CN116758360B - Land space use management method and system thereof - Google Patents
Land space use management method and system thereof Download PDFInfo
- Publication number
- CN116758360B CN116758360B CN202311053432.4A CN202311053432A CN116758360B CN 116758360 B CN116758360 B CN 116758360B CN 202311053432 A CN202311053432 A CN 202311053432A CN 116758360 B CN116758360 B CN 116758360B
- Authority
- CN
- China
- Prior art keywords
- classification
- feature
- transfer
- land space
- map
- 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
- 238000007726 management method Methods 0.000 title claims abstract description 50
- 239000013598 vector Substances 0.000 claims abstract description 127
- 238000012546 transfer Methods 0.000 claims abstract description 102
- 238000001514 detection method Methods 0.000 claims abstract description 35
- 238000012545 processing Methods 0.000 claims abstract description 23
- 230000000903 blocking effect Effects 0.000 claims abstract description 14
- 238000010586 diagram Methods 0.000 claims description 66
- 239000011159 matrix material Substances 0.000 claims description 32
- 230000004927 fusion Effects 0.000 claims description 29
- 238000000034 method Methods 0.000 claims description 18
- 230000004044 response Effects 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 7
- 238000005457 optimization Methods 0.000 claims description 5
- 230000004913 activation Effects 0.000 claims description 2
- 238000003860 storage Methods 0.000 description 16
- 238000009826 distribution Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 12
- 238000004590 computer program Methods 0.000 description 6
- 239000004973 liquid crystal related substance Substances 0.000 description 6
- 230000002159 abnormal effect Effects 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000001902 propagating effect Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 206010000117 Abnormal behaviour Diseases 0.000 description 1
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- 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
- G06N3/0455—Auto-encoder networks; Encoder-decoder 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
- G06V10/806—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/17—Terrestrial scenes taken from planes or by drones
Abstract
The application discloses a land space use management method and a land space use management system. Firstly, respectively carrying out image blocking processing on a land space planning image and an aerial image, then obtaining a plurality of land space planning image block feature vectors and a plurality of aerial image block feature vectors through a twin detection model, then calculating transfer matrixes among each group of corresponding land space planning image block feature vectors and aerial image block feature vectors to obtain a transfer feature image composed of a plurality of transfer matrixes, then optimizing the transfer feature image through a channel attention module to obtain an optimized classification feature image, and finally, passing the optimized classification feature image through a classifier to obtain a classification result for representing whether the land space is abnormally used. Thus, the management efficiency of the use condition of the land space can be improved.
Description
Technical Field
The application relates to the field of intelligent management, in particular to a land space use management method and a land space use management system.
Background
Traditional land space use management often relies on manual inspection and investigation, and is inefficient and prone to management vulnerabilities.
Accordingly, an optimized geospatial usage management scheme is desired.
Disclosure of Invention
In view of this, the present disclosure provides a method and a system for managing the use of a land space, which can improve the management efficiency of the use condition of the land space.
According to an aspect of the present disclosure, there is provided a geospatial usage management method including:
inputting a land space planning map and an aerial image map;
respectively carrying out image blocking processing on the land space planning map and the aerial image map to obtain a plurality of land space planning image blocks and a plurality of aerial image blocks;
respectively passing the plurality of land space planning image blocks and the plurality of aerial image blocks through a twin detection model comprising a first image encoder and a second image encoder to obtain a plurality of land space planning image block feature vectors and a plurality of aerial image block feature vectors, wherein the first image encoder and the second image encoder are ViT models;
calculating transfer matrixes between the land space planning image block feature vectors and the aerial image block feature vectors corresponding to each group to obtain a transfer feature map composed of a plurality of transfer matrixes;
The transfer feature images pass through a channel attention module to obtain classification feature images;
carrying out smooth response parameterization decoupling fusion on the transfer characteristic diagram and the classification characteristic diagram to obtain an optimized classification characteristic diagram;
and the optimized classification characteristic diagram is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the land space is abnormally used or not.
According to another aspect of the present disclosure, there is provided a geospatial usage management system including:
the data input module is used for inputting a land space planning map and an aerial image map;
the image blocking processing module is used for respectively carrying out image blocking processing on the land space planning map and the aerial image map so as to obtain a plurality of land space planning image blocks and a plurality of aerial image blocks;
the twin detection coding module is used for enabling the plurality of land space planning image blocks and the plurality of aerial image blocks to respectively pass through a twin detection model comprising a first image encoder and a second image encoder to obtain a plurality of land space planning image block feature vectors and a plurality of aerial image block feature vectors, wherein the first image encoder and the second image encoder are ViT models;
The transfer matrix calculation module is used for calculating transfer matrixes between each group of corresponding land space planning image block feature vectors and the aerial image block feature vectors so as to obtain a transfer feature map composed of a plurality of transfer matrixes;
the channel attention coding module is used for passing the transfer characteristic diagram through the channel attention module to obtain a classification characteristic diagram;
the fusion optimization module is used for carrying out smooth response parameterization decoupling fusion on the transfer characteristic diagram and the classification characteristic diagram so as to obtain an optimized classification characteristic diagram;
and the classification module is used for enabling the optimized classification characteristic diagram to pass through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the land space is abnormally used or not.
