CN115272853A - Industrial wasteland identification method and product based on artificial intelligence technology and big data - Google Patents
Industrial wasteland identification method and product based on artificial intelligence technology and big data Download PDFInfo
- Publication number
- CN115272853A CN115272853A CN202210892261.3A CN202210892261A CN115272853A CN 115272853 A CN115272853 A CN 115272853A CN 202210892261 A CN202210892261 A CN 202210892261A CN 115272853 A CN115272853 A CN 115272853A
- Authority
- CN
- China
- Prior art keywords
- industrial
- wasteland
- potential
- surface temperature
- preset threshold
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/176—Urban or other man-made structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- 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
-
- 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
- Y02W—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO WASTEWATER TREATMENT OR WASTE MANAGEMENT
- Y02W90/00—Enabling technologies or technologies with a potential or indirect contribution to greenhouse gas [GHG] emissions mitigation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
- Processing Of Solid Wastes (AREA)
Abstract
The embodiment of the invention provides an industrial abandoned land identification method and product based on an artificial intelligence technology and big data. The industrial waste land identification method provided by the embodiment of the invention adopts a pre-trained industrial waste land identification model to segment a potential industrial waste land from an image to be identified, and then screens out an idle industrial waste land from the potential industrial waste land by utilizing multi-source data (at least comprising people flow thermodynamic data and earth surface temperature data). In the embodiment of the invention, an industrial wasteland identification method with space and time universality and strong operability is formed by relying on a mature artificial intelligence image identification technology and open-source urban big data information and remote sensing data, a mature and efficient industrial wasteland automatic identification technical method is established, and scientific and efficient promotion of theoretical research and landing practice of a series of important strategies such as homeland space planning, urban updating and the like can be practically helped.
Description
Technical Field
The embodiment of the invention relates to the technical field of information processing, in particular to an industrial wasteland identification method and product based on an artificial intelligence technology and big data.
Background
The effective and reasonable reuse of industrial wasteland is an important hand for urban development and industrial transformation under the background of the later industrial era, and the construction of a basic database of the industrial wasteland is one of key technical links. The basic database of the industrial abandoned land needs to be established for identifying the industrial abandoned land, and the technical bottlenecks of the identification of the industrial abandoned land lie in that the land types are complex, the characteristic difference of the remote sensing images of the earth surface is large, and whether the identification target is abandoned is difficult to determine by simply relying on the remote sensing images. In order to obtain a more accurate identification result of industrial waste, it is often necessary to compare multi-temporal images by a manual visual interpretation method and confirm the comparison result by field investigation. Therefore, in the related art, the identification of industrial waste can be performed only at a limited and specific city or area level, and most of the relied key data information is not open source data, so that the acquisition difficulty is high, the application range of the method is too limited, and the mobility at a space and time level is not available.
The industrial wasteland identification methods proposed in the related art are mainly classified into the following two types: the method comprises a high-resolution remote sensing image-based identification method and a multi-source space and non-space information-based identification method.
The industrial wasteland identification method based on the high-resolution remote sensing image is mostly based on the spectral information of the remote sensing image, the industrial wasteland identification is carried out through remote sensing interpretation technologies such as supervision classification and support vector machine, the accuracy rate fluctuation is large, and the difference of the identification accuracy rates of different types of industrial wastelands is large. In addition, although the industrial waste identification method based on the high-resolution remote sensing image has low labor cost and time input cost, the identification result is greatly influenced by the image data, and it is difficult to obtain the open-source high-resolution remote sensing image.
The industrial wasteland identification method based on the multi-source space and non-space information has accurate identification result, but needs a large amount of manpower and time, most of key information is not public information, and the method is difficult to popularize.
Accordingly, there is a need for a new industrial waste identification method.
Disclosure of Invention
Embodiments of the present invention provide a method, an apparatus, an electronic device, a computer-readable storage medium, and a computer program product for identifying industrial wasteland based on an artificial intelligence technique and big data, so as to solve at least some problems in the related art.
The first aspect of the embodiment of the invention provides an industrial wasteland identification method based on an artificial intelligence technology and big data, which comprises the following steps:
inputting an image to be recognized into a pre-trained industrial abandoned land recognition model to obtain a potential industrial abandoned land contained in the image to be recognized;
screening a part of the potential industrial wasteland with human flow heat power lower than a first preset threshold value and surface temperature lower than a second preset threshold value from the potential industrial wasteland, and determining the part of the potential industrial wasteland as an industrial wasteland;
wherein the pre-trained industrial wasteland recognition model pre-learns image features of a sample potential industrial wasteland, the sample potential industrial wasteland comprising: industrial sites and industrial wasteland which are still in operation.
Optionally, the industrial wasteland recognition model is trained according to the following steps:
obtaining a sample potential industrial waste site;
and training the preset semantic segmentation model by utilizing the potential industrial waste of the sample.
Optionally, screening the part of the potential industrial wasteland with low heat of human flow and low surface temperature from the boundary of the potential industrial wasteland comprises:
acquiring the number of people flow and heat in a first preset time period of the potential industrial wasteland;
inputting the people flow heat power number into a GIS platform, and drawing a people flow heat power distribution diagram;
acquiring a surface temperature value of the potential industrial wasteland within a second preset time period;
inputting the surface temperature value into a GIS platform, and drawing a surface temperature distribution map;
and screening parts of the potential industrial wastelands with the pedestrian flow heat power lower than a first preset threshold and the surface temperature lower than a second preset threshold according to the pedestrian flow heat power distribution map, the surface temperature distribution map and the potential industrial wastelands.
