Zoom global visual deformation detection method and device, electronic equipment and medium

Abstract

The embodiment of the invention discloses a variable-focus global visual deformation detection method and device, electronic equipment and a medium. The method comprises the following steps: receiving a detection section image of each detection section of a to-be-detected body acquired by zoom image acquisition equipment; wherein different detection section images correspond to different focal length values of the zoom image acquisition equipment; the detection section image comprises a detection target deployed on the to-be-detected body; determining a detection coordinate of a detection target deployed on the to-be-detected body in a target coordinate system based on the detection section image; and determining deformation information generated by the to-be-detected body based on the detection coordinates of the detection targets and predetermined standard coordinates of the detection targets in the target coordinate system when the to-be-detected body is in the standard state. According to the technical scheme of the embodiment of the invention, different detection section images can be obtained without installing a plurality of image acquisition devices, the deformation detection cost is reduced, and the detection convenience and accuracy are improved.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of machine vision technology, and in particular to a variable-focus global visual deformation detection method, device, electronic device, and medium. Background Art

[0002] With the rapid development of machine vision technology, non-contact deformation detection technology based on machine vision is widely used in fields such as urban safety detection and health detection of bridges and dams.

[0003] In the prior art, to perform segmented detection on the object to be detected, it is necessary to install multiple image acquisition devices with different focal lengths at one end of the object to be detected to collect image information corresponding to different detection segments of the object to be detected. The deformation of each detection segment is determined based on the image information, so as to determine the overall deformation of the object to be detected based on the deformation of each detection segment.

[0004] However, in the process of implementing the present invention, it was found that the prior art has at least the following technical problems: the deformation of the object to be detected is detected by installing multiple image acquisition devices with different focal lengths, which leads to increased costs; and the performance of different image acquisition devices is inconsistent, resulting in poor accuracy of the detection results. Summary of the invention

[0005] The embodiments of the present invention provide a variable-focus global visual deformation detection method, device, electronic device and medium to achieve the purpose of reducing deformation detection costs and improving detection convenience and accuracy.

[0006] According to one aspect of the present invention, a variable-focus global visual deformation detection method is provided, comprising:

[0007] Receiving detection segment images of each detection segment of the object to be detected acquired by a zoom image acquisition device; wherein different detection segment images correspond to different focal length values ​​of the zoom image acquisition device; and the detection segment images contain detection targets deployed on the object to be detected;

[0008] Based on the detection segment image, determining the detection coordinates of the detection target deployed on the object to be detected in the target coordinate system;

[0009] Based on the detection coordinates of the detection targets and the predetermined standard coordinates of each of the detection targets in the target coordinate system when the object to be detected is in a standard state, the deformation information generated by the object to be detected is determined.

[0010] According to another aspect of the present invention, a variable-focus global visual deformation detection device is provided, the device comprising:

[0011] An image receiving module, used for receiving detection segment images of each detection segment of the object to be detected acquired by the zoom image acquisition device; wherein different detection segment images correspond to different focal length values ​​of the zoom image acquisition device; and the detection segment images contain detection targets deployed on the object to be detected;

[0012] A coordinate determination module, used to determine the detection coordinates of the detection target deployed on the object to be detected in a target coordinate system based on the detection segment image;

[0013] The information determination module is used to determine the deformation information generated by the object to be detected based on the detection coordinates of the detection target and the predetermined standard coordinates of each of the detection targets in the target coordinate system when the object to be detected is in a standard state.

[0014] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0015] at least one processor; and

[0016] a memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the variable-focus global visual deformation detection method described in any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the variable-focus global visual deformation detection method described in any embodiment of the present invention when executed.

[0019] The technical solution of the embodiment of the present invention receives the detection segment images of each detection segment of the object to be detected collected by the zoom image acquisition device; wherein different detection segment images correspond to different focal length values ​​of the zoom image acquisition device; the detection segment images contain the detection targets deployed on the object to be detected, so that by adjusting the zoom image acquisition device to different focal length values, the detection segment images corresponding to different detection segments are collected; and based on the detection segment images, the detection coordinates of the detection targets deployed on the object to be detected in the target coordinate system are determined; finally, based on the detection coordinates of the detection targets and the predetermined standard coordinates of each detection target in the target coordinate system when the object to be detected is in a standard state, the deformation information generated by the object to be detected is determined. The technical solution provided by this embodiment can obtain different detection segment images without installing multiple image acquisition devices, which reduces the cost of deformation detection and improves the convenience and accuracy of detection.

[0020] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 is a flow chart of a variable-focus global visual deformation detection method provided according to an embodiment of the present invention;

[0023] Figure 2 is a flow chart of another variable-focus global visual deformation detection method provided according to an embodiment of the present invention;

[0024] Figure 3 is a schematic diagram of a target layout provided according to an embodiment of the present invention;

[0025] Figure 4 is a structural schematic diagram of a variable-focus global visual deformation detection device provided according to an embodiment of the present invention;

[0026] Figure 5 It is a schematic diagram of the structure of an electronic device that implements the variable-focus global visual deformation detection method of an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "etc." and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0029] It should be noted that the collection, collection, updating, analysis, processing, use, transmission, storage and other aspects of user personal information involved in the technical solution of this disclosure are in compliance with the provisions of relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. Necessary measures are taken for user personal information to prevent illegal access to user personal information data and maintain the security of user personal information and network security.

