CN115797316A - Heavy load rope monitoring method and device, computer equipment and medium - Google Patents
Heavy load rope monitoring method and device, computer equipment and medium Download PDFInfo
- Publication number
- CN115797316A CN115797316A CN202211627020.2A CN202211627020A CN115797316A CN 115797316 A CN115797316 A CN 115797316A CN 202211627020 A CN202211627020 A CN 202211627020A CN 115797316 A CN115797316 A CN 115797316A
- Authority
- CN
- China
- Prior art keywords
- heavy
- target
- load rope
- monitoring
- rope
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Image Analysis (AREA)
Abstract
The embodiment of the application is suitable for the technical field of mineral exploitation, and provides a heavy load rope monitoring method, a heavy load rope monitoring device, computer equipment and a medium, wherein the method comprises the following steps: acquiring a video sequence to be processed from a monitoring video of a heavy-load rope, wherein the video sequence to be processed comprises a plurality of sample video frames; cutting out a plurality of target images containing the heavy loading ropes from a plurality of sample video frames; respectively extracting a plurality of characteristics of the target image by adopting a preset characteristic extraction network; and determining a monitoring result of the heavy-load rope according to a plurality of characteristics. By the method, the heavy-load rope can be monitored, so that potential safety hazards of the heavy-load rope can be found in time, and construction safety is guaranteed.
Description
Technical Field
The application belongs to the technical field of mineral exploitation, and particularly relates to a heavy-load rope monitoring method and device, computer equipment and a medium.
Background
The cableway is important equipment of a mine and plays an important role in conveying ores. The heavy-load rope is used as a key component of high danger in cableway equipment and is a life line for cableway transportation. The safe operation and the inspection and maintenance of the heavy-load rope on the cableway are basic guarantees for ensuring the safe production of mines.
At present, in order to guarantee construction safety, a method of regularly replacing a heavy-duty rope is generally adopted, a replacement period is determined according to the rated service life of the heavy-duty rope, the actual condition of the heavy-duty rope cannot be considered, a waste condition can be caused, and potential safety hazards can be generated when a steel wire rope is not replaced in time.
Disclosure of Invention
In view of this, the embodiment of the present application provides a method, an apparatus, a computer device and a medium for monitoring a heavy load rope, so as to realize monitoring of the heavy load rope, thereby timely discovering the potential safety hazard of the heavy load rope.
A first aspect of an embodiment of the present application provides a heavy load rope monitoring method, including:
acquiring a video sequence to be processed from a monitoring video of a heavy-load rope, wherein the video sequence to be processed comprises a plurality of sample video frames;
cutting out a plurality of target images containing the heavy loading ropes from a plurality of sample video frames;
respectively extracting a plurality of characteristics of the target image by adopting a preset characteristic extraction network;
and determining a monitoring result of the heavy-load rope according to a plurality of characteristics.
A second aspect of an embodiment of the present application provides a heavy load rope monitoring device, including:
the device comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring a video sequence to be processed from a monitoring video of a heavy-load rope, and the video sequence to be processed comprises a plurality of sample video frames;
the cutting module is used for cutting a plurality of target images containing the heavy loading ropes from a plurality of sample video frames;
the extraction module is used for respectively extracting a plurality of characteristics of the target image by adopting a preset characteristic extraction network;
and the determining module is used for determining the monitoring result of the heavy-duty rope according to the characteristics.
A third aspect of embodiments of the present application provides a computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the method according to the first aspect when executing the computer program.
A fourth aspect of embodiments of the present application provides a computer-readable storage medium, in which a computer program is stored, which, when executed by a processor, implements the method according to the first aspect as described above.
A fifth aspect of embodiments of the present application provides a computer program product, which, when run on a computer device, causes the computer device to perform the method of the first aspect.
Compared with the prior art, the embodiment of the application has the following advantages:
according to the embodiment of the application, the monitoring equipment can be used for monitoring the heavy-load rope, so that a monitoring video of the heavy-load rope is obtained. Then the heavy load rope monitoring device can extract a video sequence to be processed from the monitoring video, wherein the video sequence to be processed comprises a plurality of sample video frames. Because each video frame contains more pictures, in order to monitor the heavy-load rope more clearly, the area corresponding to the heavy-load rope can be cut out from the sample video frame, and the target image is obtained. For each target image, the heavy load rope monitoring device can respectively extract the characteristics of each target image, so that whether the heavy load rope has faults or not can be determined according to the characteristics of the target images, and the monitoring result of the heavy load rope is obtained. The embodiment of the application can realize the monitoring of the heavy-load rope through the monitoring video, thereby timely finding the fault of the heavy-load rope, ensuring the construction safety and reducing casualties and economic loss caused by the fault.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings used in the embodiments or the description of the prior art will be briefly described below.