Optionally, screening, according to the people flow thermal distribution map, the surface temperature distribution map and the potential industrial wasteland, a part of the potential industrial wasteland with people flow thermal power lower than a first preset threshold and surface temperature lower than a second preset threshold comprises:
screening out a first potential industrial waste area with the flow heat lower than a first preset threshold value according to the flow heat distribution diagram and the potential industrial waste area;
and screening out the part of the potential industrial wasteland with the surface temperature lower than a second preset threshold value according to the surface temperature distribution map and the first potential industrial wasteland.
Optionally, the image to be identified is an open-source low-resolution remote sensing image of the target area.
Optionally, before screening the part of the potential industrial wasteland with the human stream heat power lower than a first preset threshold value and the surface temperature lower than a second preset threshold value, the method further comprises:
dividing the industrial wasteland by using traffic road data to subdivide the boundary of the industrial wasteland;
screening a part of the potential industrial wasteland with human flow heat power lower than a first preset threshold value and surface temperature lower than a second preset threshold value, comprising the following steps:
and screening the part of the potential industrial wasteland with human flow heat power lower than a first preset threshold value and surface temperature lower than a second preset threshold value from the segmented potential industrial wasteland.
A second aspect of an embodiment of the present invention provides an apparatus for identifying an industrial wasteland based on an artificial intelligence technique and big data, the apparatus including:
the identification module is used for inputting the image to be identified into a pre-trained industrial abandoned place identification model to obtain a potential industrial abandoned place contained in the image to be identified;
the screening module is used for screening partial potential industrial wastelands with human flow heat power lower than a first preset threshold and surface temperature lower than a second preset threshold from the potential industrial wastelands to determine the partial potential industrial wastelands as industrial wastelands;
wherein the pre-trained industrial wasteland recognition model pre-learns image features of a sample potential industrial wasteland, the sample potential industrial wasteland comprising: industrial sites still in operation and industrial waste sites.
Optionally, the industrial wasteland recognition model is trained according to the following steps:
obtaining a sample potential industrial wasteland;
and training the preset semantic segmentation model by utilizing the potential industrial waste of the sample.
Optionally, the screening module includes:
the first acquisition submodule is used for acquiring the heat number of people flow in the potential industrial waste place within a first preset time period;
the first drawing submodule is used for inputting the people stream heat power number into a GIS platform and drawing a people stream heat power distribution diagram;
the second obtaining submodule is used for obtaining the surface temperature value of the potential industrial abandoned land within a second preset time period;
the second drawing submodule is used for inputting the surface temperature value into a GIS platform and drawing a surface temperature distribution map;
and the screening submodule is used for screening partial potential industrial wastelands with the pedestrian flow heat power lower than a first preset threshold value and the surface temperature lower than a second preset threshold value according to the pedestrian flow heat power distribution diagram, the surface temperature distribution diagram and the potential industrial wastelands.
Optionally, the screening submodule is specifically configured to:
screening out a first potential industrial wasteland with the flow heat lower than a first preset threshold value according to the flow heat distribution map and the potential industrial wasteland;
and screening out the part of the potential industrial wastelands with the surface temperature lower than a second preset threshold according to the surface temperature distribution map and the first potential industrial wastelands.
Optionally, the image to be identified is an open-source low-resolution remote sensing image of the target area.
Optionally, the apparatus further comprises:
a segmentation module for segmenting the industrial wasteland by using traffic road data to subdivide a boundary of the industrial wasteland;
the screening module is specifically configured to: and screening the part of the potential industrial wasteland with human flow heat power lower than a first preset threshold value and surface temperature lower than a second preset threshold value from the segmented potential industrial wasteland.
A third aspect of the embodiments of the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the steps in the method for identifying industrial waste based on artificial intelligence and big data according to the first aspect of the present invention.
A fourth aspect of the embodiments of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps in the industrial wasteland identification method based on artificial intelligence technology and big data according to the first aspect of the present invention.
A fifth aspect of the embodiments of the present invention provides a computer program product, which includes a computer program/instruction, and when the computer program/instruction is executed by a processor, the computer program/instruction implements the steps of the artificial intelligence technology and big data based industrial wasteland identification method according to the first aspect of the present invention.
The industrial waste land identification method based on the artificial intelligence technology and the big data provided by the embodiment of the invention adopts a pre-trained industrial waste land identification model, divides a potential industrial waste land from an image to be identified, and screens an idle industrial waste land from the potential industrial waste land by utilizing multi-source data (at least comprising people flow thermal data and earth surface temperature data) to serve as an identification result.
In the embodiment of the invention, an industrial wasteland identification method with space and time universality and strong operability is formed by relying on a mature artificial intelligence image identification technology and open-source urban big data information and remote sensing data, a mature and efficient industrial wasteland automatic identification technical method is established, and scientific and efficient promotion of theoretical research and landing practice of a series of important strategies such as homeland space planning, urban updating and the like can be practically helped.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive labor.
