Urban landscaping maintenance information management system

Abstract

This invention relates to the field of urban landscaping, and more particularly to an urban landscaping maintenance information management system. The invention utilizes the collaborative work of a data acquisition module, a tag setting module, a risk analysis module, a predictive analysis module, and a location recording module. The acquisition module obtains image data and location information of the target area. The tag setting module constructs a core buffer zone based on key monitoring points and determines whether plants have invaded the area, thereby setting risk tags. The risk analysis module analyzes the image data of the tagged areas, extracting perspective feature values ​​to determine whether an early warning signal needs to be issued. The predictive analysis module combines historical growth characteristics to predict whether plant growth will lead to shading risks, thus determining whether an early warning should be issued. The location recording module determines the warning location, thereby achieving efficient management and early warning of urban landscaping, and improving the scientific nature and effectiveness of urban landscaping management.

Description

Technical Field

[0001] This invention relates to the field of information management, and more particularly to an information management system for urban landscaping and greening maintenance. Background Technology

[0002] With the acceleration of urbanization and the continuous improvement of people's requirements for the ecological environment, the importance of urban landscaping maintenance is becoming increasingly prominent. Urban landscaping is not only closely related to the urban ecological environment, but also closely linked to the overall image of the city and the quality of life of residents. The urban landscaping maintenance information management system has become an indispensable part of improving the level of urban greening management and achieving refined management.

[0003] For example, Chinese Patent Publication No. CN118628752A relates to the field of image processing technology, specifically to an image processing-based information system for garden maintenance. The system includes: capturing an image to be processed; performing channel-wise fusion processing on the image to be processed to obtain several homomorphic layered images; performing region growing on the homomorphic layered images to obtain each homomorphic color gamut region; mapping each homomorphic color gamut region onto the image to be processed to obtain each detection region; and performing neural network recognition on the detection regions to achieve information management of garden maintenance. This invention utilizes the color change information generated by plant gaps and the color differences of surrounding plants to help determine the specific edges of objects, reducing mismatch problems caused by the presence of many plants with similar colors in the garden. It can obtain plant information and manage information more accurately, comprehensively, conveniently, and intelligently.

[0004] However, the following problems still exist in the existing technology.

[0005] In urban greening and landscaping management, due to the dynamic nature of plant growth and the instability of environmental factors, existing technologies struggle to accurately predict the growth trend and shading risks of plant branches and leaves. This is especially true in key areas such as intersections and traffic lights, where disorderly plant growth can obstruct traffic visibility and public facilities. Such obstruction not only interferes with the visual perception of drivers and pedestrians, increasing the probability of traffic accidents, but also negatively impacts the overall urban landscape, thereby reducing traffic safety and urban management efficiency. Summary of the Invention

[0006] To address this, the present invention provides an urban landscaping maintenance information management system to overcome the limitations of existing technologies in accurately predicting the growth trend and shading risk of plants due to the dynamic nature of plant growth and the instability of environmental factors. This is particularly true in key areas such as intersections and traffic lights, where disorderly plant growth can obstruct traffic visibility and public facilities, thereby reducing traffic safety and urban management efficiency.

[0007] To achieve the above objectives, the present invention provides an urban landscaping and greening maintenance information management system, which includes,

[0008] The acquisition module includes a mobile acquisition unit, an image acquisition unit mounted on the mobile acquisition unit for acquiring image data of the target area, and a positioning unit for acquiring the location information of the target area.

[0009] The tag setting module, which is connected to the acquisition module, is used to set several key monitoring points in the target area, construct a core buffer area based on the key monitoring points, determine the coverage outline of plant branches and leaves based on the image data collected in the core buffer area, so as to determine whether the plant has invaded the core buffer area, and set a risk tag for the target area.

[0010] The risk analysis module, which is connected to the label setting module, analyzes the image data collected for the target area in response to the setting of a risk label for the target area. This includes acquiring several frames of image data for the target area, extracting perspective features within the covered contour in each image data to determine the perspective feature value, and determining whether a warning signal needs to be issued.

[0011] The predictive analysis module, which is connected to the risk analysis module, is used to respond to the judgment result of the risk analysis module to determine the branch extension direction of the branch end in the image data of the target area, and predict whether there is a risk of extension occlusion in combination with historical growth characteristics, so as to issue an early warning signal.

