Channel occupancy monitoring method, device and equipment based on intelligent image recognition
By using intelligent image recognition technology to identify passageway occupancy in nuclear power plants, the problem of inaccurate passageway occupancy identification in nuclear power plants has been solved, thereby improving both safety and accuracy.
Patent Information
- Application Number
- CN202510366196.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-26
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2045-03-26
AI Technical Summary
Current technology cannot accurately identify the occupancy of passageways within nuclear power plants, which affects the operational safety of nuclear power plants.
The method adopts intelligent image recognition, establishes a network connection between the management server and the image acquisition equipment and alarm, periodically collects monitoring images, and uses preset road occupation judgment rules and image adjustment strategies to identify suspected road occupation and generate alarm commands.
It improves the accuracy of channel occupancy judgment, realizes intelligent identification and timely alarm of channel occupancy, and ensures the safe operation of nuclear power plants.
Smart Images

Figure CN120298965B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of image recognition technology, and in particular to a method, apparatus and equipment for monitoring channel occupancy based on intelligent image recognition. Background Technology
[0002] Nuclear power plants have material transport channels, personnel access channels, fire escape routes, etc., which must be kept unobstructed. When objects are piled up in these channels, obstructing them, it hinders the smooth transport of materials or personnel within the nuclear power plant, impacting operational safety. To prevent channels from being blocked for extended periods without timely and effective clearing, current technology typically involves monitoring personnel checking monitors to see if any objects are obstructing the channels. However, due to the large number of channels within a nuclear power plant, and the varying wall colors and channel dimensions, monitoring personnel cannot quickly identify obstructions from a large number of screens, affecting the accuracy of channel occupancy identification. Therefore, current methods cannot accurately identify channel occupancy within nuclear power plants. Summary of the Invention
[0003] This invention provides a method, apparatus, and device for monitoring channel occupancy based on intelligent image recognition, aiming to solve the problem that existing methods cannot accurately identify channel occupancy in nuclear power plants.
[0004] In a first aspect, embodiments of the present invention provide a channel occupancy monitoring method based on intelligent image recognition, wherein the method is applied in a management server, the management server establishing a network connection with image acquisition devices and alarms installed at each channel to achieve data information transmission, the method comprising:
[0005] The monitoring images are acquired from the image acquisition device according to the preset acquisition interval;
[0006] The monitoring images are judged according to the preset road occupation judgment rules to obtain the judgment result of whether each monitoring image is suspected of road occupation;
[0007] If the judgment result is suspected road obstruction, the monitoring image is adjusted according to the preset image adjustment strategy to obtain the corresponding target image;
[0008] The target image is matched according to a preset type matching rule to obtain the corresponding road occupancy monitoring type;
[0009] Based on the type of road occupancy monitoring, a corresponding alarm command is generated and sent to the alarm device corresponding to the target image.
[0010] Secondly, embodiments of the present invention also provide a channel occupancy monitoring device based on intelligent image recognition, wherein the device is configured in a management server, the management server establishes a network connection with image acquisition devices and alarms installed at each channel to realize data information transmission, the device is used to execute the channel occupancy monitoring method based on intelligent image recognition as described in the first aspect above, and the device includes:
[0011] The monitoring image acquisition unit is used to acquire the acquired monitoring images from the image acquisition device according to a preset acquisition interval time.
[0012] The judgment unit is used to judge each of the monitoring images according to the preset road occupation judgment rules, and to obtain the judgment result of whether each monitoring image is suspected of road occupation;
[0013] The target image acquisition unit is used to adjust the monitoring image according to a preset image adjustment strategy to obtain the corresponding target image if the judgment result is suspected road occupation.
[0014] The road occupation monitoring type acquisition unit is used to perform type matching on the target image according to the preset type matching rules to obtain the corresponding road occupation monitoring type;
[0015] An alarm command sending unit is used to generate a corresponding alarm command based on the road occupancy monitoring type and send it to the alarm corresponding to the target image.
[0016] Thirdly, embodiments of the present invention also provide a computer device, wherein the device includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;
[0017] Memory, used to store computer programs;
[0018] When a processor executes a program stored in memory, it implements the steps of the channel occupancy monitoring method based on intelligent image recognition described in the first aspect above.