FIG. 1 is a flow chart of a method of identifying industrial wasteland in accordance with an embodiment of the present invention;
FIG. 2 is a flow chart of another industrial wasteland identification method according to an embodiment of the present invention;
FIG. 3 is a graphical representation of predicted results of potential industrial wasteland from a particular embodiment of an industrial wasteland identification method of an embodiment of the present invention;
FIG. 4 is a schematic representation of the distribution of thermal forces of a stream of people resulting from a particular embodiment of an industrial wasteland identification method of an embodiment of the present invention;
FIG. 5 is a schematic representation of a surface temperature distribution obtained by a particular embodiment of an industrial wasteland identification method according to an embodiment of the present invention;
fig. 6 is a schematic diagram of an industrial wasteland identification result obtained by a specific embodiment of the industrial wasteland identification method according to the embodiment of the present invention;
fig. 7 is a block diagram showing another industrial wasteland identification apparatus according to the embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
The land use identification and monitoring technology based on the artificial intelligence method and the remote sensing image is rapidly developed on the aspects of training model construction and researching application scenes. The remote sensing image scene classification technology is also gradually opened in the continuously mature process and is combined with multi-source big data, so that the remote sensing image scene classification technology can be widely used in various disciplines.
Based on this, the embodiment of the invention proposes the inventive concept: and identifying a potential industrial wasteland from the image to be identified by utilizing a pre-trained industrial wasteland identification model based on the semantic segmentation model. However, since the image features of the industrial site and the industrial waste site which are still running are not greatly different, and the industrial waste site identification model is difficult to accurately distinguish the two, the embodiment of the present invention further proposes that: and screening the potential industrial wastelands identified by the industrial wasteland identification model based on the human flow heat and the surface temperature to determine the industrial wastelands.
Referring to fig. 1, a flowchart of an industrial wasteland identification method based on an artificial intelligence technique and big data according to an embodiment of the present invention is shown, and specifically, the industrial wasteland identification method provided by the embodiment of the present invention may include the following steps:
s101, inputting an image to be recognized into a pre-trained industrial abandoned place recognition model, and obtaining a potential industrial abandoned place contained in the image to be recognized.
Wherein the pre-trained industrial wasteland recognition model pre-learns image features of a sample potential industrial wasteland, the sample potential industrial wasteland comprising: industrial sites and industrial wasteland which are still in operation.
In the embodiment of the invention, the image to be identified is an open-source low-resolution remote sensing image of the target area. In the embodiment of the invention, after a target area to be recognized (such as a province, a city or a district) is determined, an open-source low-resolution remote sensing image of the area can be obtained and used as an image to be recognized, and a pre-trained industrial abandoned place recognition model is input for recognition.
Considering that the industrial land has obvious differences in surface characteristics from other urban construction lands (such as appearance characteristics of single industrial plants, population distribution characteristics, and significant changes of the surface caused by industrial production facilities), the industrial land can be continuously distinguished from other urban construction lands according to the image characteristics. However, it is difficult to distinguish a still-running industrial site from an already-idle industrial site according to image characteristics. Therefore, in the embodiment of the invention, the pre-trained industrial wasteland recognition model does not distinguish the two potential industrial wastelands, but screens the industrial wasteland from the potential industrial wastelands by means of the subsequent screening step.
The difficulty and the cost for obtaining the high-resolution remote sensing image are high, the data volume for processing the influence of the high-resolution remote sensing image is large, and the processing time is high. The embodiment of the invention provides industrial waste land identification based on an open-source low-resolution remote sensing image. Based on this, in the embodiment of the invention, in the process of model training, the used sample is also an open-source low-resolution remote sensing image in a potential industrial waste area.
And S102, screening partial potential industrial wastelands with human flow heat power lower than a first preset threshold value and surface temperature lower than a second preset threshold value from the potential industrial wastelands, and determining the partial potential industrial wastelands as industrial wastelands.
Considering that the industrial waste which has been left unused must be free of people or only a few people going to and staying, and that the heat radiation generated by industrial waste which is not subjected to industrial production must be significantly lower than that of the industrial waste which is still being produced. Therefore, the embodiment of the invention provides that: the industrial waste land has two remarkable characteristics of low heat of people flow and low surface temperature. Considering that the situation that the industrial production only needs a small amount of personnel to be managed on site due to high automation degree of the industrial production can occur, the invention defines the judgment condition of the industrial wasteland as follows: the magnitude of the thermal mass flow is significantly lower and the maximum value of the surface temperature within the plot is significantly lower than the average surface temperature of the known operating industrial zone.
Thus, the embodiment of the present invention proposes: and selecting the urban people flow thermodynamic data and earth surface temperature inversion data as a basis, and screening the unused industrial waste land from the potential industrial waste land as an identification result.
In an alternative embodiment, the S102 includes the following sub-steps:
and S1021, acquiring the number of people flow and heat in a first preset time period of the potential industrial wasteland.
And S1022, inputting the people stream heat power number into a GIS platform, and drawing a people stream heat power distribution diagram.
And S1023, acquiring a surface temperature value of the potential industrial waste land in a second preset time period.
And S1024, inputting the surface temperature value into a GIS platform, and drawing a surface temperature distribution map.
And S1025, screening partial potential industrial wastelands with the pedestrian flow heat power lower than a first preset threshold and the surface temperature lower than a second preset threshold according to the pedestrian flow heat distribution map, the surface temperature distribution map and the potential industrial wastelands.
In the embodiment of the invention, the corresponding people flow thermodynamic distribution diagram and the earth surface temperature distribution diagram can be obtained by utilizing a Geographic Information System (GIS) platform and obtaining people flow thermodynamic data and earth surface temperature data.
