CN114663861B - Vehicle re-identification method based on dimension decoupling and non-local relation - Google Patents
Vehicle re-identification method based on dimension decoupling and non-local relation Download PDFInfo
- Publication number
- CN114663861B CN114663861B CN202210531995.9A CN202210531995A CN114663861B CN 114663861 B CN114663861 B CN 114663861B CN 202210531995 A CN202210531995 A CN 202210531995A CN 114663861 B CN114663861 B CN 114663861B
- Authority
- CN
- China
- Prior art keywords
- local
- channel
- dimension
- space
- local relationship
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- 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
- G06N3/045—Combinations of networks
-
- 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
-
- 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 Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of vehicle heavy identification, in particular to a vehicle heavy identification method based on dimension decoupling and non-local relation, which comprises the following steps: copying partial residual layers after ResNet-50 into three branches with the same structure, and sequentially introducing a global feature extraction mechanism, a non-local relation capture mechanism and a dimension decoupling mechanism into each branch behind the residual layer; the non-local relationship capturing mechanism comprises a non-local relationship capturing module based on a channel and a non-local relationship capturing module based on a space, wherein the non-local relationship capturing module and the non-local relationship capturing module respectively perform noise reduction on the non-local relationship between the channel and the space level, and meanwhile different weights are distributed for the relationship between the channel and the position on the channel and the space level; the dimension decoupling mechanism is used for decoupling the space and the channel, and a part of the characteristics are concentrated in a specific subspace. The invention solves the problems of large intra-class difference and small inter-class difference in vehicle weight identification.
Description
Technical Field
The invention relates to the technical field of vehicle re-identification, in particular to a vehicle re-identification method based on dimension decoupling and non-local relation.
Background
With the use and popularization of automobiles, a great number of technical problems related to vehicle management and scheduling are derived to be solved urgently. Vehicle weight recognition has been reported by researchers in the industry as one of the technical difficulties associated with vehicle management and scheduling. The vehicle weight recognition aims to find vehicle images belonging to the same identity from images shot by different cameras. In recent years, the vehicle re-identification algorithm based on deep learning has been widely applied to the field of vehicle re-identification with the advantages of unique adaptivity, strong identification precision and the like. At present, the problem of vehicle heavy identification is that the vehicle heavy identification network has low generalization capability and network accuracy due to the problem of large intra-class difference and small inter-class difference.
Disclosure of Invention
The invention aims to overcome the defects in the prior art, provides a vehicle re-identification method based on dimension decoupling and non-local relation, adopts a global feature extraction mechanism, a non-local relation capture mechanism and a dimension decoupling mechanism to design, solves the problems of larger intra-class difference and smaller inter-class difference in the vehicle re-identification problem, and can improve the generalization capability and network precision of a vehicle re-identification network.
The technical scheme adopted by the invention for solving the technical problem is as follows:
a vehicle re-identification method based on dimension decoupling and non-local relation comprises the following steps:
a convolutional neural network Resnet50 is used as a backbone, partial residual error layers (res _ conv4_ 2-res _ conv5) behind ResNet-50 are copied into three branches with the same structure, and a global feature extraction mechanism, a non-local relationship capture mechanism and a dimension decoupling mechanism are sequentially introduced into each branch behind the residual error layers;
the global feature extraction mechanism is used for extracting global features of the vehicle, and feature graphs generated by a res _ conv5 layer are sequentially input into a Global Average Pooling (GAP) and a channel dimension reduction module consisting of a 1 × 1 convolution, Batch Normalization (BN) and a ReLU activation function to obtain 256-dimensional feature representation;
the non-local relationship capturing mechanism comprises a non-local relationship capturing module based on a channel and a non-local relationship capturing module based on a space, wherein the non-local relationship capturing module and the non-local relationship capturing module respectively perform noise reduction on the non-local relationship between the channel and the space level, and meanwhile, different weights are distributed for the relationship between the channel and the position on the channel and the space level; the mechanism aims to dig out useful non-local relations so as to improve the performance of the network;
the dimension decoupling mechanism is used for stripping mutual interference of information between the channel and the space, and decoupling the space and the channel, so that a part of features are concentrated in a specific subspace.
Further, the non-local relationship capture mechanism is specifically operative to: simultaneously inputting the tensors output by the res _ conv5 layer into a space-based non-local relation capturing module and a channel-based non-local relation capturing module; the feature size through the spatial and channel non-local relationship capture module is unchanged, and then the dimensionality is reduced from 2048 to 256 through Global Average Pooling (GAP), 1 × 1 convolution, Bulk Normalization (BN), and ReLU operations.