[0019] Fourthly, embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the channel occupancy monitoring method based on intelligent image recognition as described in the first aspect above.
[0020] This invention provides a method, apparatus, and device for monitoring channel occupancy based on intelligent image recognition. The method includes: acquiring monitoring images from an image acquisition device according to a preset acquisition interval; judging each monitoring image according to a preset occupancy judgment rule to obtain a judgment result of whether each monitoring image is suspected of being occupied; if the judgment result is suspected of being occupied, adjusting the monitoring image according to a preset image adjustment strategy to obtain a corresponding target image; performing type matching on the target image according to a preset type matching rule to obtain a corresponding occupancy monitoring type; generating a corresponding alarm command according to the occupancy monitoring type and sending it to the alarm corresponding to the target image. The above-described channel occupancy monitoring method can periodically acquire monitoring images and judge whether there is suspected occupancy. If suspected occupancy exists, it further adjusts the monitoring image to obtain a target image and performs type matching to obtain the corresponding occupancy monitoring type and generate an alarm command; it can achieve intelligent recognition of channel occupancy, significantly improving the accuracy of channel occupancy judgment. Attached Figure Description
[0021] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0022] Figure 1 This is a flowchart of a channel occupancy monitoring method based on intelligent image recognition provided in an embodiment of the present invention;
[0023] Figure 2 A schematic diagram illustrating an application scenario of the channel occupancy monitoring method based on intelligent image recognition provided in an embodiment of the present invention;
[0024] Figure 3 The image shows the application effect of the channel occupancy monitoring method based on intelligent image recognition provided in the embodiments of the present invention.
[0025] Figure 4 A schematic block diagram of a channel occupancy monitoring device based on intelligent image recognition provided in an embodiment of the present invention;
[0026] Figure 5 This is a schematic block diagram of a computer device provided in an embodiment of the present invention. Detailed Implementation
[0027] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0028] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.
[0029] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.
[0030] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.
[0031] This invention application provides a channel occupancy monitoring method based on intelligent image recognition. This method is applied to a management server 10, which executes a stored software program to implement the aforementioned channel occupancy monitoring method based on intelligent image recognition. The management server 10 can be a server-side device configured in the computer room of a nuclear power plant for intelligent monitoring of channel occupancy. The management server 10 can be a cluster server, parallel processing server, or other server equipment. Please refer to... Figure 2 As shown in the figure, in this management server, the management server establishes a network connection with the image acquisition device 20 and the alarm 30 set at each channel to realize the transmission of data information. The image acquisition device is configured at the channel and acquires the image of a section of the channel; the alarm 30 is also a device configured at each channel of the nuclear power plant to provide alarm prompts, such as a loudspeaker.
[0032] like Figure 1 As shown, the method includes steps S110 to S150.
[0033] S110. Acquire the acquired monitoring image from the image acquisition device according to the preset acquisition interval.
[0034] The management server can acquire monitoring images according to the acquisition interval. For example, the management server periodically sends acquisition commands to each image acquisition device according to the acquisition interval. Each image acquisition device acquires monitoring images according to the received acquisition commands and sends them to the management server. The management server can then receive the monitoring images acquired by the image acquisition devices. For example, if the acquisition interval can be set to 30 seconds, the management server can acquire one monitoring image corresponding to one image acquisition device every 30 seconds. One image acquisition device is set up for each channel.
[0035] S120. Based on the preset road occupation judgment rules, each of the monitoring images is judged to obtain the judgment result of whether each of the monitoring images is suspected of road occupation.
[0036] Furthermore, the obtained monitoring images are judged according to the pre-set road occupancy judgment rules. The road occupancy judgment rules are the specific rules used to judge whether there is an object occupying the road in the channel corresponding to the monitoring image. By judging, the judgment results of each monitoring image can be obtained, and the judgment results can reflect whether there is a suspected road occupancy situation in the monitoring image.