In the embodiment of the invention, the first preset time period can be the working time period of a working day so as to determine the people flow thermodynamic data of the working time period, thereby more accurately screening out the industrial land still running.
In an embodiment of the present invention, the second preset time period may be an operating time period of a general factory to determine a surface temperature of the potential industrial wasteland within the operating time period, so as to accurately reflect whether the potential industrial wasteland is still operating.
In the embodiment of the present invention, the first preset time period and the second preset time period may be the same preset time period or different preset time periods.
In the embodiment of the invention, after the people flow thermal distribution map, the earth surface temperature distribution map and the potential industrial waste land are obtained, the idle industrial waste land can be determined according to the first preset threshold and the second preset threshold.
In the embodiment of the present invention, the first preset threshold and the second preset threshold may be determined by a technician according to an actual situation of the target area. For example: the first preset threshold value can be determined according to the average pedestrian volume of the target area, and the second preset threshold value can be determined according to the average earth surface temperature of the common industrial area in operation in the target area.
Specifically, S1025 includes:
screening out a first potential industrial waste area with the flow heat lower than a first preset threshold value according to the flow heat distribution diagram and the potential industrial waste area; and screening out the part of the potential industrial wasteland with the surface temperature lower than a second preset threshold value according to the surface temperature distribution map and the first potential industrial wasteland.
In the embodiment of the invention, the first round of screening can be carried out by using the human flow thermodynamic data, and the second round of screening can be further carried out by using the surface temperature data, so that the still-operating industrial land is scientifically and efficiently stripped from the identification result of the potential industrial wasteland, and the identification result of the industrial wasteland is obtained.
In an alternative embodiment, the industrial obsolete identification model is trained according to the following steps:
and S1, obtaining a potential industrial waste area of the sample.
In the embodiment of the invention, the potential industrial waste area of the sample is an open-source low-resolution remote sensing image.
Specifically, in the embodiment of the invention, the Sentinel-2A open-source remote sensing image with the pixel resolution of 10 meters is applied to the geographic information system platform, 536 potential industrial wastelands of yellow stone, tangshan and 3 new cities are visually identified, and a sample potential industrial wasteland comprising the still-running industrial wasteland and the industrial wasteland is obtained and used as a data source of the training set.
In the embodiment of the invention, the model training is carried out by using the open-source low-resolution remote sensing image data, so that the data acquisition cost can be reduced, and the model training efficiency and the model processing efficiency can be improved. Therefore, the industrial waste identification method provided by the embodiment of the invention has the advantages of low application cost and strong operability.
In the embodiment of the invention, a 3-waveband false color remote sensing image raster layer formed by fusing RGB wavebands and a sample potential industrial waste raster layer are correspondingly assigned in a GIS platform, a potential industrial waste part is assigned with a value of 1, a non-industrial attribute part is assigned with a value of 0, and the sample is divided into training samples with 256 pixels multiplied by 256 pixels. In order to ensure the subsequent model training effect, the training sample set in the embodiment of the invention meets the following requirements: (1) The method comprises the steps of containing a large number of potential industrial wasteland and non-industrial attribute land with different image characteristics so as to improve the robustness of a model; (2) A sufficient number of training samples are included to ensure that model training does not suffer from overfitting problems. Finally, a training sample set consisting of 1140 tif image samples containing 256 pixel by 256 pixel assignments of potential industrial sites is obtained.
And S2, training the preset semantic segmentation model by utilizing the sample potential industrial waste land.
In the embodiment of the invention, the preset semantic segmentation model can distinguish the region of the target class from the image to be processed.
In the embodiment of the invention, all samples in the training sample set are distributed according to 20-80% to obtain a test set and a training set. Specifically, in the embodiment of the present invention, the preset semantic segmentation model may be an HRNet model. The training of the HRNet model can be understood as two processes of forward propagation and backward propagation, wherein the forward propagation is responsible for inputting the image pair into the network model for calculation and outputting a predicted value, and the backward propagation is responsible for optimizing and adjusting the weight and the biased gradient of each layer.
In the embodiment of the invention, the input of the model is 3-channel 256 × 256 label samples, 2 groups of training samples x and corresponding labels y are randomly extracted from each batch (batch size) in a training set, and sequentially enter each layer in the HRNet model to be operated until the training set traverses one training round (epoch), a category probability distribution graph of each pixel of the image is obtained through Sigmoid function activation, the prediction value of the network is represented as y _ pred, and the whole process is forward propagation of the model. And (3) obtaining an image probability distribution diagram by forward propagation, calculating the difference (loss) between the predicted value y _ pred of the model and the true value y of the data set by using a loss function, wherein the loss is closer to 0, which indicates that the effect of the model is better, otherwise, the loss is worse. The back propagation process can be simply understood as a process of finding the minimum value of the loss function, and a gradient descent algorithm is usually adopted to optimize tens of thousands of parameters in the network, so as to find the optimal parameter combination of the model. In the embodiment of the invention, an Adam optimization algorithm is adopted, 50 times of training iteration is carried out, when the gradient is reduced to be global optimal, the loss function is not reduced, the network realizes the optimal parameter combination, the model training is completed, and the industrial waste land recognition model is obtained.
