
time period [ Delta T, T + Delta T]T comprising N pedestrians0+T1Frame sequential position coordinates, front T0The frame data can construct a multi-dimensional training input sample
Figure FDA0003586605100000035
Rear T1The frame data can construct a multi-dimensional training output reference sample
Figure FDA0003586605100000036
Wherein training input samples for the nth pedestrian
Figure FDA0003586605100000037
Training output reference sample of nth pedestrian
Figure FDA0003586605100000038
(xn,i,yn,i) The position coordinates of the nth pedestrian in the ith frame are shown, i is 1,2, …, T0+T1；
By varying the starting time Δ t, i.e. Δ t ═ mTfraM is more than or equal to 0 and less than or equal to (M-1), wherein TfraFor adjacent frame time intervals, obtaining M multi-dimensional training input samples to form a training input sample set
Figure FDA0003586605100000039
And M multi-dimensional training output reference samples form a training output reference set
Figure FDA00035866051000000310
Preprocessing a test data set to generate a test input sample set
Figure FDA00035866051000000311
The process of (2) is the same as the process of preprocessing the training data set S to generate the training input sample set X.
5. The method for predicting the motion trail of the pedestrian based on the domain adaptation technology as claimed in claim 4, wherein in step S211, the abscissa component X of the input sample set X is trainedxI.e. the source domain matrix XxComprises the following steps:
Figure FDA0003586605100000041
testing the abscissa component Y of the input sample set YxI.e. the target domain matrix YxComprises the following steps:
Figure FDA0003586605100000042
in step S215, the corresponding domain is adapted to the abscissa source domain matrix
Figure FDA0003586605100000043
Comprises the following steps:
Figure FDA0003586605100000044
corresponding domain adaptation abscissa target domain matrix
Figure FDA0003586605100000045
Comprises the following steps:
Figure FDA0003586605100000046
similarly, the domain adaptation in step S22 is based on the vertical coordinate source domain matrix
Figure FDA0003586605100000047
Comprises the following steps:
Figure FDA0003586605100000048
corresponding domain adaptation ordinate target domain matrix
Figure FDA0003586605100000049
Comprises the following steps:
Figure FDA00035866051000000410
in step S23, merge
Figure FDA0003586605100000051
And
Figure FDA0003586605100000052
resulting set of domain-adapted training input samples
Figure FDA0003586605100000053
Sample of (1)
Figure FDA0003586605100000054
Comprises the following steps:
Figure FDA0003586605100000055
can be obtained by the same way, combined
Figure FDA0003586605100000056
And
Figure FDA0003586605100000057
resulting set of domain-adapted test input samples
Figure FDA0003586605100000058
Sample of (1)
Figure FDA0003586605100000059
Comprises the following steps:
Figure FDA00035866051000000510
6. the method for predicting the motion trail of the pedestrian based on the domain adaptation technology as claimed in claim 5, wherein the step S3 specifically comprises the steps of:
s31, adapting the first domain to the training input sample set
Figure FDA00035866051000000511
Sample of (1)
Figure FDA00035866051000000512
Rearranging construct sets
Figure FDA00035866051000000513
In which the sample
Figure FDA00035866051000000514
S32, input
Figure FDA00035866051000000515
Training the L-layer time sequence convolution network, taking the average displacement error between the output of the L-layer time sequence convolution network and a training output reference set X' as a loss function for calculating a training error in the training process, learning a weight value by using a random gradient descent algorithm, and storing a trained prediction model when the training termination condition is that the maximum training period number is met; wherein the convolution process of the time series convolution network is described as follows:
Figure FDA00035866051000000516
in
Figure FDA00035866051000000517
Is a2 XN dimensional matrix, will
Figure FDA00035866051000000518
Inputting L-layer time sequence convolution network to obtain first-layer output
Figure FDA00035866051000000519
And higher layer output
Figure FDA00035866051000000520
Correspond to obtain
Figure FDA0003586605100000061
First layer output of (2)
Figure FDA0003586605100000062
And higher layer output
Figure FDA0003586605100000063
Figure FDA0003586605100000064
The weights of the convolution kernels of the different layers, η the scale of the convolution kernel,
Figure FDA0003586605100000065
representing the input of the L-layer time series convolution network;
s33, remaining r-1 field adaptation training input sample set
Figure FDA0003586605100000066
And repeating the steps S31 to S32 to finally obtain r trained prediction models.
7. The method for predicting the motion trail of the pedestrian based on the domain adaptation technology as claimed in claim 6, wherein the step S4 specifically comprises the steps of:
s41, fitting r fields into the test input sample set
Figure FDA0003586605100000067
Sample of (1)
Figure FDA0003586605100000068
Rearranging r sets of structure
Figure FDA0003586605100000069
Wherein
Figure FDA00035866051000000610
S42, collecting r
Figure FDA00035866051000000611
The predicted paths are input into r prediction models trained in step S33, and r different predicted paths Tra (1), Tra (2), …, Tra (r) are obtained for each pedestrian.
8. The method for predicting the motion trail of the pedestrian based on the domain adaptation technology as claimed in claim 7, wherein: r different predicted paths Tra (1), Tra (2), …, Tra (r) for the pedestrian n, in step S5, based on Tra ═ α1Tra(1)+α2Tra(2)+…+αrTra (r) to obtain a predicted trajectory Tra of the pedestrian n,
Figure FDA00035866051000000612
αjdenotes the weight of the first predicted path tra (j), j being 1,2, …, r.
CN202210364770.9A 2022-04-08 2022-04-08 Pedestrian motion trail prediction method based on domain adaptation technology Active CN114723784B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210364770.9A CN114723784B (en) 2022-04-08 2022-04-08 Pedestrian motion trail prediction method based on domain adaptation technology