According to the embodiment of the disclosure, firstly, a land space planning image block feature vector and a plurality of aerial image block feature vectors are obtained through a twin detection model after image blocking processing is respectively carried out on the land space planning image block feature vector and the aerial image block feature vector, then, a transfer matrix between each group of corresponding land space planning image block feature vectors and the aerial image block feature vectors is calculated to obtain a transfer feature map composed of a plurality of transfer matrices, then, the transfer feature map is optimized through a channel attention module to obtain an optimized classification feature map, and finally, the optimized classification feature map is subjected to a classifier to obtain a classification result for representing whether the land space is abnormally used. Thus, the management efficiency of the use condition of the land space can be improved.
Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate exemplary embodiments, features and aspects of the present disclosure and together with the description, serve to explain the principles of the disclosure.
Fig. 1 illustrates an application scenario diagram of a geospatial usage management method according to an embodiment of the present disclosure.
Fig. 2 shows a flowchart of a geospatial usage management method according to an embodiment of the present disclosure.
Fig. 3 shows an architectural diagram of a geospatial usage management method according to an embodiment of the present disclosure.
Fig. 4 shows a flowchart of sub-step S130 of a geospatial usage management method according to an embodiment of the present disclosure.
Fig. 5 shows a flowchart of sub-step S131 of the geospatial usage management method according to an embodiment of the present disclosure.
Fig. 6 shows a flowchart of sub-step S150 of a geospatial usage management method according to an embodiment of the present disclosure.
Fig. 7 illustrates a block diagram of a geospatial usage management system in accordance with an embodiment of the present disclosure.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are also within the scope of the application.
As used in the specification and in the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.
A flowchart is used in the present application to describe the operations performed by a system according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Also, other operations may be added to or removed from these processes.
Various exemplary embodiments, features and aspects of the disclosure will be described in detail below with reference to the drawings. In the drawings, like reference numbers indicate identical or functionally similar elements. Although various aspects of the embodiments are illustrated in the accompanying drawings, the drawings are not necessarily drawn to scale unless specifically indicated.
The word "exemplary" is used herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.
In addition, numerous specific details are set forth in the following detailed description in order to provide a better understanding of the present disclosure. It will be understood by those skilled in the art that the present disclosure may be practiced without some of these specific details. In some instances, methods, means, elements, and circuits well known to those skilled in the art have not been described in detail in order not to obscure the present disclosure.
Fig. 1 illustrates an application scenario diagram of a geospatial usage management method according to an embodiment of the present disclosure. As shown in fig. 1, in this application scenario, first, a land space planning map (for example, D2 illustrated in fig. 1) and an aerial image map (for example, D1 illustrated in fig. 1) are obtained, where the aerial image map may be acquired by an unmanned aerial vehicle (for example, N illustrated in fig. 1), although the present application is merely a schematic view, the aerial image map may also be acquired by other aircraft, such as an aircraft, and then the land space planning map and the aerial image map are input to a server deployed with a land space usage management algorithm (for example, S illustrated in fig. 1), where the server can process the land space planning map and the aerial image map using the land space usage management algorithm to obtain a classification result for indicating whether the land space is abnormally used.
Fig. 2 shows a flowchart of a geospatial usage management method according to an embodiment of the present disclosure. Fig. 3 shows an architectural diagram of a geospatial usage management method according to an embodiment of the present disclosure. As shown in fig. 2 and 3, the geospatial usage management method according to an embodiment of the present application includes the steps of: s110, inputting a land space planning map and an aerial image map; s120, performing image blocking processing on the land space planning map and the aerial image map respectively to obtain a plurality of land space planning image blocks and a plurality of aerial image blocks; s130, enabling the plurality of land space planning image blocks and the plurality of aerial image blocks to respectively pass through a twin detection model comprising a first image encoder and a second image encoder to obtain a plurality of land space planning image block feature vectors and a plurality of aerial image block feature vectors, wherein the first image encoder and the second image encoder are ViT models; s140, calculating transfer matrixes between each group of corresponding land space planning image block feature vectors and the aerial image block feature vectors to obtain a transfer feature map composed of a plurality of transfer matrixes; s150, the transfer feature images pass through a channel attention module to obtain classification feature images; s160, performing smooth response parameterization decoupling fusion on the transfer feature map and the classification feature map to obtain an optimized classification feature map; and S170, enabling the optimized classification characteristic diagram to pass through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the land space is abnormally used or not.
More specifically, in step S110, a land space planning map and an aerial image map are input. The land space map can represent various uses of the land space, including cultivated land, woodland, towns, etc., and accordingly, in a specific example of the present application, the land space map may be a town map of a certain area, which is not limited to the present application. The aerial image map can provide more detailed and comprehensive land space information, such as specific terrain, roads, buildings and the like in the town, and is helpful for finding and positioning abnormal use conditions. Accordingly, in one specific example of the present application, the aerial image map is acquired in the air by an aircraft (e.g., an airplane, an unmanned aerial vehicle).