Further, the dimensional decoupling mechanism is specifically operative to: firstly, a feature map is divided into two parts from the horizontal direction in a space dimension to obtain two feature maps, and then the feature maps are decoupled on average in a channel dimension, namely the two obtained feature maps are divided into two parts on the channel dimension, aiming at cutting off redundant channels in the channel dimension in the two spaces, so that the calculated amount is reduced, and the relation between the spaces and the channels is stripped; in the third branch, the invention takes two gray features in the feature map generated by res _ conv5 as two decoupled subspaces; independently performing feature extraction operations in two subspaces after the decoupling operation: the feature maps were subjected to Global Average Pooling (GAP), 1 × 1 convolution, Bulk Normalization (BN), and ReLU operations, reducing the dimensionality from 2048 to 256.
Further, the composition structure of the space-based non-local relationship capture module is as follows: is provided withIs an input to a feature extraction module, whereinAndrespectively the width and the height of the input tensor,is the number of channels; wherein the functionIs input as a pairTo carry outA depth separable convolution operation with a convolution kernel of sizeThen obtainEach size isAnd then deforming both of them intoThen splicing is carried out in the spatial dimension to obtainRecording the matrix as A;for the input tensorPerforming 1 × 1 convolution operation, and performing deformation operation to obtainThen multiplying A by the B matrix to determine a non-local relationship and obtain a value ofA matrix of (a); using for each column on the basis of the derived non-local relationActivating functions to obtain a suitable probability matrix:
Has a size ofThen, the sum of each row of the probability matrix is calculated to obtain a weight vectorEach element of the vectorRepresents the firstA weight of each spatial location;expressed as:
space-based non-local relationship capture module final output characteristicsComprises the following steps:
in the feature extraction module,function is asA convolution kernel of sizeMay separate the convolutions. The importance of each point is measured by obtaining a global set of key-value distributions using a set of depth-separable convolution operations, and because the size of the convolution kernel isThis means that each convolution fuses all feature points to obtain a global feature representation, and different weights are assigned to different positions. WhereinFor adjustable hyper-parameters, it is found through experimentsThe present network achieves optimal performance.
Furthermore, in order to supplement the function of the space-based non-local relationship capturing module and improve the performance of the network, the channel-based non-local relationship capturing module is added in the network, and the module has a similar principle with the space-based non-local relationship capturing module, and is different in that the module focuses on the relationship between the channels, and the performance of the network is improved by establishing the non-local relationship among a plurality of groups of channels.
The channel-based non-local relationship capture module comprises the following components: first, the original features are combinedInput to two 1 × 1 convolution operations; the first 1 x 1 convolution is used to remove the channel fromIs compressed toWhereinTo be hyper-parametric and then deforming it intoOf size of(ii) a After the second 1 × 1 convolution operation, the distortion isOf size ofWill beIs transposed with respect toMatrix multiplication is carried out to obtain the value ofIs given as a global reference(ii) a Will be provided withEach column ofActivating the function to obtain a probability matrix; then, the sum of each row of the probability matrix is calculated, which is a functionRepresentation (this operation and solving in a space-based non-local relationship capture ModuleIs similar) to obtain a size ofBased on the global feature mask of the channel,
Then will beAnd input featuresAfter element dot multiplication, andadding to obtain a final output characteristic representation; channel-based non-local relationship capture module final output characteristicsComprises the following steps:
the invention has the technical effects that:
compared with the prior art, the vehicle re-identification method based on the dimensional decoupling and the non-local relation is designed by adopting a global feature extraction mechanism, a non-local relation capture mechanism and a dimensional decoupling mechanism, the global feature extraction mechanism is used for capturing relatively complete and coarse-grained features, the non-local relation capture mechanism is used for respectively extracting significance information from the feature graph obtained by the backbone network on the spatial dimension and the channel dimension, so that the network can extract the features with finer granularity, the space and the channel are thoroughly decoupled by the dimensional decoupling mechanism, and a part of the features are concentrated in a specific subspace. According to the invention, different useful information is respectively extracted through the three branches, and the three branches can assist each other, so that the performance of the model is optimal, and the generalization capability and the network precision of the vehicle weight recognition network are greatly improved.