[0037] In a specific embodiment, step S120 includes the following sub-steps: judging whether there are abnormal colors in each of the monitored images according to the color parameter information in the road occupation judgment rule, and obtaining the corresponding abnormal color judgment result; extracting the corresponding channel boundary contour from each of the monitored images according to the boundary extraction parameters in the road occupation judgment rule; judging whether there are abnormalities in the boundary contours of each of the channels according to the boundary anomaly detection parameters in the road occupation judgment rule, and obtaining the corresponding boundary contour judgment result; if the abnormal color judgment result is that there is an anomaly or the boundary contour judgment result is that there is an anomaly, obtaining the judgment result of suspected road occupation; if the abnormal color judgment result is that there is no anomaly and the boundary contour judgment result is that there is no anomaly, obtaining the judgment result of no suspected road occupation.
[0038] Specifically, the presence of abnormal colors in the monitoring image can be determined based on the color parameter information in the occupancy judgment rules. The colors of the ground, walls, and ceiling within the passage are fixed colors. If, in addition to these fixed colors, the monitoring image contains color blocks that differ significantly from the ground color, then the monitoring image is considered abnormal, and the abnormal color judgment result is "abnormal color exists." Since in reality, objects with colors similar to the walls and ground may be piled up in the passage, further identifying this occupancy, the passage boundary contour can be extracted from the monitoring image based on boundary extraction parameters. The passage boundary contour includes the contours between the ground and walls, and between the walls and ceiling within the passage. The presence of abnormalities in the passage boundary contour is then judged based on boundary anomaly detection parameters, thus obtaining the boundary contour judgment result. The boundary contour judgment result also indicates whether the monitoring image contains anomalies.
[0039] If the abnormal color judgment result of the monitoring image indicates an anomaly, or the boundary contour judgment result of the monitoring image indicates an anomaly, then the judgment result of the monitoring image is suspected road encroachment. If the abnormal color judgment result of the monitoring image indicates no anomaly, and the boundary contour judgment result also indicates no anomaly, then the judgment result of the monitoring image is not suspected road encroachment.
[0040] In a specific embodiment, the step of judging whether there are abnormal colors in each of the monitoring images based on the color parameter information in the road occupancy judgment rule, and obtaining the corresponding abnormal color judgment result, includes: obtaining the color range corresponding to the monitoring image from the color parameter information; obtaining the pixels in the monitoring image that are not located in the color range as abnormal pixels; obtaining the connected components corresponding to the abnormal pixels in the monitoring image; and judging whether the area of each connected component is greater than the area threshold in the color parameter information, so as to determine whether there are abnormal colors in the monitoring image.
[0041] Specifically, the color range corresponding to the monitored image can be obtained from the color parameter information. The color parameter information contains the color range corresponding to each channel. Therefore, the color range corresponding to the monitored image can be obtained from the color range contained in the color parameter information based on the image acquisition device of the corresponding channel of the monitored image.
[0042] Further, pixels in the monitored image that are not located within the corresponding color range are identified and designated as anomalous pixels. If other anomalous pixels exist in the vicinity of a given anomalous pixel, it indicates that the anomalous pixel is connected to these other anomalous pixels; if no other anomalous pixels exist in the vicinity of a given anomalous pixel, it indicates that the anomalous pixel is not connected to these other anomalous pixels. Anomalous pixels connected to a given anomalous pixel are then identified, and it is determined whether other anomalous pixels exist among these connected anomalous pixels. These anomalous pixels are then combined based on their connectivity to form connected regions corresponding to the anomalous pixels. The area of each formed connected region is then checked against an area threshold in the color parameter information. If the area is greater, the monitored image is determined to have an anomalous color. For example, the area threshold can be set to 25 pixels.
[0043] In a specific embodiment, the step of extracting the corresponding channel boundary contour from each of the monitoring images according to the boundary extraction parameters in the road occupancy judgment rule includes: calculating the contrast coefficient of each pixel in the monitoring image; obtaining a portion of pixels in the monitoring image corresponding to the extraction ratio as candidate pixels according to the extraction ratio in the boundary extraction parameters and the contrast coefficient; binarizing the candidate pixels to obtain the corresponding pixel contour; and selecting the pixel contour that matches the boundary reference direction from the pixel contour as the corresponding channel boundary contour according to the boundary reference direction in the boundary extraction parameters.