[0030] Figure 1 This is a flow chart of a variable-focus global visual deformation detection method provided according to an embodiment of the present invention. This embodiment is applicable to the case of determining the deformation information of the object to be detected relative to the standard state. The method can be performed by a variable-focus global visual deformation detection device, which can be implemented in the form of hardware and / or software.

[0031] like Figure 1 As shown, the method of this embodiment may specifically include:

[0032] S110: Receive detection segment images of each detection segment of the object to be detected acquired by a zoom image acquisition device.

[0033] It should be noted that the zoom image acquisition device refers to an image acquisition device that can adjust the focal length. By adjusting the focal length, the viewing angle and the magnification of the image are changed, so as to acquire images of objects at different distances and ranges. The zoom image acquisition device can be installed at one end of the object to be detected. A plurality of detection targets can be deployed on the object to be detected, and the object to be detected can be divided into a plurality of detection segments according to the detection targets. For example, the part of the object to be detected that includes two detection targets can be used as a detection segment. The detection segment image is the image corresponding to the detection segment acquired by the zoom image acquisition device.

[0034] Among them, different detection segment images correspond to different focal length values ​​of the zoom image acquisition device; the detection segment image contains the detection target deployed on the object to be detected. The object to be detected is an object whose deformation needs to be detected; illustratively, the object to be detected can be a dam, a tunnel, a bridge, etc. When the object to be detected is a bridge, the zoom image acquisition device can be installed on the detection platform built at the bridge head or the bridge tail.

[0035] In this embodiment, the detection segment images corresponding to each detection segment are collected by a zoom image acquisition device. Specifically, the focal length value corresponding to each detection segment can be predetermined. In the process of collecting the detection segment images, the zoom image device can be adjusted to a predetermined focal length value, and the image of the object to be detected can be collected according to the adjusted focal length value, so that the collected image is used as the detection segment image of the detection segment corresponding to the focal length value. Exemplarily, two focal length values ​​a and b can be predetermined. After adjusting the zoom image acquisition device according to the a value, the image is collected by the zoom image acquisition device, so as to obtain the detection segment image corresponding to the a value; after adjusting the zoom image acquisition device according to the b value, the image is collected by the zoom image acquisition device, so as to obtain the detection segment image corresponding to the b value. It should be noted that the pre-set focal length value can make the clarity of the detection segment image collected by the focal length value meet the preset clarity requirements.

[0036] In a specific implementation, in any case where deformation information of the object to be detected needs to be detected, the zoom image acquisition device can be adjusted to different focal length values ​​to obtain detection segment images of different detection segments. Exemplarily, the detection segment images can be periodically acquired to determine the deformation of the object to be detected based on the acquired detection segment images. Alternatively, the detection segment images can be acquired to determine the deformation of the object to be detected when preset conditions are met. For example, in the case of rainy or windy weather, the detection segment images are acquired to perform deformation detection.

[0037] S120 . Determine the detection coordinates of the detection target deployed on the object to be detected in the target coordinate system based on the detection segment image.

[0038] The target coordinate system may include a physical coordinate system, such as a rectangular coordinate system, a Cartesian coordinate system, and a polar coordinate system.

[0039] In this embodiment, target recognition can be performed on each detection segment image to determine the target area corresponding to the detection target contained in the detection segment image in the target coordinate system. The target area can be at least one of a rectangle, an irregular image, and a circle. The coordinate points in the target area that meet the preset position conditions are determined as the detection coordinates of the detection target. Exemplarily, when the target area is a rectangle, the preset position condition can be the center point or vertex of the rectangle as the detection coordinate. When the target area is a circle, the preset position condition can be the coordinates corresponding to the center of the circle as the detection coordinate.

[0040] S130, determining deformation information of the object to be detected based on the detection coordinates of the detection targets and the predetermined standard coordinates of each detection target in the target coordinate system when the object to be detected is in a standard state.

[0041] It should be noted that the standard state can be set according to the actual application. For example, the standard state can be the initial state of the object to be detected; or, in order to compare the impact of bad weather factors on the object to be detected, the standard state can be set to the state of the object to be detected before encountering bad weather.

[0042] In this embodiment, images of each detection segment of the object to be detected under the standard state can be collected in advance as calibration images, and the calibration focal length value of the zoom image acquisition device corresponding to each calibration image can be recorded. Through each calibration image, the standard coordinates of each detection target on the object to be detected in the target coordinate system are determined.