Drawings
FIG. 1 is a vehicle re-identification network architecture diagram based on dimensional decoupling and non-local relationships in accordance with the present invention;
FIG. 2 is a diagram of a space-based non-local relationship capture module architecture according to the present invention;
FIG. 3 is a diagram of a lane-based non-local relationship capture module architecture according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention are clearly and completely described below with reference to the drawings of the specification.
Example 1:
the embodiment relates to a vehicle re-identification method based on dimension decoupling and non-local relation, which comprises the following steps:
the convolutional neural network Resnet50 is used as a backbone network to enhance the feature extraction capability of the network, the network structure is shown in FIG. 1, partial residual error layers (res _ conv4_ 2-res _ conv5) behind ResNet-50 are copied into three branches with the same structure, and a global feature extraction mechanism, a non-local relationship capture mechanism and a dimension decoupling mechanism are sequentially introduced into each branch behind the residual error layer;
the global feature extraction mechanism is used for extracting global features of the vehicle, called global branches; the global branch inputs the feature graph generated by the res _ conv5 layer to a Global Average Pooling (GAP) and a channel dimension reduction module consisting of 1 × 1 convolution, Batch Normalization (BN) and ReLU activation function in sequence to obtain 256-dimensional feature representation;
the non-local relationship capture mechanism comprises a channel-based non-local relationship capture module and a space-based non-local relationship capture module; firstly, simultaneously inputting the tensor output by the res _ conv5 layer into a space-based non-local relation capturing module and a channel-based non-local relation capturing module, and capturing highly detailed space and channel correlation by adopting a parallel structure; the non-local relation capture module based on the channel and the non-local relation capture module based on the space respectively perform noise reduction on the non-local relation between the channel and the space level, and meanwhile different weights are distributed for the relation between the channels and the positions on the channel and the space level; the mechanism aims to dig out useful non-local relations and further improve the performance of the network. The feature size of the spatial and channel non-local relation capture module is unchanged, the subsequent operation is the same as the global branch, and the dimensionality is reduced from 2048 to 256 through Global Average Pooling (GAP), 1 × 1 convolution, Batch Normalization (BN) and ReLU operation. Because the non-local relations of the input features are not all useful, only the specific non-local relations have a remarkable effect on improving the network precision, but the redundant non-local relations can become interference factors for capturing the features with the identifiability by the network, therefore, the non-local relation capturing mechanism solves the problems that the calculation amount is too large due to the fact that all relations of all positions are calculated by the existing network, the redundant non-local relations occupy calculation resources and interfere the network to capture the features which really play the role of identification, and improves the network precision of the vehicle re-identification network.
The dimension decoupling mechanism is used for stripping mutual interference of information between the channel and the space and decoupling the space and the channel, so that a part of features are concentrated in a specific subspace; the specific operation is that the feature map is firstly divided into two parts from the horizontal direction in the space dimension to obtain two feature maps, and then the two feature maps are averagely decoupled in the channel dimension, namely the two feature maps are respectively divided into two parts in the channel direction, aiming at cutting off redundant channels in the channel dimension in the two spaces, so that the calculated amount is reduced, the relation existing between the spaces and the channels is stripped, and compared with the previous method that each subspace is associated with all the channels, the decoupling branch really extracts the local features from only partial channels and subspaces. In the third branch, as shown in fig. 1, the present invention takes the two gray features in the feature map generated by res _ conv5 as the two decoupled subspaces. After the decoupling operation, the feature extraction operation is independently executed in two subspaces, and the operation is the same as the subsequent operation of the first two branches. Because the hard division strategies are used for simply dividing the input features on the spatial level, the feature information of each region subjected to hard division on the channel dimension is ignored. Because the features to be paid attention to are different among the partitions after hard partitioning, the region of interest in the channel dimension also changes among the partitions. Therefore, the invention adopts a more accurate characteristic capture mode, namely a dimension decoupling mechanism, can reduce most of calculated amount, and effectively breaks through the problem that the information between the subspace and the channel interferes with each other to influence the network precision when the existing hard division strategy extracts fine-grained characteristics.
