Urban greening management method and system

Abstract

The invention provides an urban greening management method and system, and relates to the technical field of urban greening management, and the method comprises the steps: obtaining a growth monitoring video of an urban green belt; based on the growth monitoring video of the urban green belt, using a variational auto-encoder to generate a subsequent growth video of the urban green belt; inputting a subsequent growth video of the urban green belt into a target image frame determination model to obtain a target image frame; determining the time position of the target image frame in the subsequent growth video of the urban green belt based on the target image frame and the subsequent growth video of the urban green belt; and the greening pruning time of the urban green belt is determined based on the time position of the target image frame in the subsequent growth video of the urban green belt, so that the construction time of the urban green belt can be accurately determined, and the management efficiency of the urban green belt is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of urban greening management, and in particular to an urban greening management method and system. Background Art

[0002] Urban greening is an important part of modern urban planning and management. It not only beautifies the urban environment, but also improves air quality, regulates urban microclimate, and reduces noise pollution. With the acceleration of urbanization, how to efficiently manage and maintain urban green belts has become a challenge facing urban management. Traditional urban greening management methods rely on regular manual inspections, which is time-consuming and inefficient, and cannot meet the management needs of large-scale urban greening.

[0003] Therefore, how to accurately determine the construction time of urban green belts and improve the management efficiency of urban green belts is an urgent problem to be solved. Summary of the invention

[0004] The main technical problem solved by the present invention is how to accurately determine the construction time of urban green belts and improve the management efficiency of urban green belts.

[0005] According to a first aspect, the present invention provides an urban greening management method, comprising: obtaining a growth monitoring video of an urban green belt; generating a subsequent growth video of the urban green belt using a variational autoencoder based on the growth monitoring video of the urban green belt; inputting the subsequent growth video of the urban green belt into a target image frame determination model to obtain a target image frame; determining a time position of the target image frame in the subsequent growth video of the urban green belt based on the target image frame and the subsequent growth video of the urban green belt; and determining a greening pruning time of the urban green belt based on the time position of the target image frame in the subsequent growth video of the urban green belt.

[0006] In a possible implementation, the target image frame determination model is a gated recurrent unit, the input of the target image frame determination model is a subsequent growth video of the urban green belt, and the output of the target image frame determination model is a target image frame.

[0007] In one possible implementation, the input of the variational autoencoder is the growth monitoring video of the urban green belt, the output of the variational autoencoder is the subsequent growth video of the urban green belt, and the variational autoencoder includes an encoder and a decoder. The encoder is used to convert the input growth monitoring video of the urban green belt into latent variables, and the decoder is used to reconvert the latent variables into the subsequent growth video of the urban green belt.

[0008] In a possible implementation, determining the time position of the target image frame in the subsequent growth video of the urban green belt based on the target image frame and the subsequent growth video of the urban green belt includes: calculating the similarity between the target image frame and each image frame in the subsequent growth video of the urban green belt; and taking the time position of the image frame with the highest similarity in the subsequent growth video of the urban green belt as the time position of the target image frame in the subsequent growth video of the urban green belt.

[0009] According to a second aspect, the present invention provides an urban greening management system, comprising: An acquisition module is used to acquire growth monitoring videos of urban green belts; A subsequent growth video determination module, used to generate a subsequent growth video of the urban green belt using a variational autoencoder based on the growth monitoring video of the urban green belt; A target image frame determination module, used for inputting the subsequent growth video of the urban green belt into a target image frame determination model to obtain a target image frame; A time position determination module, used to determine the time position of the target image frame in the subsequent growth video of the urban green belt based on the target image frame and the subsequent growth video of the urban green belt; The greening pruning time determination module is used to determine the greening pruning time of the urban green belt based on the time position of the target image frame in the subsequent growth video of the urban green belt.

[0010] In a possible implementation, the target image frame determination model is a gated recurrent unit, the input of the target image frame determination model is a subsequent growth video of the urban green belt, and the output of the target image frame determination model is a target image frame.

[0011] In one possible implementation, the input of the variational autoencoder is the growth monitoring video of the urban green belt, the output of the variational autoencoder is the subsequent growth video of the urban green belt, and the variational autoencoder includes an encoder and a decoder. The encoder is used to convert the input growth monitoring video of the urban green belt into latent variables, and the decoder is used to reconvert the latent variables into the subsequent growth video of the urban green belt.