[0043] Furthermore, when deformation detection is required for the object to be detected, the detection segment images of each detection segment of the object to be detected collected by the zoom image acquisition device include: receiving the detection segment images corresponding to the detection segments collected by the zoom image acquisition device according to each calibrated focal length value. Therefore, the detection segment images and calibration images collected for the same detection segment have the same focal length value, thereby avoiding the influence of the comparison result between the standard coordinates and the detection coordinates due to the different focal length values ​​used when collecting the images, which is conducive to improving the accuracy of deformation detection.

[0044] In this embodiment, the deformation information of the object to be detected is determined by comparing the detection coordinates corresponding to each detection target with the standard coordinates. Based on the detection coordinates of the detection target and the predetermined standard coordinates of each detection target in the target coordinate system when the object to be detected is in a standard state, the specific implementation method of determining the deformation information generated by the object to be detected includes: for each detection target, determining the second coordinate difference between the detection coordinates of the detection target and the standard coordinates; determining the second coordinate difference corresponding to each detection target as the deformation information corresponding to the object to be detected.

[0045] Specifically, the method for determining the second coordinate difference between the detection coordinates and the standard coordinates of the detection target is: determining the second horizontal coordinate difference between the detection horizontal coordinate and the standard horizontal coordinate; determining the second vertical coordinate difference between the detection vertical coordinate and the standard vertical coordinate. Further, the determined second horizontal coordinate difference and the second vertical coordinate difference can be determined as the deformation information corresponding to the object to be detected. Alternatively, in order to reflect the overall deformation of the object to be detected, the first difference average value between the second horizontal coordinate differences corresponding to each detection target and the second difference average value between the second vertical coordinate differences can be determined as the deformation information corresponding to the object to be detected. This embodiment can effectively determine the direction and degree of deformation of the object to be detected by comparing the horizontal and vertical coordinates respectively.

[0046] The technical solution of the embodiment of the present invention receives the detection segment images of each detection segment of the object to be detected collected by the zoom image acquisition device; wherein different detection segment images correspond to different focal length values ​​of the zoom image acquisition device; the detection segment images contain the detection targets deployed on the object to be detected, so that by adjusting the zoom image acquisition device to different focal length values, the detection segment images corresponding to different detection segments are collected; and based on the detection segment images, the detection coordinates of the detection targets deployed on the object to be detected in the target coordinate system are determined; finally, based on the detection coordinates of the detection targets and the predetermined standard coordinates of each detection target in the target coordinate system when the object to be detected is in a standard state, the deformation information generated by the object to be detected is determined. The technical solution provided by this embodiment can obtain different detection segment images without installing multiple image acquisition devices, which reduces the cost of deformation detection and improves the convenience and accuracy of detection.

[0047] Figure 2 It is a flow chart of another variable-focus global visual deformation detection method provided according to an embodiment of the present invention. Based on the present embodiment and the above embodiment, optionally, the method of determining the detection coordinates of the detection target deployed on the object to be detected in the target coordinate system may include: for each detection segment image, based on the pixel position of the detection target, determining the first coordinate of the detection target in the target coordinate system; in the order from near to far of the detection segment distance from the zoom image acquisition device, traversing each detection segment in turn to determine the detection coordinates. Among them, the explanations of the terms that are the same or corresponding to the above embodiments are not repeated here. Figure 2 As shown, the method includes:

[0048] S210: Receive detection segment images of each detection segment of the object to be detected acquired by a zoom image acquisition device.

[0049] In order to improve the accuracy of deformation detection, detection segment images can be obtained for different detection segments. Optionally, there are multiple detection segments, each of which contains at least two detection targets, and there is at least one identical detection target in two adjacent detection segments. Exemplarily, detection segment 1 includes detection target 1 and detection target 2, detection segment 2 includes detection target 2 and detection target 3, and detection segment 3 includes detection target 3 and detection target 4.

[0050] S220 . For each detection segment image, determine a pixel position of a detection target in the detection segment image, and determine a first coordinate of the detection target in the detection segment image in a target coordinate system based on the pixel position.

[0051] In this embodiment, the specific implementation method of determining the pixel position of the detection target contained in the detection segment image includes: based on the target detection algorithm, determining the area information corresponding to the detection target in the detection segment image; for each detection target in the detection segment image, based on the area information of the detection target, performing circle fitting processing on the detection target, and determining the pixel position of the detection target using the center coordinates of the obtained fitting circle.

[0052] Among them, the target detection algorithm includes the lightweight Picodet algorithm.

[0053] In a specific implementation, the detection frame of the detection target contained in the detection segment image can be determined by the target detection algorithm, and the detection target information corresponding to the detection frame, for example, the identification of the detection target, can be determined. By expanding the detection frame, the position information of the region of interest corresponding to the detection target is obtained, and the position information of the region of interest is used as the region information corresponding to the detection target. Exemplarily, the region of interest can be obtained after the detection frame is expanded by 20 pixels. The image of the region of interest corresponding to each detection target is captured to obtain an image of the region of interest, and the image of the region of interest is subjected to circle fitting processing to obtain a fitting circle contained in the image of the region of interest. Based on the position information of the emotional zone image in the detection segment image, the center coordinates of the fitting circle are determined, and the center coordinates are determined as the pixel position of the detection target. This embodiment can quickly and accurately determine the pixel position of the detection target through the target recognition algorithm.

