Geographic information analysis method and system fusing large model and remote sensing technology
By integrating large models and remote sensing technology, multiple identification models are set up to identify geographical information in remote sensing data, the problem of inaccurate identification in the prior art is solved and the high-accurate geographical information recognition is achieved.
Patent Information
- Application Number
- CN202411422220.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-12
- Publication Date
- 2025-02-18
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
It is difficult for the prior art to accurately identify geographical information such as mountain roads, plain roads, bridges, tunnels, etc. in remote sensing data.
Using a geographic information analysis method that integrates large models and remote sensing technology, a variety of recognition models are set up to calculate recognition values by acquiring remote sensing images, and the image position is determined as a specific geographical feature based on the preset threshold.
Accurate identification of geographical information such as roads, plain roads, bridges, tunnels, etc. in the remote sensing data has been achieved, and the accuracy of geographical information recognition has been improved.
Smart Images
Figure CN119478660A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of remote sensing data analysis and identification, and more specifically, relates to a geographic information analysis method and system integrating a large model and remote sensing technology. Background Art
[0002] Remote sensing data analysis is an important tool for earth observation and environmental monitoring. Its current status reflects technological progress, expansion of data resources and in-depth application in various application fields.
[0003] Multi-source remote sensing data fusion: The sources of remote sensing data are becoming more and more diverse, including satellites, drones, aircraft, ground sensors and other platforms. These data sources cover a variety of sensing technologies such as optics, radar, lidar, thermal infrared, etc., making data fusion an important trend in remote sensing data analysis.
[0004] Support from big data and cloud computing: As the volume of remote sensing data increases, traditional data processing methods are unable to meet the demand. The popularity of big data technology and cloud computing platforms has made the storage, processing and analysis of remote sensing data more efficient.
[0005] However, there is no technical solution in the prior art that can accurately identify mountain roads / plain roads and bridges, mountain roads and plain roads, mountain roads / plain roads and tunnels, and bridges and tunnels in remote sensing data. Summary of the invention
[0006] In order to solve the above technical problems, the present invention proposes a geographic information analysis method integrating a large model and remote sensing technology, comprising:
[0007] Acquire a remote sensing image and extract remote sensing data of the remote sensing image, wherein the remote sensing data includes: pixel reflectance, fluctuation amplitude, reflection intensity, spectral gradient intensity, phase offset value and spectral intensity difference at each position;
[0008] Setting a recognition model for mountain roads / plain roads and bridges, and calculating a first recognition value based on the remote sensing data, when the first recognition value exceeds a first preset threshold, the current position of the remote sensing image is a forest, otherwise it is a bridge;
[0009] Setting a recognition model for mountain roads and plain roads, and calculating a second recognition value based on the remote sensing data, when the second recognition value exceeds a second preset threshold, the current position of the remote sensing image is a mountain road, otherwise it is a plain road;
[0010] Setting a recognition model for mountain roads / plain roads and tunnels, and calculating a third recognition value based on the remote sensing data, when the third recognition value exceeds a third preset threshold, the current position of the remote sensing image is a mountain road / plain road, otherwise it is a tunnel;
[0011] A recognition model for bridges and tunnels is set, and a fourth recognition value is calculated according to the remote sensing data. When the fourth recognition value exceeds a fourth preset threshold, the current position of the remote sensing image is a bridge, otherwise it is a tunnel.
[0012] Furthermore, the identification model of mountain roads / plain roads and bridges includes:
[0013]
[0014] Where W1(x, y) is the first recognition value at the remote sensing image (x, y), n is the number of bands, R i (x, y) is the pixel reflectance in the i-th band at the remote sensing image (x, y), ω i is the weight of the i-th band, A(x, y) is the fluctuation amplitude at the remote sensing image (x, y), B i (x, y) is the reflection intensity of the i-th band at the remote sensing image (x, y), α is the first adjustment factor of the first identification value, L(x, y) is the spectral gradient intensity at the remote sensing image (x, y), which is used to describe the edge characteristics of mountain roads / plain roads and bridges, β is the second adjustment factor of the first identification value of water bodies, x is the horizontal coordinate at the remote sensing image (x, y), and y is the vertical coordinate at the remote sensing image (x, y).
[0015] Furthermore, the identification model of mountain roads and plain roads includes:
[0016]
[0017] Where W2(x, y) is the second identification value at the remote sensing image (x, y), m is the number of bands, φ j is the first weight of the jth band, G(x, y) is the phase offset between the pixel point at the remote sensing image (x, y) and its adjacent terrain, η j is the second weight of the jth band, C j (x, y) is the spectral intensity difference in the jth band at the remote sensing image (x, y), F(x, y) is the spatial frequency change at the remote sensing image (x, y), which is used to describe the characteristic differences of mountain roads or plain roads in different directions, and γ is the adjustment factor of the second recognition value.
