Image processing-based method, system, storage medium and device for checking violation control

Abstract

The application relates to a method, system, storage medium and equipment for checking illegal buildings based on image processing, which comprises the following steps: collecting initial image information of a target area; processing the initial image information by an image processing platform, establishing an initial target building space model, and constructing an initial space model database; collecting real-time image information of the target area, and establishing a real-time target building space model according to the real-time image information; matching the real-time target building space model with the initial space model database, judging whether there is an illegal building in the target area, and generating illegal building prompt information when there is an illegal building. The initial image information of the target area is collected, processed and used to construct the initial space model database, and then the real-time target building space model constructed according to the collected real-time image information is matched, so that whether there is an illegal building in the target area can be determined conveniently, and illegal building prompt information is generated when there is an illegal building.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of urban supervision, and particularly relates to a method, system, storage medium and equipment for checking illegal buildings based on image processing. BACKGROUND

[0002] At present, the supervision of illegal buildings is relatively weak, and there is a lack of efficient and accurate monitoring means, which results in a large workload of staff and poor supervision effect. Some methods use remote sensing monitoring images to process and identify illegal buildings, but these methods still have defects such as poor image processing and identification effect, and the identification results cannot be timely notified and displayed, so that the increasingly high requirements of people on the supervision of urban illegal buildings cannot be met. SUMMARY

[0003] The present application relates to the technical field of urban supervision, and particularly relates to a method, system, storage medium and equipment for checking illegal buildings based on image processing.

[0004] The technical scheme for solving the above technical problem is as follows: a method for checking illegal buildings based on image processing, comprising the following steps:

[0005] S1: collecting initial image information of a target area by automatic cruising of a drone, and uploading the initial image information to an image processing platform;

[0006] S2: processing the initial image information by the image processing platform, establishing an initial target building space model, and constructing an initial space model database and uploading it to a cloud server;

[0007] S3: collecting real-time image information of the target area by automatic cruising of the drone, and establishing a real-time target building space model by the image processing platform according to the real-time image information;

[0008] S4: matching the real-time target building space model with the initial space model database to determine whether there is an illegal building in the target area, and generating a violation building prompt information when there is an illegal building.

[0009] The method for checking illegal buildings based on image processing of the present application can automatically collect initial image information of a target area by a drone, and process and construct an initial space model database by an image processing platform, so as to match a real-time target building space model constructed by real-time image information collected by the drone, so that it can be determined more conveniently whether there is a violation building in the target area, and a violation building prompt information is generated when there is an illegal building, which greatly improves the efficiency and accuracy of checking illegal buildings, reduces labor costs, and has good supervision effect, which is conducive to the orderly planning of cities.

[0010] Based on the technical scheme, the application can be further improved as follows.

[0011] Further, the image processing platform processes the initial image information to establish an initial target building space model, specifically including the following steps.

[0012] S21: performing feature extraction processing on the initial image information to obtain the overall contour line of the building in the target region;

[0013] S22: establishing a space coordinate system, selecting a plurality of reference points on the overall contour line along the Z-axis direction of the space coordinate system according to a first preset interval, and generating a plurality of closed reference lines along the X-axis direction of the space coordinate system based on the reference points;

[0014] S23: gradually constructing an initial target building space model in the target region based on all the reference lines.

[0015] The beneficial effects of the above further scheme are as follows: by performing feature extraction processing on the initial image information, all feature points of the initial image information can be obtained, and the overall contour line of the building in the target region can be outlined and formed according to all the feature points. Then, a plurality of reference points can be selected on the overall contour line along the Z-axis direction of the space coordinate system according to a first preset interval, so as to generate corresponding reference lines. Then, an initial target building space model in the target region can be gradually constructed according to the reference lines, so as to solidify the initial information of the building in the target region, thereby facilitating subsequent matching and comparison.

[0016] Further, the generating of a plurality of closed reference lines along the X-axis direction of the space coordinate system based on the reference points includes the following steps.