In the embodiment of the invention, in the training process of the model, the still-running industrial land and the idle industrial waste land are not distinguished, but the still-running industrial land and the idle industrial waste land are unified as a potential industrial waste land part to be assigned with a value of 1, and a non-industrial attribute land part is assigned with a value of 0. Therefore, the obtained industrial waste land identification model is trained, the identified potential industrial waste land comprises the still-running industrial waste land and the idle industrial waste land, and the identification error can be reduced by avoiding the dependence on image features on the running industrial waste land and the idle industrial waste land.
Referring to fig. 2, a flowchart of an industrial wasteland identification method based on an artificial intelligence technique and big data according to an embodiment of the present invention is shown, and specifically, the industrial wasteland identification method provided by the embodiment of the present invention may include the following steps:
s201, inputting the image to be recognized into a pre-trained industrial abandoned place recognition model, and obtaining a potential industrial abandoned place contained in the image to be recognized.
This step is similar to step S101 described above and will not be described herein again.
And S202, dividing the industrial abandoned land by using the traffic road data so as to subdivide the boundary of the industrial abandoned land.
In the embodiment of the invention, due to the problem of the accuracy of the remote sensing image, the prediction identification result cannot reasonably divide a large area of potential industrial waste land through urban roads. It can be understood that the land divided by the main traffic roads of the city is rarely the same plant area or enterprise, so in order to improve the identification accuracy and avoid the situation that a large land is judged to be an industrial waste land due to abnormal values of people flow, heat and power or surface temperature at a certain position in the subsequent screening process, the embodiment of the invention also provides that the vector data of the main traffic roads (including railways, expressways, urban expressways and primary roads) in the target area are used for dividing the identification result of the potential industrial waste land.
S203, screening partial potential industrial wastelands with the human flow heat power lower than a first preset threshold value and the surface temperature lower than a second preset threshold value from the segmented potential industrial wastelands, and determining the partial potential industrial wastelands as industrial wastelands.
This step is similar to step S102 described above and will not be described herein again.
For convenience of understanding, the method for identifying industrial waste based on artificial intelligence technology and big data provided in the embodiment of the present invention is further explained below by a specific embodiment, and it is understood that this embodiment is only used as an example:
the following description will be made in detail by taking the downtown area of the city of tang shan as an example of the target recognition area. And determining a Feng-nan area, a leveling area, a rich area, a Lu-nan area and partial blocks of 5 administrative areas in the Lu-North area as identification target areas according to a layout planning map of urban areas in the center of the Tangshan city and the vector data of administrative area ranges of the Tangshan city. Meanwhile, in order to ensure the accuracy of the result after screening the people flow thermal data and the surface temperature data, the data date used in the embodiment is the data of working days in 12 months in Tangshan City. The working day ensures that the people flow thermal data of the target area cannot be affected by holiday images, so that the situation that the people flow thermal value of the industrial land which is still running is low, and the situation is mixed with industrial waste land; the winter time is selected to ensure that the industrial land still in operation has a significantly higher surface temperature than the industrial wasteland which does not produce thermal radiation due to the thermal radiation produced by the industrial production. Therefore, the remote sensing image, the heat of people flow and the earth surface temperature data of 12, 10 and 2020 months are selected as the image for AI identification of the potential industrial wasteland and the basic data for screening.
First, a remote sensing image of a target area is predicted by using a pre-trained industrial wasteland recognition model, and a prediction result of a potential industrial wasteland is obtained, as shown in fig. 3, wherein a white part represents the potential industrial wasteland.
And then crawling the number of people flow and heat in the working time period of 12 months in 2020 and 10 days in 10 am at 10 days in 00 in 10 months in real time by a crawler in a background of the Baidu map website, performing vectorization calculation after splicing, and importing vector data into a GIS platform. The accuracy of the crawled people flow thermal data is 100 meters multiplied by 100 meters, and after vectorization calculation, the POP value of each vector point in the map layer is the people flow thermal average value within a square range of 1 hectare with the vector point as the center. If the flow heat value is less than 100 persons within the range of 1 hectare with the vector point as the center, the POP value is marked as 0, and the vectorization calculation result is not included, so that the flow heat distribution diagram is obtained, as shown in FIG. 4. According to statistics, the maximum value of the heat of the people flow in the central urban area of the Tangshan city at the time point is 2277 people/hectare, the minimum value of the statistics is 247 people/hectare, and the average value is 888.01 people/hectare.
Subsequently, performing surface temperature inversion on the Landsat8 image in the time period in the prediction range by adopting an atmospheric correction method to obtain a data range of the regional surface temperature of-7.3 ℃ -19.2 ℃, as shown in fig. 5, a surface temperature distribution schematic diagram in the city of tang mountain is shown. Wherein lighter color of each region indicates lower temperature. After the calculation of the industrial land which is determined by combining the people flow thermodynamic data and is still running, if the surface temperature of the land is over 7 ℃, the surface temperature of the land in the area is over high due to the heat radiation formed by self-heating, and the highest value of the surface temperature of the industrial abandoned land at the time point is lower than 7 ℃.
Finally, inputting the identification result of the potential abandoned land in the urban area of the Tangshan city in 2020, 12 months and 10 days, the people flow thermal data and the earth surface temperature data into a GIS platform, and screening out land blocks with the people flow thermal value less than 100 people/hectare and the highest earth surface temperature value less than 7 ℃ in the area to obtain the final identification result of the industrial abandoned land, as shown in FIG. 6, wherein the dark gray part represents that the industrial abandoned land is the result. Through statistics, the total area of 431 industrial abandoned lands is about 24.24 square kilometers, and other geographic information data such as the area of each abandoned land, the longitude and latitude of a central point and the like can be obtained by a GIS layer attribute table.