[0018] Furthermore, the identification model of mountain roads / plain roads and tunnels includes:
[0019]
[0020] Where W3(x, y) is the third identification value at the remote sensing image (x, y), p is the number of bands, λ k is the first adjustment factor of the kth band, I k (x′, y′) is the radiation intensity value of the kth band at the remote sensing image (x, y), x′ is the horizontal coordinate at the remote sensing image (x, y), y′ is the vertical coordinate at the remote sensing image (x, y), ρ k is the second adjustment factor of the kth band, and Q(x, y) is the relative radiation intensity value between the pixel point at the remote sensing image (x, y) and its adjacent terrain.
[0021] Furthermore, the identification model of the bridge and the tunnel includes:
[0022]
[0023] Wherein, W4(x, y) is the fourth identification value at the remote sensing image (x, y), q is the number of bands, P l (x, y) is the spectral feature of the lth band at the remote sensing image (x, y), μ l is the first adjustment factor of the lth band, Z l (x, y) is the spectral distribution of the lth band at the remote sensing image (x, y), δ l is the second adjustment factor of the lth band, σ is the adjustment factor of the fourth identification value, H(x, y) is the spectral brightness of the lth band at the remote sensing image (x, y), and E(x, y) is the spectral contrast of the lth band at the remote sensing image (x, y).
[0024] The present invention also proposes a geographic information analysis system integrating a large model and remote sensing technology, comprising:
[0025] A data acquisition module is used to acquire remote sensing images and extract remote sensing data of the remote sensing images, wherein the remote sensing data includes: pixel reflectance, fluctuation amplitude, reflection intensity, spectral gradient intensity, phase offset value and spectral intensity difference at each position;
[0026] A first recognition module is used to set a recognition model of mountain roads / plain roads and bridges, and calculate a first recognition value according to the remote sensing data. When the first recognition value exceeds a first preset threshold, the current position of the remote sensing image is a forest, otherwise it is a bridge;
[0027] A second recognition module is used to set a recognition model for mountain roads and plain roads, and calculate a second recognition value according to the remote sensing data. When the second recognition value exceeds a second preset threshold, the current position of the remote sensing image is a mountain road, otherwise it is a plain road;
[0028] a third recognition module, used to set a recognition model of mountain roads / plain roads and tunnels, and calculate a third recognition value according to the remote sensing data, when the third recognition value exceeds a third preset threshold, the current position of the remote sensing image is a mountain road / plain road, otherwise it is a tunnel;
[0029] The fourth recognition module is used to set the recognition model of bridges and tunnels, and calculate a fourth recognition value based on the remote sensing data. When the fourth recognition value exceeds a fourth preset threshold, the current position of the remote sensing image is a bridge, otherwise it is a tunnel.
[0030] Furthermore, the identification model of mountain roads / plain roads and bridges includes:
[0031]
[0032] Where W1(x, y) is the first recognition value at the remote sensing image (x, y), n is the number of bands, R i (x, y) is the pixel reflectance in the i-th band at the remote sensing image (x, y), ω i is the weight of the i-th band, A(x, y) is the fluctuation amplitude at the remote sensing image (x, y), B i (x, y) is the reflection intensity of the i-th band at the remote sensing image (x, y), α is the first adjustment factor of the first identification value, L(x, y) is the spectral gradient intensity at the remote sensing image (x, y), which is used to describe the edge characteristics of mountain roads / plain roads and bridges, β is the second adjustment factor of the first identification value of water bodies, x is the horizontal coordinate at the remote sensing image (x, y), and y is the vertical coordinate at the remote sensing image (x, y).
[0033] Furthermore, the identification model of mountain roads and plain roads includes:
[0034]
[0035] Where W2(x, y) is the second identification value at the remote sensing image (x, y), m is the number of bands, φ j is the first weight of the jth band, G(x, y) is the phase offset between the pixel point at the remote sensing image (x, y) and its adjacent terrain, η j is the second weight of the jth band, C j (x, y) is the spectral intensity difference in the jth band at the remote sensing image (x, y), F(x, y) is the spatial frequency change at the remote sensing image (x, y), which is used to describe the characteristic differences of mountain roads or plain roads in different directions, and γ is the adjustment factor of the second recognition value.
[0036] Furthermore, the identification model of mountain roads / plain roads and tunnels includes:
[0037]
[0038] Where W3(x, 3) is the third identification value at the remote sensing image (x, y), p is the number of bands, λ k is the first adjustment factor of the kth band, I k (x′, y′) is the radiation intensity value of the kth band at the remote sensing image (x, y), x′ is the horizontal coordinate at the remote sensing image (x, y), y′ is the vertical coordinate at the remote sensing image (x, y), ρ k is the second adjustment factor of the kth band, and Q(x, y) is the relative radiation intensity value between the pixel point at the remote sensing image (x, y) and its adjacent terrain.