[0044] When extracting pixel boundary contours, the contrast coefficient of each pixel in the monitored image can be calculated first. The contrast coefficient is used to reflect the difference between a pixel and its surrounding pixels. The larger the contrast coefficient of a pixel, the greater the difference between the pixel and its surrounding pixels. Specifically, the contrast coefficient can be calculated using formula (1):
[0045]
[0046] Where B is the contrast coefficient of a pixel in the calculated monitoring image, M is the number of pixels surrounding that pixel, and S... j S0 is the pixel value of the j-th pixel surrounding the given pixel; G is the number of pixels surrounding the given pixel with a one-layer gap; S... k The pixel value is the k-th pixel among the pixels one layer away from the given pixel, where e is the base of the natural logarithm. The pixel value is also the RGB value of a pixel, which is composed of the values of the three color channels: red (R), green (G), and blue (B).
[0047] Further pixel extraction is performed based on the extraction ratio in the boundary extraction parameters. The extraction ratio is the ratio between the number of extracted pixels and the number of pixels in the monitored image. For example, the extraction ratio can be set to 5%. Pixels with higher contrast coefficients in the monitored image can be selected as candidate pixels based on the extraction ratio.
[0048] Furthermore, the candidate pixels are binarized to obtain pixel contours based on the candidate pixels. The candidate pixels are then highlighted in the pixel contours; that is, the pixel values of non-candidate pixels in the image are set to white, and the pixel values of candidate pixels are set to black.
[0049] Pixel contours can be filtered based on the boundary reference direction in the boundary extraction parameters. Specifically, it can be first determined whether each pixel contour is a closed pixel contour. If a pixel contour is closed, it is filtered out, and non-closed pixel contours are retained. Further, the start point, midpoint, and end point are obtained from each non-closed pixel contour as marker pixels. The coordinates of the marker pixels are obtained, and the angle between the line connecting adjacent marker pixels and the boundary reference direction is calculated. It is determined whether this angle is not greater than a preset angle range. If the angles corresponding to the lines connecting adjacent marker pixels in a pixel contour are all within the angle range, then the pixel contour is determined to match the boundary reference direction; otherwise, the pixel contour is determined not to match the boundary reference direction. Based on the above method, all pixel contours that match the boundary reference direction can be obtained as the corresponding channel boundary contours.
[0050] In a specific embodiment, the step of judging whether there is an anomaly in the boundary contour of each channel according to the boundary anomaly detection parameters in the channel occupancy judgment rule, and obtaining the corresponding boundary contour judgment result, includes: judging whether the extension direction of the channel boundary contour is the same; if the extension direction of two channel boundary contours is the same, obtaining the deviation coefficient between the two channel boundary contours with the same extension direction according to the basic parameters in the boundary anomaly detection parameters; judging whether the deviation coefficient of the two channel boundary contours with the same extension direction is within the deviation range in the boundary anomaly detection parameters, so as to determine whether there is an anomaly in the channel boundary contour.
[0051] To determine if there are any anomalies in the channel boundary contours, it is possible to determine whether the extension directions of the channel boundary contours are the same. Specifically, the angle between the channel boundary contour and the horizontal line can be obtained, and the extension directions can be determined sequentially. If the difference between the angles between the two channel boundary contours and the horizontal line is less than an angle threshold, the extension directions of the two channel boundary contours are determined to be the same; otherwise, the extension directions of the two channel boundary contours are determined to be different.
[0052] If the extension directions of the two channel boundary contours are the same, the deviation coefficient between the two channel boundary contours with the same extension direction is further obtained based on the basic parameters in the boundary anomaly detection parameters. Specifically, the process of obtaining the deviation coefficient can be expressed by formula (2):
[0053]
[0054] L m θ is the minimum distance between the boundary contours of two channels with the same extension direction, θ is the angle difference between the boundary contours of two channels with the same extension direction and the horizontal line, P is the calculated deviation coefficient, and J is the basic parameter.
[0055] Further determine whether the deviation coefficient of the channel boundary contour is within the deviation range of the boundary anomaly detection parameters. If it is within the deviation range, it indicates that the channel boundary contour being judged does not have an anomaly. If it is not within the deviation range, it indicates that the channel boundary contour being judged has a large-scale discontinuity, that is, there is an anomaly. In this case, the area between the two channel boundary contours being judged can be marked (e.g., using a special color that is significantly different from the ground and wall to replace the color of the area between the two channel boundary contours).