[0017] S221: calculating the areas of the planar regions surrounded by the reference lines corresponding to two adjacent reference points, and determining whether the areas are equal;

[0018] S222: if the areas of the planar regions surrounded by the reference lines corresponding to two adjacent reference points are equal, then the corresponding reference lines are directly generated along the X-axis direction of the space coordinate system according to the two adjacent reference points, respectively; otherwise,

[0019] S223: performing subdivision cutting on the two adjacent reference points along the Z-axis direction of the space coordinate system to obtain new reference points and update the reference points;

[0020] S224: Calculate the area of the plane region surrounded by the reference line corresponding to the lower one of the two reference points before updating and the updated reference point, and determine whether the areas are equal, and return to step S222 until all the reference points are traversed.

[0021] The beneficial effect of the above further scheme is that by calculating whether the areas of the plane regions surrounded by the reference lines corresponding to two adjacent reference points are equal, it can be determined whether the structure of the building in the target region changes from bottom to top, and when the change occurs, the reference lines can be obtained more accurately by refining the reference points, and the initial target building space model of the entire building can be more accurately constructed subsequently.

[0022] Further, the step of gradually constructing the initial target building space model in the target region based on all the reference lines comprises the following steps:

[0023] S231: Select two adjacent reference lines in all the reference lines as a group, select the higher reference line in each group, and construct a polygonal column with the Z-axis direction interval between each group of reference lines as the height, and insert it into the target building space model in the initial state;

[0024] S232: Select the lower reference line in each group, and construct a polygonal column with the Z-axis direction interval between each group of reference lines as the height, and insert it into the target building space model in the initial state;

[0025] S233: Repeat the above steps until the polygonal column between each group of adjacent reference lines is inserted, and the initial target building space model is obtained.

[0026] The beneficial effect of the above further scheme is that by taking the higher reference line and the lower reference line in each group of reference lines as the reference, and constructing a polygonal column with the Z-axis direction interval between each group of reference lines as the height, the polygonal column corresponding to each group of reference lines can be constructed more accurately, and the polygonal columns corresponding to all groups of reference lines can constitute the initial target building space model of the target building, which can be uploaded to the cloud server for storage.

[0027] The application also provides a violation checking and controlling system based on image processing, which comprises a collection module, an image processing platform and a matching prompting module.

[0028] The collection module is used for collecting initial image information of a target region and uploading the initial image information to the image processing platform.

[0029] The image processing platform is used for processing the initial image information, establishing an initial target building space model, constructing an initial space model database and uploading to a cloud server.

[0030] The acquisition module is further used for acquiring real-time image information of the target area.

[0031] The image processing platform is further used for establishing a real-time target building space model according to the real-time image information.

[0032] The matching prompt module is used for matching the real-time target building space model with the initial space model database, judging whether there is illegal building in the target area, and generating illegal building prompt information when there is illegal building.

[0033] The system for checking illegal buildings based on image processing has the advantages that the initial image information of the target area is automatically acquired by the unmanned aerial vehicle, and the image processing platform processes the initial image information and constructs an initial space model database, so that the real-time target building space model constructed by the real-time image information acquired by the unmanned aerial vehicle is matched, so that whether there is illegal building in the target area can be determined more conveniently, and illegal building prompt information is generated when there is illegal building, thereby greatly improving the efficiency and accuracy of checking illegal buildings, reducing labor cost, improving supervision effect, and facilitating orderly planning of cities.

[0034] On the basis of the above technical solution, the application can also be improved as follows:

[0035] Further, the image processing platform processes the initial image information to establish an initial target building space model, and the specific implementation is as follows:

[0036] The initial image information is subjected to feature extraction processing to obtain the overall contour line of the building in the target area;

[0037] A space coordinate system is established, a plurality of reference points are selected on the overall contour line along the Z-axis direction of the space coordinate system according to a first preset interval, and a plurality of closed reference lines are generated along the X-axis direction of the space coordinate system based on the reference points;

[0038] The initial target building space model in the target area is gradually constructed based on all the reference lines.

[0039] The beneficial effect of the above further scheme is that all feature points of the initial image information can be obtained by performing feature extraction processing on the initial image information, and the overall contour line of the building in the target region is outlined and formed according to all the feature points, so that a plurality of reference points can be selected on the overall contour line along the Z-axis direction of the spatial coordinate system according to a first preset interval, thereby generating corresponding reference lines, and the initial target building space model in the target region is gradually constructed according to the reference lines, and the initial information of the building in the target region is solidified, so as to facilitate subsequent matching comparison.