[0054] In order to facilitate deformation comparison, the target coordinate system includes a physical coordinate system. Optionally, based on the pixel position of the detection target contained in the detection segment image, determining the first coordinate of the detection target in the detection segment image in the target coordinate system includes: based on a predetermined scale factor matching the focal length value corresponding to the detection segment image and the pixel position of the detection target in the detection segment image, determining the physical coordinate of the detection target in the detection segment image in the physical coordinate system, and using the physical coordinate as the first coordinate.

[0055] In a specific implementation, the correspondence between different focal length values ​​and scale factors can be determined by a pre-calibration method. Specifically, the actual physical size of each detection target can be measured in advance. Under a standard state, for each detection target, a calibration image containing the detection target that can meet the preset image requirements is collected through a zoom image acquisition device, and the calibration focal length value corresponding to the calibration image is recorded. Among them, the preset image requirements may include that the pixel size of the detection target in the calibration image is greater than the preset size. Determine the pixel size of the detection target in each obtained calibration image. For each detection target, the ratio between the actual physical size and the pixel size of the detection target can be used as a scale factor. Based on the first mapping relationship between the pixel size of the detection target and the calibration focal length value, and the second mapping relationship between the pixel size of the detection target and the scale factor, the correspondence between the calibration focal length value and the scale factor is determined.

[0056] Exemplarily, the calibration focal length value q1 is acquired to obtain the calibration image t1, in which the pixel size of the detection target 1 is determined to be b1, and the actual physical size of the detection target 1 is b2. The ratio of b2 to b1 can be used as the scale factor corresponding to the calibration focal length value q1.

[0057] It should be noted that when acquiring the detection segment image, the focal length of the zoom image acquisition device can be adjusted in sequence according to the calibrated focal length value, and the image of the detection segment of the object to be detected can be acquired.

[0058] In this embodiment, when determining the first coordinate, the focal length value corresponding to the detection segment image can be determined first, and based on the correspondence between the pre-recorded calibrated focal length value and the scale factor, the scale factor corresponding to the focal length value of the detection segment image is determined, and the scale factor corresponding to the detection segment image is multiplied by the pixel position of the detection target in the detection segment image, and the product is used as the physical coordinate of the detection target in the detection segment image in the physical coordinate system, and the physical coordinate is used as the first coordinate.

[0059] In this embodiment, the correspondence between the focal length value and the scale factor is determined by pre-calibration, so that when determining the physical coordinates, the influence of the focal length value of the detection segment image is taken into consideration, so that the physical coordinates of the detection target can be accurately and quickly determined.

[0060] S230, traverse each detection segment in sequence in the order from near to far of the detection segment from the zoom image acquisition device; when the current detection segment currently traversed is the detection segment closest to the zoom image acquisition device, determine the detection coordinates of the current target based on the first coordinates of the current target contained in the current detection segment image corresponding to the current detection segment.

[0061] The current target is the detection target contained in the current detection segment image.

[0062] It should be noted that the zoom image acquisition device is installed at one end of the object to be detected. When acquiring the image of the detection segment, the closer the detection segment is to the zoom image acquisition device, the smaller the focal length value used; conversely, the larger the focal length value used.

[0063] In this embodiment, in order to determine the detection coordinates of each detection target, each detection segment can be traversed in sequence according to the order from near to far of the detection segment distance to the zoom image acquisition device. When the current detection segment currently traversed is the detection segment closest to the zoom image acquisition device, the first coordinate of the current target contained in the current detection segment image corresponding to the current detection segment can be directly determined as the detection coordinates of the current target.

[0064] In practical applications, zoom image acquisition equipment is used outdoors for a long time. Temperature changes cause the internal and external structural parts of the zoom image acquisition equipment to expand and contract, thereby changing the internal and external parameters of the zoom image acquisition equipment. Long-term illumination can easily cause periodic pixel shifts in the images collected by the zoom image acquisition equipment. In order to solve this problem, a reference target can be set to remove the influence of the changes in the internal and external parameters of the zoom image acquisition equipment on the image detection results.

[0065] Optionally, based on the first coordinates of the current target contained in the current detection segment image corresponding to the current detection segment, the detection coordinates of the current target are determined, including: determining the second coordinates of the reference target contained in the current detection segment image in the target coordinate system; for each current target in the current detection segment image, based on the difference between the first coordinates of the current target and the second coordinates of the reference target, determining the detection coordinates of the current target.

[0066] The reference target can be installed at one end of the object to be detected, at a preset distance from the zoom image acquisition device. For example, the preset distance can be between 1 meter and 2 meters. The size of the reference target can be 80*80 mm, and the size of the detection target can be 150*150 mm.