[0056] S130. If the judgment result is suspected road obstruction, the monitoring image is adjusted according to the preset image adjustment strategy to obtain the corresponding target image.
[0057] If the assessment result of the monitoring image is suspected road occupation, the monitoring image can be adjusted according to the image adjustment strategy. After adjusting one monitoring image, a corresponding target image can be obtained. If the assessment result of the monitoring image is not suspected road occupation, no further processing is required for the monitoring image, and the process returns to step S110.
[0058] In a specific embodiment, step S130 includes the following sub-steps: obtaining the adjustment mapping model corresponding to the monitoring image in the image adjustment strategy; and adjusting the coordinate positions of each pixel in the monitoring image according to the coordinate mapping relationship in the adjustment mapping model to obtain the corresponding target image.
[0059] The image adjustment strategy includes adjustment mapping models corresponding to each image acquisition device. These models are generated based on the installation position and orientation of the image acquisition devices within the channel. Each adjustment mapping model contains the mapping relationship between the current position and orientation of the image acquisition device and the reference image. Since the installation position and orientation of the image acquisition devices may vary, the image adjustment strategy includes multiple adjustment mapping models. The adjustment mapping model corresponding to the monitoring image whose judgment result is suspected of obstructing the road can be obtained. This adjustment mapping model contains the coordinate mapping relationship corresponding to each coordinate point in the monitoring image, which maps the coordinate position of a coordinate point to a coordinate position in the reference image. For example... Figure 3 As shown, the adjustment mapping model corresponding to a certain monitoring image can map and adjust point A1 of the monitoring image to point A2 through the corresponding coordinate mapping relationship. Similarly, based on the coordinate mapping relationship, points B1, C1, and D1 can be mapped and adjusted to points B2, C2, and D2 respectively, so as to correct the image content of the monitoring image. If there is pixel overlap at the same coordinate position after correction, the average value of multiple pixel values with the same coordinate position is taken as the pixel value at that coordinate position. After the above mapping adjustment, a target image that conforms to the direction of the reference image can be obtained.
[0060] S140. Perform type matching on the target image according to the preset type matching rules to obtain the corresponding road occupancy monitoring type.
[0061] The target image can be type-matched according to the type matching rules. Channels in the target image may have different occupancy conditions. To distinguish between these different occupancy conditions, type matching can be performed to obtain the corresponding occupancy monitoring type. Thus, each target image can correspond to a specific occupancy monitoring type, which reflects the specific occupancy status within the channel.
[0062] In a specific embodiment, step S140 includes the following sub-steps: partitioning the target image according to the image template in the type matching rule; obtaining the ratio between the road-occupying object and the channel cross-section in the target image based on the partitioning result; and obtaining the type that matches the ratio from the type matching rule as the corresponding road-occupying monitoring type.
[0063] Since the target images have all undergone correction processing, they can be partitioned based on the image template corresponding to the reference image to determine the orientation of each partition. Furthermore, based on the partitioning results, the ratio between the object occupying the channel and the channel cross-section in the target image is obtained; the ratio between the pixel area of the region with abnormal color or the pixel area of the marked region in the target image and the pixel area of the channel cross-section in the target image can be obtained as the corresponding ratio value.
[0064] In the type matching rules, each type corresponds to a ratio range. This range is then matched with the corresponding ratio value in the target image to obtain the type corresponding to the ratio range containing that ratio value. This type is then used as the road occupancy monitoring type for the target image. For example, the types defined in the type matching rules can include minor, moderate, and severe.
[0065] S150. Generate a corresponding alarm command based on the road occupancy monitoring type and send it to the alarm device corresponding to the target image.
[0066] The system can generate a corresponding alarm command based on the type of road occupancy detection in the target image and send the alarm command to the alarm device located on the same side as the image acquisition device of the target image. Each alarm device can be set on one side of an image acquisition device; upon receiving the alarm command, the alarm device can issue an alarm prompt to remind operators passing through the passage.
[0067] After completing the above steps, you can return to step S110 to periodically collect monitoring images of each channel, thereby realizing periodic monitoring of channel occupancy.