[0039] Furthermore, the identification model of the bridge and the tunnel includes:
[0040]
[0041] Wherein, W4(x, y) is the fourth identification value at the remote sensing image (x, y), q is the number of bands, P l (x, y) is the spectral feature of the lth band at the remote sensing image (x, y), μ l is the first adjustment factor of the lth band, Z l (x, y) is the spectral distribution of the lth band at the remote sensing image (x, y), δ l is the second adjustment factor of the lth band, σ is the adjustment factor of the fourth identification value, H(x, y) is the spectral brightness of the lth band at the remote sensing image (x, y), and E(x, y) is the spectral contrast of the lth band at the remote sensing image (x, y).
[0042] In general, the above technical solution conceived by the present invention has the following beneficial effects compared with the prior art:
[0043] The present invention can accurately identify mountain roads / plain roads and bridges, mountain roads and plain roads, mountain roads / plain roads and tunnels, and bridges and tunnels in remote sensing data, thereby improving the accuracy of geographic information recognition. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] Figure 1 is a flow chart of the method of embodiment 1 of the present invention;
[0045] Figure 2 It is a structural diagram of the system of embodiment 2 of the present invention. DETAILED DESCRIPTION
[0046] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.
[0047] The method provided by the present invention can be implemented in the following terminal environment, and the terminal may include one or more of the following components: a processor, a storage medium, and a display screen. The storage medium stores at least one instruction, and the instruction is loaded and executed by the processor to implement the method described in the following embodiment.
[0048] The processor may include one or more processing cores. The processor uses various interfaces and lines to connect various parts in the entire terminal, and executes various functions of the terminal and processes data by running or executing instructions, programs, code sets or instruction sets stored in the storage medium, and calling data stored in the storage medium.
[0049] The storage medium may include a random access memory (RAM) or a read-only memory (ROM). The storage medium may be used to store instructions, programs, codes, code sets or instructions.
[0050] The display screen is used to display the user interface of each application.
[0051] In addition, those skilled in the art can understand that the structure of the above terminal does not constitute a limitation on the terminal, and the terminal may include more or fewer components, or combine certain components, or arrange the components differently. For example, the terminal also includes components such as a radio frequency circuit, an input unit, a sensor, an audio circuit, and a power supply, which will not be described in detail here.
[0052] Example 1
[0053] like Figure 1 As shown, an embodiment of the present invention provides a geographic information analysis method integrating a large model and remote sensing technology, including:
[0054] Step 101, acquiring a remote sensing image, and extracting remote sensing data of the remote sensing image, wherein the remote sensing data includes: pixel reflectance, fluctuation amplitude, reflection intensity, spectral gradient intensity, phase offset value, and spectral intensity difference at each position;
[0055] Step 102, setting a recognition model for mountain roads / plain roads and bridges, and calculating a first recognition value based on the remote sensing data, when the first recognition value exceeds a first preset threshold, the current position of the remote sensing image is a forest, otherwise it is a bridge;
[0056] Specifically, the recognition model of mountain roads / plain roads and bridges includes:
[0057]
[0058] Where W1(x, y) is the first recognition value at the remote sensing image (x, y), n is the number of bands, R i (x, y) is the pixel reflectance in the i-th band at the remote sensing image (x, y), ω i is the weight of the i-th band, A(x, y) is the fluctuation amplitude at the remote sensing image (x, y), B i (x, y) is the reflection intensity of the i-th band at the remote sensing image (x, y), α is the first adjustment factor of the first identification value, L(x, y) is the spectral gradient intensity at the remote sensing image (x, y), which is used to describe the edge characteristics of mountain roads / plain roads and bridges, β is the second adjustment factor of the first identification value of water bodies, x is the horizontal coordinate at the remote sensing image (x, y), and y is the vertical coordinate at the remote sensing image (x, y).
[0059] Step 103, setting a recognition model for mountain roads and plain roads, and calculating a second recognition value based on the remote sensing data, when the second recognition value exceeds a second preset threshold, the current position of the remote sensing image is a mountain road, otherwise it is a plain road;
[0060] Specifically, the recognition model of mountain roads and plain roads includes:
[0061]
[0062] Where W2(x, y) is the second identification value at the remote sensing image (x, y), m is the number of bands, φ j is the first weight of the jth band, G(x, y) is the phase offset between the pixel point at the remote sensing image (x, y) and its adjacent terrain, η j is the second weight of the jth band, C j (x, y) is the spectral intensity difference in the jth band at the remote sensing image (x, y), F(x, y) is the spatial frequency change at the remote sensing image (x, y), which is used to describe the characteristic differences of mountain roads or plain roads in different directions, and γ is the adjustment factor of the second recognition value.