[0012] The key monitoring points are intersections.

[0013] Furthermore, the label setting module, used to construct a core buffer area based on key monitoring points, includes:

[0014] A core buffer zone is constructed with key monitoring points as the center and a predetermined distance as the radius.

[0015] Furthermore, the label setting module is used to determine the coverage outline of plant branches and leaves based on image data to determine whether the plant has invaded the core buffer area, and to set a risk label for the target area, including...

[0016] Used to determine the outline of the plant's foliage cover;

[0017] Used to determine the target feature contour in the image data, and to determine whether the covering contour overlaps with the target feature contour;

[0018] If the coverage contour overlaps with the target feature contour, it is determined that the plant branches and leaves have invaded the core buffer area, and a risk label is set for the target area.

[0019] The target feature contour is predetermined.

[0020] Furthermore, the risk analysis module is used to extract perspective features within the covered contours in each image data, including,

[0021] Used to determine the chromaticity difference between adjacent pixels in the image data;

[0022] If the chromaticity difference is less than a preset clustering chromaticity threshold, then the adjacent pixels are classified into clusters, and several clusters are determined.

[0023] Perspective regions are selected based on the chromaticity difference between the images within the cluster and the target feature contour, and the total area of ​​the perspective regions is determined as the perspective feature.

[0024] The ratio of the total area of ​​the perspective region to the area of ​​the covered contour is determined as the perspective feature value.

[0025] Furthermore, the risk analysis module filters perspective regions based on the chromatic difference between the cluster and the target feature contour image, including:

[0026] If the chromaticity difference between the cluster and the image within the target feature contour is less than a preset chromaticity threshold, then the cluster is selected as a perspective region.

[0027] Furthermore, the risk analysis module is used to determine whether a warning signal needs to be issued, including:

[0028] If the perspective feature value is less than the preset perspective feature threshold, it is determined that a warning signal needs to be issued.

[0029] Furthermore, the predictive analysis module is used to respond to the judgment result of the risk analysis module, including,

[0030] If no risk label is set for the target area, it is used to determine the branch extension direction of the branch ends in the image data within the target area, and combined with historical growth characteristics to predict whether there is a risk of extension occlusion, so as to issue an early warning signal.

[0031] Furthermore, the predictive analysis module is used to determine the branch extension direction of the branch ends in the image data within the target area, including:

[0032] Used to determine the main growth direction of the branch tip based on the obtained branch tip outline;

[0033] The main growth direction at the end of the branch is taken as the branch derivation direction.

[0034] Furthermore, the prediction analysis module is also used to predict the branch growth distance based on historical growth characteristics, and to extend the branch end in the corresponding branch growth direction in the image data to generate prediction image data.

[0035] Determine the target feature contours and the coverage contours of plant branches and leaves in the predicted image data, and determine the area ratio of the coverage contours located within the target feature contours in order to determine whether there is a risk of derivative occlusion.

[0036] If the area ratio is greater than the predetermined derivative area ratio threshold, it is determined that there is a risk of derivative occlusion.

[0037] Furthermore, it also includes a location recording module, which determines the warning location in response to the warning signal issued by the risk analysis module and / or the predictive analysis module.

[0038] Compared with existing technologies, this invention relates to the field of urban landscaping, and more particularly to an urban landscaping maintenance information management system. This invention utilizes the collaborative work of a data acquisition module, a tag setting module, a risk analysis module, a predictive analysis module, and a location recording module. The data acquisition module obtains image data and location information of the target area. The tag setting module constructs a core buffer zone based on key monitoring points and determines whether plants have invaded the area, thereby setting risk tags. The risk analysis module analyzes the image data of the areas with risk tags, extracting perspective feature values ​​to determine whether an early warning signal needs to be issued. The predictive analysis module combines historical growth characteristics to predict whether plant growth will lead to shading risks, thus determining whether an early warning should be issued. The location recording module determines the warning location, thereby achieving efficient management and early warning of urban landscaping, and improving the scientific nature and effectiveness of urban landscaping management.