As shown in fig. 2, the structure of the space-based non-local relationship capture module is as follows: is provided withInput data for a feature extraction module, whereinAndrespectively the width and the height of the input tensor,is the number of channels. Wherein the functionIs input as a pairTo carry outA (a)For adjustable hyper-parameters) depth separable convolution operation with a convolution kernel size ofThen obtainEach size isAnd then deforming both of them intoThen spliced in the spatial dimension to obtainOf the matrix of (a). Let this matrix be a.For the input tensorPerforming 1 × 1 convolution operation, and performing deformation operation to obtainThen multiplying A by the B matrix to determine a non-local relationship and obtain a value ofA matrix of (a); using for each column on the basis of the derived non-local relationActivating functions to obtain a suitable probability matrix:
Has a size ofThen, the sum of each row of the probability matrix is calculated to obtain a weight vectorEach element of the vectorRepresents the firstA weight of each spatial location;expressed as:
space-based non-local relationship captureFinal output characteristics of the moduleComprises the following steps:
in the feature extraction module,function is asA convolution kernel of sizeMay separate the convolutions. The importance of each point is measured by obtaining a global set of key-value distributions using a set of depth-separable convolution operations, and because the size of the convolution kernel isThis means that each convolution fuses all feature points to obtain a global feature representation, and different weights are assigned to different positions. WhereinFor adjustable hyper-parameters, it is found through experimentsThe network achieves optimal performance.
In order to supplement the functions of the non-local relationship capturing module based on the space and improve the performance of the network, the non-local relationship capturing module based on the channel is added in the network, the principle of the non-local relationship capturing module based on the space is similar to that of the non-local relationship capturing module based on the space, the difference is that the module focuses on the relationship between the channels, and the performance of the network is improved by establishing the non-local relationship among a plurality of groups of channels.
As shown in fig. 3, the component structure of the channel-based non-local relationship capture module is: first, the original features are combinedInput to two 1 × 1 convolution operations; the first 1 x 1 convolution is used to remove the channel fromIs compressed to(For adjustable hyper-parameters, the network willSet to 4) and then deformed into(size). After the second 1 × 1 convolution operation, the distortion is(size) Will beIs transposed with respect toMatrix multiplication is carried out to obtain the value ofIs given as a global reference. Will be provided withEach column ofThe function is activated to obtain a probability matrix. Then, the sum of each row of the probability matrix is calculated, which is a functionRepresentation (this operation and solving in a space-based non-local relationship capture ModuleThe operation is similar) to obtain a dimension ofGlobal feature mask based on channel,
Then will beAnd input featuresAfter element dot multiplication, andthe addition yields the final output characteristic representation. Channel-based non-local relationship capture module final output characteristicsComprises the following steps:
in order to improve the learning and identification capability of the network, the invention adopts a cross entropy loss function and a triple loss function to constrain the network:
the invention uses ResNet-50 as backbone network, setting batch size as 16, training number as 450 rounds, and image size as 256 × 256 before inputting into network. In the training phase, the 256-dimensional features after dimension reduction are constrained by utilizing the triplet loss training. In addition, the reduced-dimension features are passed through a full connectivity layer (fc) to convert the 256-dimension features into the number of vehicle IDs for the dataset, and then cross-entropy loss is used for training constraints. In the testing stage, the Euclidean distance is used for carrying out similarity measurement on the vehicle images.
The invention provides a vehicle re-identification network based on dimension decoupling and non-local relation, which is used for a vehicle re-identification task. In both dimension-based decoupling and non-local relationship networks, three branches are used to learn a variety of useful information. The first branch captures relatively complete and coarse-grained features; for the second branch, the significance information of the feature graph obtained by the backbone network is respectively extracted on the space dimension and the channel dimension, so that the network can extract the features with finer granularity. The third branch makes a complete decoupling of the space and the channel, with some features dedicated to a particular one of the subspaces. In general, three branches respectively extract different useful information, and the three branches can assist each other to optimize the performance of the model.
The above embodiments are only specific examples of the present invention, and the scope of the present invention includes but is not limited to the above embodiments, and any suitable changes or modifications by those of ordinary skill in the art, which are consistent with the claims of the present invention, shall fall within the scope of the present invention.