[0067] Specifically, the second coordinate of the reference target in the target coordinate system can be determined in the current detection segment image by the target detection algorithm through the preset reference target identifier. For each current target in the current detection segment image, the second coordinate of the reference target can be subtracted from the first coordinate of the current target, and the difference obtained can be used as the detection coordinate of the current target.

[0068] In this embodiment, the difference between the first coordinate and the second coordinate of the reference target is used as the detection coordinate, thereby eliminating the influence of the internal and external parameter changes of the zoom image acquisition device on the coordinate determination, which is beneficial to improving the accuracy of the detection coordinate.

[0069] In this embodiment, the process of traversing each detection segment also includes: when the current detection segment currently traversed is not the detection segment closest to the zoom image acquisition device, determining the same target contained in the current detection segment image and the previous detection segment image of the previous detection segment of the previous traversal, determining the first coordinate difference between the detection coordinates corresponding to the same target in the previous detection segment image and the first coordinates corresponding to the current detection segment image, and determining the detection coordinates of the current target contained in the current detection segment image based on the first coordinate difference.

[0070] In order to eliminate the influence of different focal length values ​​on the detection coordinates determined by the detection target, a global coordinate cascade transformation can be performed to transform the coordinates of all detection targets within the detection field of view into a physical coordinate system with the reference target as the origin.

[0071] Specifically, when the current detection segment currently being traversed is not the detection segment closest to the zoom image acquisition device, it can be determined that the current target contained in the current detection segment image is the same target as the previous target contained in the previous detection segment image of the previous detection segment last traversed. Exemplarily, the current target includes target 3 and target 2, and the previous target includes target 1 and target 2, then target 2 is the same target.

[0072] Furthermore, the first coordinate difference between the first coordinate of the same target in the current detection segment image and the corresponding detection coordinate in the previous detection segment image is determined. For each current target, the difference between the first coordinate corresponding to the current target in the current detection segment image and the first coordinate difference is used as the detection coordinate of the current target.

[0073] Exemplarily, the current target includes target 3 and target 2, the same target is target 2, the detection coordinates of target 2 in the previous detection segment image are (x2, y2), the first coordinates corresponding to target 2 in the current detection segment image are (x2′, y2′), and the first coordinates corresponding to target 3 in the current detection segment image are (x3′, y3′). Determine the difference Δx obtained by subtracting x2 from x2′, and determine the difference Δy obtained by subtracting y2 from y2′, so that (Δx, Δy) is the first coordinate difference. The current target includes target 2 and target 3, then the detection coordinates of target 2 are (x2, y2), and the detection coordinates of target 3 are (x3′-Δx, y3′-Δy).

[0074] S240, determining deformation information of the object to be detected based on the detection coordinates of the detection targets and the predetermined standard coordinates of each detection target in the target coordinate system when the object to be detected is in a standard state.

[0075] In this embodiment, the detection coordinates of the current target are determined based on the first coordinate difference of the same target, thereby eliminating the influence of different focal length values ​​on the detection coordinates determined by the detection target, realizing single-purpose long-distance detection, and removing the cumulative error introduced by the zoom image acquisition device due to the changes in internal and external parameters through full-domain cascading.

[0076] The above describes in detail the embodiments corresponding to the variable focus global visual deformation detection method. In order to make those skilled in the art further understand the technical solution of the method, please refer to Figure 3 , taking the object to be detected as the bridge body, and the detection targets including target 1, target 2, target 3 and target 4 as an example for explanation.

[0077] The state of the zoom image acquisition device, the detection target and the reference target after installation and debugging can be used as the standard state of the object to be detected. Under the standard state, parameter calibration can be performed first. Specifically, the zoom image acquisition device can be adjusted to the minimum focal length value first. After automatic focusing, the reference target, target 1 and target 2 can be clearly seen in the lens. For targets 3 and 4 at the minimum focal length value, the requirements of high-precision detection are not met. At this time, the current focal length value is recorded as F0. Then gradually increase the focal length value until target 2 and target 3 can be clearly seen, and record the current focal length value as F1. By analogy, the focal length value at which target 3 and target 4 can be clearly seen is recorded as F2. F0, F1 and F2 can all be regarded as calibrated focal length values.

[0078] Furthermore, the scale factors corresponding to different focal length values ​​can be determined based on the calibration images obtained at focal length values ​​of F0, F1 and F2. The formula for determining the scale factor is as follows:

[0079] SF_n=target_physical_size / target_pixel_size_n

[0080] Among them, SF_n represents the scale factor corresponding to the focal length value Fn, target_physical_size_n represents the actual physical size of the detection target, and target_pixel_size_n represents the pixel size of the detection target in the calibration image corresponding to the focal length value Fn. The value of n can be 0, 1, and 2.