More specifically, in step S120, the geospatial planning map and the aerial image map are respectively subjected to image blocking processing to obtain a plurality of geospatial planning image blocks and a plurality of aerial image blocks. Since the hidden features of the land space planning map and the aerial image map about town planning in a certain area are small-scale fine feature information, such as feature information of topography, roads, buildings and the like, it is difficult to perform sufficient capturing and extraction. And because of the inherent limitations of convolution operations, pure CNN methods have difficulty learning explicit global and remote semantic information interactions. Therefore, in order to improve the expression capability of the fine features of the land space planning map and the aerial image map, which are hidden in a small scale in relation to the space planning of the town, so as to improve the accuracy of detecting the abnormal use of the land space, the land space planning map and the aerial image map are subjected to image blocking processing to obtain a plurality of land space planning image blocks and a plurality of aerial image blocks.
More specifically, in step S130, the plurality of land space planning image blocks and the plurality of aerial image blocks are respectively passed through a twin detection model including a first image encoder and a second image encoder to obtain a plurality of land space planning image block feature vectors and a plurality of aerial image block feature vectors, wherein the first image encoder and the second image encoder are ViT models. The first image encoder and the second image encoder of the twinning detection model have the same network structure. It should be understood that the image encoder with the same network structure is used for extracting the features of the images, so that feature information of the images with the same network structure, which is not obvious in difference at the image source domain end, can be mined, and the accuracy of the difference comparison of the hidden features of the town planning in the images of the images can be improved, so that the anomaly detection of the land space use condition of the town is facilitated.
Accordingly, in one possible implementation, as shown in fig. 4, the plurality of land space planning image blocks and the plurality of aerial image blocks are respectively passed through a twin detection model including a first image encoder and a second image encoder to obtain a plurality of land space planning image block feature vectors and a plurality of aerial image block feature vectors, where the first image encoder and the second image encoder are ViT models, and include: s131, embedding each of the plurality of land space planning image blocks by using an embedding layer of the first image encoder of the twin detection model to obtain a plurality of land space planning image block embedding vectors, and embedding each of the plurality of aerial image blocks by using an embedding layer of the second image encoder of the twin detection model to obtain a plurality of aerial image block embedding vectors; and S132, passing the plurality of land space planning image block embedding vectors through a converter of the first image encoder of the twinning detection model to obtain the plurality of land space planning image block feature vectors, and passing the plurality of aerial image block embedding vectors through a converter of the second image encoder of the twinning detection model to obtain the plurality of aerial image block feature vectors.
Accordingly, in one possible implementation, as shown in fig. 5, the embedding layer of the first image encoder using the twin detection model respectively embeds each of the plurality of land space planning image blocks to obtain a plurality of land space planning image block embedding vectors, and the embedding layer of the second image encoder using the twin detection model respectively embeds each of the plurality of aerial image blocks to obtain a plurality of aerial image block embedding vectors, including: s1311, expanding a two-dimensional pixel value matrix of each of the plurality of land space planning image blocks into a one-dimensional pixel value vector to obtain a sequence of first one-dimensional pixel value vectors, and expanding a two-dimensional pixel value matrix of each of the plurality of aerial image blocks into a one-dimensional pixel value vector to obtain a sequence of second one-dimensional pixel value vectors; and S1312, performing full-connection encoding on each first one-dimensional pixel value vector in the sequence of first one-dimensional pixel value vectors by using an embedding layer of the first image encoder of the twin detection model to obtain a plurality of land space planning image block embedding vectors, and performing full-connection encoding on each second one-dimensional pixel value vector in the sequence of second one-dimensional pixel value vectors by using an embedding layer of the second image encoder of the twin detection model to obtain a plurality of aerial image block embedding vectors.
More specifically, in step S140, a transfer matrix between each set of corresponding land space planning image block feature vectors and the aerial image block feature vectors is calculated to obtain a transfer feature map composed of a plurality of transfer matrices. The implicit differential correlation characteristic information of each local area in the land space planning map and the aerial image map is represented, so that a transfer characteristic map composed of a plurality of transfer matrixes is obtained, namely, the differential correlation characteristic information of each local area between the land space planning map and the aerial image map is integrated, and the subsequent classification and identification of abnormal behaviors in the land space are facilitated.
Accordingly, in one possible implementation manner, calculating a transfer matrix between each set of corresponding land space planning image block feature vectors and the aerial image block feature vectors to obtain a transfer feature map composed of a plurality of transfer matrices includes: calculating transfer matrixes among each group of corresponding land space planning image block feature vectors and the aerial image block feature vectors according to a transfer matrix calculation formula to obtain a plurality of transfer matrixes; the calculation formula of the transfer matrix is as follows:
Wherein, the liquid crystal display device comprises a liquid crystal display device,andeach set of corresponding land space planning image block feature vectors and aerial image block feature vectors are represented respectively,representing a transfer matrix between each set of corresponding land space planning image block feature vectors and the aerial image block feature vectors,representing vector multiplication; and arranging the plurality of transfer matrixes to obtain the transfer characteristic diagram.