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210364770.9A CN114723784B (en) 2022-04-08 2022-04-08 Pedestrian motion trail prediction method based on domain adaptation technology

Publications (2)

Publication Number Publication Date
CN114723784A true CN114723784A (en) 2022-07-08
CN114723784B CN114723784B (en) 2024-06-14

Family

ID=82242090

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210364770.9A Active CN114723784B (en) 2022-04-08 2022-04-08 Pedestrian motion trail prediction method based on domain adaptation technology

Country Status (1)

Country Link
CN (1) CN114723784B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115272395A (en) * 2022-07-11 2022-11-01 哈尔滨工业大学重庆研究院 Cross-domain migratable pedestrian trajectory prediction method based on depth map convolutional network
CN115345390A (en) * 2022-10-19 2022-11-15 武汉大数据产业发展有限公司 Behavior trajectory prediction method and device, electronic equipment and storage medium

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101930072A (en) * 2010-07-28 2010-12-29 重庆大学 Multi-feature fusion based infrared small dim moving target track starting method
CN113316788A (en) * 2021-04-20 2021-08-27 深圳市锐明技术股份有限公司 Method and device for predicting pedestrian motion trail, electronic equipment and storage medium
CN113689470A (en) * 2021-09-02 2021-11-23 重庆大学 Pedestrian motion trajectory prediction method under multi-scene fusion
CN113920170A (en) * 2021-11-24 2022-01-11 中山大学 Pedestrian trajectory prediction method and system combining scene context and pedestrian social relationship and storage medium

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101930072A (en) * 2010-07-28 2010-12-29 重庆大学 Multi-feature fusion based infrared small dim moving target track starting method
CN113316788A (en) * 2021-04-20 2021-08-27 深圳市锐明技术股份有限公司 Method and device for predicting pedestrian motion trail, electronic equipment and storage medium
CN113689470A (en) * 2021-09-02 2021-11-23 重庆大学 Pedestrian motion trajectory prediction method under multi-scene fusion
CN113920170A (en) * 2021-11-24 2022-01-11 中山大学 Pedestrian trajectory prediction method and system combining scene context and pedestrian social relationship and storage medium

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
CAO JIANAO: ""Multi-UAVs Cooperative Target Tracking"", 《2021 33RD CHINESE CONTROL AND DECISION CONFERENCE (CCDC)》, 30 November 2021 (2021-11-30) *
高铭: ""基于深度学习的复杂交通环境下目标跟踪与轨迹预测研究"", 《中国博士学位论文全文数据库 工程科技II辑》, 15 August 2020 (2020-08-15) *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115272395A (en) * 2022-07-11 2022-11-01 哈尔滨工业大学重庆研究院 Cross-domain migratable pedestrian trajectory prediction method based on depth map convolutional network
CN115345390A (en) * 2022-10-19 2022-11-15 武汉大数据产业发展有限公司 Behavior trajectory prediction method and device, electronic equipment and storage medium

Also Published As

Publication number Publication date
CN114723784B (en) 2024-06-14

Similar Documents

Publication Publication Date Title
CN109344736B (en) Static image crowd counting method based on joint learning
Varma et al. Transformers in self-supervised monocular depth estimation with unknown camera intrinsics
CN111581966B (en) Context feature-fused aspect-level emotion classification method and device
CN110263912A (en) A kind of image answering method based on multiple target association depth reasoning
CN113610126A (en) Label-free knowledge distillation method based on multi-target detection model and storage medium
CN112348849A (en) Twin network video target tracking method and device
CN114332578A (en) Image anomaly detection model training method, image anomaly detection method and device
CN114723784A (en) Pedestrian motion trajectory prediction method based on domain adaptation technology
CN110334589A (en) A kind of action identification method of the high timing 3D neural network based on empty convolution
CN111047078B (en) Traffic characteristic prediction method, system and storage medium
CN115100574A (en) Action identification method and system based on fusion graph convolution network and Transformer network
CN113920170B (en) Pedestrian track prediction method, system and storage medium combining scene context and pedestrian social relationship
CN110110372B (en) Automatic segmentation prediction method for user time sequence behavior
CN111508000A (en) Deep reinforcement learning target tracking method based on parameter space noise network
CN111052128A (en) Descriptor learning method for detecting and locating objects in video
CN115311502A (en) Remote sensing image small sample scene classification method based on multi-scale double-flow architecture
CN113688765A (en) Attention mechanism-based action recognition method for adaptive graph convolution network
CN114692732A (en) Method, system, device and storage medium for updating online label
Qiao et al. SF-Net: Learning scene flow from RGB-D images with CNNs
CN103839280B (en) A kind of human body attitude tracking of view-based access control model information
CN111179272A (en) Rapid semantic segmentation method for road scene
Son et al. Partial convolutional LSTM for spatiotemporal prediction of incomplete data
Artemov et al. Subsystem for simple dynamic gesture recognition using 3DCNNLSTM
CN116311504A (en) Small sample behavior recognition method, system and equipment
Zhang et al. Mobile robot localization based on gradient propagation particle filter network

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