[0081] In order to convert the coordinates of all targets into a physical coordinate system with the reference target as the origin, a cascade transformation of the global coordinates can be performed. The pixel position corresponding to the detection target can be expressed as (pixel_cx_n_j, pixel_cy_n_j), where pixel_cx_n_j represents the horizontal coordinate of target j in the calibration image corresponding to the focal length value Fn, and pixel_cy_n_j represents the vertical coordinate of target j in the calibration image corresponding to the focal length value Fn. The pixel position of the reference target can be (pixel_cx, pixel_cy). The third coordinate corresponding to the detection target in the standard state and the fourth coordinate of the reference target in the standard state can be determined by the pixel position and the determined scale factor. The fourth coordinate of the reference target is determined as follows:

[0082] physical_cx=SF_0*pixel_cx

[0083] physical_cy=SF_0*pixel_cy

[0084] Among them, physical_cx is the horizontal axis value corresponding to the fourth coordinate, physical_cy is the vertical axis value corresponding to the fourth coordinate, and SF_0 is the scale factor corresponding to the focal length value F0.

[0085] Furthermore, the third coordinate of the detection target is determined as follows:

[0086] physical_cx_n_j=SF_n*pixel_cx_n_j

[0087] physical_cy_n_j=SF_n*pixel_cy_n_j

[0088] Wherein, physical_cx_n_j represents the horizontal axis value of the third coordinate of target j in the calibration image corresponding to the focal length value Fn, physical_cy_n_j represents the vertical axis value of the third coordinate of target j in the calibration image corresponding to the focal length value Fn. SF_n represents the scale factor corresponding to the focal length value Fn.

[0089] Next, it is necessary to subtract the fourth coordinates from the third coordinates of target 1 and target 2 respectively, to obtain the standard coordinates of target 1 and target 2 in the physical coordinate system with the center of the reference target as the origin corresponding to the standard state. For the calibration image corresponding to the focal length value F1, targets 2 and 3 can be clearly seen, and the physical coordinates of target 3 and target 2 in the physical coordinate system corresponding to the calibration image of the focal length value F1 are determined. The coordinates obtained by subtracting the physical coordinates of target 2 from the physical coordinates of target 3 are added to the standard coordinates of target 2, and the obtained coordinates are used as the standard coordinates of target 3, thus completing a cascade coordinate conversion. Similarly, the coordinates obtained by subtracting the physical coordinates of target 3 from the physical coordinates of target 4 can be added to the standard coordinates of target 3 to determine the standard coordinates of target 4. At this point, the calibration of the target coordinates under the standard state is completed.

[0090] In this embodiment, deformation detection can be performed in real time. At the detection time, the detection coordinates of target 1, target 2, target 3 and target 4 are determined in the same manner as the standard coordinates. For each detection target, the deformation amount generated at the detection position corresponding to the detection target is determined by determining the difference between the detection coordinates of the detection target and the standard coordinates. For example, taking target 1 as an example, the deformation amounts obtained include:

[0091] dx_t=cx_t-cx_0

[0092] dy_t=cy_t-cy_0

[0093] Among them, dx_t represents the horizontal axis deformation of target 1 at the detection time t, cx_t represents the detected horizontal coordinate of target 1 at the detection time t, cx_0 represents the standard horizontal coordinate of target 1, cy_t represents the detected vertical coordinate of target 1 at the detection time t, and cx_0 represents the standard vertical coordinate of target 1.

[0094] This embodiment uses a zoom image acquisition device to clearly capture the detection segment image containing each detection target without increasing the cost; and, by setting reference targets and performing global cascading and other operations, it avoids the situation where the internal and external parameters of the zoom image acquisition device are changed due to the outdoor environment, which affects the detection results, thereby improving the detection accuracy and effectiveness.

[0095] Figure 4 1 is a schematic diagram of the structure of a variable-focus global visual deformation detection device provided according to an embodiment of the present invention, and the device is used to execute the variable-focus global visual deformation detection method provided by any of the above embodiments. The device and the variable-focus global visual deformation detection method of the above embodiments belong to the same inventive concept, and the details not described in detail in the embodiment of the variable-focus global visual deformation detection device can be referred to the embodiment of the above variable-focus global visual deformation detection method. Figure 4As shown, the device comprises:

[0096] The image receiving module 10 is used to receive the detection segment images of each detection segment of the object to be detected acquired by the zoom image acquisition device; wherein different detection segment images correspond to different focal length values ​​of the zoom image acquisition device; and the detection segment images contain detection targets deployed on the object to be detected;

[0097] A coordinate determination module 11 is used to determine the detection coordinates of the detection target deployed on the object to be detected in the target coordinate system based on the detection segment image;

[0098] The information determination module 12 is used to determine the deformation information generated by the object to be detected based on the detection coordinates of the detection targets and the predetermined standard coordinates of each detection target in the target coordinate system when the object to be detected is in a standard state.