More specifically, in step S150, the diversion feature map is passed through a channel attention module to obtain a classification feature map. The channel attention can focus on the correlation and importance among the characteristic channels, so that the transfer characteristic map is weighted according to the importance of each channel, the channels with important classification results can obtain higher weight values, and channels with unimportant classification results are ignored. Therefore, the differential correlation characteristics focused on planning characteristics of the towns in the two images can be better obtained, so that the space uses of different areas in the towns can be distinguished, and the detection accuracy of the urban land space abnormal use is improved.
Accordingly, in one possible implementation, as shown in fig. 6, the step of passing the diversion feature map through a channel attention module to obtain a classification feature map includes: s151, performing explicit space coding on the transfer feature map by using the channel attention module to obtain a differential correlation feature map; s152, calculating the global average value of each feature matrix of the differential correlation feature map along the channel dimension to obtain a channel feature vector; s153, inputting the channel feature vector into a Sigmoid activation function to obtain a channel attention weighted feature vector; s154, correcting the characteristic value of each position in the channel attention weighted characteristic vector based on the autocovariance matrix of the channel attention weighted characteristic vector to obtain an optimized channel attention weighted characteristic vector; and S155, respectively weighting each feature matrix of the differential correlation feature map along the channel dimension by taking the feature value of each position in the optimized channel attention weighted feature vector as a weight to obtain the classification feature map.
More specifically, in step S160, the transfer feature map and the classification feature map are subjected to smoothing response parameterization decoupling fusion to obtain an optimized classification feature map. When the plurality of land space planning image blocks and the plurality of aerial image blocks are respectively passed through a twin detection model comprising a first image encoder and a second image encoder, due to image semantic difference between the land space planning image block and the aerial image block, when context correlation feature extraction of image segmentation semantics is performed by the image encoder, difference between the plurality of land space planning image block feature vectors and the plurality of aerial image block feature vectors on overall feature distribution is further amplified, so that more significant distribution imbalance exists between overall feature distribution of the plurality of land space planning image block feature vectors and overall feature distribution of the plurality of aerial image block feature vectors, and the difference between the overall feature distribution of the plurality of land space planning image block feature vectors and overall feature distribution of the plurality of aerial image block feature vectors is caused to influence expression consistency of a plurality of transfer matrices obtained by calculating transfer matrices between each corresponding to the land space planning image block feature vectors and the aerial image block feature vectors, so that the transfer feature map composed of the plurality of transfer matrices is caused to deviate from the corresponding feature distribution map of transfer feature vectors on transfer feature dimension by a channel attention module, and thus the classification rule is such that the classification rule is based on the transfer feature distribution And the classification feature map, e.g. noted asPerforming smooth response parameterization decoupling fusion to obtain an optimized classification characteristic diagram, for example, marked as。
Accordingly, in one possible implementation manner, performing smooth response parameterization decoupling fusion on the transfer feature map and the classification feature map to obtain an optimized classification feature map, including: carrying out smooth response parameterization decoupling fusion on the transfer characteristic diagram and the classification characteristic diagram by using a fusion formula to obtain the optimized classification characteristic diagram;
wherein, the fusion formula is:
wherein, the liquid crystal display device comprises a liquid crystal display device,the transfer characteristic map is represented by a graph of the transfer characteristics,the classification characteristic diagram is represented by a graph,representing the transfer characteristic diagramAnd the classification characteristic diagramThe cosine distance between the two,the per-position point multiplication of the feature map is represented,an addition operation representing a feature map is performed,the subtraction of the feature map is represented,is a logarithm based on 2, andand representing the optimized classification characteristic diagram.
Here, the smooth response parameterized decoupling fusion passesDecoupling principle using smooth parameterization function based on the transfer feature mapAnd the classification characteristic diagramNon-negative symmetry of cosine distances between to compile the transfer feature map And the classification characteristic diagramPoint-by-point embedding between features of (1) to infer the transferred feature map with a spatial transformation (transformation) between featuresAnd the classification characteristic diagramInformation distribution transfer (information distribution shift) between the features so as to express information structured fusion of smooth response between the features under the domain transfer feature distribution rule of feature space distribution dimension, thereby improving the optimized classification feature mapAnd the correspondence of the transfer feature map on the domain transfer features belonging to the feature matrix dimension is used for improving the expression effect of the classification feature map.
More specifically, in step S170, the optimized classification feature map is passed through a classifier to obtain a classification result for indicating whether the land space is abnormally used. After the classification result is obtained, the use condition of the land space can be automatically managed and the abnormality is detected based on the classification result, so that corresponding management processing is carried out on the abnormal use region in time.
It should be appreciated that the role of the classifier is to learn the classification rules and classifier using a given class, known training data, and then classify (or predict) the unknown data. Logistic regression (logistics), SVM, etc. are commonly used to solve the classification problem, and for multi-classification problems (multi-class classification), logistic regression or SVM can be used as well, but multiple bi-classifications are required to compose multiple classifications, but this is error-prone and inefficient, and the commonly used multi-classification method is the Softmax classification function.