[0063] Step 104, setting a recognition model of mountain roads / plain roads and tunnels, and calculating a third recognition value based on the remote sensing data, when the third recognition value exceeds a third preset threshold, the current position of the remote sensing image is a mountain road / plain road, otherwise it is a tunnel;
[0064] Specifically, the recognition model of mountain roads / plain roads and tunnels includes:
[0065]
[0066] Wherein, W3(x, y) is the third identification value at the remote sensing image (x, y), p is the number of bands, λ is the first adjustment factor of the kth band, and I k (x′, y′) is the radiation intensity value of the kth band at the remote sensing image (x, y), x′ is the horizontal coordinate at the remote sensing image (x, y), y′ is the vertical coordinate at the remote sensing image (x, y), ρ k is the second adjustment factor of the kth band, and Q(x, y) is the relative radiation intensity value between the pixel point at the remote sensing image (x, y) and its adjacent terrain.
[0067] Step 105, setting a recognition model for bridges and tunnels, and calculating a fourth recognition value based on the remote sensing data, when the fourth recognition value exceeds a fourth preset threshold, the current position of the remote sensing image is a bridge, otherwise it is a tunnel.
[0068] Specifically, the identification model of the bridge and the tunnel includes:
[0069]
[0070] Wherein, W4(x, y) is the fourth identification value at the remote sensing image (x, y), q is the number of bands, P l (x, y) is the spectral feature of the lth band at the remote sensing image (x, y), μ l is the first adjustment factor of the lth band, Z l (x, y) is the spectral distribution of the lth band at the remote sensing image (x, y), δ l is the second adjustment factor of the lth band, σ is the adjustment factor of the fourth identification value, H(x, y) is the spectral brightness of the lth band at the remote sensing image (x, y), and E(x, y) is the spectral contrast of the lth band at the remote sensing image (x, y).
[0071] Specifically, mountain roads, plain roads, bridges and tunnels are marked to provide reference for users when navigating.
[0072] Example 2
[0073] like Figure 2 As shown, the embodiment of the present invention also provides a geographic information analysis system integrating a large model and remote sensing technology, including:
[0074] A data acquisition module is used to acquire remote sensing images and extract remote sensing data of the remote sensing images, wherein the remote sensing data includes: pixel reflectance, fluctuation amplitude, reflection intensity, spectral gradient intensity, phase offset value and spectral intensity difference at each position;
[0075] A first recognition module is used to set a recognition model of mountain roads / plain roads and bridges, and calculate a first recognition value according to the remote sensing data. When the first recognition value exceeds a first preset threshold, the current position of the remote sensing image is a forest, otherwise it is a bridge;
[0076] Specifically, the recognition model of mountain roads / plain roads and bridges includes:
[0077]
[0078] Where W1(x, y) is the first recognition value at the remote sensing image (x, y), n is the number of bands, R i (x, y) is the pixel reflectance in the i-th band at the remote sensing image (x, y), ω i is the weight of the i-th band, A(x, y) is the fluctuation amplitude at the remote sensing image (x, y), B i (x, y) is the reflection intensity of the i-th band at the remote sensing image (x, y), α is the first adjustment factor of the first identification value, L(x, y) is the spectral gradient intensity at the remote sensing image (x, y), which is used to describe the edge characteristics of mountain roads / plain roads and bridges, β is the second adjustment factor of the first identification value of water bodies, x is the horizontal coordinate at the remote sensing image (x, y), and y is the vertical coordinate at the remote sensing image (x, y).
[0079] A second recognition module is used to set a recognition model for mountain roads and plain roads, and calculate a second recognition value according to the remote sensing data. When the second recognition value exceeds a second preset threshold, the current position of the remote sensing image is a mountain road, otherwise it is a plain road;
[0080] Specifically, the recognition model of mountain roads and plain roads includes:
[0081]
[0082] Where W2(x, y) is the second identification value at the remote sensing image (x, y), m is the number of bands, φ j is the first weight of the jth band, G(x, y) is the phase offset between the pixel point at the remote sensing image (x, y) and its adjacent terrain, η j is the second weight of the jth band, C j (x, y) is the spectral intensity difference in the jth band at the remote sensing image (x, y), F(x, y) is the spatial frequency change at the remote sensing image (x, y), which is used to describe the characteristic differences of mountain roads or plain roads in different directions, and γ is the adjustment factor of the second recognition value.
[0083] a third recognition module, used to set a recognition model of mountain roads / plain roads and tunnels, and calculate a third recognition value according to the remote sensing data, when the third recognition value exceeds a third preset threshold, the current position of the remote sensing image is a mountain road / plain road, otherwise it is a tunnel;
[0084] Specifically, the recognition model of mountain roads / plain roads and tunnels includes:
[0085]
[0086] Where W3(x, y) is the third identification value at the remote sensing image (x, y), p is the number of bands, λ k is the first adjustment factor of the kth band, I k (x′, y′) is the radiation intensity value of the kth band at the remote sensing image (x, y), x′ is the horizontal coordinate at the remote sensing image (x, y), y′ is the vertical coordinate at the remote sensing image (x, y), ρ k is the second adjustment factor of the kth band, and Q(x, y) is the relative radiation intensity value between the pixel point at the remote sensing image (x, y) and its adjacent terrain.