FIG. 1 is a schematic flow chart illustrating steps of a method for monitoring a heavy haul rope according to an embodiment of the present disclosure;
FIG. 2 is a schematic flow chart illustrating steps of another method for monitoring a heavy haul rope according to an embodiment of the present disclosure;
FIG. 3 is a schematic view of a heavy duty rope monitoring apparatus according to an embodiment of the present application;
fig. 4 is a schematic diagram of a computer device according to an embodiment of the present application.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.
The heavy-load rope can be a steel wire rope and can be widely applied to departments such as mines, machinery, buildings, petroleum, coal, chemical industry, aquatic products, forestry, electronics, metallurgy, traffic, tourism, communication, aviation, shipping, buildings and the like as a main bearing component.
The inspection of the heavy-duty rope on the mine still stays in the traditional mode of completely depending on visual detection, and detection personnel have potential safety hazards in the mode and are easy to miss, misjudge and other inaccurate factors due to artificial factors. The safe operation of the cableway heavy-load rope is the basic guarantee of mine safety production, and once any small problem occurs, a large accident can be caused, so that a great burden is brought to the safety. Based on the method, the heavy-load rope monitoring method is used for automatically monitoring the heavy-load rope, so that potential safety hazards of the heavy-load rope can be found in time.
The technical solution of the present application will be described below by way of specific examples.
Referring to fig. 1, a schematic flow chart illustrating steps of a heavy load rope monitoring method provided in an embodiment of the present application is shown, which specifically includes the following steps:
s101, a video sequence to be processed is obtained from a monitoring video of the heavy-load rope, wherein the video sequence to be processed comprises a plurality of sample video frames.
The method provided by the embodiment of the application can be applied to computer devices such as a mobile phone, a tablet personal computer, a wearable device, a vehicle-mounted device, an Augmented Reality (AR)/Virtual Reality (VR) device, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a Personal Digital Assistant (PDA), a camera and the like, and the embodiment of the application does not limit the specific types of the computer devices at all. The computer device may be deployed with a heavy load rope monitoring device, and the heavy load rope monitoring device may be used to implement the monitoring method of the heavy load rope in this embodiment.
In a possible implementation manner, a camera device may be installed in a working environment of the heavy load rope, the camera device may communicate with a computer device, and the computer device may acquire a monitoring video of the camera device every preset time. In addition, some positions exist in the heavy load rope and are difficult to install the camera device, and to these positions, can control unmanned aerial vehicle by the computer equipment at every preset time and patrol and examine to gather corresponding surveillance video through unmanned aerial vehicle.
The monitoring video can be acquired once every preset time, which is equivalent to acquiring the monitoring video within the preset time, so that fault judgment is performed on the heavy-load rope within the preset time based on the monitoring video. The monitoring video comprises a plurality of video frames, but the video frames may cause the image to be unclear due to other reasons such as light or dust. Obviously, the fault of the heavy-load rope can be judged better by a clear image, so that a clearer video frame can be selected from a plurality of video frames to serve as a sample video frame. Specifically, edge dispersion values of a plurality of video frames of the monitoring video can be respectively determined, and the edge dispersion values are used for describing the definition of the video frames; and then taking the video frame with the edge dispersion value higher than the preset threshold value as a sample video frame.
In one possible implementation, the method of determining the sharpness of a video frame may be as follows: the image of the video frame can be converted into a gray image, and then the gray value of each pixel point in the image is obtained. Selecting a plurality of proper convolution kernels according to the image size of the video frame, performing convolution calculation on the video frame respectively, and obtaining the edge pixel value of each pixel point of the video frame corresponding to each convolution kernel respectively; according to the edge pixel value of each pixel point, the edge dispersion value of the dispersion circle corresponding to each convolution kernel can be determined; and taking the edge dispersion value of each pixel point in the video frame as the edge dispersion value of the video frame image. When the edge dispersion value of the video frame is lower, it is indicated that all the pixel points in the video frame converge, that is, the video frame may be unclear due to reasons such as fogging. Therefore, a video frame whose edge dispersion value is higher than a preset threshold value can be taken as a sample video frame.
S102, cutting out a plurality of target images containing the reloading ropes from the sample video frames.
The picture of the heavy-duty rope in the surveillance video is generally a slender line. Therefore, there are many pictures in the video frame that are not related to the heavy load rope. To better determine the case of a reloading rope in a video frame, a target area containing the reloading rope can be cut out from the sample video frame. Because the picture of the heavy load rope in the monitoring video is generally a long and thin line, the target area can be a rectangular area, the length of the rectangular area can be the length of the video frame, and determining the target area is the height of the rectangular area.