Accordingly, in one possible implementation, passing the optimized classification feature map through the classifier to obtain a classification loss function value includes: the classifier processes the optimized classification feature map with a classification formula to generate a classification result, wherein the classification formula is:whereinRepresenting the projection of the optimized classification feature map as a vector,to the point ofFor the weight matrix of each full connection layer,to the point ofRepresenting the bias matrix for each fully connected layer.
In summary, according to the land space usage management method of the embodiment of the present application, firstly, a land space planning map and an aerial image map are respectively subjected to image blocking processing, then a plurality of land space planning image block feature vectors and a plurality of aerial image block feature vectors are obtained through a twin detection model, then, a transfer matrix between each group of corresponding land space planning image block feature vectors and aerial image block feature vectors is calculated to obtain a transfer feature map composed of a plurality of transfer matrices, then, the transfer feature map is passed through a channel attention module to obtain a classification feature map, and finally, the optimized classification feature map is passed through a classifier to obtain a classification result for indicating whether a land space is abnormally used. Thus, the management efficiency of the use condition of the land space can be improved.
Fig. 7 shows a block diagram of a geospatial usage management system 100 in accordance with an embodiment of the present disclosure. As shown in fig. 7, the geospatial usage management system 100 according to an embodiment of the present application includes: the data input module 110 is used for inputting a land space planning map and an aerial image map; the image blocking processing module 120 is configured to perform image blocking processing on the land space planning map and the aerial image map respectively to obtain a plurality of land space planning image blocks and a plurality of aerial image blocks; a twin detection encoding module 130, configured to pass the plurality of land space planning image blocks and the plurality of aerial image blocks through a twin detection model including a first image encoder and a second image encoder to obtain a plurality of land space planning image block feature vectors and a plurality of aerial image block feature vectors, where the first image encoder and the second image encoder are ViT models; a transfer matrix calculation module 140, configured to calculate transfer matrices between each set of corresponding land space planning image block feature vectors and the aerial image block feature vectors to obtain a transfer feature map composed of a plurality of transfer matrices; a channel attention encoding module 150, configured to pass the diversion feature map through a channel attention module to obtain a classification feature map; the fusion optimization module 160 is configured to perform smooth response parameterization decoupling fusion on the transfer feature map and the classification feature map to obtain an optimized classification feature map; and a classification module 170, configured to pass the optimized classification feature map through a classifier to obtain a classification result, where the classification result is used to indicate whether the land space is abnormally used.
Accordingly, in one possible implementation, the fusion optimization module 160 is configured to: carrying out smooth response parameterization decoupling fusion on the transfer characteristic diagram and the classification characteristic diagram by using a fusion formula to obtain the optimized classification characteristic diagram;
wherein, the fusion formula is:
wherein, the liquid crystal display device comprises a liquid crystal display device,the transfer characteristic map is represented by a graph of the transfer characteristics,the classification characteristic diagram is represented by a graph,representing the transfer characteristic diagramAnd the classification characteristic diagramThe cosine distance between the two,the per-position point multiplication of the feature map is represented,an addition operation representing a feature map is performed,the subtraction of the feature map is represented,is a logarithm based on 2, andand representing the optimized classification characteristic diagram.
Accordingly, in one possible implementation, the classification module 170 includes:
the classifier processes the optimized classification feature map with a classification formula to generate a classification result, wherein the classification formula is:whereinRepresenting the projection of the optimized classification feature map as a vector,to the point ofFor the weight matrix of each full connection layer,to the point ofRepresenting the bias matrix for each fully connected layer.
Here, it will be understood by those skilled in the art that the specific functions and operations of the respective units and modules in the above-described geospatial usage management system 100 have been described in detail in the above description of the geospatial usage management method with reference to fig. 1 to 6, and thus, repetitive descriptions thereof will be omitted.
As described above, the geospatial usage management system 100 according to an embodiment of the present application may be implemented in various wireless terminals, for example, a server or the like having a geospatial usage management algorithm. In one possible implementation, the geospatial usage management system 100 according to an embodiment of the present application may be integrated into a wireless terminal as one software module and/or hardware module. For example, the geospatial usage management system 100 may be a software module in the operating system of the wireless terminal or may be an application developed for the wireless terminal; of course, the geospatial usage management system 100 could equally be one of a number of hardware modules of the wireless terminal.
Alternatively, in another example, the geospatial usage management system 100 and the wireless terminal may be separate devices, and the geospatial usage management system 100 may be connected to the wireless terminal through a wired and/or wireless network and transmit interactive information in a agreed data format.
In an exemplary embodiment, a non-transitory computer readable storage medium is also provided, such as a memory including computer program instructions executable by a processing component of an apparatus to perform the above-described method.
The present disclosure may be a system, method, and/or computer program product. The computer program product may include a computer readable storage medium having computer readable program instructions embodied thereon for causing a processor to implement aspects of the present disclosure.
The computer readable storage medium may be a tangible device that can hold and store instructions for use by an instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: portable computer disks, hard disks, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static Random Access Memory (SRAM), portable compact disk read-only memory (CD-ROM), digital Versatile Disks (DVD), memory sticks, floppy disks, mechanical coding devices, punch cards or in-groove structures such as punch cards or grooves having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media, as used herein, are not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., optical pulses through fiber optic cables), or electrical signals transmitted through wires.