[0039] In particular, this invention constructs a core buffer zone based on key monitoring points and determines the coverage outline of plant branches and leaves based on image data to determine whether plants have invaded the core buffer zone. In urban landscaping maintenance and management, especially in key areas such as intersections and traffic lights, the dynamic and uncertain nature of plant growth means that disorderly growth of branches and leaves may obstruct important facilities such as traffic lights and signs, thereby interfering with the visual perception of drivers and pedestrians, increasing the probability of traffic accidents, and negatively impacting the city's aesthetics and management efficiency. By constructing a core buffer zone at key monitoring points, a specific area requiring focused monitoring and protection can be clearly defined. Determining the coverage outline of plant branches and leaves based on image data enables real-time monitoring of plant growth. Once plant branches and leaves are detected invading the core buffer zone, risk tags can be promptly set to support subsequent warnings. By setting monitoring points at these key locations, resources can be concentrated for focused monitoring, avoiding indiscriminate comprehensive monitoring of the entire city, improving resource utilization efficiency, and thus enhancing the scientific and effective management of urban landscaping.

[0040] In particular, this invention extracts perspective features within the covered contours of each image data to determine perspective feature values ​​and thus whether a warning signal needs to be issued. Relying solely on whether plant branches and leaves intrude into the core buffer zone to determine the need for action could lead to unnecessary interventions, making it difficult to accurately assess the severity and actual impact of occlusion, and failing to distinguish between minor and severe occlusion. For example, even if plant branches and leaves slightly intrude into the core buffer zone, the actual degree of occlusion may be very small, having almost no impact on traffic visibility or public facilities. In such cases, issuing a warning and taking measures such as pruning are unnecessary and would waste manpower, resources, and time. Perspective features, by calculating parameters such as the area and transmittance of the perspective region within the coverage outline, can accurately quantify the actual shading of key areas by plant branches and leaves. Determining perspective feature values ​​based on perspective features can effectively avoid misjudgments caused by slight plant intrusion into the core buffer area, and also avoid missing serious shading due to ignoring slight shading. Therefore, by extracting perspective feature values, areas with real risk of serious shading can be accurately located. When the perspective feature value reaches a preset threshold, an early warning signal is issued and corresponding maintenance measures are taken, improving resource utilization efficiency and thus enhancing the scientificity and effectiveness of urban landscaping management.

[0041] In particular, this invention uses the branch extension direction of the branch ends in image data within a target area to predict the existence of potential shading risks by combining historical growth characteristics, thus issuing an early warning signal. Since plant growth is a dynamic process, its future growth direction and speed may change with time and environmental conditions. In reality, completing a comprehensive inspection of large cities requires a long period, during which plants continue to grow. While plant branches and leaves that have not yet invaded the core buffer zone may not pose a direct shading risk at the current moment, their future growth trend may gradually lead to shading problems. Therefore, this invention, by predicting the extension direction of plant branch ends and combining it with historical growth characteristics, can determine in advance whether plants may cause shading in key areas in the future. This provides sufficient time for landscape maintenance personnel to implement preventative intervention measures, effectively avoiding the formation of shading risks. The core advantage of this method is that it can curb shading risks at the nascent stage, preventing them from developing into actual shading problems, thereby reducing potential interference with urban traffic visibility and public facility functions. This proactive risk management strategy can reduce maintenance costs, thereby improving the scientific nature and effectiveness of urban landscaping management. Attached Figure Description

[0042] Figure 1 This is a system block diagram of the urban landscaping maintenance information management system according to an embodiment of the invention;

[0043] Figure 2A logic diagram for determining whether plants have invaded the core buffer zone and setting risk labels for the target area in an embodiment of the invention;

[0044] Figure 3 This is a logic diagram illustrating whether a warning signal needs to be issued, as shown in an embodiment of the invention.

[0045] Figure 4 This is a logic block diagram of the target area analysis in response to the judgment result of the risk analysis module, as an embodiment of the invention. Detailed Implementation

[0046] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0047] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0048] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the term "connection" should be interpreted broadly. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be a connection within two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0049] Please see Figure 1 The diagram shown is a system block diagram of the urban landscaping maintenance information management system according to an embodiment of the invention. The urban landscaping maintenance information management system according to this embodiment of the invention includes:

[0050] The acquisition module includes a mobile acquisition unit, an image acquisition unit mounted on the mobile acquisition unit for acquiring image data of the target area, and a positioning unit for acquiring the location information of the target area.