In one possible implementation, a coordinate system may be established with the lower left corner of the video frame as the origin, the left line of the video frame as the Y-axis, and the lower line of the video frame as the X-axis. The rectangular region may include four edges, i.e., an upper edge, a lower edge, a left edge, a right edge, and a left edge and a right edge, where the left edge and the right edge are two edges of the video frame, and then determining the rectangular region is equivalent to determining the upper edge and the lower edge of the rectangular region. The upper edge line and the lower edge line are parallel to the X axis, and therefore, it is equivalent to determining the ordinate corresponding to the upper edge line and the lower edge line. And taking the ordinate corresponding to the upper sideline as a first ordinate, and taking the ordinate corresponding to the lower sideline as a second ordinate.
Because the camera device is fixed, the video picture shot by the camera device is also fixed, and then the position of the heavy-load rope in each video frame of the monitoring video is also relatively fixed. Therefore, a first ordinate of the target and a second ordinate of the target in the area where the heavy load rope is located can be determined, and then for each sample video frame, an image between a straight line corresponding to the first ordinate of the target and a straight line corresponding to the second ordinate of the target can be captured as a target image.
For each sample video frame, a target area where the heavy load rope is located can be determined respectively, the target area has corresponding coordinate information, and the coordinate information comprises a first ordinate and a second ordinate. And determining the target coordinate information of the heavy-load rope according to the coordinate information of the plurality of target areas. Exemplarily, a minimum value in the first ordinate corresponding to the plurality of target regions may be taken as the first target ordinate; taking the maximum value in the second vertical coordinates corresponding to the plurality of target areas as a second target vertical coordinate; and taking the first target vertical coordinate and the second target vertical coordinate as target coordinate information. Based on this determined target area, all heavy load ropes may be included. Some deviation may exist in the position of the heavy haul rope in each sample video frame due to the possible deformation of the heavy haul rope, etc. The smallest first vertical coordinate and the largest second vertical coordinate are selected as target coordinate information, so that the combination of target images cut from each sample video frame can be guaranteed to comprise a complete heavy-load rope.
After the target coordinate information is determined, the target image can be cut out from each video frame according to the target coordinate information. The target coordinate information comprises a first target ordinate and a second target ordinate, two straight lines parallel to the X axis can be determined from each sample video frame according to the first target ordinate and the second target ordinate, and an image between the two straight lines is a target image.
In another possible implementation manner, a worker can mark the position of the heavy-load rope in the monitoring video in advance, so that the target coordinate information is determined according to the marking result of the worker. And correspondingly acquiring each sample video frame, and intercepting a target image by adopting target coordinate information.
And S103, respectively extracting a plurality of characteristics of the target image by adopting a preset characteristic extraction network.
In a possible implementation manner, a plurality of preset heavy load rope images can be adopted to train the convolution network, so that a feature extraction network capable of extracting features of the heavy load rope images is obtained.
And respectively inputting each target image into the feature extraction network, and obtaining an output result of the feature extraction network, namely the feature of the target image.
S104, determining a monitoring result of the heavy-load rope according to the characteristics.
The features of the target image are used to reflect the features of the load line, and thus, the monitoring result of the load line may be determined based on a plurality of features.
In one possible implementation, each surveillance video corresponds to a partial area of the heavy load rope. For the partial region, a plurality of features may be determined according to the method in the embodiment of the present application, so that the monitoring result of the partial region is determined based on the plurality of features.
For each monitoring video, a corresponding monitoring result can be obtained, and based on each monitoring result, a monitoring report of the whole heavy-load rope can be generated, so that whether the heavy-load rope has a fault or not can be determined in time, the faulty heavy-load rope can be replaced in time, and the construction safety is guaranteed.
In this embodiment, can select clear sample video frame from the surveillance video to confirm the target image who contains the heavy load rope from sample video frame, through the characteristic of the heavy load rope of drawing out in the target image, can confirm the monitoring result of heavy load rope, can realize the automatic monitoring to the heavy load rope, avoided a large amount of manual labor in the monitoring process, avoid the error that the naked eye detected and brought simultaneously.
Referring to fig. 2, a schematic flow chart illustrating steps of another heavy haul rope monitoring method provided in the embodiment of the present application is shown, which specifically includes the following steps:
s201, acquiring a plurality of abnormal images of the heavy-load rope, wherein the heavy-load rope in each abnormal image is in an abnormal state.