[0087] The fourth recognition module is used to set the recognition model of bridges and tunnels, and calculate a fourth recognition value based on the remote sensing data. When the fourth recognition value exceeds a fourth preset threshold, the current position of the remote sensing image is a bridge, otherwise it is a tunnel.
[0088] Specifically, the identification model of the bridge and the tunnel includes:
[0089]
[0090] Wherein, W4(x, y) is the fourth identification value at the remote sensing image (x, y), q is the number of bands, P l (x, y) is the spectral feature of the lth band at the remote sensing image (x, y), μ l is the first adjustment factor of the lth band, Z l (x, y) is the spectral distribution of the lth band at the remote sensing image (x, y), δ l is the second adjustment factor of the lth band, σ is the adjustment factor of the fourth identification value, H(x, y) is the spectral brightness of the lth band at the remote sensing image (x, y), and E(x, y) is the spectral contrast of the lth band at the remote sensing image (x, y).
[0091] Specifically, mountain roads, plain roads, bridges and tunnels are marked to provide reference for users when navigating.
[0092] Example 3
[0093] The embodiment of the present invention further proposes a storage medium storing a plurality of instructions, wherein the instructions are used to implement the geographic information analysis method integrating a large model with remote sensing technology.
[0094] Optionally, in this embodiment, the above storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.
[0095] Optionally, in this embodiment, the storage medium is configured to store program codes for executing the following steps: Step 101, acquiring a remote sensing image, and extracting remote sensing data of the remote sensing image, wherein the remote sensing data includes: pixel reflectance, fluctuation amplitude, reflection intensity, spectral gradient intensity, phase offset value, and spectral intensity difference at each position;
[0096] Step 102, setting a recognition model for mountain roads / plain roads and bridges, and calculating a first recognition value based on the remote sensing data, when the first recognition value exceeds a first preset threshold, the current position of the remote sensing image is a forest, otherwise it is a bridge;
[0097] Specifically, the recognition model of mountain roads / plain roads and bridges includes:
[0098]
[0099] Where W1(x, y) is the first recognition value at the remote sensing image (x, y), n is the number of bands, R i (x, y) is the pixel reflectance in the i-th band at the remote sensing image (x, y), ω i is the weight of the i-th band, A(x, y) is the fluctuation amplitude at the remote sensing image (x, y), B i (x, y) is the reflection intensity of the i-th band at the remote sensing image (x, y), α is the first adjustment factor of the first identification value, L(x, y) is the spectral gradient intensity at the remote sensing image (x, y), which is used to describe the edge characteristics of mountain roads / plain roads and bridges, β is the second adjustment factor of the first identification value of water bodies, x is the horizontal coordinate at the remote sensing image (x, y), and y is the vertical coordinate at the remote sensing image (x, y).
[0100] Step 103, setting a recognition model for mountain roads and plain roads, and calculating a second recognition value based on the remote sensing data, when the second recognition value exceeds a second preset threshold, the current position of the remote sensing image is a mountain road, otherwise it is a plain road;
[0101] Specifically, the recognition model of mountain roads and plain roads includes:
[0102]
[0103] Where W2(x, y) is the second identification value at the remote sensing image (x, y), m is the number of bands, φ j is the first weight of the jth band, G(x, y) is the phase offset between the pixel point at the remote sensing image (x, y) and its adjacent terrain, η j is the second weight of the jth band, C j (x, y) is the spectral intensity difference in the jth band at the remote sensing image (x, y), F(x, y) is the spatial frequency change at the remote sensing image (x, y), which is used to describe the characteristic differences of mountain roads or plain roads in different directions, and γ is the adjustment factor of the second recognition value.
[0104] Step 104, setting a recognition model of mountain roads / plain roads and tunnels, and calculating a third recognition value based on the remote sensing data, when the third recognition value exceeds a third preset threshold, the current position of the remote sensing image is a mountain road / plain road, otherwise it is a tunnel;
[0105] Specifically, the recognition model of mountain roads / plain roads and tunnels includes:
[0106]
[0107] Where W3(x, y) is the third identification value at the remote sensing image (x, y), p is the number of bands, λ k is the first adjustment factor of the kth band, I k (x′, y′) is the radiation intensity value of the kth band at the remote sensing image (x, y), x′ is the horizontal coordinate at the remote sensing image (x, y), y′ is the vertical coordinate at the remote sensing image (x, y), ρ k is the second adjustment factor of the kth band, and Q(x, y) is the relative radiation intensity value between the pixel point at the remote sensing image (x, y) and its adjacent terrain.
[0108] Step 105, setting a recognition model for bridges and tunnels, and calculating a fourth recognition value based on the remote sensing data, when the fourth recognition value exceeds a fourth preset threshold, the current position of the remote sensing image is a bridge, otherwise it is a tunnel.