[0040] Further, the image processing platform generates a plurality of closed reference lines along the X-axis direction of the spatial coordinate system based on the reference points, and the specific implementation is as follows:

[0041] Calculate the area of the planar region surrounded by the reference lines corresponding to the two adjacent reference points, and determine whether they are equal;

[0042] If the areas of the planar regions surrounded by the reference lines corresponding to the two adjacent reference points are equal, then the corresponding reference lines are directly generated along the X-axis direction of the spatial coordinate system according to the two adjacent reference points, respectively; otherwise,

[0043] Subdivide and cut the two adjacent reference points along the Z-axis direction of the spatial coordinate system to obtain new reference points and update them;

[0044] Calculate the area of the planar region surrounded by the reference lines corresponding to the updated reference point and the lower reference point of the two reference points before updating, and determine whether the areas are equal, and repeat the process until all the reference points are traversed.

[0045] The beneficial effect of the above further scheme is that by calculating whether the areas of the planar regions surrounded by the reference lines corresponding to the two adjacent reference points are equal, it can be determined more conveniently whether the structure of the building in the target region changes from bottom to top, and when the structure changes, the reference lines can be refined to obtain more detailed reference lines, thereby facilitating more accurate construction of the initial target building space model of the entire building.

[0046] Further, the image processing platform gradually constructs the initial target building space model in the target region based on all the reference lines, and the specific implementation is as follows:

[0047] Select two adjacent reference lines in all the reference lines as a group, select the higher reference line in each group, and construct a polygonal column body with the Z-axis direction interval between the reference lines in each group as the height, and insert the target building space model in the initial state;

[0048] Select the lower reference line in each group, construct polygonal columns with the Z-axis spacing between the reference lines in each group as the height, and insert them into the target building space model in the initial state;

[0049] This process is repeated until the polygonal columnar bodies between each set of adjacent reference lines are inserted, thus obtaining the initial target architectural space model.

[0050] The beneficial effect of the above-mentioned further solution is that by using the higher and lower reference lines in each set of reference lines as references and constructing polygonal columns with the Z-axis interval between each set of reference lines as the height, the polygonal columns corresponding to each set of reference lines can be constructed more accurately. In this way, the polygonal columns corresponding to all sets of reference lines can constitute the initial target building space model of the target building and be uploaded to the cloud server for storage.

[0051] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of the image processing-based violation detection and control method are implemented.

[0052] The present invention also provides an image processing-based device for detecting and controlling violations, including the aforementioned storage medium, a processor, and a computer program stored in the storage medium and executable on the processor. When the processor executes the computer program, it implements the image processing-based steps for detecting and controlling violations. Attached Figure Description

[0053] Figure 1 This is a flowchart illustrating a method for detecting and controlling violations based on image processing according to an embodiment of the present invention.

[0054] Figure 2 This is a schematic diagram of the structure of a violation detection and control system based on image processing according to an embodiment of the present invention. Detailed Implementation

[0055] The principles and features of the present invention are described below with reference to the accompanying drawings. The examples given are only for explaining the present invention and are not intended to limit the scope of the present invention.

[0056] like Figure 1 As shown, a method for detecting and controlling violations based on image processing includes the following steps:

[0057] S1: Use an unmanned aerial vehicle (UAV) for automatic cruise to collect initial image information of the target area, and upload the initial image information to the image processing platform;

[0058] S2: the image processing platform processes the initial image information, establishes an initial target building space model, and constructs an initial space model database and uploads to a cloud server;

[0059] S3: real-time image information of a target area is collected by automatic cruising of a drone, and the image processing platform establishes a real-time target building space model according to the real-time image information;

[0060] S4: the real-time target building space model is matched with the initial space model database to determine whether there is illegal building in the target area, and illegal building prompt information is generated when there is illegal building.

[0061] The method for checking illegal buildings based on image processing of the application can automatically collect initial image information of a target area by using a drone, and the image processing platform processes and constructs an initial space model database, so that the real-time target building space model constructed by the real-time image information collected by the drone is matched, so that it can be determined more conveniently whether there is illegal building in the target area, and illegal building prompt information is generated when there is illegal building, greatly improving the efficiency and accuracy of checking illegal buildings, reducing labor costs, improving regulatory effect, and facilitating orderly planning of cities.