Claims (4)
1. A vehicle re-identification method based on dimension decoupling and non-local relation is characterized in that: the method comprises the following steps: a convolutional neural network Resnet50 is used as a backbone, partial residual error layers behind ResNet-50 are copied into three branches with the same structure, and a global feature extraction mechanism, a non-local relationship capture mechanism and a dimension decoupling mechanism are respectively introduced into the three branches behind the residual error layers;
the global feature extraction mechanism is used for extracting global features of the vehicle, and sequentially inputting feature maps generated by a res _ conv5 layer into a global average pooling module and a channel dimension reduction module consisting of 1 x 1 convolution, batch standardization and a ReLU activation function to obtain 256-dimensional feature representation;
the non-local relationship capturing mechanism comprises a non-local relationship capturing module based on a channel and a non-local relationship capturing module based on a space, wherein the non-local relationship capturing module and the non-local relationship capturing module respectively perform noise reduction on the non-local relationship between the channel and the space level, and meanwhile different weights are distributed for the relationship between the channel and the position on the channel and the space level; the mechanism aims to dig out useful non-local relations so as to improve the performance of the network;
the dimension decoupling mechanism is used for stripping mutual interference of information between the channel and the space and decoupling the space and the channel, so that a part of features are concentrated in a specific subspace;
the composition structure of the space-based non-local relationship capture module is as follows: let X ∈ R C×H×W The method comprises the following steps of inputting a feature extraction module, wherein W and H are the width and the height of an input tensor respectively, and C is the number of channels; wherein the function f (x) is to perform r depth separable convolution operations on input x, the convolution kernel is H × W, then r output features with the size of C × 1 × 1 are obtained, then all the output features are deformed into C × 1, and then the output features are spliced in the space dimension to obtain a C × r matrix, and the matrix is marked as A; g (x) performing 1 × 1 convolution operation on an input tensor x, performing deformation operation to obtain a matrix B of HW × C, and multiplying the matrix B by the matrix A to determine a non-local relationship and obtain a matrix of HW × r; using the softmax activation function for each column based on the derived non-local relations to derive a suitable probability matrix x p :
x p =softmax(f(x)×g(x));
x p Is HW × r, and then sums each row of the probability matrix to obtain a weight vector Q, each element Q of the vector i A weight representing the ith spatial position; q i Expressed as:
space-based non-local relationship capture module final output feature S f Comprises the following steps:
S f =Q*x+x;
in the feature extraction module, the f (x) function is a depth separable convolution with r convolution kernels of size H × W;
the channel-based non-local relationship capture module comprises the following components: firstly, the original characteristic X belongs to R C×H×W Input to two 1 × 1 convolution operations; the first 1 × 1 convolution is used to compress the channel from C to C/g, where g is the hyperparameter, and then deform it to J, the size of HW × C/g; after the second 1 × 1 convolution operation, the transform is K, with dimensions HW × C, and the transpose of K is matrix multiplied by J to obtain a global reference with size C × (C/g), denoted x g (ii) a X is to be g Using the softmax activation function to obtain a probability matrix; then, each row of the probability matrix is summed, this operation being represented by a function α (x), resulting in a channel-based global feature mask M of size C,
M=α(softmax(K T ×J));
then, carrying out element point multiplication on M and the input characteristic x, and then adding the M and the input characteristic x to obtain a final output characteristic representation; channel-based non-local relationship capture module final output feature S f Comprises the following steps:
S f =M*x+x。
2. the method of claim 1 for vehicle re-identification based on dimensional decoupling and non-local relationships, characterized by: the non-local relationship capture mechanism is specifically operative to: simultaneously inputting the tensors output by the res _ conv5 layer into a space-based non-local relation capturing module and a channel-based non-local relation capturing module; the feature size through the spatial and channel non-local relationship capture module is unchanged, and then the dimensionality is reduced from 2048 to 256 through global average pooling, 1 × 1 convolution, batch normalization and ReLU operation.
3. The dimension decoupling and non-local relationship based vehicle re-identification method of claim 1, wherein: the dimension decoupling mechanism is specifically operative to: firstly, dividing a feature map into two parts in the horizontal direction in a space dimension to obtain two feature maps, and then equally dividing the two obtained feature maps into two parts in a channel dimension; after the decoupling operation, independently performing feature extraction operations in two subspaces: the feature map is subjected to global average pooling, 1 × 1 convolution, batch normalization and ReLU operation, and the dimensionality is reduced from 2048 to 256.