[0099] On the basis of any optional technical solution in the embodiment of the present invention, optionally, the number of detection segments is multiple, each detection segment contains at least two detection targets, and there is at least one identical detection target in two adjacent detection segments; the coordinate determination module 11 includes:

[0100] A pixel position determination submodule, for determining, for each detection segment image, a pixel position of a detection target in the detection segment image, and determining, based on the pixel position, a first coordinate of the detection target in the detection segment image in a target coordinate system;

[0101] The detection segment traversal submodule is used to traverse each detection segment in sequence according to the order from near to far of the detection segment distance to the zoom image acquisition device;

[0102] A detection coordinate determination submodule, for determining the detection coordinates of the current target based on the first coordinates of the current target contained in the current detection segment image corresponding to the current detection segment, when the current detection segment currently traversed is the detection segment closest to the zoom image acquisition device;

[0103] The current target is the detection target contained in the current detection segment image.

[0104] Based on any optional technical solution in the embodiments of the present invention, optionally, the method further includes:

[0105] The same target determination submodule is used to determine the same target contained in the current detection segment image and the previous detection segment image of the previous detection segment of the previous traversal when the current detection segment currently traversed is not the detection segment closest to the zoom image acquisition device, determine the first coordinate difference between the detection coordinates corresponding to the same target in the previous detection segment image and the first coordinates corresponding to the same target in the current detection segment image, and determine the detection coordinates of the current target contained in the current detection segment image based on the first coordinate difference.

[0106] Based on any optional technical solution in the embodiments of the present invention, optionally, the detection coordinate determination submodule includes:

[0107] The first coordinate determining unit is used to determine the physical coordinates of the detection target in the detection segment image in the physical coordinate system based on a predetermined scale factor matching the focal length value corresponding to the detection segment image and the pixel position of the detection target in the detection segment image, and use the physical coordinates as the first coordinates.

[0108] Based on any optional technical solution in the embodiments of the present invention, optionally, the detection coordinate determination submodule includes:

[0109] A second coordinate determination unit, used to determine a second coordinate of a reference target contained in the current detection segment image in a target coordinate system;

[0110] The detection coordinate determining unit is used to determine the detection coordinates of the current target based on the difference between the first coordinates of the current target and the second coordinates of the reference target for each current target in the current detection segment image.

[0111] Based on any optional technical solution in the embodiments of the present invention, optionally, the detection coordinate determination submodule includes:

[0112] A region information determination unit, used to determine region information corresponding to a detection target in a detection segment image based on a target detection algorithm;

[0113] The pixel position determination unit is used to perform circle fitting processing on each detection target in the detection segment image based on the area information of the detection target, and determine the pixel position of the detection target using the center coordinates of the obtained fitting circle.

[0114] Based on any optional technical solution in the embodiment of the present invention, optionally, the information determination module 12 includes:

[0115] A second coordinate difference determination submodule, used to determine, for each detection target, a second coordinate difference between the detection coordinates of the detection target and the standard coordinates;

[0116] The deformation information determination submodule is used to determine the second coordinate difference corresponding to each detection target as the deformation information corresponding to the object to be detected.

[0117] The technical solution of the embodiment of the present invention receives the detection segment images of each detection segment of the object to be detected collected by the zoom image acquisition device; wherein different detection segment images correspond to different focal length values ​​of the zoom image acquisition device; the detection segment images contain the detection targets deployed on the object to be detected, so that by adjusting the zoom image acquisition device to different focal length values, the detection segment images corresponding to different detection segments are collected; and based on the detection segment images, the detection coordinates of the detection targets deployed on the object to be detected in the target coordinate system are determined; finally, based on the detection coordinates of the detection targets and the predetermined standard coordinates of each detection target in the target coordinate system when the object to be detected is in a standard state, the deformation information generated by the object to be detected is determined. The technical solution provided by this embodiment can obtain different detection segment images without installing multiple image acquisition devices, which reduces the cost of deformation detection and improves the convenience and accuracy of detection.

[0118] It is worth noting that in the embodiment of the above-mentioned variable-focus global visual deformation detection device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0119] Figure 5 1 is a schematic diagram of the structure of an electronic device that implements the variable-focus global visual deformation detection method of an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0120] like Figure 5As shown, the electronic device 20 includes at least one processor 21, and a memory connected to the at least one processor 21, such as a read-only memory (ROM) 22, a random access memory (RAM) 23, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 21 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 22 or the computer program loaded from the storage unit 28 to the random access memory (RAM) 23. In RAM23, various programs and data required for the operation of the electronic device 20 can also be stored. The processor 21, ROM22 and RAM23 are connected to each other through a bus 24. An input / output (I / O) interface 25 is also connected to the bus 24.

[0121] A number of components in the electronic device 20 are connected to the I / O interface 25, including: an input unit 26, such as a keyboard, a mouse, etc.; an output unit 27, such as various types of displays, speakers, etc.; a storage unit 28, such as a disk, an optical disk, etc.; and a communication unit 29, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 29 allows the electronic device 20 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0122] The processor 21 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 21 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 21 executes the various methods and processes described above, such as a variable-focus global visual deformation detection method.

[0123] In some embodiments, the variable-focus global visual deformation detection method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 28. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 20 via the ROM 22 and / or the communication unit 29. When the computer program is loaded into the RAM 23 and executed by the processor 21, one or more steps of the variable-focus global visual deformation detection method described above may be performed. Alternatively, in other embodiments, the processor 21 may be configured to perform the variable-focus global visual deformation detection method in any other appropriate manner (e.g., by means of firmware).

[0124] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0125] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0126] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0127] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0128] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0129] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0130] This embodiment also provides a computer program product, including a computer program, which, when executed by a processor, implements the variable-focus global visual deformation detection method provided in any embodiment of the present application.

[0131] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0132] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0133] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A variable-focus global visual deformation detection method, characterized in that: include: Receiving detection segment images of each detection segment of the object to be detected acquired by a zoom image acquisition device; wherein different detection segment images correspond to different focal length values ​​of the zoom image acquisition device; and the detection segment images contain detection targets deployed on the object to be detected; Based on the detection segment image, determining the detection coordinates of the detection target deployed on the object to be detected in the target coordinate system; Based on the detection coordinates of the detection targets and the predetermined standard coordinates of each of the detection targets in the target coordinate system when the object to be detected is in a standard state, the deformation information generated by the object to be detected is determined.

2. The method according to claim 1, characterized in that: There are multiple detection segments, each of which contains at least two detection targets, and at least one identical detection target exists in two adjacent detection segments; The step of determining the detection coordinates of the detection target deployed on the object to be detected in the target coordinate system based on the detection segment image includes: For each of the detection segment images, determine a pixel position of a detection target in the detection segment image, and determine a first coordinate of the detection target in the detection segment image in the target coordinate system based on the pixel position; Traversing each of the detection segments in sequence according to the order of the detection segments being closer to the zoom image acquisition device; In a case where the current detection segment currently traversed is the detection segment closest to the zoom image acquisition device, determining the detection coordinates of the current target based on the first coordinates of the current target contained in the current detection segment image corresponding to the current detection segment; The current target is a detection target contained in the current detection segment image.

3. The method according to claim 2, characterized in that Also includes: In the case that the current detection segment currently traversed is not the detection segment closest to the zoom image acquisition device, determine the same target contained in the current detection segment image and the previous detection segment image of the previous detection segment of the previous traversal, determine the first coordinate difference between the detection coordinates corresponding to the same target in the previous detection segment image and the first coordinates corresponding to the current detection segment image, and determine the detection coordinates of the current target contained in the current detection segment image based on the first coordinate difference.

4. The method according to claim 2, characterized in that: The target coordinate system includes a physical coordinate system, and determining a first coordinate of the detection target in the detection segment image in the target coordinate system based on a pixel position of the detection target contained in the detection segment image includes: Based on a predetermined scale factor that matches the focal length value corresponding to the detection segment image and a pixel position of the detection target in the detection segment image, a physical coordinate of the detection target in the detection segment image in a physical coordinate system is determined, and the physical coordinate is used as the first coordinate.

5. The method according to claim 2, characterized in that: The determining the detection coordinates of the current target based on the first coordinates of the current target contained in the current detection segment image corresponding to the current detection segment includes: Determining a second coordinate of a reference target contained in the current detection segment image in the target coordinate system; For each current target in the current detection segment image, the detection coordinates of the current target are determined based on a difference between the first coordinates of the current target and the second coordinates of the reference target.

6. The method according to claim 2, characterized in that The determining the pixel position of the detection target contained in the detection segment image includes: Based on the target detection algorithm, determining the area information corresponding to the detection target in the detection segment image; For each detection target in the detection segment image, a circle fitting process is performed on the detection target based on the region information of the detection target, and the pixel position of the detection target is determined using the center coordinates of the obtained fitting circle.

7. The method according to claim 1, characterized in that The step of determining deformation information of the object to be detected based on the detection coordinates of the detection target and the predetermined standard coordinates of each detection target in the target coordinate system when the object to be detected is in a standard state includes: For each of the detection targets, determining a second coordinate difference between the detection coordinates of the detection target and the standard coordinates; The second coordinate difference corresponding to each of the detection targets is determined as the deformation information corresponding to the object to be detected.

8. A variable-focus global visual deformation detection device, characterized in that: include: An image receiving module, used for receiving detection segment images of each detection segment of the object to be detected acquired by the zoom image acquisition device; wherein different detection segment images correspond to different focal length values ​​of the zoom image acquisition device; and the detection segment images contain detection targets deployed on the object to be detected; A coordinate determination module, used to determine the detection coordinates of the detection target deployed on the object to be detected in a target coordinate system based on the detection segment image; The information determination module is used to determine the deformation information generated by the object to be detected based on the detection coordinates of the detection target and the predetermined standard coordinates of each of the detection targets in the target coordinate system when the object to be detected is in a standard state.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to 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 so that the at least one processor can execute the variable-focus global visual deformation detection method described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the variable-focus global visual deformation detection method according to any one of claims 1 to 7 when executed.

Images