[0109] Specifically, the identification model of the bridge and the tunnel includes:
[0110]
[0111] Wherein, w4(x, y) is the fourth identification value at the remote sensing image (x, y), q is the number of bands, P l(x, y) is the spectral feature of the lth band at the remote sensing image (x, y), μ l is the first adjustment factor of the lth band, Z l (x, y) is the spectral distribution of the lth band at the remote sensing image (x, y), δ l is the second adjustment factor of the lth band, σ is the adjustment factor of the fourth identification value, H(x, y) is the spectral brightness of the lth band at the remote sensing image (x, y), and E(x, y) is the spectral contrast of the lth band at the remote sensing image (x, y).
[0112] Specifically, mountain roads, plain roads, bridges and tunnels are marked to provide reference for users when navigating.
[0113] Example 4
[0114] An embodiment of the present invention also proposes an electronic device, including a processor and a storage medium connected to the processor, wherein the storage medium stores a plurality of instructions, and the instructions can be loaded and executed by the processor so that the processor can execute the geographic information analysis method that integrates a large model and remote sensing technology.
[0115] Specifically, the electronic device of this embodiment may be a computer terminal, and the computer terminal may include: one or more processors, and a storage medium.
[0116] Among them, the storage medium can be used to store software programs and modules, such as a geographic information analysis method that integrates a large model and remote sensing technology in an embodiment of the present invention, and the corresponding program instructions / modules. The processor executes various functional applications and data processing by running the software programs and modules stored in the storage medium, that is, realizing the above-mentioned geographic information analysis method that integrates a large model and remote sensing technology. The storage medium may include a high-speed random storage medium, and may also include a non-volatile storage medium, such as one or more magnetic storage systems, flash memory, or other non-volatile solid-state storage media. In some instances, the storage medium may further include a storage medium remotely arranged relative to the processor, and these remote storage media may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0117] The processor can call the information and application program stored in the storage medium through the transmission system to perform the following steps: Step 101, acquiring a remote sensing image, and extracting remote sensing data of the remote sensing image, wherein the remote sensing data includes: pixel reflectivity, fluctuation amplitude, reflection intensity, spectral gradient intensity, phase offset value, and spectral intensity difference at each position;
[0118] Step 102, setting a recognition model for mountain roads / plain roads and bridges, and calculating a first recognition value based on the remote sensing data, when the first recognition value exceeds a first preset threshold, the current position of the remote sensing image is a forest, otherwise it is a bridge;
[0119] Specifically, the recognition model of mountain roads / plain roads and bridges includes:
[0120]
[0121] Where W1(x, y) is the first recognition value at the remote sensing image (x, y), n is the number of bands, R i (x, y) is the pixel reflectance in the i-th band at the remote sensing image (x, y), ω i is the weight of the i-th band, A(x, y) is the fluctuation amplitude at the remote sensing image (x, y), B i (x, y) is the reflection intensity of the i-th band at the remote sensing image (x, y), α is the first adjustment factor of the first identification value, L(x, y) is the spectral gradient intensity at the remote sensing image (x, y), which is used to describe the edge characteristics of mountain roads / plain roads and bridges, β is the second adjustment factor of the first identification value of water bodies, x is the horizontal coordinate at the remote sensing image (x, y), and y is the vertical coordinate at the remote sensing image (x, y).
[0122] Step 103, setting a recognition model for mountain roads and plain roads, and calculating a second recognition value based on the remote sensing data, when the second recognition value exceeds a second preset threshold, the current position of the remote sensing image is a mountain road, otherwise it is a plain road;
[0123] Specifically, the recognition model of mountain roads and plain roads includes:
[0124]
[0125] Where W2(x, y) is the second identification value at the remote sensing image (x, y), m is the number of bands, φ j is the first weight of the jth band, G(x, y) is the phase offset between the pixel point at the remote sensing image (x, y) and its adjacent terrain, η j is the second weight of the jth band, C j (x, y) is the spectral intensity difference in the jth band at the remote sensing image (x, y), F(x, y) is the spatial frequency change at the remote sensing image (x, y), which is used to describe the characteristic differences of mountain roads or plain roads in different directions, and γ is the adjustment factor of the second recognition value.
[0126] Step 104, setting a recognition model of mountain roads / plain roads and tunnels, and calculating a third recognition value based on the remote sensing data, when the third recognition value exceeds a third preset threshold, the current position of the remote sensing image is a mountain road / plain road, otherwise it is a tunnel;
[0127] Specifically, the recognition model of mountain roads / plain roads and tunnels includes:
[0128]
[0129] Where W3(x, y) is the third identification value at the remote sensing image (x, y), p is the number of bands, λ k is the first adjustment factor of the kth band, I k (x′, y′) is the radiation intensity value of the kth band at the remote sensing image (x, y), x′ is the horizontal coordinate at the remote sensing image (x, y), y′ is the vertical coordinate at the remote sensing image (x, y), ρ k is the second adjustment factor of the kth band, and Q(x, y) is the relative radiation intensity value between the pixel point at the remote sensing image (x, y) and its adjacent terrain.
[0130] Step 105, setting a recognition model for bridges and tunnels, and calculating a fourth recognition value based on the remote sensing data, when the fourth recognition value exceeds a fourth preset threshold, the current position of the remote sensing image is a bridge, otherwise it is a tunnel.
[0131] Specifically, the identification model of the bridge and the tunnel includes:
[0132]
[0133] Wherein, W4(x, y) is the fourth identification value at the remote sensing image (x, y), q is the number of bands, P l (x, y) is the spectral feature of the lth band at the remote sensing image (x, y), μ l is the first adjustment factor of the lth band, Z l (x, y) is the spectral distribution of the lth band at the remote sensing image (x, y), δ l is the second adjustment factor of the lth band, σ is the adjustment factor of the fourth identification value, H(x, y) is the spectral brightness of the lth band at the remote sensing image (x, y), and E(x, y) is the spectral contrast of the lth band at the remote sensing image (x, y).
[0134] Specifically, mountain roads, plain roads, bridges and tunnels are marked to provide reference for users when navigating.
[0135] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.
[0136] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0137] In the several embodiments provided by the present invention, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the system embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.
[0138] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0139] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0140] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only storage medium (ROM, Read-Only Memory), random access storage medium (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.
[0141] Obviously, the above embodiments are merely examples for the purpose of clear explanation, and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived therefrom are still within the scope of protection of the invention.
Claims
1. A geographic information analysis method integrating a large model and remote sensing technology, characterized in that: include: Acquire a remote sensing image and extract remote sensing data of the remote sensing image, wherein the remote sensing data includes: pixel reflectance, fluctuation amplitude, reflection intensity, spectral gradient intensity, phase offset value and spectral intensity difference at each position; Setting a recognition model for mountain roads / plain roads and bridges, and calculating a first recognition value based on the remote sensing data, when the first recognition value exceeds a first preset threshold, the current position of the remote sensing image is a forest, otherwise it is a bridge; Setting a recognition model for mountain roads and plain roads, and calculating a second recognition value based on the remote sensing data, when the second recognition value exceeds a second preset threshold, the current position of the remote sensing image is a mountain road, otherwise it is a plain road; Setting a recognition model of mountain roads / plain roads and tunnels, and calculating a third recognition value based on the remote sensing data, when the third recognition value exceeds a third preset threshold, the current position of the remote sensing image is a mountain road / plain road, otherwise it is a tunnel; A recognition model for bridges and tunnels is set, and a fourth recognition value is calculated according to the remote sensing data. When the fourth recognition value exceeds a fourth preset threshold, the current position of the remote sensing image is a bridge, otherwise it is a tunnel.
2. A geographic information analysis method integrating a large model and remote sensing technology as claimed in claim 1, characterized in that: The identification model of mountain roads / plain roads and bridges includes: Where W1(x, y) is the first recognition value at the remote sensing image (x, y), n is the number of bands, R i (x, y) is the pixel reflectance in the i-th band at the remote sensing image (x, y), ω i is the weight of the i-th band, A(x, y) is the fluctuation amplitude at the remote sensing image (x, y), B i (x, y) is the reflection intensity of the i-th band at the remote sensing image (x, y), α is the first adjustment factor of the first identification value, L(x, y) is the spectral gradient intensity at the remote sensing image (x, y), which is used to describe the edge characteristics of mountain roads / plain roads and bridges, β is the second adjustment factor of the first identification value of water bodies, x is the horizontal coordinate at the remote sensing image (x, y), and y is the vertical coordinate at the remote sensing image (x, y).
3. A geographic information analysis method integrating a large model and remote sensing technology as claimed in claim 2, characterized in that: The identification model of mountain roads and plain roads includes: Where W2(x,y) is the second identification value at the remote sensing image (x,y), m is the number of bands, φ j is the first weight of the jth band, G(x, y) is the phase offset between the pixel point at the remote sensing image (x, y) and its adjacent terrain, η j is the second weight of the jth band, C j (x, y) is the spectral intensity difference in the jth band at the remote sensing image (x, y), F(x, y) is the spatial frequency change at the remote sensing image (x, y), which is used to describe the characteristic differences of mountain roads or plain roads in different directions, and γ is the adjustment factor of the second recognition value.
4. A geographic information analysis method integrating a large model and remote sensing technology as claimed in claim 3, characterized in that: The identification model of mountain roads / plain roads and tunnels includes: Where W3(x, y) is the third identification value at the remote sensing image (x, y), p is the number of bands, λ k is the first adjustment factor of the kth band, I k (x′, y′) is the radiation intensity value of the kth band at the remote sensing image (x, y), x′ is the horizontal coordinate at the remote sensing image (x, y), y′ is the vertical coordinate at the remote sensing image (x, y), ρ k is the second adjustment factor of the kth band, and Q(x, y) is the relative radiation intensity value between the pixel point at the remote sensing image (x, y) and its adjacent terrain.
5. A geographic information analysis method integrating a large model and remote sensing technology as claimed in claim 4, characterized in that: The identification model of the bridge and tunnel includes: Where W4(x, y) is the fourth identification value at the remote sensing image (x, y), q is the number of bands, P l (x, y) is the spectral feature of the lth band at the remote sensing image (x, y), μ l is the first adjustment factor of the lth band, Z l (x, y) is the spectral distribution of the lth band at the remote sensing image (x, y), δ l is the second adjustment factor of the lth band, σ is the adjustment factor of the fourth identification value, H(x, y) is the spectral brightness of the lth band at the remote sensing image (x, y), and E(x, y) is the spectral contrast of the lth band at the remote sensing image (x, y).
6. A geographic information analysis method integrating a large model and remote sensing technology as claimed in claim 1, characterized in that: Mountain roads, plain roads, bridges and tunnels are marked to provide reference for users when navigating.
7. A geographic information analysis system integrating large models and remote sensing technology, characterized in that: include: A data acquisition module is used to acquire remote sensing images and extract remote sensing data of the remote sensing images, wherein the remote sensing data includes: pixel reflectivity, fluctuation amplitude, reflection intensity, spectral gradient intensity, phase offset value and spectral intensity difference at each position; A first recognition module is used to set a recognition model of mountain roads / plain roads and bridges, and calculate a first recognition value according to the remote sensing data. When the first recognition value exceeds a first preset threshold, the current position of the remote sensing image is a forest, otherwise it is a bridge; a second recognition module, used to set a recognition model of mountain roads and plain roads, and calculate a second recognition value according to the remote sensing data, when the second recognition value exceeds a second preset threshold value, the current position of the remote sensing image is a mountain road, otherwise it is a plain road; a third recognition module, used to set a recognition model of mountain roads / plain roads and tunnels, and calculate a third recognition value according to the remote sensing data, when the third recognition value exceeds a third preset threshold, the current position of the remote sensing image is a mountain road / plain road, otherwise it is a tunnel; The fourth recognition module is used to set the recognition model of bridges and tunnels, and calculate a fourth recognition value based on the remote sensing data. When the fourth recognition value exceeds a fourth preset threshold, the current position of the remote sensing image is a bridge, otherwise it is a tunnel.
8. A geographic information analysis system integrating a large model and remote sensing technology as claimed in claim 7, characterized in that: The identification model of mountain roads / plain roads and bridges includes: Where W1(x, y) is the first recognition value at the remote sensing image (x, y), n is the number of bands, R i (x, y) is the pixel reflectance in the i-th band at the remote sensing image (x, y), ω i is the weight of the i-th band, A(x, y) is the fluctuation amplitude at the remote sensing image (x, y), B i (x, y) is the reflection intensity of the i-th band at the remote sensing image (x, y), α is the first adjustment factor of the first identification value, L(x, y) is the spectral gradient intensity at the remote sensing image (x, y), which is used to describe the edge characteristics of mountain roads / plain roads and bridges, β is the second adjustment factor of the first identification value of water bodies, x is the horizontal coordinate at the remote sensing image (x, y), and y is the vertical coordinate at the remote sensing image (x, y).
9. A geographic information analysis system integrating a large model and remote sensing technology as claimed in claim 8, characterized in that: The identification model of mountain roads and plain roads includes: Where W2(x, y) is the second identification value at the remote sensing image (x, y), m is the number of bands, φ j is the first weight of the jth band, G(x,y) is the phase offset between the pixel point at the remote sensing image (x, y) and its adjacent terrain, η j is the second weight of the jth band, C j (x, y) is the spectral intensity difference in the jth band at the remote sensing image (x, y), F(x, y) is the spatial frequency change at the remote sensing image (x, y), which is used to describe the characteristic differences of mountain roads or plain roads in different directions, and γ is the adjustment factor of the second recognition value.
10. A geographic information analysis system integrating a large model and remote sensing technology as claimed in claim 9, characterized in that: The identification model of mountain roads / plain roads and tunnels includes: Where W3(x, y) is the third identification value at the remote sensing image (x, y), p is the number of bands, λ k is the first adjustment factor of the kth band, I k (x′, y′) is the radiation intensity value of the kth band at the remote sensing image (x, y), x′ is the horizontal coordinate at the remote sensing image (x, y), y′ is the vertical coordinate at the remote sensing image (x, y), ρ k is the second adjustment factor of the kth band, and Q(x, y) is the relative radiation intensity value between the pixel point at the remote sensing image (x, y) and its adjacent terrain.