[0068] The channel occupancy monitoring method based on intelligent image recognition disclosed in the above embodiments includes: acquiring monitoring images from an image acquisition device according to a preset acquisition interval; judging each monitoring image according to a preset occupancy judgment rule to obtain a judgment result of whether each monitoring image is suspected of occupancy; if the judgment result is suspected occupancy, adjusting the monitoring image according to a preset image adjustment strategy to obtain a corresponding target image; performing type matching on the target image according to a preset type matching rule to obtain a corresponding occupancy monitoring type; generating a corresponding alarm command according to the occupancy monitoring type and sending it to the alarm corresponding to the target image. The above channel occupancy monitoring method can periodically acquire monitoring images and judge whether there is suspected occupancy. If there is suspected occupancy, it further adjusts the monitoring image to obtain a target image and performs type matching to obtain the corresponding occupancy monitoring type and generate an alarm command; it can achieve intelligent recognition of channel occupancy, significantly improving the accuracy of channel occupancy judgment.
[0069] This invention also provides a channel occupancy monitoring device based on intelligent image recognition. This device can be configured in a management server and is used to execute any embodiment of the aforementioned channel occupancy monitoring method based on intelligent image recognition. Specifically, please refer to... Figure 4 , Figure 4 This is a schematic block diagram of a channel occupancy monitoring device based on intelligent image recognition, provided in an embodiment of the present invention.
[0070] like Figure 4 As shown, the channel occupancy monitoring device 100 based on intelligent image recognition includes a detection signal judgment unit 110, an image set acquisition unit 120, a cropped image acquisition unit 130, an individual feature information acquisition unit 140, and a detection result acquisition unit 150.
[0071] The monitoring image acquisition unit 110 is used to acquire the acquired monitoring images from the image acquisition device according to a preset acquisition interval time.
[0072] The judgment unit 120 is used to judge each of the monitoring images according to the preset road occupation judgment rules, and to obtain the judgment result of whether each monitoring image is suspected of road occupation;
[0073] The target image acquisition unit 130 is used to adjust the monitoring image according to a preset image adjustment strategy to obtain the corresponding target image if the judgment result is suspected road occupation.
[0074] The road occupation monitoring type acquisition unit 140 is used to perform type matching on the target image according to a preset type matching rule to obtain the corresponding road occupation monitoring type;
[0075] The alarm command sending unit 150 is used to generate a corresponding alarm command according to the road occupation monitoring type and send it to the alarm corresponding to the target image.
[0076] The channel occupancy monitoring device based on intelligent image recognition provided in this embodiment of the invention applies the aforementioned channel occupancy monitoring method based on intelligent image recognition. It acquires monitoring images from an image acquisition device according to a preset acquisition interval; judges each monitoring image according to a preset occupancy judgment rule to obtain a judgment result indicating whether each monitoring image is suspected of occupancy; if the judgment result is suspected occupancy, it adjusts the monitoring image according to a preset image adjustment strategy to obtain a corresponding target image; it performs type matching on the target image according to a preset type matching rule to obtain the corresponding occupancy monitoring type; and it generates a corresponding alarm command based on the occupancy monitoring type and sends it to the alarm corresponding to the target image. This channel occupancy monitoring method can periodically acquire monitoring images and determine whether there is suspected occupancy. If suspected occupancy exists, it further adjusts the monitoring image to obtain a target image and performs type matching to obtain the corresponding occupancy monitoring type and generate an alarm command; it can achieve intelligent identification of channel occupancy, significantly improving the accuracy of channel occupancy judgment.
[0077] The aforementioned channel occupancy monitoring device based on intelligent image recognition can be implemented as a computer program, which can, for example... Figure 5 It runs on the computer device shown.
[0078] Please see Figure 5 , Figure 5 This is a schematic block diagram of a computer device provided in an embodiment of the present invention. The computer device may be a management server used to execute a channel occupancy monitoring method based on intelligent image recognition to intelligently identify whether a channel is occupied.
[0079] See Figure 5 The computer device 500 includes a processor 502, a memory, and a communication interface 505 connected via a communication bus 501. The memory may include a storage medium 503 and internal memory 504.
[0080] The storage medium 503 may store an operating system 5031 and a computer program 5032. When the computer program 5032 is executed, it enables the processor 502 to execute a channel occupancy monitoring method based on intelligent image recognition. The storage medium 503 may be a volatile storage medium or a non-volatile storage medium.