[0012] In a possible implementation manner, the time position determination module is further used to: Calculating the similarity between the target image frame and each image frame in the subsequent growth video of the urban green belt; The time position of the image frame with the highest similarity in the subsequent growth video of the urban green belt is used as the time position of the target image frame in the subsequent growth video of the urban green belt.

[0013] According to a third aspect, an embodiment of the present invention provides an electronic device, comprising: a processor; a memory; and a computer program; wherein the computer program is stored in the memory and configured to be executed by the processor to implement a method as described above, the method comprising: obtaining a growth monitoring video of an urban green belt; generating a subsequent growth video of the urban green belt based on the growth monitoring video of the urban green belt using a variational autoencoder; inputting the subsequent growth video of the urban green belt into a target image frame determination model to obtain a target image frame; determining a time position of the target image frame in the subsequent growth video of the urban green belt based on the target image frame and the subsequent growth video of the urban green belt; and determining a greening pruning time of the urban green belt based on the time position of the target image frame in the subsequent growth video of the urban green belt.

[0014] According to the fourth aspect, the present embodiment provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the urban greening management method provided above, the method comprising: obtaining a growth monitoring video of an urban green belt; generating a subsequent growth video of the urban green belt using a variational autoencoder based on the growth monitoring video of the urban green belt; inputting the subsequent growth video of the urban green belt into a target image frame determination model to obtain a target image frame; determining a time position of the target image frame in the subsequent growth video of the urban green belt based on the target image frame and the subsequent growth video of the urban green belt; and determining a greening pruning time of the urban green belt based on the time position of the target image frame in the subsequent growth video of the urban green belt.

[0015] The present invention provides an urban greening management method and system, which comprises obtaining a growth monitoring video of an urban green belt; generating a subsequent growth video of the urban green belt using a variational autoencoder based on the growth monitoring video of the urban green belt; inputting the subsequent growth video of the urban green belt into a target image frame determination model to obtain a target image frame; determining the time position of the target image frame in the subsequent growth video of the urban green belt based on the target image frame and the subsequent growth video of the urban green belt; and determining the greening pruning time of the urban green belt based on the time position of the target image frame in the subsequent growth video of the urban green belt. The method can accurately determine the repair time of the urban green belt and improve the management efficiency of the urban green belt. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of an application scenario of an urban greening management method provided by an embodiment of the present invention; Figure 2 A schematic diagram of a process flow of an urban greening management method provided by an embodiment of the present invention; Figure 3 A schematic diagram of a process for determining a time position of a target image frame in a subsequent growth video of an urban green belt provided by an embodiment of the present invention; Figure 4 A schematic diagram of an urban greening management system provided by an embodiment of the present invention; Figure 5 A schematic diagram of an electronic device provided by an embodiment of the present invention; Figure 6 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The present invention is further described in detail below by specific embodiments in conjunction with the accompanying drawings. Wherein similar elements in different embodiments adopt associated similar element numbers. In the following embodiments, many detailed descriptions are for making the present invention better understood. However, those skilled in the art can easily recognize that some features can be omitted in different situations, or can be replaced by other elements, materials, methods. In some cases, some operations related to the present invention are not shown or described in the specification, this is to avoid the core part of the present invention being overwhelmed by too much description, and for those skilled in the art, it is not necessary to describe these related operations in detail, and they can fully understand the related operations according to the description in the specification and the general technical knowledge in the art.

[0018] Figure 1 A schematic diagram of an application scenario of an urban greening management method provided by an embodiment of the present invention. Figure 1 The application scenario of the urban greening management method may include a server 11 , a network 12 , a terminal 13 and a storage device 14 .

[0019] In some embodiments, the server 11 may be a single server or a server group. The server 11 may access information and / or data stored in the terminal 13 or the storage device 14 through the network 12. In some embodiments, the server 11 may be used to execute Figure 2 The urban greening management methods shown in .

[0020] The network 12 may facilitate the exchange of information and / or data. In some embodiments, the network 12 may be any form of wired or wireless network, or any combination thereof.

[0021] Terminal 13 may refer to one or more terminal devices used by a user. In some embodiments, terminal 13 may include one or more combinations of a mobile device, a tablet computer, a laptop computer, etc. For example, a terminal may display a growth monitoring video of a city green belt.

[0022] The storage device 14 may store data and / or instructions. For example, the storage device 14 may store data instructions of an urban greening management method.

[0023] In an embodiment of the present invention, there is provided Figure 2 A method for managing urban greening is shown, the method comprising steps S1 to S5: Step S1, obtaining a growth monitoring video of an urban green belt.

[0024] Urban green belts refer to areas in cities where trees, shrubs, lawns and other plants are planted, usually located on both sides of roads, in parks, squares, etc. For example, a green belt beside a main urban road.

[0025] The growth monitoring video of the urban green belt is a video stream captured by video monitoring equipment installed near the urban green belt, which is used to record the growth of plants. These videos can be continuous video streams or video clips taken at regular intervals. For example, a fixed camera installed next to the green belt automatically shoots a 30-second video every 10 minutes.

[0026] Step S2, using a variational autoencoder based on the growth monitoring video of the urban green belt to generate a subsequent growth video of the urban green belt.

[0027] The subsequent growth video of the urban green belt is the subsequent growth video of the urban green belt output by the variational autoencoder.

[0028] The input of the variational autoencoder is the growth monitoring video of the urban green belt, and the output of the variational autoencoder is the subsequent growth video of the urban green belt. The variational autoencoder includes an encoder and a decoder. The encoder is used to convert the input growth monitoring video of the urban green belt into latent variables, and the decoder is used to reconvert the latent variables into the subsequent growth video of the urban green belt.

[0029] Variational Autoencoder (VAE) is a generative model that can learn the latent representation of data and generate new samples from it.

[0030] The growth monitoring video of the urban green belt can be regarded as a sequence of image frames. The encoder is a neural network that receives the input video frame and maps it to a distribution in a latent space. This distribution is usually a multivariate Gaussian distribution, represented by a mean and a variance. The latent variables are the distribution parameters output by the encoder, which represent the key features and patterns of the input data. The decoder is another neural network that maps the samples of the latent variables back to the original data space, that is, generates new image frames. The output is a series of new image frames that represent the subsequent growth state of the urban green belt. In some embodiments, the encoder and the decoder may include a bidirectional long-term and short-term neural network structure, which encodes the video frame sequence to obtain the latent variables of each frame, and the bidirectional long-term and short-term neural network structure in the decoder can be used to generate a video frame sequence. The reason why the variational autoencoder can generate the subsequent growth video of the urban green belt is that it can learn the key features and temporal variation laws of the input video frames, and predict future video frames through the transformation of the latent space.

[0031] Step S3, inputting the subsequent growth video of the urban green belt into a target image frame determination model to obtain a target image frame.

[0032] The target image frame refers to a specific image in a video sequence, which represents a critical time point at which the urban green belt reaches a state that requires pruning.

[0033] The target image frame determination model is a gated recurrent unit, the input of the target image frame determination model is the subsequent growth video of the urban green belt, and the output of the target image frame determination model is the target image frame. The gated recurrent unit (GRU) is used to process sequence data and timing information. The gated recurrent unit includes three components: a memory unit, an update gate, and a reset gate.

[0034] In some embodiments, the target image frame determination model includes an overgrowth video segment determination layer, a plurality of representative image frame determination layers, and a target image frame determination layer. The input of the overgrowth video segment determination layer is the subsequent growth video of the urban green belt, the output of the overgrowth video segment determination layer is the overgrowth initial clipping video of the urban green belt, the input of the plurality of representative image frame determination layers is the overgrowth initial clipping video of the urban green belt, the output of the plurality of representative image frame determination layers is a plurality of representative green belt image frames, the input of the target image frame determination layer is a plurality of representative green belt image frames, and the output of the target image frame determination layer is the target image frame. The overgrowth video segment determination layer is responsible for screening out the time period containing the overgrowth feature from the complete subsequent growth video. The plurality of representative image frame determination layers are responsible for selecting representative image frames from the overgrowth video segment. The target image frame determination layer finally determines the target image frame, that is, selects the frame that best meets the trimming condition from the plurality of representative image frames. By layering, unnecessary data can be gradually filtered out to reduce the amount of calculation. Each layer can focus on extracting features at different levels, such as the first layer extracting the overall trend and the second layer refining to specific details.

[0035] Step S4, determining the time position of the target image frame in the subsequent growth video of the urban green belt based on the target image frame and the subsequent growth video of the urban green belt.

[0036] In some embodiments, Figure 3 A schematic diagram of a process for determining a time position of a target image frame in a subsequent growth video of an urban green belt provided by an embodiment of the present invention, wherein the process for determining the time position of a target image frame in a subsequent growth video of an urban green belt comprises steps S21 to S22: Step S21, calculating the similarity between the target image frame and each image frame in the subsequent growth video of the urban green belt.

[0037] In some embodiments, the similarity between the target image frame and each image frame in the video may be determined based on a structural similarity index (SSIM), a peak signal-to-noise ratio (PSNR), or other image similarity metrics.

[0038] Step S22: taking the time position of the image frame with the highest similarity in the subsequent growth video of the urban green belt as the time position of the target image frame in the subsequent growth video of the urban green belt.

[0039] By calculating the similarity, we can find the image frame that best matches the target image frame, and then determine the time position. Based on the result of the similarity calculation, we find the image frame with the highest similarity to the target image frame, and determine its time position in the video. Assuming that the image frame at the 200th second of the video has the highest similarity to the target image frame, then the 200th second is the time position of the target image frame in the video.

[0040] Step S5, determining the greening pruning time of the urban green belt based on the time position of the target image frame in the subsequent growth video of the urban green belt. After determining the time position of the target image frame in the subsequent growth video of the urban green belt, the greening pruning time of the urban green belt is calculated based on the correspondence between the time position of the target image frame in the subsequent growth video of the urban green belt and the specific date of the pruning work, and the specific date and time of the pruning work are arranged.

[0041] Based on the same inventive concept, Figure 4 A schematic diagram of an urban greening management system provided by an embodiment of the present invention, the urban greening management system includes: An acquisition module 41 is used to acquire a growth monitoring video of an urban green belt; A subsequent growth video determination module 42, configured to generate a subsequent growth video of the urban green belt using a variational autoencoder based on the growth monitoring video of the urban green belt; A target image frame determination module 43, used for inputting the subsequent growth video of the urban green belt into a target image frame determination model to obtain a target image frame; A time position determination module 44, configured to determine a time position of the target image frame in the subsequent growth video of the urban green belt based on the target image frame and the subsequent growth video of the urban green belt; The greening trimming time determination module 45 is used to determine the greening trimming time of the urban green belt based on the time position of the target image frame in the subsequent growth video of the urban green belt.

[0042] Based on the same inventive concept, an embodiment of the present invention provides an electronic device, such as Figure 5 As shown, including: It includes: a processor 51; a memory 52; and a computer program; wherein the computer program is stored in the memory 52 and is configured to be executed by the processor 51 to implement the urban greening management method provided above, the method comprising: obtaining a growth monitoring video of an urban green belt; generating a subsequent growth video of the urban green belt using a variational autoencoder based on the growth monitoring video of the urban green belt; inputting the subsequent growth video of the urban green belt into a target image frame determination model to obtain a target image frame; determining the time position of the target image frame in the subsequent growth video of the urban green belt based on the target image frame and the subsequent growth video of the urban green belt; and determining the greening pruning time of the urban green belt based on the time position of the target image frame in the subsequent growth video of the urban green belt.

[0043] Based on the same inventive concept, this embodiment provides a computer-readable storage medium having a computer program stored thereon, which, when executed by the processor 51, implements the urban greening management method provided above, the method comprising: obtaining a growth monitoring video of an urban green belt; generating a subsequent growth video of the urban green belt using a variational autoencoder based on the growth monitoring video of the urban green belt; inputting the subsequent growth video of the urban green belt into a target image frame determination model to obtain a target image frame; determining the time position of the target image frame in the subsequent growth video of the urban green belt based on the target image frame and the subsequent growth video of the urban green belt; determining the greening pruning time of the urban green belt based on the time position of the target image frame in the subsequent growth video of the urban green belt.

[0044] The urban greening management method provided in the embodiments of the present application can be applied to terminal devices (such as mobile phones), tablet computers, laptops, ultra-mobile personal computers (UMPCs), handheld computers, netbooks, personal digital assistants (PDAs), wearable devices (such as smart watches, smart glasses or smart helmets, etc.), augmented reality (AR) and virtual reality (VR) devices, smart home devices, car computers and other electronic devices, and the embodiments of the present application do not impose any restrictions on this.

[0045] Taking the mobile phone 100 as an example of the electronic device, Figure 6 A schematic structural diagram of the mobile phone 100 is shown.

[0046] like Figure 6As shown, the mobile phone 100 may include a processing module 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, an earphone interface 170D, a sensor module 180, a button 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc.

[0047] The processing module 110 may include one or more processing units, for example, the processing module 110 may include an application processor (AP), a modem processor, a graphics processor (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Different processing units may be independent devices or integrated into one or more processors.

[0048] The processing module 110 can be used to: obtain a growth monitoring video of an urban green belt; generate a subsequent growth video of the urban green belt using a variational autoencoder based on the growth monitoring video of the urban green belt; input the subsequent growth video of the urban green belt into a target image frame determination model to obtain a target image frame; determine the time position of the target image frame in the subsequent growth video of the urban green belt based on the target image frame and the subsequent growth video of the urban green belt; determine the greening pruning time of the urban green belt based on the time position of the target image frame in the subsequent growth video of the urban green belt.

[0049] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0050] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0051] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0052] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0053] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A method for urban greening management, characterized in that: include: Obtain growth monitoring videos of urban green belts; Based on the growth monitoring video of the urban green belt, a subsequent growth video of the urban green belt is generated using a variational autoencoder, wherein the input of the variational autoencoder is the growth monitoring video of the urban green belt, and the output of the variational autoencoder is the subsequent growth video of the urban green belt. The variational autoencoder includes an encoder and a decoder, wherein the encoder is used to convert the input growth monitoring video of the urban green belt into a latent variable, and the decoder is used to reconvert the latent variable into the subsequent growth video of the urban green belt; Inputting the subsequent growth video of the urban green belt into a target image frame determination model to obtain a target image frame; Determining a time position of the target image frame in the subsequent growth video of the urban green belt based on the target image frame and the subsequent growth video of the urban green belt; The greening pruning time of the urban green belt is determined based on the time position of the target image frame in the subsequent growth video of the urban green belt.

2. The urban greening management method according to claim 1, characterized in that: The target image frame determination model is a gated recurrent unit, the input of the target image frame determination model is a subsequent growth video of the urban green belt, and the output of the target image frame determination model is a target image frame.

3. The urban greening management method according to claim 1, characterized in that: The step of determining the time position of the target image frame in the subsequent growth video of the urban green belt based on the target image frame and the subsequent growth video of the urban green belt comprises: Calculating the similarity between the target image frame and each image frame in the subsequent growth video of the urban green belt; The time position of the image frame with the highest similarity in the subsequent growth video of the urban green belt is used as the time position of the target image frame in the subsequent growth video of the urban green belt.

4. An urban greening management system, characterized in that: include: An acquisition module is used to acquire growth monitoring videos of urban green belts; A subsequent growth video determination module, used to generate a subsequent growth video of the urban green belt based on the growth monitoring video of the urban green belt using a variational autoencoder, wherein the input of the variational autoencoder is the growth monitoring video of the urban green belt, and the output of the variational autoencoder is the subsequent growth video of the urban green belt. The variational autoencoder includes an encoder and a decoder, wherein the encoder is used to convert the input growth monitoring video of the urban green belt into a latent variable, and the decoder is used to reconvert the latent variable into a subsequent growth video of the urban green belt; A target image frame determination module, used for inputting the subsequent growth video of the urban green belt into a target image frame determination model to obtain a target image frame; A time position determination module, used to determine the time position of the target image frame in the subsequent growth video of the urban green belt based on the target image frame and the subsequent growth video of the urban green belt; The greening pruning time determination module is used to determine the greening pruning time of the urban green belt based on the time position of the target image frame in the subsequent growth video of the urban green belt.

5. The urban greening management system according to claim 4, characterized in that: The target image frame determination model is a gated recurrent unit, the input of the target image frame determination model is a subsequent growth video of the urban green belt, and the output of the target image frame determination model is a target image frame.

6. The urban greening management system according to claim 4, characterized in that: The time position determination module is also used for: Calculating the similarity between the target image frame and each image frame in the subsequent growth video of the urban green belt; The time position of the image frame with the highest similarity in the subsequent growth video of the urban green belt is used as the time position of the target image frame in the subsequent growth video of the urban green belt.

7. An electronic device, characterized in that: include: processor; Memory; And a computer program; wherein the computer program is stored in the memory and is configured to be executed by the processor to implement the urban greening management method as described in any one of claims 1 to 3.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the urban greening management method as described in any one of claims 1 to 3 is implemented.

Images