C-hook tilt detection method, device, equipment and readable storage medium

Through image recognition technology, the inclination angle of the C-type hook is detected in real time, and the problem of poor inclination detection of the C-type hook in the prior art is solved, high-precision and rapid detection are achieved, and production safety and economic benefits are ensured.

CN114092432BActive Publication Date: 2024-11-26CERI DIGITAL TECHNOLOGY (BEIJING) CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202111352457.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-11-16
Publication Date
2024-11-26
Estimated Expiration
2041-11-16

AI Technical Summary

Technical Problem

In the prior art, the C-type hook inclination detection effect of high-speed wire suspension conveyor is poor, and it relies on manual inspection to be time-consuming and labor-intensive and has low accuracy. The existing device is high in installation cost and difficult to maintain, and the sensor is susceptible to high temperature and external factors. The accuracy of the detection cannot be guaranteed.

Method used

Image recognition technology is used to obtain images on the C-type hook through the surveillance camera, perform image enhancement, mean filtering, color splitting and contrast processing, filter out the contours of the horizontal edges, calculate the inclination angle, and notify the control system if it exceeds the safety range and The operator takes emergency measures.

Benefits of technology

Real-time detection of C-type hook tilt is realized, which improves the speed and accuracy of detection, prompt warning, avoids overturning accidents and economic losses, and reduces labor costs and maintenance difficulties.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114092432B_ABST
    Figure CN114092432B_ABST
Patent Text Reader

Abstract

The present invention is a C-hook tilt detection method, device, equipment and readable storage medium. The C-hook tilt detection method comprises the following steps: obtaining an image containing a horizontal edge on the C-hook; processing the image to filter out the contour of the horizontal edge in the image; comparing the contour of the horizontal edge with a horizontal line to obtain the angle between the contour of the horizontal edge and the horizontal line; and obtaining the tilt angle of the C-hook according to the angle. The present invention solves the technical problem of poor tilt detection effect of the C-hook of a high-speed wire suspension conveyor.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of steel production, and further relates to a C-hook tilt detection method, device, equipment and readable storage medium, and in particular to a C-hook tilt detection method, device, equipment and readable storage medium for a high-speed wire suspension conveyor. Background Art

[0002] The high-speed wire cold zone is mainly composed of air cooling line, vertical coiling core frame or double core rod, PF line (i.e., hanging conveyor), baler and weighing scale. After rolling from the rolling mill, the steel is coiled by the laying machine, and then cooled by the roller of the air cooling line and transported to the vertical coiling core frame or double core rod. The loose coils on the vertical coiling core frame or double core rod after tilting horizontally are taken away by the transport trolley in the collection area and transported to the C-hook of the PF line. The C-hook is powered by the drive device and the drive chain. During the movement, it can brake in some designated areas and perform operations such as cutting, sampling, packaging or weighing and hanging on the steel wire. After all processes are completed, the finished steel coils on the C-hook are taken off by the unloading trolley and placed in the finished product warehouse or designated area.

[0003] During the entire coil production process, if the C-hook on the PF line is not placed correctly when hanging the coil, causing the C-hook to tilt, accidents such as tipping may occur, which will cause the following consequences:

[0004] 1. The C-type hook is equipped with a clamp and a balance rail when it is used in the coiling, trimming, packaging, weighing and hanging stations. However, due to the cutting or breaking of the wire in the middle, the center of gravity of the C-type hook may shift and cause a tipping accident. Once it tips over in the above stations, it is very likely to damage the clamp and the balance rail. Since the balance rail is welded to the main span beam on the PF line through the support beam, the tipping may even cause more beams to be knocked crooked, which requires a lot of time for inspection and maintenance.

[0005] 2. If the C-hook tips over during operation, production may be forced to stop, seriously affecting the production rhythm, and even causing production accidents such as the steel billets being rolled on the rolling line being forced to be scrapped.

[0006] Therefore, during the production process, it is necessary to detect in real time whether the C-hook is tilted to ensure normal and safe production.

[0007] At present, the detection of C-hook tilt mainly relies on manual inspection, which is completely based on naked eye observation and the operator's independent judgment. The disadvantages of this method are: time-consuming and labor-intensive, extremely high labor costs, low accuracy, poor timeliness, and it is difficult to achieve timely warning;

[0008] In addition, in addition to the traditional manual monitoring solution, there is also a C-hook tilt detection device, such asFigure 1 As shown, the C-hook tilt detection device includes a ribbon 200, a color sensor 300 and a clamp mechanism 400. The ribbon 200 is arc-shaped (or crescent-shaped), the middle position of the ribbon 200 is white, and the positions from the middle position to the two ends of the ribbon 200 gradually turn black. The ribbon 200 is fixedly placed on the side of the C-hook body 100, and the color sensor 300 is placed toward the ribbon 200 and fixed by the clamp mechanism 400. The color sensor 300 can identify the color of the corresponding position on the ribbon 200 at different tilt degrees of the C-hook body 100. Therefore, when the C-hook body 100 is in a horizontal position, the corresponding color on the color ribbon 200 collected by the color sensor 300 is white, which is a normal state; when the C-hook body 100 is tilted, the corresponding color on the color ribbon 200 collected by the color sensor 300 changes (black when the tilt angle is maximum). At this time, an alarm can be sent to the control system to control the clamping mechanism 400 to tighten the C-hook body 100 or use other methods to brake the moving C-hook body 100, thereby preventing accidents. However, the disadvantages of this method are: since there are a large number of C-hooks on the PF line, each C-hook of this solution needs to be installed with equipment such as a ribbon 200, a color sensor 300 and a clamp mechanism 400, which has high installation costs and difficult maintenance; during the production process, the temperature of the coil on the C-hook is relatively high (usually higher than 100 degrees Celsius), and the sensor is a sensitive device, and long-term high-temperature steaming and baking will affect the performance of the color sensor 300 and it is very easy to be damaged; in addition, external factors (such as light brightness, dust, etc.) will also affect the color detection effect, and the detection accuracy cannot be guaranteed. Therefore, the actual use of this method is not ideal.

[0009] With regard to the problem of poor detection effect of the C-hook tilt of the high-speed wire suspension conveyor in the related art, no effective solution has been given so far.

[0010] Therefore, the inventor, relying on many years of experience and practice in related industries, proposes a C-hook tilt detection method, device, equipment and readable storage medium to overcome the defects of the prior art. Summary of the invention

[0011] The object of the present invention is to provide a C-hook tilt detection method, device, equipment and readable storage medium. Through image recognition, the tilt angle of the workstation where the C-hook is located can be detected in real time. If it is found that the tilt angle exceeds the safe angle range, the control system and the operator will be notified to take corresponding emergency measures in time, which can effectively prevent the occurrence of rollover accidents and the resulting economic losses.

[0012] The purpose of the present invention can be achieved by adopting the following technical solutions:

[0013] The present invention provides a C-hook tilt detection method, comprising the following steps:

[0014] Acquire an image including a horizontal edge of the C-hook;

[0015] Processing the image to filter out the contour of the horizontal edge in the image;

[0016] Comparing the contour of the horizontal side with a horizontal line to obtain an angle between the contour of the horizontal side and the horizontal line;

[0017] According to the included angle, the inclination angle of the C-hook is obtained.

[0018] In a preferred embodiment of the present invention, the step of acquiring an image including a horizontal edge of the C-shaped hook comprises:

[0019] Collecting video stream data at the location of the C-hook in real time;

[0020] Intercepting the monitoring image at the current moment in the video stream data;

[0021] A region including the horizontal edge is divided on the monitoring image to obtain an image of the horizontal edge.

[0022] In a preferred embodiment of the present invention, the processing of the image to filter out the contour of the horizontal edge in the image includes:

[0023] Performing image enhancement processing on the image;

[0024] Performing mean filtering on the image after image enhancement processing;

[0025] Perform color segmentation processing on the image after mean filtering;

[0026] Selecting the image after color splitting processing according to a preset saturation to obtain a first image;

[0027] Performing contrast enhancement processing on each pixel in the first image to obtain a second image;

[0028] Filtering the second image according to saturation to obtain a high-saturation area in the second image;

[0029] A rectangular wireframe is drawn along the edge of the high-saturation region in the second image to obtain the outline of the C-hook.

[0030] In a preferred embodiment of the present invention, in the image enhancement processing performed on the image, the contrast between the high-frequency area and the low-frequency area in the image is increased to amplify the difference in pixel values ​​between each point in the image.

[0031] In a preferred embodiment of the present invention, in the mean filtering process performed on the image after image enhancement, the grayscale value of the image is linearly smoothed.

[0032] In a preferred embodiment of the present invention, in the color segmentation process of the image after the mean filtering process, the RGB segmentation method and the HSV segmentation method are used to perform color segmentation process on the image.

[0033] In a preferred embodiment of the present invention, in the process of increasing the contrast of each pixel in the first image, the grayscale value of the first image is multiplied by any constant greater than or equal to 2 to obtain the second image.

[0034] In a preferred embodiment of the present invention, in the screening of the second image by saturation, screening is performed based on the area occupied by the C-shaped hook in the second image and the position of the C-shaped hook in the second image to obtain a high-saturation area in the second image.

[0035] In a preferred embodiment of the present invention, the video stream data at the location of the C-hook is collected by a monitoring camera, the installation position of the monitoring camera is opposite to the C-hook, and the monitoring camera is placed in a horizontal direction.

[0036] In a preferred embodiment of the present invention, the video stream data is subjected to depth of field processing by the monitoring camera.

[0037] In a preferred embodiment of the present invention, the processing of the image to filter out the contour of the horizontal edge in the image includes:

[0038] Performing filtering processing on the image to obtain the contour shape of the C-hook in the image;

[0039] According to the different gray values ​​of the C-shaped hook and the background in the image, a dot-line diagram of the upper edge and / or the lower edge of the horizontal direction side is obtained;

[0040] A straight line fitting process is performed on the point-line graph to obtain a fitting straight line of the upper edge and / or the lower edge of the horizontal side.

[0041] In a preferred embodiment of the present invention, after obtaining the inclination angle of the C-hook according to the included angle, the method further comprises:

[0042] Presetting a threshold value of the inclination angle of the C-hook;

[0043] If it is detected that the inclination angle of the C-hook is greater than the threshold, an external warning is issued.

[0044] The present invention provides a C-hook tilt detection device, comprising:

[0045] An image acquisition unit, used for acquiring an image including a horizontal edge of the C-shaped hook;

[0046] A contour screening unit, used for processing the image to screen out the contour of the horizontal edge in the image;

[0047] A comparison unit, configured to compare the contour of the horizontal edge with a horizontal line to obtain an angle between the contour of the horizontal edge and the horizontal line;

[0048] The inclination angle obtaining unit is used to obtain the inclination angle of the C-hook according to the included angle.

[0049] In a preferred embodiment of the present invention, the profile screening unit comprises:

[0050] An image enhancement module, used for performing image enhancement processing on the image;

[0051] A mean filter module is used to perform mean filter processing on the image after image enhancement processing;

[0052] A color splitting module is used to perform color splitting on the image after the mean filtering process;

[0053] A first image acquisition module, used for selecting the image after color separation processing according to a preset saturation to obtain a first image;

[0054] A second image acquisition module, used for performing contrast enhancement processing on each pixel in the first image to obtain a second image;

[0055] A region screening module, used for screening the second image according to saturation to obtain a high-saturation region in the second image;

[0056] The contour acquisition module is used to circumscribe a rectangular wireframe along the edge of the high-saturation area in the second image to obtain the contour of the C-hook.

[0057] In a preferred embodiment of the present invention, the profile screening unit comprises:

[0058] A contour shape acquisition module, used for performing filtering processing on the image to obtain the contour shape of the C-hook in the image;

[0059] A point-line graph acquisition module, used for obtaining a point-line graph of the upper edge and / or the lower edge of the horizontal direction edge according to different gray values ​​of the C-shaped hook and the background in the image;

[0060] The straight line fitting module is used to perform straight line fitting processing on the point-line graph to obtain a fitting straight line of the upper edge and / or the lower edge of the horizontal side.

[0061] The present invention provides a computer device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned C-hook tilt detection method when executing the computer program.

[0062] The present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for executing the above-mentioned C-hook tilt detection method.

[0063] As described above, the characteristics and advantages of the C-hook inclination detection method, device, equipment and readable storage medium of the present invention are: an image containing a horizontal edge on the C-hook is obtained by a monitoring camera, and the image is processed to ensure that the contour of the horizontal edge on the C-hook in the image can be screened out, and then the contour of the horizontal edge is compared with the horizontal line. The obtained angle is the inclination angle of the C-hook. The inclination angle of the C-hook can be detected in real time through the above-mentioned image recognition method, which is convenient and fast, and has high detection accuracy. If it is found that the inclination angle exceeds the preset safety angle range, the control system and the operator can be notified in time to take emergency measures, thereby effectively preventing the occurrence of C-hook tipping accidents, ensuring the personal safety of the staff and avoiding economic losses caused by tipping over of the C-hook. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] The following drawings are only intended to illustrate and explain the present invention, and are not intended to limit the scope of the present invention.

[0065] in:

[0066] Figure 1 : It is a structural schematic diagram of an existing C-hook tilt detection device.

[0067] Figure 2 : is one of the flow charts of the C-hook tilt detection method of the present invention.

[0068] Figure 3 : This is the second flow chart of the C-hook tilt detection method of the present invention.

[0069] Figure 4 : This is the third flow chart of the C-hook tilt detection method of the present invention.

[0070] Figure 5 : This is the fourth flow chart of the C-hook tilt detection method of the present invention.

[0071] Figure 6 : This is the fifth flow chart of the C-hook tilt detection method of the present invention.

[0072] Figure 7 : is one of the structural block diagrams of the C-hook tilt detection device of the present invention.

[0073] Figure 8 : This is the second structural block diagram of the C-hook tilt detection device of the present invention.

[0074] Fig. 9 : This is the third structural block diagram of the C-hook tilt detection device of the present invention.

[0075] Fig.10 : is a schematic diagram of a monitoring image captured in the C-hook tilt detection method of the present invention.

[0076] Fig.11 :for Fig.10 Display diagram of the surveillance image of the location in area 2.

[0077] Fig.12 :For Fig.11 The display image after image enhancement processing.

[0078] Fig.13 : It is a schematic diagram of the calculation formula of the mean filter in the C-hook tilt detection method of the present invention.

[0079] Fig.14 :For Fig.12 The display image after mean filtering.

[0080] Fig.15 :For Fig.14 A display diagram of the selected first image after color separation processing.

[0081] Fig.16 :For Fig.15 Display diagram of the second image after contrast enhancement processing.

[0082] Fig.17 : This is a display diagram of a C-hook in a normal state obtained in the C-hook tilt detection method of the present invention.

[0083] Fig.18 : This is a display diagram of a C-hook in a severe tilt state obtained in the C-hook tilt detection method of the present invention.

[0084] Fig.19 : is a schematic diagram of a monitoring image captured after depth of field processing in the C-hook tilt detection method of the present invention.

[0085] Fig. 20 :For Fig.19 The display diagram after straight line fitting processing.

[0086] The accompanying drawings in the background art are:

[0087] 100, C-hook body; 200, ribbon;

[0088] 300. Color sensor; 400. Clamping mechanism.

[0089] The accompanying drawings in the present invention are:

[0090] 10. Image acquisition unit; 20. Contour screening unit;

[0091] 30. Comparison unit; 40. Inclination angle acquisition unit;

[0092] 2001. Image enhancement module; 2002. Mean filter module;

[0093] 2003. Color separation module; 2004. First image acquisition module;

[0094] 2005. Second image acquisition module; 2006. Region screening module;

[0095] 2007, contour acquisition module;

[0096] 2011. Contour shape acquisition module; 2012. Point and line graph acquisition module;

[0097] 2013. Linear fitting module. DETAILED DESCRIPTION

[0098] In order to have a clearer understanding of the technical features, purposes and effects of the present invention, specific embodiments of the present invention are now described with reference to the accompanying drawings.

[0099] Implementation Method 1

[0100] like Figure 2 , Figure 6 As shown, the present invention provides a C-hook tilt detection method, the C-hook tilt detection method comprises the following steps:

[0101] Step S1: Acquire an image including a horizontal edge of the C-shaped hook;

[0102] Step S2: Processing the image to filter out the contour of the horizontal edge of the C-hook in the image;

[0103] Step S3: comparing the contour of the horizontal edge with the horizontal line to obtain the angle between the contour of the horizontal edge and the horizontal line;

[0104] Step S4: Obtain the inclination angle of the C-hook according to the angle between the contour of the horizontal side and the horizontal line.

[0105] Step S5: Presetting a threshold value of the inclination angle of the C-hook;

[0106] Step S6: If it is detected that the inclination angle of the C-hook is greater than a threshold, an external warning is issued.

[0107] In an optional embodiment of the present invention, Figure 3 As shown, step S1 includes:

[0108] Step S101: collecting video stream data at the location of the C-hook in real time (the video stream data includes both the C-hook and the factory environment where the C-hook is located);

[0109] Step S102: Intercept the collected video stream data such as Fig.10 The monitoring image (eg, Fig.10 Area 1);

[0110] Step S103: Divide the monitoring image into a rectangular area containing the horizontal side of the C-shaped hook (such as Fig.10 In order to obtain the image of the horizontal edge of the C-hook, the area 2 in the image is divided into two parts. Since the horizontal edge of the C-hook and the background image mainly composed of the factory environment exist in the area 2 (that is, the part of the area 2 other than the horizontal edge of the C-hook), which will affect the recognition accuracy of the image, it is necessary to process the divided area 2 to filter out the contour of the horizontal edge of the C-hook in the image.

[0111] Furthermore, the video stream data at the location of the C-hook can be collected by installing a surveillance camera. The installation position of the surveillance camera needs to be directly opposite the C-hook, and the surveillance camera must be placed in the horizontal direction to ensure that the horizontal edge of the C-hook in the collected video stream data extends along the horizontal line when the C-hook is not tilted, otherwise it will affect the recognition accuracy of the image. Of course, other image acquisition devices such as industrial cameras can also be used instead of surveillance cameras to meet the image acquisition requirements for the C-hook.

[0112] like Fig.11As shown, in the process of processing the image, the present invention needs to completely, accurately and quickly filter out the horizontal side of the C-hook (i.e., the rectangular area of ​​the upper arm of the C-hook in area 2) in area 2 on the intercepted monitoring image. Therefore, it is necessary to extract the unique features of the C-hook in the image so as to distinguish the horizontal side of the C-hook from its background image (e.g., the yellow stripes and black stripes alternately displayed on the outer wall of the C-hook can be used as the unique features of the C-hook, and it is only necessary to filter out the area where the yellow stripes and the black stripes are located as the rectangular area of ​​the C-hook in area 2). However, since the image is collected by the monitoring camera, the following problems often occur: 1. The background of the background image is too messy, which interferes with the image screening; 2. During the production process, there will be direct sunlight, which interferes with the image screening; 3. Long-term use will accumulate a lot of dust, making the display effect of the unique feature area on the C-hook poor (e.g., the area where the yellow stripes and black stripes alternately displayed on the outer wall of the C-hook appear gray). Therefore, the image needs to be processed to accurately screen out the contour of the horizontal edge of the C-hook in the image. The specific processing method is as follows:

[0113] like Figure 4 As shown, step S2 includes:

[0114] Step S201: Fig.12 As shown, the image is enhanced to increase the contrast between the high-frequency area and the low-frequency area in the image, so as to amplify the difference in pixel values ​​between points in the image. This processing method makes the image clearer and can remove the interference of external factors such as dust and light on the image clarity.

[0115] Specifically, the calculation formula for image enhancement processing is:

[0116] res=round((orig-mean)×Factor)+orig;

[0117] Among them: res is the new pixel value of the point after enhancement calculation, orig is the pixel value of the point on the original image, mean is the average pixel value of all points within the kernel size range, and Factor is the enhancement coefficient.

[0118] Step S202: performing mean filtering on the image after image enhancement processing;

[0119] Further, the mean filtering process is performed on the image after the image enhancement process: the selected image is smoothed by the mean, so that the gray value of the image after the image enhancement process is linearly smoothed, which is the mean filtering.

[0120] Specifically, Fig.13 As shown in the figure, the calculation formula of mean filtering is:

[0121]

[0122] in, is the convolution symbol, and the element k in h(x, y) is the area of ​​the surrounding neighborhood (that is, the product of the height and width of the surrounding area is k).

[0123] In the present invention, the mean filtering of the image is a method of taking the average of the target pixel and the surrounding pixels and then filling the target pixel back to achieve the filtering purpose. This method can be used to traverse all the pixels in the image to achieve the mean filtering of the entire image. It can be seen from the above mean filtering formula that when the k value is larger, the closer the filtered pixel is to the surrounding pixels, the more blurred the image is; combined with the on-site C-hook image (i.e.: Fig.11 ) It can be seen that the area showing the C-hook in the image is the area of ​​alternating yellow stripes and black stripes, and the color is relatively single, while the background image is messy (it can be composed of multiple colors). The purpose of performing mean filtering on the image is to make the area of ​​alternating yellow stripes and black stripes mixed into a single color as much as possible without changing the original color of the C-hook, thereby improving the color saturation of the area where the C-hook is located, making it easier to distinguish the area where the C-hook is located from the background image area, and improving the accuracy of identifying the area where the C-hook is located. Therefore, in a specific embodiment of the present invention, the height of the h(x, y) matrix can be set to 25 and the width to 200, that is, a 200×25 matrix. The parameters can be appropriately adjusted according to actual conditions; by calculation, such as Fig.14 As shown, the yellow stripes and the black stripes in the area where the C-hook is located can be merged together to form a color with higher saturation, while the saturation of the area where the background image is located is still lower than that of the area where the C-hook is located due to the chaotic colors.

[0124] Step S203: performing color segmentation processing on the image after the mean filtering processing;

[0125] Specifically, the RGB (R: red; G: green; B: blue) splitting method and the HSV (H: hue; S: saturation; V: brightness) splitting method can be used to perform color splitting processing on the image after the mean filtering processing.

[0126] Step S204: Select the image after color segmentation processing according to the preset saturation S to obtain Fig.15 The first image shown; wherein, the preset saturation S can be set according to the saturation of the area where the C-hook is located and the saturation of the background image area, ensuring that the area where the C-hook is located and the background image area can be clearly distinguished.

[0127] Step S205: Perform contrast enhancement processing on each pixel in the first image to obtain Fig.16 The second image shown;

[0128] Specifically, the grayscale value of the first image can be multiplied by any constant greater than or equal to 2 to obtain the second image. The purpose is to increase the contrast between each pixel in the first image, thereby increasing the difference between the saturation of the area where the C-hook is located and the saturation of the background image area.

[0129] Step S206: screening the second image according to the high-saturation area and the low-saturation area to obtain the high-saturation area in the second image (ie, the area where the C-hook is located);

[0130] Step S207: Since there is still a small amount of background image area in the high saturation area of ​​the filtered second image, it is necessary to Fig.11 The area of ​​the C-shaped hook in the second image is used to determine the high saturation area in the second image. The specific method is: a rectangular wireframe (i.e., the outline of the C-shaped hook) is circumscribed along the edge of the high saturation area in the second image, so as to obtain Fig.17 , Fig.18 The profile of a C-hook is shown.

[0131] Specifically, screening is performed based on the area occupied by the C-shaped hook in the second image and the position of the C-shaped hook in the second image to obtain a high-saturation area in the second image, and then a rectangular wireframe is circumscribed along the edge of the high-saturation area in the second image.

[0132] like Fig.17 As shown in the figure, the contours of two C-hooks are identified in the image, and the angles between them and the horizontal line are 0.7° and 0.85° respectively, which are almost parallel to the horizontal line and do not exceed the preset threshold of the inclination angle of the C-hooks (the threshold can be set according to the actual situation to ensure that the C-hooks will not tip over within the threshold), which is a normal state; Fig.18 As shown, when the outline of the C-hook identified in the image is severely tilted (i.e., the angle between the outline of the C-hook and the horizontal line exceeds the preset threshold of the tilt angle of the C-hook), but the C-hook is severely tilted, a rollover accident has often occurred; if the C-hook is severely tilted but a rollover accident has not occurred, an external alarm system can be used to alarm, notifying the control system and the operator to take corresponding emergency measures in a timely manner, which can effectively prevent the occurrence of rollover accidents and the resulting economic losses.

[0133] In an optional embodiment of the present invention, the surveillance camera can be upgraded to have a depth of field function. The surveillance camera performs depth of field processing on the video stream data to improve the clarity of the C-hook area in the image and blur the background image area, thereby obtaining the following image: Fig.19 The image shown has been processed with depth of field.

[0134] Further, such as Figure 5 As shown, step S2 includes:

[0135] Step S211: filtering the image after the depth-processing to obtain the contour shape of the C-hook in the image after the depth-processing;

[0136] Specifically, a Sobel filter is used to filter the image after depth processing. The filter type may be but is not limited to "thin_sum_abs", and the size of the mask is 3. After filtering, the contour shape of the C-hook can be obtained.

[0137] Step S212: obtaining a dot-line diagram of the upper edge and / or lower edge of the horizontal side of the C-shaped hook in the image according to the different grayscale values ​​of the C-shaped hook area and the background image area in the filtered image;

[0138] Step S213: Perform straight line fitting processing on the point-line diagram of the upper edge and / or lower edge of the horizontal side of the C-shaped hook to obtain Fig. 20 The fitted straight line of the upper edge and / or lower edge of the horizontal side of the C-hook shown.

[0139] Specifically, the point-line graph can be fitted with a straight line according to the Hough straight line detection method, and the obtained fitting straight line is the outline of the C-hook. Fig. 20 As shown, the angle between the fitting straight line and the horizontal line can be obtained to be less than the threshold value of the oblique angle, and there is no danger of tipping over.

[0140] The characteristics and advantages of the C-hook tilt detection method of the present invention are:

[0141] The C-hook tilt detection device can detect the tilt angle of the C-hook in real time through image recognition, which is convenient and fast, and has high detection accuracy. If it is found that the tilt angle exceeds the preset safety angle range, the control system and the operator can be notified in time to take emergency measures, thereby effectively preventing the occurrence of C-hook tipping accidents, ensuring the personal safety of the staff and avoiding economic losses caused by the tipping of the C-hook. The device is suitable for popularization and use.

[0142] Implementation Method 2

[0143] like Figure 7As shown, the present invention provides a C-hook inclination detection device, which includes an image acquisition unit 10, a contour screening unit 20, a comparison unit 30 and an inclination angle acquisition unit 40. The image acquisition unit 10 is used to acquire an image containing a horizontal edge on the C-hook; the contour screening unit 20 is used to process the image to filter out the contour of the horizontal edge in the image; the comparison unit 30 is used to compare the contour of the horizontal edge with the horizontal line to obtain the angle between the contour of the horizontal edge and the horizontal line; the inclination angle acquisition unit 40 is used to obtain the inclination angle of the C-hook according to the angle.

[0144] In an optional embodiment of the present invention, Figure 8 As shown, the contour screening unit 20 includes an image enhancement module 2001, a mean filtering module 2002, a color separation module 2003, a first image acquisition module 2004, a second image acquisition module 2005, a region screening module 2006 and a contour acquisition module 2007. Among them, the image enhancement module 2001 is used to perform image enhancement processing on the image; the mean filtering module 2002 is used to perform mean filtering processing on the image after the image enhancement processing; the color separation module 2003 is used to perform color separation processing on the image after the mean filtering processing; the first image acquisition module 2004 is used to select the image after the color separation processing according to the preset saturation to obtain the first image; the second image acquisition module 2005 is used to increase the contrast of each pixel in the first image to obtain the second image; the region screening module 2006 is used to filter the second image according to the saturation to obtain the high saturation area in the second image; the contour acquisition module 2007 is used to circumscribe a rectangular wire frame along the edge of the high saturation area in the second image to obtain the contour of the C-hook.

[0145] Furthermore, the image enhancement module 2001 performs image enhancement processing on the image to increase the contrast between the high-frequency area and the low-frequency area in the image so as to amplify the difference in pixel values ​​between points in the image. This processing method makes the image clearer and can remove interference to the image clarity caused by external factors such as dust and light.

[0146] Furthermore, the mean filtering module 2002 smoothes the selected image by the mean, thereby performing linear smoothing on the grayscale value of the image after the image enhancement processing.

[0147] Furthermore, the color segmentation module 2003 can use the RGB segmentation method and the HSV segmentation method to perform color segmentation processing on the image after the mean filtering processing.

[0148] Furthermore, the second image acquisition module 2005 can multiply the grayscale value of the first image by any constant greater than or equal to 2 to obtain the second image, the purpose of which is to increase the contrast between each pixel in the first image, thereby increasing the difference between the saturation of the area where the C-hook is located and the saturation of the background image area.

[0149] Furthermore, the contour acquisition module 2007 can filter according to the area occupied by the C-shaped hook in the second image and the position of the C-shaped hook in the second image to obtain the high-saturation area in the second image, and then circumscribe a rectangular wireframe along the edge of the high-saturation area in the second image.

[0150] In an optional embodiment of the present invention, the surveillance camera has the function of performing depth of field processing on the video stream data, such as Fig. 9 As shown, the contour screening unit 20 includes a contour shape acquisition module 2011, a point-line graph acquisition module 2012 and a straight line fitting module 2013. The contour shape acquisition module 2011 is used to filter the image to obtain the contour shape of the C-shaped hook in the image; the point-line graph acquisition module 2012 is used to obtain the point-line graph of the upper edge and / or lower edge of the horizontal direction of the C-shaped hook according to the different gray values ​​of the C-shaped hook and the background in the image; the straight line fitting module 2013 is used to perform straight line fitting processing on the point-line graph to obtain the fitting straight line of the upper edge and / or lower edge of the horizontal direction.

[0151] Furthermore, the contour shape acquisition module 2011 may use a Sobel filter to filter the image after depth processing. The filter type may be but is not limited to "thin_sum_abs", and the size of the mask is 3. After filtering, the contour shape of the C-hook can be obtained.

[0152] Furthermore, the straight line fitting module 2013 may perform straight line fitting on the point-line graph according to the Hough straight line detection method.

[0153] The characteristics and advantages of the C-hook tilt detection device of the present invention are:

[0154] The C-hook tilt detection device can detect the tilt angle of the C-hook in real time by image recognition, which is convenient and fast, and has high detection accuracy. It can effectively ensure the personal safety of workers and avoid economic losses caused by tipping over of the C-hook, and is suitable for popularization and use.

[0155] Implementation Method 3

[0156] The present invention provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned C-hook tilt detection method is implemented.

[0157] Specifically, the computer device may be a computer terminal, a server or a similar computing device.

[0158] Implementation Method 4

[0159] The present invention provides a computer-readable storage medium storing a computer program for executing the above-mentioned C-hook tilt detection method.

[0160] Specifically, computer-readable storage media include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer-readable storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable storage media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0161] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0162] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1A device that provides the functions specified in a block or multiple blocks.

[0163] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0164] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0165] The above description is only an illustrative embodiment of the present invention and is not intended to limit the scope of the present invention. Any equivalent changes and modifications made by any person skilled in the art without departing from the concept and principle of the present invention shall fall within the scope of protection of the present invention.

Claims

1. A method for detecting the tilt of a C-hook, It is characterized in that The steps include: Acquire an image including a horizontal edge of the C-hook; Processing the image to filter out the contour of the horizontal edge in the image; Comparing the contour of the horizontal side with a horizontal line to obtain an angle between the contour of the horizontal side and the horizontal line; According to the included angle, obtaining the inclination angle of the C-hook; The step of acquiring an image including a horizontal edge of the C-shaped hook comprises: Collecting video stream data at the location of the C-hook in real time; Intercepting the monitoring image at the current moment in the video stream data; Dividing a region including the horizontal edge on the monitoring image to obtain an image of the horizontal edge; The processing of the image to filter out the contour of the horizontal edge in the image includes: Performing image enhancement processing on the image; wherein, extracting features on the C-shaped hook from the image to distinguish the horizontal edge of the C-shaped hook from the background image, the features on the C-shaped hook comprising yellow stripes and black stripes alternately displayed on the outer wall of the C-shaped hook; The image after image enhancement processing is subjected to mean filtering processing; wherein, without changing the original color of the C-shaped hook, the areas of the yellow stripes and the black stripes alternately displayed on the C-shaped hook are mixed into a single color, and the color saturation of the area where the C-shaped hook is located is increased, so that the area where the C-shaped hook is located is distinguished from the background image area; Perform color segmentation processing on the image after mean filtering; Selecting the image after color splitting processing according to a preset saturation to obtain a first image; Performing contrast enhancement processing on each pixel in the first image to obtain a second image; Filtering the second image according to saturation to obtain a high-saturation area in the second image; A rectangular wireframe is drawn along the edge of the high-saturation region in the second image to obtain the outline of the C-hook.

2. The C-hook tilt detection method according to claim 1, It is characterized in that In the image enhancement processing performed on the image, the contrast between the high-frequency area and the low-frequency area in the image is increased to amplify the difference in pixel values ​​between points in the image.

3. The C-hook tilt detection method according to claim 1, It is characterized in that In the mean filtering process performed on the image after the image enhancement process, the grayscale value of the image is linearly smoothed.

4. The C-hook tilt detection method according to claim 1, It is characterized in that In the color segmentation process of the image after the mean filtering process, the RGB segmentation method and the HSV segmentation method are used to perform color segmentation process on the image.

5. The C-hook tilt detection method according to claim 1, It is characterized in that In the process of increasing the contrast of each pixel in the first image, the grayscale value of the first image is multiplied by any constant greater than or equal to 2 to obtain the second image.

6. The C-hook tilt detection method according to claim 1, It is characterized in that In the screening of the second image according to saturation, screening is performed according to the area occupied by the C-shaped hook in the second image and the position of the C-shaped hook in the second image to obtain a high-saturation area in the second image.

7. The C-hook tilt detection method according to claim 1, It is characterized in that The video stream data at the position where the C-shaped hook is located is collected by a monitoring camera, the installation position of the monitoring camera is directly opposite to the C-shaped hook, and the monitoring camera is placed in a horizontal direction.

8. The C-hook tilt detection method according to claim 7, It is characterized in that The video stream data is subjected to depth-of-field processing by the surveillance camera.

9. The C-hook tilt detection method according to claim 8, It is characterized in that The processing of the image to filter out the contour of the horizontal edge in the image includes: Performing filtering processing on the image to obtain the contour shape of the C-hook in the image; According to the different grayscale values ​​of the C-shaped hook and the background in the image, obtaining a dot-line graph of the upper edge and / or the lower edge of the horizontal direction side; A straight line fitting process is performed on the point-line graph to obtain a fitting straight line of the upper edge and / or the lower edge of the horizontal side.

10. The C-hook tilt detection method according to claim 1, It is characterized in that After obtaining the inclination angle of the C-hook according to the included angle, the method further includes: Presetting a threshold value of the inclination angle of the C-hook; If it is detected that the inclination angle of the C-hook is greater than the threshold, an external warning is issued.

11. A C-hook tilt detection device, which detects the tilt of the C-hook using the C-hook tilt detection method according to any one of claims 1 to 10. It is characterized in that The C-hook tilt detection device comprises: An image acquisition unit, used for acquiring an image including a horizontal edge of the C-shaped hook; A contour screening unit, used for processing the image to screen out the contour of the horizontal edge in the image; A comparison unit, configured to compare the contour of the horizontal edge with a horizontal line to obtain an angle between the contour of the horizontal edge and the horizontal line; The inclination angle obtaining unit is used to obtain the inclination angle of the C-hook according to the included angle.

12. The C-hook tilt detection device according to claim 11, It is characterized in that The profile screening unit comprises: An image enhancement module, used for performing image enhancement processing on the image; A mean filter module is used to perform mean filter processing on the image after image enhancement processing; A color splitting module is used to perform color splitting on the image after the mean filtering process; A first image acquisition module, used for selecting the image after color separation processing according to a preset saturation to obtain a first image; A second image acquisition module, used for performing contrast enhancement processing on each pixel in the first image to obtain a second image; A region screening module, used for screening the second image according to saturation to obtain a high-saturation region in the second image; The contour acquisition module is used to circumscribe a rectangular wireframe along the edge of the high-saturation area in the second image to obtain the contour of the C-hook.

13. The C-hook tilt detection device according to claim 11, It is characterized in that The profile screening unit comprises: A contour shape acquisition module, used for performing filtering processing on the image to obtain the contour shape of the C-hook in the image; A point-line diagram acquisition module, used for obtaining a point-line diagram of the upper edge and / or the lower edge of the horizontal direction edge according to different gray values ​​of the C-shaped hook and the background in the image; The straight line fitting module is used to perform straight line fitting processing on the point-line graph to obtain a fitting straight line of the upper edge and / or the lower edge of the horizontal side.

14. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer program, the C-hook tilt detection method according to any one of claims 1 to 10 is implemented.

15. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a computer program for executing the C-hook tilt detection method according to any one of claims 1 to 10.