[0062] In one or more embodiments of the application, the image processing platform processes the initial image information to establish an initial target building space model, specifically including the following steps:

[0063] S21: performing feature extraction processing on the initial image information to obtain the overall contour line of the building in the target area;

[0064] S22: establishing a space coordinate system, selecting a plurality of reference points on the overall contour line along the Z-axis direction of the space coordinate system according to a first preset interval, and generating a plurality of closed reference lines along the X-axis direction of the space coordinate system based on the reference points;

[0065] S23: gradually constructing an initial target building space model in the target area based on all the reference lines.

[0066] By performing feature extraction processing on the initial image information, all feature points of the initial image information can be obtained, and the overall contour line of the building in the target area is outlined and formed according to all the feature points, so that a plurality of reference points can be selected on the overall contour line along the Z-axis direction of the space coordinate system according to a first preset interval, so that corresponding reference lines are generated, and the initial target building space model in the target area is gradually constructed according to the reference lines, so that the initial information of the building in the target area is fixed, so as to facilitate subsequent matching and comparison.

[0067] In one or more embodiments of the present application, the generating a plurality of closed reference lines along the X-axis direction of the spatial coordinate system based on the reference points comprises the following steps:

[0068] S221: calculating the areas of the planar regions surrounded by the reference lines corresponding to the adjacent two reference points, and determining whether the areas are equal;

[0069] S222: if the areas of the planar regions surrounded by the reference lines corresponding to the adjacent two reference points are equal, then directly generating the corresponding reference lines along the X-axis direction of the spatial coordinate system according to the adjacent two reference points respectively; otherwise, entering S223;

[0070] S223: subdividing and cutting the adjacent two reference points along the Z-axis direction of the spatial coordinate system to obtain new reference points and update them;

[0071] S224: calculating the areas of the planar regions surrounded by the reference lines corresponding to the updated reference point and the lower one of the two reference points before updating, and determining whether the areas are equal, and returning to step S222 until all the reference points are traversed.

[0072] By calculating whether the areas of the planar regions surrounded by the reference lines corresponding to the adjacent two reference points are equal, it can be more convenient to determine whether the structure of the building in the target region changes from bottom to top, and when the change occurs, the reference lines can be obtained by refining the reference points, and then the initial target building space model of the entire building can be more accurately constructed subsequently.

[0073] Here, in order to improve the efficiency of subdivision, when the areas of the planar regions surrounded by the reference lines corresponding to the adjacent two reference points are not equal, the position of the average value of the Z coordinates of the adjacent two reference points can be selected as a new reference point, and then the areas of the planar regions surrounded by the reference lines corresponding to the updated reference point and the lower one of the two reference points before updating are calculated. In this way, the position where the areas of the planar regions surrounded by the reference lines corresponding to the adjacent two reference points change can be quickly found, and this position can be used as the final updated reference point for calculation, thereby greatly improving the efficiency of subdivision.

[0074] In one or more embodiments of the present application, the gradually constructing an initial target building space model in the target region based on all the reference lines comprises the following steps:

[0075] S231: Select two adjacent reference lines in all the reference lines as a group, select the higher reference line in each group, and construct a polygonal column with the Z-axis direction interval between each group of reference lines as the height, and insert the target building space model in the initial state;

[0076] S232: Select the lower reference line in each group, and construct a polygonal column with the Z-axis direction interval between each group of reference lines as the height, and insert the target building space model in the initial state;

[0077] S233: Repeat the above steps until the polygonal column between each group of adjacent reference lines is inserted, and the initial target building space model is obtained.

[0078] By taking the higher reference line and the lower reference line in each group of reference lines as the reference, and constructing a polygonal column with the Z-axis direction interval between each group of reference lines as the height, the polygonal column corresponding to each group of reference lines can be accurately constructed. Thus, the polygonal columns corresponding to all groups of reference lines can constitute the initial target building space model of the target building, and be uploaded to the cloud server for storage.

[0079] In one or more embodiments of the present application, in step S4, the specific process of matching the real-time target building space model with the initial space model database can be:

[0080] The coordinates of the boundary contour endpoints of the real-time target building space model and the initial space model are read in real time, and it is determined whether the coordinates of the boundary contour endpoints are equal. When the coordinates (any one or more of X coordinate, Y coordinate and Y coordinate) of the boundary contour endpoints of the target building space model are greater than the coordinates of the boundary contour endpoints of the initial space model, it is determined whether there is illegal building in the target area, and illegal building prompt information is generated when there is illegal building, otherwise there is no illegal building. This judgment method is very accurate, which can ensure that the addition of buildings in any direction can be discovered in time.