[0081] The processor 502 provides computing and control capabilities to support the operation of the entire computer device 500.
[0082] The internal memory 504 provides an environment for the operation of the computer program 5032 in the storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute a channel occupancy monitoring method based on intelligent image recognition.
[0083] This communication interface 505 is used for network communication, such as providing data transmission. Those skilled in the art will understand that... Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present invention and does not constitute a limitation on the computer device 500 to which the present invention is applied. The specific computer device 500 may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.
[0084] The processor 502 is used to run the computer program 5032 stored in the memory to implement the corresponding functions in the channel occupancy monitoring method based on intelligent image recognition described above.
[0085] Those skilled in the art will understand that Figure 5 The embodiments of the computer device shown do not constitute a limitation on the specific configuration of the computer device. In other embodiments, the computer device may include more or fewer components than illustrated, or combine certain components, or have different component arrangements. For example, in some embodiments, the computer device may include only memory and a processor. In such embodiments, the structure and function of the memory and processor are different from those shown. Figure 5The embodiments shown are consistent and will not be repeated here.
[0086] It should be understood that, in this embodiment of the invention, the processor 502 may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.
[0087] In another embodiment of the invention, a computer-readable storage medium is provided. This computer-readable storage medium may be volatile or non-volatile. The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps included in the above-described channel occupancy monitoring method based on intelligent image recognition.
[0088] Those skilled in the art will readily understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this invention.
[0089] In the embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Units with the same function may be grouped into one unit. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices, or units, or it may be an electrical, mechanical, or other form of connection.
[0090] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of the present invention, depending on actual needs.
[0091] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0092] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a computer-readable storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned computer-readable storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), magnetic disks, or optical disks.
[0093] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.
Claims
1. A channel occupancy monitoring method based on intelligent image recognition, characterized in that, The method is applied in a management server, which establishes a network connection with the image acquisition devices and alarms installed at each channel to achieve data information transmission. The method includes: The monitoring images are acquired from the image acquisition device according to the preset acquisition interval; The monitoring images are judged according to the preset road occupation judgment rules to obtain the judgment result of whether each monitoring image is suspected of road occupation; If the judgment result is suspected road obstruction, the monitoring image is adjusted according to the preset image adjustment strategy to obtain the corresponding target image; The target image is matched according to a preset type matching rule to obtain the corresponding road occupancy monitoring type; Based on the type of road occupancy monitoring, a corresponding alarm command is generated and sent to the alarm device corresponding to the target image; The step of judging each monitoring image according to a preset road occupation judgment rule to obtain a judgment result on whether each monitoring image is suspected of road occupation includes: Based on the color parameter information in the road occupation judgment rule, the presence of abnormal colors in each of the monitoring images is judged to obtain the corresponding abnormal color judgment result; The corresponding channel boundary contour is extracted from each of the monitoring images according to the boundary extraction parameters in the road occupation judgment rule; Based on the boundary anomaly detection parameters in the road occupancy judgment rules, the boundary contours of each channel are judged to determine whether there are any anomalies, and the corresponding boundary contour judgment results are obtained. If the abnormal color judgment result is that there is an abnormality or the boundary contour judgment result is that there is an abnormality, a judgment result of suspected road occupation is obtained. If the abnormal color judgment result is no abnormality and the boundary contour judgment result is no abnormality, the judgment result of no suspected road occupation is obtained; The step of extracting the corresponding channel boundary contour from each of the monitoring images according to the boundary extraction parameters in the road occupancy judgment rule includes: Calculate the contrast coefficient of each pixel in the monitored image; the contrast coefficient is calculated using the following formula: Where B is the contrast coefficient of a pixel in the calculated monitoring image, M is the number of pixels surrounding that pixel, and S... j S0 is the pixel value of the j-th pixel surrounding the given pixel; G is the number of pixels surrounding the given pixel with a one-layer gap; Sj is the pixel value of the given pixel. k Let e be the pixel value of the k-th pixel among the pixels that are one pixel apart from the given pixel, where e is the base of the natural logarithm. Based on the extraction ratio in the boundary extraction parameters and the contrast coefficient, a subset of pixels corresponding to the extraction ratio are obtained from the monitoring image as candidate pixels. The candidate pixels are binarized to obtain the corresponding pixel contours; The pixel contours that match the boundary reference direction are selected from the pixel contours according to the boundary extraction parameters and used as the corresponding channel boundary contours. The step of judging whether there are anomalies in the boundary contours of each channel according to the boundary anomaly detection parameters in the channel occupancy judgment rule, and obtaining the corresponding boundary contour judgment result, includes: Determine whether the extension directions of the channel boundary contours are the same; If the two channel boundary contours extend in the same direction, the deviation coefficient between the two channel boundary contours extending in the same direction is obtained according to the basic parameters in the boundary anomaly detection parameters; the deviation coefficient is obtained by formula... Calculated; L m θ is the minimum distance between the boundary contours of two channels with the same extension direction, θ is the angle difference between the boundary contours of two channels with the same extension direction and the horizontal line, P is the calculated deviation coefficient, and J is the basic parameter. Determine whether the deviation coefficients of the boundary contours of the two channels with the same extension direction are within the deviation range of the boundary anomaly detection parameters, so as to determine whether there is an anomaly in the channel boundary contours.