[0051] The tag setting module, which is connected to the acquisition module, is used to set several key monitoring points in the target area, construct a core buffer area based on the key monitoring points, determine the coverage outline of plant branches and leaves based on the image data collected in the core buffer area, so as to determine whether the plant has invaded the core buffer area, and set a risk tag for the target area.

[0052] The risk analysis module, which is connected to the label setting module, analyzes the image data collected for the target area in response to the setting of a risk label for the target area. This includes acquiring several frames of image data for the target area, extracting perspective features within the covered contour in each image data to determine the perspective feature value, and determining whether a warning signal needs to be issued.

[0053] The predictive analysis module, which is connected to the risk analysis module, is used to respond to the judgment result of the risk analysis module to determine the branch extension direction of the branch end in the image data of the target area, and predict whether there is a risk of extension occlusion in combination with historical growth characteristics, so as to issue an early warning signal.

[0054] The key monitoring points are intersections.

[0055] Specifically, the target area is determined based on the city road network map, and the road network is divided into several target areas for regional analysis, which will not be elaborated further.

[0056] Specifically, the structure of the tag setting module, risk analysis module, and predictive analysis module is not limited, and they can be composed of logic components or combinations of logic components. The logic components include field-programmable processors, computers, or microprocessors in computers.

[0057] Specifically, the mobile acquisition unit can be an inspection vehicle, the image acquisition unit can be a camera device installed at the front of the inspection vehicle to acquire images of the front, and the positioning unit can be a GPS positioning device installed on the inspection vehicle, which will not be elaborated further.

[0058] Specifically, the label setting module is used to construct a core buffer area based on key monitoring points, including:

[0059] A core buffer zone is constructed with key monitoring points as the center and a predetermined distance as the radius.

[0060] Specifically, the traffic conditions at the intersection are relatively complex, so the predetermined distance is set within the range of [30m, 50m] as a key consideration for the intersection area.

[0061] Please see Figure 2 As shown, this is a logic diagram for determining whether a plant has invaded the core buffer zone and setting a risk label for the target area according to an embodiment of the invention. Specifically, the label setting module is used to determine the coverage outline of plant branches and leaves based on image data to determine whether the plant has invaded the core buffer zone. Setting a risk label for the target area includes...

[0062] Used to determine the outline of the plant's foliage cover;

[0063] Used to determine the target feature contour in the image data, and to determine whether the covering contour overlaps with the target feature contour;

[0064] If the coverage contour overlaps with the target feature contour, it is determined that the plant branches and leaves have invaded the core buffer area, and a risk label is set for the target area.

[0065] The target feature contour is predetermined.

[0066] In practice, there is no limitation on the method for determining the coverage contour of the plant branches and leaves and the target feature contour. It can be achieved by image segmentation algorithm or edge detection algorithm. As long as the actual coverage contour of the plant branches and leaves and the target feature contour can be accurately extracted, it will not be elaborated further.

[0067] In implementation, the target feature is the road, and the target feature contour is the road edge contour.

[0068] This invention constructs a core buffer zone based on key monitoring points and determines the coverage outline of plant branches and leaves based on image data to determine whether plants have invaded the core buffer zone. In urban landscaping maintenance and management, especially in key areas such as intersections and traffic lights, the dynamic and uncertain nature of plant growth means that disorderly growth of branches and leaves may obstruct important facilities such as traffic lights and signs, interfering with the visual perception of drivers and pedestrians, increasing the probability of traffic accidents, and negatively impacting the city's aesthetics and management efficiency. By constructing a core buffer zone at key monitoring points, a specific area requiring focused monitoring and protection can be clearly defined. Determining the coverage outline of plant branches and leaves based on image data allows for real-time monitoring of plant growth. Once plant branches and leaves are detected invading the core buffer zone, risk tags can be promptly set to support subsequent warnings. By setting monitoring points at these key locations, resources can be concentrated for focused monitoring, avoiding indiscriminate monitoring of the entire city, improving resource utilization efficiency, and thus enhancing the scientific and effective management of urban landscaping.

[0069] The risk analysis module is used to extract perspective features within the covered contours in each image data, including,

[0070] Used to determine the chromaticity difference between adjacent pixels in the image data;

[0071] If the chromaticity difference is less than a preset clustering chromaticity threshold, then the adjacent pixels are classified into clusters, and several clusters are determined.

[0072] Perspective regions are selected based on the chromaticity difference between the images within the cluster and the target feature contour, and the total area of ​​the perspective regions is determined as the perspective feature.

[0073] The ratio of the total area of ​​the perspective region to the area of ​​the covered contour is determined as the perspective feature value.

[0074] In implementation, the preset clustering chromaticity threshold is predetermined. Several mobile acquisition units collect image data in advance, and those skilled in the art mark the light-transmitting areas. The average chromaticity difference between several pixels in each light-transmitting area and their adjacent pixels is determined. The clustering chromaticity threshold is set as the product of the average chromaticity difference and the error coefficient. The error coefficient is selected in the range [1.25, 1.35].

[0075] Specifically, the risk analysis module filters perspective regions based on the chromaticity difference between clusters and the target feature contour image, including:

[0076] If the chromaticity difference between the cluster and the image within the target feature contour is less than a preset chromaticity threshold, then the cluster is selected as a perspective region.

[0077] In practice, the preset color chromaticity threshold is predetermined. Several mobile acquisition units collect image data in advance. Those skilled in the art mark the light-transmitting areas and determine the average color difference between several pixels in each light-transmitting area and their adjacent pixels. The color chromaticity threshold is set as the product of the average color difference and the error coefficient. The error coefficient is selected within the range [1.2, 1.25].

[0078] Please see Figure 3 The diagram shown illustrates the logic for determining whether a warning signal needs to be issued according to an embodiment of the invention. Specifically, the risk analysis module is used to determine whether a warning signal needs to be issued, including...

[0079] If the perspective feature value is less than the preset perspective feature threshold, it is determined that a warning signal needs to be issued.

[0080] In practice, the purpose of setting the perspective feature threshold is to take into account the impact on the occlusion of the line of sight. In practice, it is usually in the range of [40%, 50%].

[0081] Please see Figure 4 The diagram shown is a logical block diagram of the target area analysis in response to the judgment result of the risk analysis module according to an embodiment of the invention. Specifically, the predictive analysis module is used to respond to the judgment result of the risk analysis module, including:

[0082] If no risk label is set for the target area, it is used to determine the branch extension direction of the branch ends in the image data within the target area, and combined with historical growth characteristics to predict whether there is a risk of extension occlusion, so as to issue an early warning signal.

[0083] In practice, there are no restrictions on the way warning signals are issued. Warnings can be issued through local audible and visual alarm devices or remote communication modules, as long as they can promptly and accurately notify relevant personnel or systems.

[0084] This invention extracts perspective features within the covered contours of each image data point to determine perspective feature values ​​and thus whether a warning signal is needed. Relying solely on whether plant branches and leaves encroach on the core buffer zone to determine the need for action could lead to unnecessary interventions, making it difficult to accurately assess the severity and actual impact of occlusion, and failing to distinguish between minor and severe occlusion. For example, even if plant branches and leaves slightly encroach on the core buffer zone, the actual degree of occlusion may be very small, having almost no impact on traffic visibility or public facilities. In such cases, issuing a warning and taking measures such as pruning are unnecessary and waste manpower, resources, and time. Perspective features, by calculating parameters such as the area and transmittance of the perspective region within the coverage outline, can accurately quantify the actual shading of key areas by plant branches and leaves. Determining perspective feature values ​​based on perspective features can effectively avoid misjudgments caused by slight plant intrusion into the core buffer area, and also avoid missing serious shading due to ignoring slight shading. Therefore, by extracting perspective feature values, areas with real risk of serious shading can be accurately located. When the perspective feature value reaches a preset threshold, an early warning signal is issued and corresponding maintenance measures are taken, improving resource utilization efficiency and thus enhancing the scientificity and effectiveness of urban landscaping management.

[0085] Specifically, the predictive analysis module is used to determine the branch extension direction at the branch ends in the image data within the target area, including:

[0086] Used to determine the main growth direction of the branch tip based on the obtained branch tip outline;

[0087] The main growth direction at the end of the branch is taken as the branch derivation direction.

[0088] In practice, there are no restrictions on the method for obtaining the outline of the branch end. Edge detection algorithms or image segmentation methods can be used, as long as the outline of the branch end can be accurately extracted. This will not be elaborated further.

[0089] In practice, there is no limitation on the method of determining the main growth direction of the branch end. First, the outline of the branch end is extracted. The outline of the branch end is an outline segment at a predetermined length from the branch end.

[0090] Determine the endpoints at both ends of the outline segment, connect the endpoints to construct a ray, and the ray's derivation direction is the main growth direction of the branch's end, with a predetermined length of 0.1 times the branch's outline length.

[0091] This invention uses the branch extension direction of the branch tips in image data within a target area to predict the potential for shading by combining historical growth characteristics, thus issuing an early warning signal. Since plant growth is a dynamic process, its future growth direction and speed may change with time and environmental conditions. While plant branches and leaves that have not yet invaded the core buffer zone may not pose a direct shading risk at the current moment, their future growth trend may gradually lead to shading problems. Therefore, this invention, by predicting the extension direction of plant branch tips and combining historical growth characteristics, can preemptively determine whether plants may cause shading in key areas in the future. This provides sufficient time for landscape maintenance personnel to implement preventative intervention measures, effectively avoiding the formation of shading risks. The core advantage of this method is its ability to curb shading risks at the nascent stage, preventing them from developing into actual shading problems, thereby reducing potential interference with urban traffic visibility and public facility functions. This proactive risk management strategy can reduce maintenance costs, thereby improving the scientific nature and effectiveness of urban landscaping management.

[0092] Specifically, the predictive analysis module is further used to predict the branch growth distance based on historical growth characteristics, and to extend the branch end in the corresponding branch growth direction in the image data to generate predictive image data.

[0093] Determine the target feature contours and the coverage contours of plant branches and leaves in the predicted image data, and determine the area ratio of the coverage contours located within the target feature contours in order to determine whether there is a risk of derivative occlusion.

[0094] If the area ratio is greater than the predetermined derivative area ratio threshold, it is determined that there is a risk of derivative occlusion.

[0095] Specifically, historical growth characteristics include the growth length of branches of similar plants at corresponding growth ages over a predetermined period of time, based on which the growth distance of branches can be predicted.

[0096] In practice, the scheduled time is predetermined. Preferably, if there is a regular inspection or maintenance plan for urban gardens, the scheduled time can be set as the interval between two inspections. For example, if the growth of branches is checked every three months, the scheduled time can be set to four months. Alternatively, historical growth data of the branches can be analyzed to determine their average growth cycle. For example, if the average growth cycle of the branches is one growing season, such as from spring to autumn, the scheduled time can be set as the length of one growing season.

[0097] In implementation, the purpose of the preset derivative area proportion threshold is to characterize the critical size of the predicted occupied area in the image, used to distinguish between normal growth status and status that may cause occlusion risk. The image data is pre-screened by those skilled in the art, marking image data where plants may cause occlusion risk, calculating the area proportion in each marked image data, and solving for the average area proportion to characterize situations where the occupied area range may be large. Typically, the derivative area proportion threshold is set to 0.85 times the average area proportion.

[0098] Specifically, it also includes a location recording module, which determines the warning location in response to the warning signal issued by the risk analysis module and / or the predictive analysis module.

[0099] In practice, when the acquisition module acquires image data, it simultaneously determines the location information at the time of acquisition. The risk analysis module and the predictive analysis module determine whether to issue an early warning signal based on the image data. When it is determined that an early warning signal needs to be issued, the corresponding image data is determined and then the location information is determined, and the early warning location is further determined. This will not be elaborated further.

[0100] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. An information management system for urban landscaping and greening maintenance, characterized in that, include: The acquisition module includes a mobile acquisition unit, an image acquisition unit mounted on the mobile acquisition unit for acquiring image data of the target area, and a positioning unit for acquiring the location information of the target area. The tag setting module, which is connected to the acquisition module, is used to set several key monitoring points in the target area, construct a core buffer area based on the key monitoring points, determine the coverage outline of plant branches and leaves based on the image data acquired in the core buffer area, so as to determine whether the plant has invaded the core buffer area, and set a risk tag for the target area. The risk analysis module, connected to the label setting module, analyzes image data collected from the target area in response to a risk label being set for that area. This includes acquiring several frames of image data for the target area, extracting perspective features within the covered contours of each image data frame to determine perspective feature values. Used to determine the chromaticity difference between adjacent pixels in the image data; If the chromaticity difference is less than a preset clustering chromaticity threshold, then the adjacent pixels are classified into clusters, and several clusters are determined. Perspective regions are selected based on the chromaticity difference between the images within the cluster and the target feature contour, and the total area of ​​the perspective regions is determined as the perspective feature. The ratio of the total area of ​​the perspective region to the area of ​​the covered contour is determined as the perspective feature value; Determine whether an early warning signal needs to be issued; The predictive analysis module, which is connected to the risk analysis module, is used to respond to the judgment result of the risk analysis module to determine the branch extension direction of the branch end in the image data of the target area, and predict whether there is a risk of extension occlusion in combination with historical growth characteristics, so as to issue an early warning signal. The key monitoring points are intersections.

2. The urban landscaping and greening maintenance information management system according to claim 1, characterized in that, The label setting module is used to construct a core buffer area based on key monitoring points, including: A core buffer zone is constructed with key monitoring points as the center and a predetermined distance as the radius.

3. The urban landscaping and greening maintenance information management system according to claim 1, characterized in that, The label setting module is used to determine the coverage outline of plant branches and leaves based on image data, in order to determine whether the plant has invaded the core buffer area, and to set a risk label for the target area, including... Used to determine the outline of the plant's foliage cover; Used to determine the target feature contour in the image data, and to determine whether the covering contour overlaps with the target feature contour; If the coverage contour overlaps with the target feature contour, it is determined that the plant branches and leaves have invaded the core buffer area, and a risk label is set for the target area. The target feature contour is predetermined.

4. The urban landscaping and greening maintenance information management system according to claim 1, characterized in that, The risk analysis module filters perspective regions based on the color difference between clusters and the target feature contour image, including... If the chromaticity difference between the cluster and the image within the target feature contour is less than a preset chromaticity threshold, then the cluster is selected as a perspective region.

5. The urban landscaping and greening maintenance information management system according to claim 4, characterized in that, The risk analysis module is used to determine whether a warning signal needs to be issued, including... If the perspective feature value is less than the preset perspective feature threshold, a warning signal is required.

6. The urban landscaping and greening maintenance information management system according to claim 1, characterized in that, The predictive analysis module is used to respond to the judgment result of the risk analysis module, including, If no risk label is set for the target area, it is used to determine the branch extension direction of the branch ends in the image data within the target area, and combined with historical growth characteristics to predict whether there is a risk of extension occlusion, so as to issue an early warning signal.

7. The urban landscaping and greening maintenance information management system according to claim 6, characterized in that, The predictive analysis module is used to determine the branch extension direction at the branch ends in the image data within the target area, including: Used to determine the main growth direction of the branch tip based on the obtained branch tip outline; The main growth direction at the end of the branch is taken as the branch derivation direction.

8. The urban landscaping and greening maintenance information management system according to claim 7, characterized in that, The predictive analysis module is also used to predict the branch growth distance based on historical growth characteristics, and to extend the branch end in the corresponding branch growth direction in the image data to generate predictive image data. Determine the target feature contours and the coverage contours of plant branches and leaves in the predicted image data, and determine the area ratio of the coverage contours located within the target feature contours in order to determine whether there is a risk of derivative occlusion. If the area ratio is greater than the predetermined derivative area ratio threshold, it is determined that there is a risk of derivative occlusion.

9. The urban landscaping and greening maintenance information management system according to claim 8, characterized in that, It also includes a location recording module, which determines the warning location in response to the warning signal issued by the risk analysis module and / or the predictive analysis module.

Images