The computer readable program instructions described herein may be downloaded from a computer readable storage medium to a respective computing/processing device or to an external computer or external storage device over a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmissions, wireless transmissions, routers, firewalls, switches, gateway computers and/or edge servers. The network interface card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium in the respective computing/processing device.
Computer program instructions for performing the operations of the present disclosure can be assembly instructions, instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, c++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions may be executed entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, aspects of the present disclosure are implemented by personalizing electronic circuitry, such as programmable logic circuitry, field Programmable Gate Arrays (FPGAs), or Programmable Logic Arrays (PLAs), with state information of computer readable program instructions, which can execute the computer readable program instructions.
Various aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.
These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer readable medium having the instructions stored therein includes an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.
The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The foregoing description of the embodiments of the present disclosure has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the improvement of technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (8)
1. A method of geospatial use management comprising:
inputting a land space planning map and an aerial image map;
respectively carrying out image blocking processing on the land space planning map and the aerial image map to obtain a plurality of land space planning image blocks and a plurality of aerial image blocks;
respectively passing the plurality of land space planning image blocks and the plurality of aerial image blocks through a twin detection model comprising a first image encoder and a second image encoder to obtain a plurality of land space planning image block feature vectors and a plurality of aerial image block feature vectors, wherein the first image encoder and the second image encoder are ViT models;
Calculating transfer matrixes between the land space planning image block feature vectors and the aerial image block feature vectors corresponding to each group to obtain a transfer feature map composed of a plurality of transfer matrixes;
the transfer feature images pass through a channel attention module to obtain classification feature images;
carrying out smooth response parameterization decoupling fusion on the transfer characteristic diagram and the classification characteristic diagram to obtain an optimized classification characteristic diagram;
the optimized classification characteristic diagram passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the land space is abnormally used or not;
the step of performing smooth response parameterization decoupling fusion on the transfer feature map and the classification feature map to obtain an optimized classification feature map comprises the following steps: carrying out smooth response parameterization decoupling fusion on the transfer characteristic diagram and the classification characteristic diagram by using a fusion formula to obtain the optimized classification characteristic diagram;
wherein, the fusion formula is:
wherein (1)>Representing the transfer profile,/->Representing the classification characteristic map,>representing the transfer profile->And the classification characteristic map->Cosine distance between>By position point multiplication representing a feature map, +. >Addition representing a feature map, ++>Subtracting operation representing feature map, ++>Is a logarithm based on 2, and/>and representing the optimized classification characteristic diagram.
2. The geospatial usage management method according to claim 1, wherein passing the plurality of geospatial planning image blocks and the plurality of aerial image blocks through a twin detection model comprising a first image encoder and a second image encoder to obtain a plurality of geospatial planning image block feature vectors and a plurality of aerial image block feature vectors, respectively, wherein the first image encoder and the second image encoder are ViT models, comprising:
embedding each of the plurality of land space planning image blocks by using an embedding layer of the first image encoder of the twin detection model to obtain a plurality of land space planning image block embedding vectors, and embedding each of the plurality of aerial image blocks by using an embedding layer of the second image encoder of the twin detection model to obtain a plurality of aerial image block embedding vectors;
the method further comprises the steps of passing the plurality of land space planning image block embedding vectors through a converter of the first image encoder of the twin detection model to obtain the plurality of land space planning image block feature vectors, and passing the plurality of aerial image block embedding vectors through a converter of the second image encoder of the twin detection model to obtain the plurality of aerial image block feature vectors.
3. The geospatial usage management method according to claim 2, wherein embedding each of the plurality of geospatial planning image blocks with the embedding layer of the first image encoder of the twinning detection model to obtain a plurality of geospatial planning image block embedding vectors, respectively, and embedding each of the plurality of aerial image blocks with the embedding layer of the second image encoder of the twinning detection model to obtain a plurality of aerial image block embedding vectors, respectively, comprises:
expanding a two-dimensional pixel value matrix of each of the plurality of land space planning image blocks into a one-dimensional pixel value vector to obtain a sequence of first one-dimensional pixel value vectors, and expanding a two-dimensional pixel value matrix of each of the plurality of aerial image blocks into a one-dimensional pixel value vector to obtain a sequence of second one-dimensional pixel value vectors;
and performing full-connection encoding on each first one-dimensional pixel value vector in the sequence of first one-dimensional pixel value vectors by using an embedding layer of the first image encoder of the twin detection model to obtain a plurality of land space planning image block embedding vectors, and performing full-connection encoding on each second one-dimensional pixel value vector in the sequence of second one-dimensional pixel value vectors by using an embedding layer of the second image encoder of the twin detection model to obtain a plurality of aerial image block embedding vectors.