2. The channel occupancy monitoring method based on intelligent image recognition according to claim 1, characterized in that, The step of judging whether there are abnormal colors in each of the monitored images based on the color parameter information in the road occupation judgment rule, and obtaining the corresponding abnormal color judgment result, includes: Obtain the color range corresponding to the monitoring image from the color parameter information; Pixels in the monitored image that are not located within the color range are identified as abnormal pixels. Obtain the connected components corresponding to the abnormal pixels in the monitored image; Determine whether the area of each connected component is greater than the area threshold in the color parameter information to determine whether there are abnormal colors in the monitored image.
3. The channel occupancy monitoring method based on intelligent image recognition according to any one of claims 1-2, characterized in that, The step of adjusting the monitored image according to a preset image adjustment strategy to obtain the corresponding target image includes: Obtain the adjustment mapping model corresponding to the monitored image in the image adjustment strategy; The coordinate positions of each pixel in the monitoring image are adjusted according to the coordinate mapping relationship in the adjustment mapping model to obtain the corresponding target image.
4. The channel occupancy monitoring method based on intelligent image recognition according to any one of claims 1-2, characterized in that, The step of performing type matching on the target image according to preset type matching rules to obtain the corresponding road occupancy monitoring type includes: The target image is partitioned according to the image template in the type matching rule; Based on the partitioning results, obtain the ratio between the object occupying the channel and the channel cross-section in the target image; The type that matches the ratio value is obtained from the type matching rules and used as the corresponding road occupancy monitoring type.
5. A channel occupancy monitoring device based on intelligent image recognition, characterized in that, The device is configured in a management server, which establishes a network connection with the image acquisition devices and alarms installed at each channel to achieve data information transmission. The device is used to execute the channel occupancy monitoring method based on intelligent image recognition as described in any one of claims 1-4, and the device includes: The monitoring image acquisition unit is used to acquire the acquired monitoring images from the image acquisition device according to a preset acquisition interval time. The judgment unit is used to judge each of the monitoring images according to the preset road occupation judgment rules, and to obtain the judgment result of whether each monitoring image is suspected of road occupation; The target image acquisition unit is used to adjust the monitoring image according to a preset image adjustment strategy to obtain the corresponding target image if the judgment result is suspected road occupation. The road occupation monitoring type acquisition unit is used to perform type matching on the target image according to the preset type matching rules to obtain the corresponding road occupation monitoring type; An alarm command sending unit is used to generate a corresponding alarm command based on the road occupancy monitoring type and send it to the alarm corresponding to the target image.
6. A computer device, characterized in that, The device includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; When a processor executes a program stored in memory, it implements the steps of the channel occupancy monitoring method based on intelligent image recognition as described in any one of claims 1-4.
7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the channel occupancy monitoring method based on intelligent image recognition as described in any one of claims 1-4.
Citation Information
Patent Citations
Method and system for detecting illegal lane occupation of vehicle
CN112163543A
Cable stacking control method, device and equipment based on automatic positioning and medium
CN117142156A
Traffic sign recognition device and traffic sign recognition method
US20230237812A1