In the embodiment of the invention, a Sentinel-2A open-source remote sensing image with the pixel resolution of 10 meters is used as a data source to carry out model training and industrial waste land identification, and the identification result of the model is further screened according to multi-source data (at least comprising people stream data, surface temperature data and road data) so as to judge whether the potential industrial waste land obtained by the model is really waste or not more accurately and scientifically and ensure that the identification result is more accurate.
By adopting the industrial wasteland identification method provided by the embodiment of the invention, the identification efficiency can be greatly improved and the manpower and material resources can be saved under the condition of ensuring the accuracy and credibility of the identification result. Meanwhile, the open source resolution data is used as a data base, the data acquisition approach is simple, the technical use threshold is low, and the applicable scene can be effectively expanded.
Based on the same inventive concept, an embodiment of the present invention provides an industrial wasteland identification apparatus based on an artificial intelligence technique and big data, and referring to fig. 7, fig. 7 is a schematic diagram of the industrial wasteland identification apparatus provided by the embodiment of the present invention. As shown in fig. 7, the apparatus includes:
the identification module 701 is used for inputting an image to be identified into a pre-trained industrial abandoned place identification model to obtain a potential industrial abandoned place contained in the image to be identified;
a screening module 702, configured to screen, from the potential industrial wastelands, a part of the potential industrial wastelands where human flow heat is lower than a first preset threshold and a surface temperature is lower than a second preset threshold, and determine the part of the potential industrial wastelands as industrial wastelands;
wherein the pre-trained industrial wasteland recognition model pre-learns image features of a sample potential industrial wasteland, the sample potential industrial wasteland comprising: industrial sites and industrial wasteland which are still in operation.
Optionally, the industrial obsolete identification model is trained according to the following steps:
obtaining a sample potential industrial waste site;
and training the preset semantic segmentation model by utilizing the potential industrial waste of the sample.
Optionally, the screening module 702 includes:
the first acquisition submodule is used for acquiring the heat number of people flow in the potential industrial waste place within a first preset time period;
the first drawing submodule is used for inputting the people stream heat power number into a GIS platform and drawing a people stream heat power distribution diagram;
the second obtaining submodule is used for obtaining the surface temperature value of the potential industrial abandoned land within a second preset time period;
the second drawing submodule is used for inputting the surface temperature value into a GIS platform and drawing a surface temperature distribution map;
and the screening submodule is used for screening partial potential industrial wastelands with the pedestrian flow heat power lower than a first preset threshold value and the surface temperature lower than a second preset threshold value according to the pedestrian flow heat power distribution diagram, the surface temperature distribution diagram and the potential industrial wastelands.
Optionally, the screening submodule is specifically configured to:
screening out a first potential industrial wasteland with the flow heat lower than a first preset threshold value according to the flow heat distribution map and the potential industrial wasteland;
and screening out the part of the potential industrial wasteland with the surface temperature lower than a second preset threshold value according to the surface temperature distribution map and the first potential industrial wasteland.
Optionally, the image to be identified is an open-source low-resolution remote sensing image.
Optionally, the apparatus further comprises:
and the segmentation module is used for segmenting the industrial abandoned land by using the traffic road data so as to subdivide the boundary of the industrial abandoned land.
Based on the same inventive concept, an embodiment of the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to implement the steps of the industrial waste area identification method according to any one of the above embodiments.
Based on the same inventive concept, embodiments of the present invention provide a computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the method for identifying industrial wasteland based on artificial intelligence technology and big data according to any of the above embodiments.
Based on the same inventive concept, embodiments of the present invention provide a computer program product, which includes a computer program/instruction, and when the computer program/instruction is executed by a processor, the computer program/instruction implements the steps of the method for identifying industrial wasteland based on artificial intelligence technology and big data according to any of the above embodiments.
For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the embodiments of the invention.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrases "comprising one of 8230; \8230;" 8230; "does not exclude the presence of additional like elements in a process, method, article, or terminal device that comprises the element.
The method, the device, the electronic device, the computer-readable storage medium and the computer program product for identifying industrial wasteland based on artificial intelligence technology and big data provided by the invention are described in detail, and the principle and the implementation mode of the invention are explained by applying specific examples, and the description of the embodiments is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. An industrial wasteland identification method based on artificial intelligence technology and big data is characterized by comprising the following steps:
inputting an image to be recognized into a pre-trained industrial abandoned land recognition model to obtain a potential industrial abandoned land contained in the image to be recognized;
screening a part of the potential industrial wasteland with human flow heat power lower than a first preset threshold value and surface temperature lower than a second preset threshold value from the potential industrial wasteland, and determining the part of the potential industrial wasteland as an industrial wasteland;
wherein the pre-trained industrial wasteland recognition model pre-learns image features of a sample potential industrial wasteland, the sample potential industrial wasteland comprising: industrial sites still in operation and industrial waste sites.
2. The industrial wasteland recognition method based on artificial intelligence technology and big data as claimed in claim 1, wherein said industrial wasteland recognition model is trained according to the following steps:
obtaining a sample potential industrial waste site;
and training the preset semantic segmentation model by utilizing the sample potential industrial waste.