[0081] In practice, since the illegal building is generally added, the surface area or volume of the building will increase, therefore, in practice, the surface area or volume comparison method can be used to determine whether there is illegal building, when matching the real-time target building space model with the initial space model database, the surface area or volume of the target building can be calculated according to the coordinates of the boundary contour endpoints of the real-time target building space model and the initial space model, whether there is illegal building is determined by comparing the surface area or volume of the real-time target building space model and the initial space model, when the surface area or volume of the real-time target building space model is greater than the surface area or volume of the initial space model, it can be confirmed that there is illegal building, otherwise there is no illegal building.

[0082] Of course, in practice, in order to discover illegal building more timely, the most ideal situation is not to discover after the illegal building is completed, but to timely warn when the building in the target area has any shape change, for example, before the illegal building, part of the existing building may be demolished and then newly built, at this time, the coordinates of the boundary contour endpoints of the target building space model (any one or more of the X coordinate, Y coordinate and Y coordinate) will be less than the coordinates of the boundary contour endpoints of the initial space model, or the surface area or volume of the real-time target building space model is less than the surface area or volume of the initial space model, if it is directly determined as no illegal building according to the above method, but in practice, it may be in the early stage of illegal building. At this time, if the change is discovered and warned in time, illegal building can be effectively prevented.

[0083] Therefore, in the embodiment, when matching the real-time target building space model with the initial space model database, as long as the matching parameters of the real-time target building space model and the initial space model are not equal, and the matching parameters of the real-time target building space model are looser than the matching parameters of the initial space model, a warning information is generated, for example, the coordinates of the boundary contour endpoints of the target building space model (any one or more of the X coordinate, Y coordinate and Y coordinate) are less than the coordinates of the boundary contour endpoints of the initial space model, or the surface area or volume of the real-time target building space model is less than the surface area or volume of the initial space model, then a warning information is generated, which facilitates the relevant function to discover the change of the building in the target area in time, and lays a good foundation for avoiding subsequent illegal building.

[0084] As shown in Figure 2 The application also provides an illegal building control and detection system based on image processing, which comprises a collection module, an image processing platform and a matching prompt module.

[0085] The collection module is used for collecting initial image information of a target area and uploading the initial image information to the image processing platform.

[0086] The image processing platform is used for processing the initial image information, establishing an initial target building space model, constructing an initial space model database and uploading to a cloud server.

[0087] The collection module is further used for collecting real-time image information of the target area.

[0088] The image processing platform is further used for establishing a real-time target building space model according to the real-time image information.

[0089] The matching prompt module is used for matching the real-time target building space model with the initial space model database, judging whether there is illegal building in the target area, and generating illegal building prompt information when there is illegal building.

[0090] The system for checking illegal buildings based on image processing can automatically collect initial image information of a target area by using a drone, and process the initial image information by the image processing platform to construct an initial space model database, so as to match the real-time target building space model constructed by real-time image information collected by the drone, so that whether there is illegal building in the target area can be determined more conveniently, and illegal building prompt information is generated when there is illegal building, so that the efficiency and accuracy of checking illegal buildings are greatly improved, the labor cost is low, the supervision effect is good, and the orderly planning of the city is facilitated.

[0091] In one or more embodiments of the present application, the collection module can use an existing drone.

[0092] In one or more embodiments of the present application, the image processing platform processes the initial image information to establish an initial target building space model, and the specific implementation is as follows:

[0093] performing feature extraction processing on the initial image information to obtain the overall contour line of the building in the target area;

[0094] establishing a space coordinate system, selecting a plurality of reference points on the overall contour line according to a first preset interval along the Z-axis direction of the space coordinate system, and generating a plurality of closed reference lines along the X-axis direction of the space coordinate system based on the reference points;

[0095] gradually constructing the initial target building space model in the target area based on all the reference lines.