4. A geospatial usage management method according to claim 3, in which calculating transfer matrices between each corresponding set of the geospatial planning image block feature vectors and the aerial image block feature vectors to obtain a transfer feature map consisting of a plurality of transfer matrices, comprises:
calculating transfer matrixes among each group of corresponding land space planning image block feature vectors and the aerial image block feature vectors according to a transfer matrix calculation formula to obtain a plurality of transfer matrixes;
the calculation formula of the transfer matrix is as follows:
wherein (1)>And->Respectively representing each group of corresponding land space planning image block characteristic vectors and aerial image block characteristic vectors,/for>Representing a transfer matrix between each corresponding set of said geospatial planning image block feature vectors and said aerial image block feature vectors +.>Representing vector multiplication;
and arranging the plurality of transfer matrixes to obtain the transfer characteristic diagram.
5. The geospatial usage management method according to claim 4 wherein passing the diversion feature map through a channel attention module to obtain a classification feature map comprises:
Using the channel attention module to carry out explicit space coding on the transfer characteristic diagram so as to obtain a differential correlation characteristic diagram;
calculating the global average value of each feature matrix of the differential correlation feature map along the channel dimension to obtain a channel feature vector;
inputting the channel feature vector into a Sigmoid activation function to obtain a channel attention weighted feature vector;
correcting the feature values of each position in the channel attention weighted feature vector based on the auto-covariance matrix of the channel attention weighted feature vector to obtain an optimized channel attention weighted feature vector;
and respectively weighting each feature matrix of the differential correlation feature map along the channel dimension by taking the feature value of each position in the optimized channel attention weighted feature vector as a weight to obtain the classification feature map.
6. The geospatial usage management method according to claim 5, wherein passing the optimized classification feature map through a classifier to obtain a classification result comprises:
the classifier processes the optimized classification feature map with a classification formula to generate a classification result, wherein the classification formula is: Wherein->Representing the projection of the optimized classification feature map as a vector,/->To->Weight matrix for all connection layers of each layer, < ->To->Representing the bias matrix for each fully connected layer.
7. A geospatial use management system comprising:
the data input module is used for inputting a land space planning map and an aerial image map;
the image blocking processing module is used for respectively carrying out image blocking processing on the land space planning map and the aerial image map so as to obtain a plurality of land space planning image blocks and a plurality of aerial image blocks;
the twin detection coding module is used for enabling the plurality of land space planning image blocks and the plurality of aerial image blocks to respectively pass through a twin detection model comprising a first image encoder and a second image encoder to obtain a plurality of land space planning image block feature vectors and a plurality of aerial image block feature vectors, wherein the first image encoder and the second image encoder are ViT models;
the transfer matrix calculation module is used for calculating transfer matrixes between each group of corresponding land space planning image block feature vectors and the aerial image block feature vectors so as to obtain a transfer feature map composed of a plurality of transfer matrixes;
The channel attention coding module is used for passing the transfer characteristic diagram through the channel attention module to obtain a classification characteristic diagram;
the fusion optimization module is used for carrying out smooth response parameterization decoupling fusion on the transfer characteristic diagram and the classification characteristic diagram so as to obtain an optimized classification characteristic diagram;
the classification module is used for enabling the optimized classification feature map to pass through a classifier to obtain a classification result, and the classification result is used for indicating whether the land space is abnormally used or not;
the fusion optimization module is used for: carrying out smooth response parameterization decoupling fusion on the transfer characteristic diagram and the classification characteristic diagram by using a fusion formula to obtain the optimized classification characteristic diagram;
wherein, the fusion formula is:
wherein (1)>Representing the transfer profile,/->Representing the classification characteristic map,>representing the transfer profile->And the classification bitsSyndrome/pattern of->Cosine distance between>By position point multiplication representing a feature map, +.>Addition representing a feature map, ++>Subtracting operation representing feature map, ++>Is a logarithm based on 2, and +.>And representing the optimized classification characteristic diagram.
8. The geospatial usage management system according to claim 7 wherein the classification module comprises:
The classifier processes the optimized classification feature map with a classification formula to generate a classification result, wherein the classification formula is:wherein->Representing the projection of the optimized classification feature map as a vector,/->To->Weight matrix for all connection layers of each layer, < ->To->Representing the bias matrix for each fully connected layer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311053432.4A CN116758360B (en) | 2023-08-21 | 2023-08-21 | Land space use management method and system thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311053432.4A CN116758360B (en) | 2023-08-21 | 2023-08-21 | Land space use management method and system thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116758360A CN116758360A (en) | 2023-09-15 |
| CN116758360B true CN116758360B (en) | 2023-10-20 |
Family
ID=87961332
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311053432.4A Active CN116758360B (en) | 2023-08-21 | 2023-08-21 | Land space use management method and system thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116758360B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117315749A (en) * | 2023-09-25 | 2023-12-29 | 惠州市沃生照明有限公司 | Intelligent light regulation and control method and system for desk lamp |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111539296A (en) * | 2020-04-17 | 2020-08-14 | 河海大学常州校区 | Method and system for identifying illegal building based on remote sensing image change detection |
| CN114239250A (en) * | 2021-11-24 | 2022-03-25 | 新泰市国土空间规划服务中心(新泰市建筑设计院、新泰市水利设计院) | System and method for territorial space planning design |
| CN114821340A (en) * | 2022-06-01 | 2022-07-29 | 河南大学 | Land utilization classification method and system |
| CN114842343A (en) * | 2022-05-17 | 2022-08-02 | 武汉理工大学 | ViT-based aerial image identification method |
| CN115187127A (en) * | 2022-07-27 | 2022-10-14 | 重庆市规划和自然资源信息中心 | Detailed planning hierarchical management intelligent detection method based on spatial analysis |
| CN115424059A (en) * | 2022-08-24 | 2022-12-02 | 珠江水利委员会珠江水利科学研究院 | Remote sensing land use classification method based on pixel level comparison learning |
| CN115545166A (en) * | 2022-10-31 | 2022-12-30 | 南京信息工程大学 | Improved ConvNeXt convolutional neural network and remote sensing image classification method thereof |
| CN115964599A (en) * | 2022-12-07 | 2023-04-14 | 中国测绘科学研究院 | Large-scale land utilization/coverage change transfer matrix device and using method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11657230B2 (en) * | 2020-06-12 | 2023-05-23 | Adobe Inc. | Referring image segmentation |
-
2023
- 2023-08-21 CN CN202311053432.4A patent/CN116758360B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111539296A (en) * | 2020-04-17 | 2020-08-14 | 河海大学常州校区 | Method and system for identifying illegal building based on remote sensing image change detection |
| CN114239250A (en) * | 2021-11-24 | 2022-03-25 | 新泰市国土空间规划服务中心(新泰市建筑设计院、新泰市水利设计院) | System and method for territorial space planning design |
| CN114842343A (en) * | 2022-05-17 | 2022-08-02 | 武汉理工大学 | ViT-based aerial image identification method |
| CN114821340A (en) * | 2022-06-01 | 2022-07-29 | 河南大学 | Land utilization classification method and system |
| CN115187127A (en) * | 2022-07-27 | 2022-10-14 | 重庆市规划和自然资源信息中心 | Detailed planning hierarchical management intelligent detection method based on spatial analysis |
| CN115424059A (en) * | 2022-08-24 | 2022-12-02 | 珠江水利委员会珠江水利科学研究院 | Remote sensing land use classification method based on pixel level comparison learning |
| CN115545166A (en) * | 2022-10-31 | 2022-12-30 | 南京信息工程大学 | Improved ConvNeXt convolutional neural network and remote sensing image classification method thereof |
| CN115964599A (en) * | 2022-12-07 | 2023-04-14 | 中国测绘科学研究院 | Large-scale land utilization/coverage change transfer matrix device and using method |
Non-Patent Citations (3)
| Title |
|---|
| Xiaoting Rui.A new version of transfer matrix method for multibody systems.Multibody System Dynamics.2016,全文. * |
| 朱岩彬 ; 徐启恒 ; 杨俊涛 ; 莫海林 ; .基于全卷积神经网络的高分辨率航空影像建筑物提取方法研究.地理信息世界.2020,(第02期),全文. * |
| 项明钧.基于电信大数据的城市功能分区及异常检测算法实现.中国优秀硕士学位论文全文数据库.2021,全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116758360A (en) | 2023-09-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | A unified convolutional neural network integrated with conditional random field for pipe defect segmentation | |
| US10885383B2 (en) | Unsupervised cross-domain distance metric adaptation with feature transfer network | |
| US20200327363A1 (en) | Image retrieval method and apparatus | |
| CN109740588B (en) | X-ray picture contraband positioning method based on weak supervision and deep response redistribution | |
| US10824674B2 (en) | Label propagation in graphs | |
| CN112424769A (en) | System and method for geographic location prediction | |
| Tian et al. | Weakly-supervised nucleus segmentation based on point annotations: A coarse-to-fine self-stimulated learning strategy | |
| US11255678B2 (en) | Classifying entities in digital maps using discrete non-trace positioning data | |
| CN111488873B (en) | Character level scene text detection method and device based on weak supervision learning | |
| CN116758360B (en) | Land space use management method and system thereof | |
| US20220092407A1 (en) | Transfer learning with machine learning systems | |
| CN115244587A (en) | Efficient ground truth annotation | |
| WO2023001059A1 (en) | Detection method and apparatus, electronic device and storage medium | |
| CN108154153B (en) | Scene analysis method and system and electronic equipment | |
| CN113129311A (en) | Label optimization point cloud example segmentation method | |
| CN116451139A (en) | Live broadcast data rapid analysis method based on artificial intelligence | |
| Oga et al. | River state classification combining patch-based processing and CNN | |
| CN104077765A (en) | Image segmentation device, image segmentation method and program | |
| CN115482436B (en) | Training method and device for image screening model and image screening method | |
| CN116258877A (en) | Land utilization scene similarity change detection method, device, medium and equipment | |
| CN114241411B (en) | Counting model processing method and device based on target detection and computer equipment | |
| CN113255819B (en) | Method and device for identifying information | |
| US20240071056A1 (en) | Percentile-based pseudo-label selection for multi-label semi-supervised classification | |
| WO2022180705A1 (en) | Information acquisition device, information acquisition method, and information acquisition program | |
| EP4345689A1 (en) | Evaluation and training methods for unsupervised representation encoders |
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 |