3. The method for identifying industrial wastelands based on artificial intelligence technology and big data as claimed in claim 1, wherein screening the boundary of the potential industrial wastelands for the part of the potential industrial wastelands with low human stream heat power and low surface temperature comprises:
acquiring the number of people flow and heat in a first preset time period of the potential industrial wasteland;
inputting the people flow heat power number into a GIS platform, and drawing a people flow heat power distribution diagram;
acquiring a surface temperature value of the potential industrial abandoned land within a second preset time period;
inputting the surface temperature value into a GIS platform, and drawing a surface temperature distribution map;
and screening the part of the potential industrial wasteland with the pedestrian flow heat power lower than a first preset threshold and the surface temperature lower than a second preset threshold according to the pedestrian flow heat power distribution diagram, the surface temperature distribution diagram and the potential industrial wasteland.
4. The method for identifying industrial wastelands based on artificial intelligence technology and big data according to claim 3, wherein screening the part of the potential industrial wastelands with the pedestrian heat power lower than a first preset threshold and the surface temperature lower than a second preset threshold according to the pedestrian heat power distribution map, the surface temperature distribution map and the potential industrial wastelands comprises:
screening out a first potential industrial waste area with the flow heat lower than a first preset threshold value according to the flow heat distribution diagram and the potential industrial waste area;
and screening out the part of the potential industrial wasteland with the surface temperature lower than a second preset threshold value according to the surface temperature distribution map and the first potential industrial wasteland.
5. The method for identifying the industrial wasteland based on the artificial intelligence technology and the big data according to any one of claims 1 to 4, wherein the image to be identified is an open source low resolution remote sensing image of the target area.
6. The artificial intelligence technology and big data based industrial wasteland identification method according to any one of claims 1 to 4, wherein before screening a part of the potential industrial wasteland with a human flow heat force lower than a first preset threshold and a surface temperature lower than a second preset threshold from the potential industrial wasteland, the method further comprises:
dividing the industrial wasteland by using traffic road data to subdivide the boundary of the industrial wasteland;
screening a part of the potential industrial wasteland with human flow heat power lower than a first preset threshold value and surface temperature lower than a second preset threshold value, comprising the following steps:
and screening the part of the potential industrial wasteland with the human flow heat power lower than a first preset threshold value and the surface temperature lower than a second preset threshold value from the segmented potential industrial wasteland.
7. An apparatus for identifying industrial wasteland based on artificial intelligence technology and big data, the apparatus comprising:
the identification module is used for inputting the image to be identified into a pre-trained industrial abandoned place identification model to obtain a potential industrial abandoned place contained in the image to be identified;
the screening module is used for screening partial potential industrial wastelands with human flow heat power lower than a first preset threshold and surface temperature lower than a second preset threshold from the potential industrial wastelands to determine the partial potential industrial wastelands as industrial wastelands;
wherein the pre-trained industrial wasteland recognition model pre-learns image features of a sample potential industrial wasteland, the sample potential industrial wasteland comprising: industrial sites and industrial wasteland which are still in operation.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the artificial intelligence and big data based industrial wasteland identification method of any of claims 1 to 6 when executing the program.
9. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, carries out the steps of the method for identifying industrial obsolescence based on artificial intelligence technology and big data according to any one of claims 1 to 6.
10. A computer program product comprising computer programs/instructions, characterized in that the computer programs/instructions, when executed by a processor, implement the steps of the artificial intelligence technology and big data based industrial wasteland identification method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210892261.3A CN115272853B (en) | 2022-07-27 | 2022-07-27 | Industrial abandoned land identification method and product based on artificial intelligence technology and big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210892261.3A CN115272853B (en) | 2022-07-27 | 2022-07-27 | Industrial abandoned land identification method and product based on artificial intelligence technology and big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115272853A true CN115272853A (en) | 2022-11-01 |
| CN115272853B CN115272853B (en) | 2023-06-27 |
Family
ID=83770121
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210892261.3A Active CN115272853B (en) | 2022-07-27 | 2022-07-27 | Industrial abandoned land identification method and product based on artificial intelligence technology and big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115272853B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117408438A (en) * | 2023-12-14 | 2024-01-16 | 中国测绘科学研究院 | Industrial park low-utility land extraction method and system based on multi-source big data |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130108102A1 (en) * | 2011-10-31 | 2013-05-02 | International Business Machines Corporation | Abandoned Object Recognition Using Pedestrian Detection |