4. The method for vehicle re-identification based on dimensional decoupling and non-local relationship as claimed in any one of claims 1-3, wherein: and (3) constraining the network by adopting a cross entropy loss function and a triplet loss function:
using ResNet-50 as a backbone network, setting the batch size to be 16, setting the number of training rounds to be 450 rounds, and adjusting the size of an image to be 256 multiplied by 256 before inputting the image into the network; in the training stage, the 256-dimensional features after dimension reduction are constrained by utilizing triple loss training; in addition, the 256-dimensional features are changed into the number of vehicle IDs of the data set through a full connection layer after the features are subjected to dimension reduction, and then cross entropy loss is used for training and constraining; in the testing stage, the Euclidean distance is used for carrying out similarity measurement on the vehicle images.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210531995.9A CN114663861B (en) | 2022-05-17 | 2022-05-17 | Vehicle re-identification method based on dimension decoupling and non-local relation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210531995.9A CN114663861B (en) | 2022-05-17 | 2022-05-17 | Vehicle re-identification method based on dimension decoupling and non-local relation |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114663861A CN114663861A (en) | 2022-06-24 |
CN114663861B true CN114663861B (en) | 2022-08-26 |
Family
ID=82037194
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210531995.9A Active CN114663861B (en) | 2022-05-17 | 2022-05-17 | Vehicle re-identification method based on dimension decoupling and non-local relation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114663861B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116665019B (en) * | 2023-07-31 | 2023-09-29 | 山东交通学院 | Multi-axis interaction multi-dimensional attention network for vehicle re-identification |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113420742A (en) * | 2021-08-25 | 2021-09-21 | 山东交通学院 | Global attention network model for vehicle weight recognition |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114651284A (en) * | 2019-12-20 | 2022-06-21 | 英特尔公司 | Lightweight multi-branch and multi-scale heavy person identification |
CN113822246B (en) * | 2021-11-22 | 2022-02-18 | 山东交通学院 | Vehicle weight identification method based on global reference attention mechanism |
CN114332919A (en) * | 2021-12-11 | 2022-04-12 | 南京行者易智能交通科技有限公司 | Pedestrian detection method and device based on multi-spatial relationship perception and terminal equipment |
CN114005078B (en) * | 2021-12-31 | 2022-03-29 | 山东交通学院 | Vehicle weight identification method based on double-relation attention mechanism |
CN114398979A (en) * | 2022-01-13 | 2022-04-26 | 四川大学华西医院 | Ultrasonic image thyroid nodule classification method based on feature decoupling |
-
2022
- 2022-05-17 CN CN202210531995.9A patent/CN114663861B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113420742A (en) * | 2021-08-25 | 2021-09-21 | 山东交通学院 | Global attention network model for vehicle weight recognition |
Also Published As
Publication number | Publication date |
---|---|
CN114663861A (en) | 2022-06-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110245665B (en) | Image semantic segmentation method based on attention mechanism | |
Wang et al. | Exploring linear relationship in feature map subspace for convnets compression | |
CN111738143B (en) | Pedestrian re-identification method based on expectation maximization | |
CN113822246B (en) | Vehicle weight identification method based on global reference attention mechanism | |
CN107292225B (en) | Face recognition method | |
CN108416270B (en) | Traffic sign identification method based on multi-attribute combined characteristics | |
CN112580480B (en) | Hyperspectral remote sensing image classification method and device | |
CN109670418B (en) | Unsupervised object identification method combining multi-source feature learning and group sparsity constraint | |
CN107564007B (en) | Scene segmentation correction method and system fusing global information | |
CN114998958B (en) | Face recognition method based on lightweight convolutional neural network | |
CN114005078B (en) | Vehicle weight identification method based on double-relation attention mechanism | |
CN115330643B (en) | Earthquake denoising method based on convolutional neural network and visual transformation neural network | |
CN112084895B (en) | Pedestrian re-identification method based on deep learning | |
CN114663861B (en) | Vehicle re-identification method based on dimension decoupling and non-local relation | |
CN112733590A (en) | Pedestrian re-identification method based on second-order mixed attention | |
CN112766360A (en) | Time sequence classification method and system based on time sequence bidimensionalization and width learning | |
CN112785636A (en) | Multi-scale enhanced monocular depth estimation method | |
CN113222998A (en) | Semi-supervised image semantic segmentation method and device based on self-supervised low-rank network | |
CN112967210B (en) | Unmanned aerial vehicle image denoising method based on full convolution twin network | |
CN114005046A (en) | Remote sensing scene classification method based on Gabor filter and covariance pooling | |
CN113221992A (en) | Based on L2,1Large-scale data rapid clustering method of norm | |
CN115830637B (en) | Method for re-identifying blocked pedestrians based on attitude estimation and background suppression | |
CN116229323A (en) | Human body behavior recognition method based on improved depth residual error network | |
CN116030495A (en) | Low-resolution pedestrian re-identification algorithm based on multiplying power learning | |
Li et al. | POLSAR Target Recognition Using a Feature Fusion Framework Based on Monogenic Signal and Complex-Valued Nonlocal 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 |