[0096] Through feature extraction processing on the initial image information, all feature points of the initial image information can be obtained, and the overall contour line of the building in the target region is outlined and formed according to all the feature points, so that a plurality of reference points can be selected on the overall contour line along the Z-axis direction of the spatial coordinate system according to a first preset interval, thereby generating corresponding reference lines, and the initial target building space model in the target region is gradually constructed according to the reference lines, and the initial information of the building in the target region is solidified, so as to facilitate subsequent matching comparison.

[0097] In one or more embodiments of the present application, the specific implementation of the image processing platform generating a plurality of closed reference lines along the X-axis direction of the spatial coordinate system based on the reference points is:

[0098] The areas of the planar regions surrounded by the reference lines corresponding to the two adjacent reference points are calculated, and it is determined whether the areas are equal;

[0099] If the areas of the planar regions surrounded by the reference lines corresponding to the two adjacent reference points are equal, the corresponding reference lines are directly generated along the X-axis direction of the spatial coordinate system according to the two adjacent reference points, respectively; otherwise,

[0100] The two adjacent reference points are subdivided along the Z-axis direction of the spatial coordinate system to obtain new reference points and update them;

[0101] The areas of the planar regions surrounded by the reference lines corresponding to the updated reference points and the lower reference point of the two reference points before updating are calculated, and it is determined whether the areas are equal, and the process is repeated until all the reference points are traversed.

[0102] By calculating whether the areas of the planar regions surrounded by the reference lines corresponding to the two adjacent reference points are equal, it can be determined whether the structure of the building in the target region changes from bottom to top, and when the structure changes, the reference lines can be refined by refining the reference points, thereby facilitating more accurate construction of the initial target building space model of the entire building.

[0103] In one or more embodiments of the present application, the specific implementation of the image processing platform gradually constructing an initial target building space model in the target region based on all the reference lines is:

[0104] Selecting two adjacent reference lines in all the reference lines as a group, selecting the higher reference line in each group, and constructing a polygonal columnar body with the Z-axis direction interval between the reference lines in each group as the height, and inserting the target building space model in the initial state;

[0105] The lower reference line in each group is selected, and polygonal columnar bodies are constructed with the Z-axis direction interval between the reference lines in each group as the height, and are inserted into the target building space model in the initial state;

[0106] This is repeated until the polygonal columnar bodies between each group of adjacent reference lines are inserted, and the initial target building space model is obtained.

[0107] By taking the higher reference line and the lower reference line in each group of reference lines as the reference, and constructing polygonal columnar bodies with the Z-axis direction interval between the reference lines in each group as the height, the polygonal columnar bodies corresponding to each group of reference lines can be accurately constructed, and the polygonal columnar bodies corresponding to all groups of reference lines can constitute the initial target building space model of the target building, and can be uploaded to a cloud server for storage.

[0108] The application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to realize the steps of the image processing-based violation checking and control method.

[0109] The application further provides an image processing-based violation checking and control device, which comprises the storage medium, the processor, and the computer program stored in the storage medium and executable on the processor, and the processor executes the computer program to realize the steps of the image processing-based violation checking and control method.

[0110] The above description is only the preferred embodiment of the application, and is not intended to limit the application, and any modification, equivalent replacement, improvement, etc. within the spirit and principle of the application shall be included in the protection scope of the application.

Claims

1. An image processing-based method for checking and controlling violations, characterized in that, The method comprises the following steps: S1: collecting initial image information of a target area by automatic cruising of a UAV, and uploading the initial image information to an image processing platform; S2: processing the initial image information by the image processing platform, establishing an initial target building space model, constructing an initial space model database, and uploading the initial space model database to a cloud server; S3: collecting real-time image information of the target area by automatic cruising of the UAV, and establishing a real-time target building space model by the image processing platform according to the real-time image information; S4: matching the real-time target building space model with the initial space model database, judging whether there is illegal building in the target area, and generating illegal building prompt information when there is illegal building; The method for processing the initial image information by the image processing platform to establish the initial target building space model comprises the following steps: S21: performing feature extraction processing on the initial image information to obtain the overall contour line of the building in the target area; S22: establishing a space coordinate system, selecting a plurality of reference points on the overall contour line according to a first preset interval along the Z-axis direction of the space coordinate system, and generating a plurality of closed reference lines along the X-axis direction of the space coordinate system based on the reference points; S23: gradually constructing the initial target building space model in the target area based on all the reference lines; The method for generating a plurality of closed reference lines along the X-axis direction of the space coordinate system based on the reference points comprises the following steps: S221: calculating the areas of the planar regions surrounded by the reference lines corresponding to two adjacent reference points, and judging whether the areas are equal; S222: if the areas of the planar regions surrounded by the reference lines corresponding to two adjacent reference points are equal, then directly generating corresponding reference lines along the X-axis direction of the space coordinate system according to the two adjacent reference points, respectively; Otherwise; S223: subdividing and cutting the two adjacent reference points along the Z-axis direction of the space coordinate system to obtain new reference points and update the reference points; S224: calculating the areas of the planar regions surrounded by the reference lines corresponding to the updated reference points and the lower reference point of the two reference points before updating, judging whether the areas are equal, and returning to step S222 until all the reference points are traversed; The method for gradually constructing the initial target building space model in the target area based on all the reference lines comprises the following steps: S231: selecting two adjacent reference lines in all the reference lines as a group, selecting the higher reference line in each group, constructing a polygonal column with the Z-axis direction interval between the reference lines in each group as the height, and inserting the polygonal column into the target building space model in the initial state; S232: selecting the lower reference line in each group, constructing a polygonal column with the Z-axis direction interval between the reference lines in each group as the height, and inserting the polygonal column into the target building space model in the initial state; S233: repeat the above steps until the polygonal columnar body insertion between each group of adjacent reference lines is completed, and the initial target building space model is obtained.

2. An image processing-based contraband detection system, comprising: The system comprises a collection module, an image processing platform and a matching prompt module. The collection module is configured to collect initial image information of a target area and upload the initial image information to the image processing platform. The image processing platform is configured to process the initial image information, establish an initial target building space model, construct an initial space model database and upload the initial space model database to a cloud server. The collection module is further configured to collect real-time image information of the target area. The image processing platform is further configured to establish a real-time target building space model according to the real-time image information. The matching prompt module is configured to match the real-time target building space model with the initial space model database, determine whether there is illegal building in the target area, and generate illegal building prompt information when there is illegal building. The image processing platform processes the initial image information to establish the initial target building space model in the following manner: perform feature extraction processing on the initial image information to obtain the overall contour line of the building in the target area; establish a space coordinate system, select a plurality of reference points on the overall contour line according to a first preset interval along the Z-axis direction of the space coordinate system, and generate a plurality of closed reference lines along the X-axis direction of the space coordinate system based on the reference points; gradually construct the initial target building space model in the target area based on all the reference lines. The image processing platform generates a plurality of closed reference lines along the X-axis direction of the space coordinate system based on the reference points in the following manner: calculate the areas of the planar regions surrounded by the reference lines corresponding to two adjacent reference points, and determine whether the areas are equal; if the areas of the planar regions surrounded by the reference lines corresponding to two adjacent reference points are equal, directly generate the corresponding reference lines along the X-axis direction of the space coordinate system according to the two adjacent reference points, respectively; otherwise; subdivide and cut the two adjacent reference points along the Z-axis direction of the space coordinate system to obtain new reference points and update the reference points; calculate the areas of the planar regions surrounded by the reference lines corresponding to the updated reference points and the lower reference point of the two reference points before updating, and determine whether the areas are equal, and repeat the operation until all the reference points are traversed; The image processing platform gradually constructs the initial target building space model in the target area based on all the reference lines in the following manner: select two adjacent reference lines in all the reference lines as a group, select the higher reference line in each group, construct a polygonal columnar body with the Z-axis direction interval between the reference lines in each group as the height, and insert the polygonal columnar body into the target building space model in the initial state; select the lower reference line in each group, construct a polygonal columnar body with the Z-axis direction interval between the reference lines in each group as the height, and insert the polygonal columnar body into the target building space model in the initial state; This is repeated until the polygonal columnar body insertion between each set of adjacent reference lines is completed, obtaining the initial target building space model.

3. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the image processing-based violation checking method of claim 1.

4. An image processing-based contraband searching device, characterized by comprising: The computer program is executed by the processor to implement the steps of the image processing-based violation checking method of claim 1. At least one processor; And The memory is in communication with the at least one processor; wherein The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the image processing-based violation checking method of claim 1.

Images