| CN108038116A (en) * | 2017-10-24 | 2018-05-15 | 安徽四创电子股份有限公司 | A kind of density of stream of people monitoring method based on GIS |
| CN109101955A (en) * | 2018-09-12 | 2018-12-28 | 北京英视睿达科技有限公司 | Industrial heat anomaly area recognizing method based on Multi-sensor satellite remote sensing |
| CN110263675A (en) * | 2019-06-03 | 2019-09-20 | 武汉联一合立技术有限公司 | A kind of the rubbish target identification system and its recognition methods of community security robot |
| CN111629335A (en) * | 2020-05-29 | 2020-09-04 | 四川亨通网智科技有限公司 | Method and system for realizing real-time people flow thermodynamic diagram of scenic spot based on big data |
| CN112561971A (en) * | 2020-12-16 | 2021-03-26 | 珠海格力电器股份有限公司 | People flow statistical method, device, equipment and storage medium |
| CN113516059A (en) * | 2021-06-23 | 2021-10-19 | 南京华高生态环境遥感技术研究院有限公司 | Solid waste identification method and device, electronic device and storage medium |
| CN113780057A (en) * | 2021-07-23 | 2021-12-10 | 贵州图智信息技术有限公司 | Idle land identification method and device |
| CN114021348A (en) * | 2021-11-05 | 2022-02-08 | 中国矿业大学(北京) | Mining area vegetation carbon sink remote sensing inversion method of fine land utilization type |
| CN114241332A (en) * | 2021-12-17 | 2022-03-25 | 深圳博沃智慧科技有限公司 | Deep learning-based solid waste field identification method and device and storage medium |
-
2022
- 2022-07-27 CN CN202210892261.3A patent/CN115272853B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130108102A1 (en) * | 2011-10-31 | 2013-05-02 | International Business Machines Corporation | Abandoned Object Recognition Using Pedestrian Detection |
| CN108038116A (en) * | 2017-10-24 | 2018-05-15 | 安徽四创电子股份有限公司 | A kind of density of stream of people monitoring method based on GIS |
| CN109101955A (en) * | 2018-09-12 | 2018-12-28 | 北京英视睿达科技有限公司 | Industrial heat anomaly area recognizing method based on Multi-sensor satellite remote sensing |
| CN110263675A (en) * | 2019-06-03 | 2019-09-20 | 武汉联一合立技术有限公司 | A kind of the rubbish target identification system and its recognition methods of community security robot |
| CN111629335A (en) * | 2020-05-29 | 2020-09-04 | 四川亨通网智科技有限公司 | Method and system for realizing real-time people flow thermodynamic diagram of scenic spot based on big data |
| CN112561971A (en) * | 2020-12-16 | 2021-03-26 | 珠海格力电器股份有限公司 | People flow statistical method, device, equipment and storage medium |
| CN113516059A (en) * | 2021-06-23 | 2021-10-19 | 南京华高生态环境遥感技术研究院有限公司 | Solid waste identification method and device, electronic device and storage medium |
| CN113780057A (en) * | 2021-07-23 | 2021-12-10 | 贵州图智信息技术有限公司 | Idle land identification method and device |
| CN114021348A (en) * | 2021-11-05 | 2022-02-08 | 中国矿业大学(北京) | Mining area vegetation carbon sink remote sensing inversion method of fine land utilization type |
| CN114241332A (en) * | 2021-12-17 | 2022-03-25 | 深圳博沃智慧科技有限公司 | Deep learning-based solid waste field identification method and device and storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117408438A (en) * | 2023-12-14 | 2024-01-16 | 中国测绘科学研究院 | Industrial park low-utility land extraction method and system based on multi-source big data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115272853B (en) | 2023-06-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liping et al. | Monitoring and predicting land use and land cover changes using remote sensing and GIS techniques—A case study of a hilly area, Jiangle, China | |
| Ke et al. | A partitioned and asynchronous cellular automata model for urban growth simulation | |
| Al-Sharif et al. | A novel approach for predicting the spatial patterns of urban expansion by combining the chi-squared automatic integration detection decision tree, Markov chain and cellular automata models in GIS | |
| CN116385689B (en) | Visual information management method, system and medium for site pollution data | |
| CN111179244B (en) | Automatic crack detection method based on cavity convolution | |
| Shekhar | Detecting slums from Quick Bird data in Pune using an object oriented approach | |
| CN111127449A (en) | Automatic crack detection method based on encoder-decoder | |
| Alzraiee et al. | Detecting of pavement marking defects using faster R-CNN | |
| Espa et al. | GIS based models and estimation methods for the probability of archaeological site location | |
| Muttaqin et al. | MaxEnt (Maximum Entropy) model for predicting prehistoric cave sites in Karst area of Gunung Sewu, Gunung Kidul, Yogyakarta | |
| CN115272853A (en) | Industrial wasteland identification method and product based on artificial intelligence technology and big data | |
| Prasad et al. | An efficient traffic forecasting system based on spatial data and decision trees. | |
| DOĞAN et al. | Modeling of temporal and spatial changes of land cover and land use by artificial neural networks: Kastamonu sample | |
| Chan et al. | Missing traffic data imputation for artificial intelligence in intelligent transportation systems: Review of methods, limitations, and challenges | |
| Kumar et al. | Urban modelling and forecasting of landuse using SLEUTH model | |
| KR102359902B1 (en) | Crossroads LOS Prediction Method Based on Big Data and AI, and Storage Medium Having the Same | |
| CN117275215A (en) | Urban road congestion space-time prediction method based on graph process neural network | |
| CN116091850A (en) | Mining area land coverage classification model establishment and classification method | |
| Gan et al. | Water Level Classification for Flood Monitoring System Using Convolutional Neural Network | |
| Sinha et al. | Sustainable time series model for vehicular traffic trends prediction in metropolitan network | |
| Shabab et al. | Exploring dmd-type algorithms for modeling signalised intersections | |
| CN115169466A (en) | Method and device for drawing image of land, electronic equipment and computer readable medium | |
| Wang et al. | MATLAB code to estimate landslide volume from single remote sensed image using genetic algorithm and imagery similarity measurement | |
| CN114155447A (en) | Artificial intelligence big data acquisition system | |
| CN114331206A (en) | Point location addressing method and device, electronic equipment and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |