Speed difference automatic controller falling risk early warning method and system based on image dynamic analysis

Abstract

The invention relates to the technical field of image data processing, in particular to a speed difference automatic controller falling risk early warning method and system based on image dynamic analysis, and the method comprises the steps: obtaining a brightness image; obtaining the gradient magnitude and gradient direction of each pixel point in the brightness image; determining a reflection starting point of the brightness image based on the gradient magnitude of each pixel point in the brightness image so as to obtain a reflection starting area of the brightness image; acquiring a light intensity quantized value of an adjacent pixel point of the reflection starting area, and further acquiring a safety rope path of the brightness image; acquiring an off-center value of the path of the safety rope, judging whether the safety rope shakes abnormally, and acquiring a mask image of the brightness image under the condition that the safety rope does not shake abnormally; and acquiring the falling risk of the safety rope at the current moment by using the corresponding path of the safety rope in the continuous frame mask image, and further adjusting the tensioning force of the safety rope. According to the invention, the accuracy of operator falling risk judgment can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image data processing, in particular to a fall risk early warning method and system of a speed-difference self-controller based on image dynamic analysis. BACKGROUND

[0002] The speed-difference self-controller, also known as a fall arrest speed-difference device, is a high-performance fall protection equipment. When the worker moves slowly, the safety rope is slowly pulled out or retracted. When the worker falls, the safety rope is rapidly pulled out.

[0003] The existing problem: since the speed-difference self-controller is used to determine whether the worker falls by sensing the speed difference, the speed-difference self-controller may be tightened due to the worker's misoperation. Therefore, the existing technology analyzes the movement state of the safety rope during the slow descent process by installing a video device on the speed-difference self-controller, so as to quickly identify the abnormal swing of the safety rope during the slow descent process, which is beneficial to the accurate judgment of the abnormal falling state of the speed-difference self-controller during the slow descent process. However, the images collected by the existing technology during the slow descent process of the safety rope are blurred, which affects the accuracy of the positioning of the safety rope and further affects the accuracy of the judgment of the falling risk of the worker. SUMMARY

[0004] The present application provides a fall risk early warning method and system of a speed-difference self-controller based on image dynamic analysis to solve the existing problem.

[0005] The fall risk early warning method and system of a speed-difference self-controller based on image dynamic analysis provided by the present application adopts the following technical scheme: One embodiment of the present application provides a fall risk early warning method of a speed-difference self-controller based on image dynamic analysis, which comprises the following steps: Collecting continuous frame safety rope images, preprocessing each frame safety rope image, and obtaining the corresponding brightness image of each frame safety rope image; Obtaining the gradient amplitude and gradient direction of each pixel point in each frame brightness image; Based on the gradient amplitude of each pixel point in each frame brightness image, determining all reflection starting points of each frame brightness image; using the gradient amplitude and brightness value of each reflection starting point of each frame brightness image, obtaining all reflection starting regions of each frame brightness image; Obtaining the adjacent pixel points of each reflection starting region, and obtaining the light intensity quantization value of each adjacent pixel point of each reflection starting region according to the gradient direction of each adjacent pixel point of each reflection starting region and the gradient direction of each pixel point in each reflection starting region; Based on the light intensity quantization value of each adjacent pixel point of each reflection starting region, obtaining all safety rope paths of each frame brightness image; The light intensity quantization value of each adjacent pixel point in each safety rope path of each frame of luminance image is used to obtain the deviation center value of each safety rope path, and whether the safety rope abnormally shakes is judged according to the deviation center value of each safety rope path, and in the case that the safety rope does not abnormally shake, a mask image of each frame of luminance image is obtained; The falling risk of the safety rope at the current moment is obtained by using the corresponding path of the safety rope in the continuous frame mask image; According to the falling risk of the safety rope at the current moment, the tension of the safety rope in the speed difference automatic controller is adjusted.

[0006] Further, the pre-processing of each frame of safety rope image to obtain the corresponding luminance image of each frame of safety rope image comprises the following specific steps: Filtering each frame of safety rope image to obtain a filtered image; Extracting the luminance value of each pixel point in the filtered image to obtain an image after extracting the luminance value; Gray processing the image after extracting the luminance value to obtain the corresponding luminance image of each frame of safety rope image.

[0007] Further, the gradient amplitude of each pixel point in each frame of luminance image is used to determine all the reflection starting points of each frame of luminance image, which comprises the following specific steps: The gradient amplitudes of each pixel point in each frame of luminance image are sorted in descending order to obtain a gradient amplitude sequence; First-order difference is performed on the gradient amplitude sequence to obtain a gradient difference sequence; The maximum value in the gradient difference sequence is obtained, and the gradient amplitude corresponding to the maximum value is taken as an end point, and the gradient amplitude sequence is divided into a highlight sequence and a non-highlight sequence; All the pixel points corresponding to the highlight sequence are determined as all the reflection starting points of each frame of luminance image.

[0008] Further, the gradient amplitude and luminance value of each reflection starting point of each frame of luminance image are used to obtain all the reflection starting regions of each frame of luminance image, which comprises the following specific steps: The luminance value of each reflection starting point is updated by using the gradient amplitude and luminance value of each reflection starting point of each frame of luminance image to obtain the updated luminance value of each reflection starting point; Based on the updated luminance value of each reflection starting point, adjacent reflection starting points are merged to obtain all the reflection starting regions of each frame of luminance image.

[0009] Further, the gradient direction of each adjacent pixel point of each reflection starting region and the gradient direction of each pixel point in each reflection starting region are used to obtain the light intensity quantization value of each adjacent pixel point of each reflection starting region, including the following specific steps: For each adjacent pixel point of each reflection starting region, the minimum value of the difference between the gradient direction of the adjacent pixel point and the gradient direction of each pixel point in the reflection starting region is obtained, and the minimum value is determined as the minimum gradient difference value of each adjacent pixel point of each reflection starting region. The sum of the minimum gradient difference values of all adjacent pixel points of each reflection starting region is obtained. The light intensity quantization value of each adjacent pixel point of each reflection starting region is obtained by using the minimum gradient difference value of each adjacent pixel point of each reflection starting region and the sum of the minimum gradient difference values of all adjacent pixel points of each reflection starting region.

[0010] Further, the light intensity quantization value of each adjacent pixel point of each reflection starting region is used to obtain all safety rope paths of each frame of brightness image, including the following specific steps: The minimum value of the light intensity quantization value of all adjacent pixel points of each reflection starting region is obtained, and the adjacent pixel point corresponding to the minimum value is taken as a starting point. The edges formed by all adjacent pixel points of each reflection starting region are traversed to obtain a light intensity quantization value sequence of the edges. The mean value of the light intensity quantization value sequence of the edges and the standard deviation of the light intensity quantization value sequence of the edges are obtained. Based on the mean value of the light intensity quantization value sequence of the edges and the standard deviation of the light intensity quantization value sequence of the edges, a preset edge light intensity quantization value threshold is obtained. Elements in the light intensity quantization value sequence of the edges that are greater than the preset edge light intensity quantization value threshold are taken as sequence nodes. Adjacent sequence nodes are combined to form a node group, and the node group containing the most nodes is determined as a maximum node group. The adjacent pixel points corresponding to the maximum node group are incorporated into the reflection starting region to obtain an effective extension path of each reflection starting region. The effective extension path of each reflection starting region is determined as each safety rope path of each frame of brightness image, and all safety rope paths of each frame of brightness image are obtained.

[0011] Further, the light intensity quantization value of each adjacent pixel point in each safety rope path of each frame of brightness image is used to obtain a deviation center value of each safety rope path, and the deviation center value of each safety rope path is used to determine whether the safety rope is abnormally swinging. In the case where the safety rope does not abnormally swing, a mask image of each frame of brightness image is obtained, including the following specific steps: For each safety rope path of each frame of luminance image, a normalized value of a sum of light intensity quantization values of all adjacent pixels on the path is determined as a deviation center value of each safety rope path; It is judged whether the sum of the deviation center values of all safety rope paths is greater than a preset deviation center value threshold; In the case that the sum of the deviation center values of all safety rope paths is greater than the preset deviation center value threshold, it is determined that the safety rope abnormally swings, and the speed difference self-controller is locked; In the case that the sum of the deviation center values of all safety rope paths is less than or equal to the preset deviation center value threshold, each safety rope path is subjected to mask processing to obtain a mask image of each frame of luminance image.

[0012] Further, the use of the corresponding path of the safety rope in the continuous frame mask image to obtain the falling risk of the safety rope at the current time comprises the following specific steps: Superimpose two adjacent mask images in the continuous frame mask image to obtain the corresponding path of the safety rope in the continuous frame mask image and the overlapping area of the corresponding path of the safety rope in the continuous frame mask image; Calculate the sum of the areas of all paths of the safety rope in the continuous frame mask image and the sum of the areas of the overlapping area of the corresponding path of the safety rope in the continuous frame mask image; Based on the sum of the areas of all paths of the safety rope in the continuous frame mask image and the sum of the areas of the overlapping area of the corresponding path of the safety rope in the continuous frame mask image, the swing amplitude of the safety rope is obtained; Obtain the light intensity quantization value of each path corresponding to the safety rope in the continuous frame mask image; Based on the light intensity quantization value of each path corresponding to the safety rope in the continuous frame mask image, the mean and standard deviation of the light intensity quantization value of all paths corresponding to the safety rope in the continuous frame mask image are obtained; Using the swing amplitude of the safety rope and the mean and standard deviation of the light intensity quantization value of all paths corresponding to the safety rope in the continuous frame mask image, the falling risk of the safety rope at the current time is obtained.

[0013] Further, the adjustment of the tension of the safety rope in the speed difference self-controller according to the falling risk of the safety rope at the current time comprises the following specific steps: Collect the tension of the safety rope at the current time; Calculate the difference between the tension of the safety rope at the current time and the locked tension; Obtain the normalized value of the falling risk of the safety rope at the current time; An adjustment value of the tensioning force of the safety rope at the current moment is obtained based on a difference between the tensioning force of the safety rope at the current moment and the locking tensioning force, and a normalized value of the falling risk of the safety rope at the current moment; The tensioning force of the safety rope in the speed-difference self-control device is adjusted according to the adjustment value of the tensioning force of the safety rope at the current moment.

[0014] An embodiment of the present application provides a speed-difference self-control device falling risk early warning system based on image dynamic analysis, which comprises the following modules: A collection and preprocessing module is configured to collect continuous frame safety rope images, pre-process each frame safety rope image, and obtain a brightness image corresponding to each frame safety rope image; An analysis module is configured to obtain gradient amplitudes and gradient directions of each pixel point in each frame brightness image, determine all reflection starting points of each frame brightness image based on the gradient amplitudes of each pixel point in each frame brightness image, obtain all reflection starting regions of each frame brightness image by using the gradient amplitudes and brightness values of the reflection starting points of each frame brightness image, obtain adjacent pixel points of each reflection starting region, obtain light intensity quantization values of each adjacent pixel point of each reflection starting region according to the gradient directions of the adjacent pixel points of each reflection starting region and the gradient directions of each pixel point in each reflection starting region, obtain all safety rope paths of each frame brightness image based on the light intensity quantization values of each adjacent pixel point of each reflection starting region, obtain a deviation center value of each safety rope path by using the light intensity quantization values of the adjacent pixel points in each safety rope path of each frame brightness image, determine whether the safety rope abnormally swings according to the deviation center value of each safety rope path, and obtain a mask image of each frame brightness image in the case that the safety rope does not abnormally swing, and obtain a falling risk of the safety rope at the current moment by using corresponding paths of the safety rope in continuous frame mask images. An adjustment module is configured to adjust the tensioning force of the safety rope in the speed-difference self-control device according to the falling risk of the safety rope at the current moment.

[0015] The technical scheme of the present application has the following beneficial effects: the speed-difference self-control device falling risk early warning method and system based on image dynamic analysis are provided in the embodiment of the present application, the true safety rope region in the image is screened by using the different reflection characteristics of the safety rope and the background on light, the abnormal movement of the worker is further evaluated according to the movement trajectory and the movement range of the safety rope, and then the tensioning force of the speed-difference self-control device is adjusted. The embodiment of the present application can avoid the case that the positioning accuracy of the safety rope region is low due to the motion blur caused by the movement of the safety rope, thereby improving the accuracy of the falling risk judgment of the worker. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0017] Figure 1 A step flow chart of a falling risk early warning method of a speed difference automatic controller based on image dynamic analysis according to an embodiment of the present application; Figure 2 A block diagram of a falling risk early warning system of a speed difference automatic controller based on image dynamic analysis according to an embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined purposes, the following will combine the drawings and preferred embodiments to specifically describe a falling risk early warning method and system of a speed difference automatic controller based on image dynamic analysis according to the present application, the specific implementation, structure, features and effects of which are described in detail as follows. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0020] The following will specifically describe the specific scheme of a falling risk early warning method and system of a speed difference automatic controller based on image dynamic analysis provided by the present application in combination with the drawings.

[0021] Please refer to Figure 1 which shows a step flow chart of a falling risk early warning method of a speed difference automatic controller based on image dynamic analysis according to an embodiment of the present application. The method comprises the following steps: Step S001: Collecting continuous frame safety rope images, pre-processing each frame safety rope image, and obtaining the corresponding brightness image of each frame safety rope image.

[0022] It should be noted that the present invention proposes a fall risk warning method and system for a speed differential controller based on dynamic image analysis. This method utilizes the different light reflection characteristics between the safety rope and the background to screen the actual safety rope area in the image. This method further assesses whether the worker has experienced abnormal movement based on the safety rope's trajectory and range of motion, and then adjusts the tension of the speed differential controller. This method avoids the low accuracy of safety rope area positioning caused by motion blur caused by the movement of the safety rope, thereby improving the accuracy of fall risk assessment for workers.

[0023] In this embodiment, each frame of the safety rope image is filtered to obtain a filtered image; the brightness value of each pixel in the filtered image is extracted to obtain an image after the brightness value is extracted; and the image after the brightness value is extracted is grayscaled to obtain a brightness image corresponding to each frame of the safety rope image.

[0024] Specifically: first, a high-speed camera is installed on the axial direction of the speed difference controller, and images are collected at a frequency of 30 frames per second. The images are transmitted to the central controller through the communication bus, thereby completing the image collection.

[0025] Then pass The acquired image is filtered using a Gaussian filter (with a standard deviation of 1.5) to suppress noise and preserve edge information.

[0026] Finally, the brightness channel is extracted from the filtered image and grayscaled to obtain a brightness image.

[0027] Step S002: Obtain the gradient magnitude and gradient direction of each pixel in each frame of the brightness image.

[0028] Specifically, gradient extraction is performed on each pixel in the brightness image to obtain gradient data, which includes gradient magnitude and gradient direction.

[0029] Step S003: Based on the gradient amplitude of each pixel point in each frame of brightness image, all reflection starting points of each frame of brightness image are determined; and all reflection starting areas of each frame of brightness image are obtained using the gradient amplitude and brightness value of each reflection starting point of each frame of brightness image.

[0030] It should be noted that the safety rope and the background have different reflection characteristics for light. Based on this, the image is analyzed to distinguish the safety rope area from the background area.

[0031] In this embodiment, the gradient amplitudes of each pixel point in each frame of luminance image are sorted in descending order to obtain a gradient amplitude sequence; first-order difference is performed on the gradient amplitude sequence to obtain a gradient difference sequence; the maximum value in the gradient difference sequence is obtained, and the gradient amplitude corresponding to the maximum value is taken as an end point, and the gradient amplitude sequence is divided into a highlight sequence and a non-highlight sequence; all pixel points corresponding to the highlight sequence are determined as all reflection starting points of each frame of luminance image.

[0032] Specifically, the highlight points in the luminance image are extracted: the gradient amplitudes of all pixel points in the luminance image are sorted in descending order to obtain a descending sequence, and first-order difference is performed to obtain a gradient difference sequence, the maximum difference value is extracted from the gradient difference sequence, and the two gradient amplitudes corresponding to the maximum difference value are extracted from the descending sequence, and the descending sequence is split into two partial sequences with the two gradient amplitudes as end points. The sequence with the larger end point is taken as the highlight sequence, and each pixel point corresponding to the highlight sequence is taken as a reflection starting point. Thus, all reflection starting points of each frame of luminance image are obtained.

[0033] In this embodiment, the gradient amplitudes and luminance values of each reflection starting point of each frame of luminance image are used to update the luminance values of each reflection starting point to obtain updated luminance values of each reflection starting point; based on the updated luminance values of each reflection starting point, adjacent reflection starting points are merged to obtain all reflection starting regions of each frame of luminance image.

[0034] It should be noted that: in order to improve the positioning convenience of the highlight points, the luminance values of all highlight points are updated. The updated highlight points have significant reflectivity, and based on the significant reflectivity of the highlight points, accurate identification of the safety rope region can be realized.

[0035] Specifically, the expression of the updated luminance value of the highlight point is as follows:

[0036] Wherein, represents the updated luminance value of the i-th highlight point, represents the gradient amplitude of the i-th highlight point, represents the maximum gradient amplitude in the highlight sequence, represents the updated luminance value of the i-th highlight point, represents the updated luminance value of the i-th highlight point. It should be noted that: when the updated luminance value is greater than 255, the updated luminance value of the highlight point is recorded as 255.

[0037] It should be noted that: when the updated luminance value is greater than 255, the updated luminance value of the highlight point is recorded as 255.

[0038] ​After the brightness values of all highlight points are updated, since each highlight point is taken as a reflection starting point, then the reflection starting points after the updated brightness values are merged to obtain each reflection starting region.

[0039] Step S004: obtaining the adjacent pixel points of each reflection starting region, obtaining the light intensity quantization value of each adjacent pixel point of each reflection starting region according to the gradient direction of each adjacent pixel point of each reflection starting region and the gradient direction of each pixel point in each reflection starting region.

[0040] It should be noted that the trend of the reflection starting region radiating outward is judged to obtain the reflection significance of the pixel points adjacent to the reflection starting region, that is, the real trajectory of the safety rope and the moving blur are distinguished according to the flat extension characteristic of the safety rope and the texture direction of the brightness variation; the surface of the real trajectory of the safety rope is relatively flat, and the blur is formed by the change of the direction of the reflection, so the real trajectory of the safety rope and the moving blur are distinguished according to the extension of the reflection starting region outward.

[0041] In this embodiment, for each adjacent pixel point of each reflection starting region, the minimum value of the difference between the gradient direction of the adjacent pixel point and the gradient direction of each pixel point in the reflection starting region is obtained, and the minimum value is determined as the minimum gradient difference of each adjacent pixel point of each reflection starting region; the sum of the minimum gradient differences of all adjacent pixel points of each reflection starting region is obtained; and the light intensity quantization value of each adjacent pixel point of each reflection starting region is obtained by using the minimum gradient difference of each adjacent pixel point of each reflection starting region and the sum of the minimum gradient differences of all adjacent pixel points of each reflection starting region.

[0042] It should be noted that all the pixel points adjacent to the current reflection starting region are extracted, and for any one of the pixel points, the minimum value of the difference between the gradient direction and the gradient direction of all the pixel points in the current reflection starting region is judged, and the gradient direction flatness is judged to expect that it is closer to the flat characteristic of the safety rope. That is, the stronger the reflection effect of the current adjacent pixel point, and the more consistent the reflection intensity difference with the remaining non-real trajectory points in its direction, the more likely the current adjacent pixel point is the real trajectory of the safety rope.

[0043] Therefore, first, the reflection effect difference between the reflection starting region and the surrounding is evaluated: the lower the total gradient variation of the remaining pixel points after the current adjacent pixel point is removed from the reflection starting region compared to the gradient deviation of the current adjacent pixel point, the more likely the motion trajectory is extended from the reflection starting region in the direction of the current adjacent pixel point.

[0044] Specifically, the gradient deviation of the current adjacent pixel point is calculated first the minimum value of the difference between the gradient direction of the and the gradient direction of each pixel point in the reflection starting area the sum of the minimum values of the differences of all adjacent pixel points the ratio of the and and the light intensity quantization value of the current adjacent pixel point.

[0045] At this point, the light intensity quantization value of each adjacent pixel point of each reflection starting area is obtained.

[0046] Step S005: Based on the light intensity quantization value of each adjacent pixel point of each reflection starting area, all safety rope paths of each frame of brightness image are obtained.

[0047] It should be noted that when the safety rope moves and extends, it is not always extended by a single pixel point, but the true trajectory of the safety rope is relatively consistent in direction, so the effective extension direction in the neighborhood of the reflection starting area needs to be screened.

[0048] In this embodiment, the minimum value of the light intensity quantization value of all adjacent pixel points of each reflection starting area is obtained, the adjacent pixel point corresponding to the minimum value is taken as the starting point, the edge formed by all adjacent pixel points of each reflection starting area is traversed, and the light intensity quantization value sequence of the edge is obtained; the mean value of the light intensity quantization value sequence of the edge and the standard deviation of the light intensity quantization value sequence of the edge are obtained; based on the mean value of the light intensity quantization value sequence of the edge and the standard deviation of the light intensity quantization value sequence of the edge, a preset edge light intensity quantization value threshold is obtained; elements greater than the preset edge light intensity quantization value threshold in the light intensity quantization value sequence of the edge are taken as sequence nodes; combinations of adjacent sequence nodes are taken as node groups, the node group containing the most nodes is determined as the maximum node group, the adjacent pixel point corresponding to the maximum node group is incorporated into the reflection starting area, the effective extension path of each reflection starting area is obtained, the effective extension path of each reflection starting area is determined as each safety rope path of each frame of brightness image, and all safety rope paths of each frame of brightness image are obtained.

[0049] ​Specifically, first, the pixel points adjacent to the reflection starting area are single-pixel edge points, and therefore the light intensity quantization values of the adjacent pixel points are filled into the edge formed by the adjacent pixel points, and starting from the position corresponding to the minimum light intensity quantization value on the edge, the edge is traversed in an arbitrary direction to obtain a sequence of light intensity quantization values of the edge, the mean value of the sequence of light intensity quantization values is taken, and the standard deviation of the sequence of light intensity quantization values is calculated, and the sequence nodes greater than three times the standard deviation of the mean value in the current sequence are selected, and further, the node group with the largest number of adjacent nodes in these nodes is extracted, and the node group is incorporated into the reflection starting area to update the reflection starting area. The updated reflection starting area is updated according to the above steps until the reflection starting area cannot be updated any more, and the effective extension path of each reflection starting area is obtained.

[0050] It should be noted that in this embodiment, three times the standard deviation of the mean value is used as the preset edge light intensity quantization value threshold.

[0051] For any effective extension path of a reflection starting area, it can only appear on one safety rope, and therefore the effective extension path of each reflection starting area is recorded as a safety rope path. Thus, all safety rope paths of each frame of luminance image are obtained.

[0052] Step S006: The deviation center value of each safety rope path is obtained using the light intensity quantization values of the adjacent pixel points in each safety rope path of each frame of luminance image, and whether the safety rope is abnormally swinging is determined according to the deviation center value of each safety rope path, and in the case where the safety rope is not abnormally swinging, the mask image of each frame of luminance image is obtained.

[0053] It should be noted that the abnormal swinging of the safety rope causes the safety rope to deviate from the center position of the speed difference controller, and therefore the deviation of the safety rope relative to the visual angle of the speed difference controller is first determined, and then the actual swinging amplitude of the safety rope is obtained according to the area of the safety rope in the continuous frames of images.

[0054] In this embodiment, for each safety rope path of each frame of luminance image, the normalized value of the sum of the light intensity quantization values of all adjacent pixel points on the path is determined as the deviation center value of each safety rope path, whether the sum of the deviation center values of all safety rope paths is greater than a preset deviation center value threshold is determined, in the case where the sum of the deviation center values of all safety rope paths is greater than the preset deviation center value threshold, it is determined that the safety rope is abnormally swinging, and the speed difference controller is locked; in the case where the sum of the deviation center values of all safety rope paths is less than or equal to the preset deviation center value threshold, each safety rope path is subjected to mask processing to obtain the mask image of each frame of luminance image.

[0055] It should be noted that the preset deviation from the center value threshold is set according to specific circumstances and is not specifically limited here. In this embodiment, the preset deviation from the center value threshold is 0.8.

[0056] Specifically, first calculate the sum of the light intensity quantization values ​​of all adjacent pixels on the safety rope path , then by The normalized function of Perform normalization processing and The normalized value of is taken as the deviation from the center of the safety rope path.

[0057] It is determined whether the sum of the deviation values ​​of all safety rope paths is greater than 0.8. If it is greater than 0.8, it is determined that the current safety rope should be tightened to avoid the risk of falling caused by abnormal shaking of the safety rope.

[0058] If the sum of the deviation values ​​of all safety rope paths is less than or equal to 0.8, the corresponding pixel points of each safety rope path in the brightness image are marked as 1, and the remaining pixels are marked as 0 to obtain an independent mask. Then, each pixel point is assigned a corresponding value based on the path corresponding to the pixel point. The normalized value of the pixel point The corresponding value in the channel (red channel) is obtained. For example, the pixel point corresponds to the path The normalized value of is 0.8, and the pixel is If the corresponding value in the channel (red channel) is 255, then 0.8×255 should be assigned as the false color mask result for the pixel.

[0059] At this point, the mask image of each frame of the brightness image is obtained.

[0060] Step S007: using the path corresponding to the safety rope in the continuous frame mask image, the falling risk of the safety rope at the current moment is obtained.

[0061] It should be noted that the safety rope's swing is determined based on real-time continuous frame images, and the tension of the speed differential controller is adaptively adjusted to reduce the risk of falling. The safety rope's swing is determined based on the safety rope path marked in the mask image: the safety rope path marked in the current frame must be matched in subsequent frames to determine the safety rope's motion trajectory. The safety rope swings around a fixed point. Because the speed differential controller is connected to the operator, any abnormal change in the operator's posture (such as a gust of wind causing the operator to move) may cause the safety rope to release rapidly, causing the operator to fall. The operator's abnormal movement behavior is reflected in the motion trajectory of the safety rope connected to the speed differential controller.

[0062] In this embodiment, two adjacent mask images in the continuous frame mask image are superimposed to obtain the corresponding path of the safety rope in the continuous frame mask image and the overlapping area of the corresponding path of the safety rope in the continuous frame mask image; the sum of the areas of all the paths corresponding to the safety rope in the continuous frame mask image and the sum of the areas of the overlapping areas of the corresponding paths of the safety rope in the continuous frame mask image are calculated; the swing amplitude of the safety rope is obtained based on the sum of the areas of all the paths corresponding to the safety rope in the continuous frame mask image and the sum of the areas of the overlapping areas of the corresponding paths of the safety rope in the continuous frame mask image; the light intensity quantization value of each path corresponding to the safety rope in the continuous frame mask image is obtained; the mean and standard deviation of the light intensity quantization values of all the paths corresponding to the safety rope in the continuous frame mask image are obtained based on the light intensity quantization value of each path corresponding to the safety rope in the continuous frame mask image; and the falling risk of the safety rope at the current time is obtained by using the swing amplitude of the safety rope and the mean and standard deviation of the light intensity quantization values of all the paths corresponding to the safety rope in the continuous frame mask image.

[0063] Specifically, first, for two adjacent images in the continuous frame mask image, the front and rear images are superimposed, and the safety rope path in the previous image is the safety rope path with the largest overlapping area in the subsequent image is taken as the corresponding path of the safety rope path in the previous image . The subsequent image is iterated to obtain the corresponding path sequence of the safety rope in each image. The risk factor is evaluated according to the change of the abnormal state of the safety rope in the moving process represented by the corresponding path sequence, and the tension of the speed difference controller is adjusted according to the risk factor, so as to realize intelligent processing of the falling risk.

[0064] Then, the areas of all the paths in the path sequence are superimposed, and the sum of the areas of all the paths and the sum of the areas of the overlapping areas are taken as the swing amplitude of the current safety rope. The smaller the sum of the areas of the superimposed areas, the greater the swing amplitude of the safety rope, and the more likely the current path sequence represents the abnormal movement range of the worker.

[0065] Further, the fluctuation of the light intensity quantization value of each safety rope path is judged: the safety rope motion trajectory changes greatly, and the motion presents a fast motion feature due to blurring in the process, which is specifically embodied in that the light intensity quantization value of each safety rope path always maintains a high numerical level in the continuous frame image, so as to indicate that the safety rope is always in an abnormal motion state.

[0066] Specifically, the falling risk at the current time is calculated:

[0067] wherein, represents the falling risk of the safety rope at the current time, represents the sum of the areas of the overlapping regions of the corresponding paths of the safety rope in the continuous frame mask images, represents the sum of the areas of all the corresponding paths of the safety rope in the continuous frame mask images, represents the mean of the light intensity quantization values of all the corresponding paths of the safety rope in the continuous frame mask images, represents the standard deviation of the light intensity quantization values of all the corresponding paths of the safety rope in the continuous frame mask images, represents the light intensity quantization value of each path of the safety rope in the continuous frame mask images.

[0068] It should be noted that the light intensity quantization values of the adjacent pixels contained in each path of the safety rope in the continuous frame mask images are summed up as the light intensity quantization value of each path.

[0069] The greater this value, the more significant the falling risk up to the current time, so that the speed difference self-controller should make more adjustment of the tensioning force at the current time.

[0070] Step S008: adjusting the tensioning force of the safety rope in the speed difference self-controller according to the falling risk of the safety rope at the current time.

[0071] In this embodiment, the tensioning force of the safety rope at the current time is collected; the difference between the tensioning force of the safety rope at the current time and the locking tensioning force is calculated; the normalized value of the falling risk of the safety rope at the current time is obtained; based on the difference between the tensioning force of the safety rope at the current time and the locking tensioning force, and the normalized value of the falling risk of the safety rope at the current time, the adjustment value of the tensioning force of the safety rope at the current time is obtained; and the tensioning force of the safety rope in the speed difference self-controller is adjusted according to the adjustment value of the tensioning force of the safety rope at the current time.

[0072] Specifically, the tensioning force of the safety rope at the current time is collected ; The difference between the current tensioning force and the prior locking tensioning force is calculated , wherein, ; The product of the difference and the normalized value of the falling risk is taken as the adjustment value of the current tensioning force , wherein, ; so the tensioning force at the current time should be adjusted to .

[0073] Please refer to Figure 2 ​It shows a block diagram of a falling risk early warning system of a speed difference self-controller based on image dynamic analysis provided by an embodiment of the present application, and the system comprises the following modules: The acquisition and preprocessing module 100 is used for acquiring continuous frame safety rope images, pre-processing each frame safety rope image, and obtaining a brightness image corresponding to each frame safety rope image. The analysis module 200 is used for obtaining the gradient amplitude and gradient direction of each pixel point in each frame brightness image; determining all reflection starting points of each frame brightness image based on the gradient amplitude of each pixel point in each frame brightness image; obtaining all reflection starting regions of each frame brightness image by using the gradient amplitude and brightness value of each reflection starting point of each frame brightness image; obtaining the adjacent pixel points of each reflection starting region, and obtaining the light intensity quantization value of each adjacent pixel point of each reflection starting region according to the gradient direction of the adjacent pixel points of each reflection starting region and the gradient direction of each pixel point in each reflection starting region; obtaining all safety rope paths of each frame brightness image based on the light intensity quantization value of each adjacent pixel point of each reflection starting region; obtaining the deviation center value of each safety rope path by using the light intensity quantization value of each adjacent pixel point in each safety rope path of each frame brightness image, and judging whether the safety rope abnormally shakes according to the deviation center value of each safety rope path; and obtaining a mask image of each frame brightness image in the case that the safety rope does not abnormally shake; and obtaining the falling risk of the safety rope at the current moment by using the corresponding path of the safety rope in the continuous frame mask image. The adjustment module 300 is used for adjusting the tension of the safety rope in the speed difference self-controller according to the falling risk of the safety rope at the current moment.

[0074] Thus, the present application is completed.

[0075] To sum up, in the embodiment of the present application, the true safety rope region in the image is screened by using the different reflection characteristics of the safety rope and the background to light, so as to further evaluate whether the abnormal movement of the worker occurs according to the movement trajectory and movement range of the safety rope, and then the tension of the speed difference self-controller is adjusted. The embodiment of the present application can avoid the case that the positioning accuracy of the safety rope region is low due to the motion blur caused by the movement of the safety rope, thereby improving the accuracy of the judgment of the falling risk of the worker.

[0076] The above only describes the preferred embodiments of the present application and should not be used to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the principles of the present application shall be included in the protection scope of the present application.

Claims

1. A speed difference automatic controller falling risk early warning method based on image dynamic analysis, characterized in that, The method comprises the following steps: The method comprises the following steps: Collecting continuous frame safety rope images, preprocessing each frame safety rope image, and obtaining the brightness image corresponding to each frame safety rope image; Obtaining the gradient amplitude and gradient direction of each pixel point in each frame brightness image; Based on the gradient amplitude of each pixel point in each frame brightness image, determine all reflection starting points of each frame brightness image; using the gradient amplitude and brightness value of each reflection starting point of each frame brightness image, obtain all reflection starting regions of each frame brightness image; Obtaining the adjacent pixel points of each reflection starting region, and obtaining the light intensity quantization value of each adjacent pixel point of each reflection starting region according to the gradient direction of each adjacent pixel point of each reflection starting region and the gradient direction of each pixel point in each reflection starting region; Based on the light intensity quantization value of each adjacent pixel point of each reflection starting region, obtain all safety rope paths of each frame brightness image; Using the light intensity quantization value of each adjacent pixel point in each safety rope path of each frame brightness image, obtaining the deviation center value of each safety rope path, judging whether the safety rope is abnormally swinging according to the deviation center value of each safety rope path, and obtaining the mask image of each frame brightness image in the case that the safety rope does not abnormally swing; Using the corresponding path of the safety rope in the continuous frame mask image, obtaining the falling risk of the safety rope at the current moment; 2. The fall risk early warning method based on image dynamic analysis of the speed difference automatic controller according to claim 1, characterized in that, According to the falling risk of the safety rope at the current moment, adjusting the tensioning force of the safety rope in the speed difference automatic controller. The specific steps of preprocessing each frame safety rope image and obtaining the brightness image corresponding to each frame safety rope image are as follows: Filtering each frame safety rope image to obtain a filtered image; Extracting the brightness value of each pixel point in the filtered image to obtain an image after extracting the brightness value; 3. The fall risk early warning method based on image dynamic analysis of the speed difference automatic controller according to claim 2, characterized in that, Performing gray scale processing on the image after extracting the brightness value to obtain the brightness image corresponding to each frame safety rope image. The specific steps of determining all reflection starting points of each frame brightness image based on the gradient amplitude of each pixel point in each frame brightness image are as follows: Sort the gradient amplitudes of each pixel point in each frame brightness image in descending order to obtain a gradient amplitude sequence; First-order difference is performed on the gradient amplitude sequence to obtain a gradient difference sequence; Obtain the maximum value in the gradient difference sequence, and take the gradient amplitude corresponding to the maximum value as the end point, and divide the gradient amplitude sequence into a high-light sequence and a non-high-light sequence; 4. The fall risk early warning method based on image dynamic analysis of the speed difference automatic controller according to claim 3, characterized in that, All pixel points corresponding to the high-light sequence are determined as all reflection starting points of each frame brightness image. The specific steps of obtaining all reflection starting regions of each frame brightness image using the gradient amplitude and brightness value of each reflection starting point of each frame brightness image are as follows: Using the gradient amplitude and brightness value of each reflection starting point of each frame brightness image, updating the brightness value of each reflection starting point to obtain the updated brightness value of each reflection starting point; Based on the updated brightness value of each reflection starting point, merging adjacent reflection starting points to obtain all reflection starting regions of each frame brightness image.

5. The fall risk early warning method based on image dynamic analysis of the speed difference automatic controller according to claim 4, characterized in that, The specific steps for obtaining the light intensity quantization value of each adjacent pixel point of each reflection starting region according to the gradient direction of each adjacent pixel point of each reflection starting region and the gradient direction of each pixel point in each reflection starting region include the following steps. For each adjacent pixel point of each reflection starting region, a minimum value of a difference between the gradient direction of the adjacent pixel point and the gradient direction of each pixel point in the reflection starting region is obtained, and the minimum value is determined as a minimum gradient difference value of each adjacent pixel point of each reflection starting region. A sum of the minimum gradient difference values of all adjacent pixel points of each reflection starting region is obtained. The light intensity quantization value of each adjacent pixel point of each reflection starting region is obtained by using the minimum gradient difference value of each adjacent pixel point of each reflection starting region and the sum of the minimum gradient difference values of all adjacent pixel points of each reflection starting region.

6. The fall risk early warning method based on image dynamic analysis of the speed difference automatic controller according to claim 5, characterized in that, The specific steps for obtaining all safety rope paths of each frame of brightness image based on the light intensity quantization value of each adjacent pixel point of each reflection starting region include the following steps. A minimum value of the light intensity quantization values of all adjacent pixel points of each reflection starting region is obtained, and the adjacent pixel point corresponding to the minimum value is taken as a starting point; edges formed by all adjacent pixel points of each reflection starting region are traversed to obtain a light intensity quantization value sequence of the edges; A mean value of the light intensity quantization value sequence of the edges and a standard deviation of the light intensity quantization value sequence of the edges are obtained. A preset edge light intensity quantization value threshold is obtained based on the mean value of the light intensity quantization value sequence of the edges and the standard deviation of the light intensity quantization value sequence of the edges. Elements greater than the preset edge light intensity quantization value threshold in the light intensity quantization value sequence of the edges are taken as sequence nodes. Adjacent sequence nodes are combined to form a node group, the node group with the largest number of nodes is determined as a maximum node group, and adjacent pixel points corresponding to the maximum node group are integrated into the reflection starting region to obtain an effective extension path of each reflection starting region, the effective extension path of each reflection starting region is determined as each safety rope path of each frame of brightness image, and all safety rope paths of each frame of brightness image are obtained.

7. The fall risk early warning method based on image dynamic analysis of the speed difference automatic controller according to claim 6, characterized in that, The specific steps for obtaining the deviation center value of each safety rope path by using the light intensity quantization value of each adjacent pixel point in each safety rope path of each frame of brightness image, judging whether the safety rope abnormally swings according to the deviation center value of each safety rope path, and obtaining a mask image of each frame of brightness image in the case where the safety rope does not abnormally swing include the following steps. For each safety rope path of each frame of brightness image, a normalized value of a sum of the light intensity quantization values of all adjacent pixel points on the path is determined as the deviation center value of each safety rope path. It is judged whether a sum of the deviation center values of all safety rope paths is greater than a preset deviation center value threshold. In the case where the sum of the deviation center values of all safety rope paths is greater than the preset deviation center value threshold, it is determined that the safety rope abnormally swings, and the speed difference automatic controller is locked. In a case where the sum of the deviation center values of all the safety rope paths is less than or equal to a preset deviation center value threshold, each safety rope path is masked to obtain a mask image of each frame of luminance image.

8. The fall risk early warning method based on image dynamic analysis of the speed difference automatic controller according to claim 7, characterized in that, The corresponding path of the safety rope in the continuous frame mask image is used to obtain the falling risk of the safety rope at the current moment, and the specific steps include the following: The two adjacent mask images in the continuous frame mask image are superimposed to obtain the corresponding path of the safety rope in the continuous frame mask image and the overlapping area of the corresponding path of the safety rope in the continuous frame mask image. The sum of the areas of all the corresponding paths of the safety rope in the continuous frame mask image and the sum of the areas of the overlapping areas of the corresponding paths of the safety rope in the continuous frame mask image are calculated. Based on the sum of the areas of all the corresponding paths of the safety rope in the continuous frame mask image and the sum of the areas of the overlapping areas of the corresponding paths of the safety rope in the continuous frame mask image, the swing amplitude of the safety rope is obtained. The light intensity quantization value of each path corresponding to the safety rope in the continuous frame mask image is obtained. Based on the light intensity quantization value of each path corresponding to the safety rope in the continuous frame mask image, the mean and standard deviation of the light intensity quantization values of all the paths corresponding to the safety rope in the continuous frame mask image are obtained. The falling risk of the safety rope at the current moment is obtained by using the swing amplitude of the safety rope and the mean and standard deviation of the light intensity quantization values of all the paths corresponding to the safety rope in the continuous frame mask image.

9. The fall risk early warning method based on image dynamic analysis of the speed difference automatic controller according to claim 8, characterized in that, According to the falling risk of the safety rope at the current moment, the tightening force of the safety rope in the speed difference controller is adjusted, and the specific steps include the following: The tightening force of the safety rope at the current moment is collected. The difference between the tightening force of the safety rope at the current moment and the locking tightening force is calculated. The normalized value of the falling risk of the safety rope at the current moment is obtained. Based on the difference between the tightening force of the safety rope at the current moment and the locking tightening force and the normalized value of the falling risk of the safety rope at the current moment, the adjustment value of the tightening force of the safety rope at the current moment is obtained. The tightening force of the safety rope in the speed difference controller is adjusted according to the adjustment value of the tightening force of the safety rope at the current moment.

10. A speed difference automatic controller falling risk early warning system based on image dynamic analysis, characterized in that, The system includes the following modules: The acquisition and preprocessing module is used to collect continuous frame safety rope images, pre-process each frame of safety rope image, and obtain the corresponding luminance image of each frame of safety rope image. The analysis module is used to obtain the gradient amplitude and gradient direction of each pixel point in each frame of luminance image. Based on the gradient amplitude of each pixel point in each frame of luminance image, all the reflection starting points of each frame of luminance image are determined; and the gradient amplitude and luminance value of each reflection starting point of each frame of luminance image are used to obtain all the reflection starting regions of each frame of luminance image. Obtaining the adjacent pixel points of each reflection starting area, obtaining the light intensity quantization value of each adjacent pixel point of each reflection starting area according to the gradient direction of each adjacent pixel point of each reflection starting area and the gradient direction of each pixel point in each reflection starting area; obtaining all the safety rope paths of each frame of brightness image based on the light intensity quantization value of each adjacent pixel point of each reflection starting area; obtaining the deviation center value of each safety rope path by using the light intensity quantization value of each adjacent pixel point in each safety rope path of each frame of brightness image, judging whether the safety rope abnormally swings according to the deviation center value of each safety rope path, and obtaining the mask image of each frame of brightness image in the case that the safety rope does not abnormally swing; Obtaining the falling risk of the safety rope at the current moment by using the corresponding path of the safety rope in the continuous frame mask image; The adjusting module is used for adjusting the tensioning force of the safety rope in the speed difference automatic controller according to the falling risk of the safety rope at the current moment.

Images