The method provided by the embodiment of the application can be applied to computer devices such as a mobile phone, a tablet personal computer, a wearable device, a vehicle-mounted device, an Augmented Reality (AR)/Virtual Reality (VR) device, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a Personal Digital Assistant (PDA), a camera and the like, and the embodiment of the application does not limit the specific types of the computer devices at all. The computer device may be deployed with a heavy load rope monitoring device, and the heavy load rope monitoring device may be used to implement the monitoring method of the heavy load rope in this embodiment.
Specifically, a plurality of images of a heavy load rope with a fault may be acquired, for each image, a target image including the heavy load rope may be determined according to the method in the previous embodiment, and the target image is used as an abnormal image. Each abnormal image may have a corresponding failure, and the failures corresponding to the plurality of abnormal images may be different from each other. For example, heavy duty ropes may suffer from a variety of failures including section breakage, corrosion breakage, strain breakage, abrasion breakage, loosening breakage, and load breakage. The fracture surface is in a shear shape, and the forced fracture is caused by excessive resistance on a certain bending part of the heavy load rope. The corrosion fracture is the broken wire caused by the over-corrosion of the heavy-load rope, and the broken wire is in a needle point state and has an irregular shape. The phenomenon that the internal structure of a steel wire is easily damaged, namely the metal fatigue phenomenon, occurs to a heavy-duty rope in the long-term use process, in a common situation, when the heavy-duty rope winds a winding drum or a pulley, the steel wire rope bears the fatigue load through bending in each working cycle, and the outer layer of the steel wire on the side with the most serious bending degree is easy to cause fatigue wire breakage. The abrasion breakage means that the strands are mutually twisted when viewed from the inside of the heavy-duty rope, and the strands are mutually staggered to generate tiny displacement when the axial force is applied, namely, internal fretting wear. Kink fracture means that the fracture is smooth and flat. The load fracture refers to the dispersion of the broken wire parts of the heavy-load rope, and is caused by huge external force compression and overweight load. The appearance of the heavy-duty rope corresponding to each different fault is different, so that the corresponding abnormal image is also different.
S202, respectively extracting the abnormal features of the abnormal images, wherein the abnormal features are used for describing corresponding faults of the heavy-duty rope.
The same feature extraction network as in the previous embodiment may be used to extract the abnormal features of the abnormal images, and since each abnormal image may have a corresponding fault, the extracted abnormal features may be used to reflect the fault of the heavy load rope.
S203, a video sequence to be processed is obtained from the monitoring video of the heavy-load rope, and the video sequence to be processed comprises a plurality of sample video frames.
S204, cutting out a plurality of target images containing the heavy loading ropes from the sample video frames.
And S205, respectively extracting a plurality of features of the target image by adopting a preset feature extraction network.
S203-S205 in the present embodiment are similar to S101-S103 in the previous embodiment, and may refer to each other, which is not described herein again.
S206, respectively calculating the feature similarity of the plurality of features and the plurality of abnormal features.
Illustratively, the extracted features may be vectors, and feature similarity between the features and the abnormal features may be represented by cosine values of the vectors.
For each feature, its feature similarity to any abnormal feature can be calculated separately. Since the abnormal features can characterize the fault features of the heavy-duty rope, whether the fault corresponding to the abnormal features exists in the heavy-duty rope can be determined based on the feature similarity.
S207, if any feature similarity is larger than a preset threshold value, the heavy-load rope is determined to be in a fault state.
A preset threshold value may be preset, and if the feature similarity between the features of the target image and the abnormal features is greater than the preset threshold value, it may be indicated that the features of the target image are similar to the abnormal features, and the heavy load rope may have a fault represented by the corresponding abnormal features. Specifically, a target abnormal feature corresponding to the feature similarity greater than a preset threshold may be determined; and then generating fault prompt information of the heavy-load rope according to the fault of the heavy-load rope corresponding to the target abnormal characteristic so as to prompt a worker to replace the heavy-load rope at the corresponding position in time.
In one possible implementation, different faults correspond to different solutions as each anomalous feature has a corresponding fault. Therefore, the computer equipment can generate a corresponding solution according to the fault corresponding to the target abnormal characteristic and remind the staff to process the fault in time.
The computer device may store the position of the reloading rope corresponding to each surveillance video. When the fault of the heavy-load rope is determined based on the monitoring video, the computer equipment can determine the position of the heavy-load rope with the fault based on the monitoring video, so that the fault can be timely eliminated, and the construction safety is guaranteed.
According to the embodiment of the application, the abnormal features can be extracted based on the image of the heavy load rope in the fault state, whether the heavy load rope has faults or not is determined based on the similarity between the image features of the heavy load rope in the monitoring video and the abnormal features, so that the monitoring on the heavy load rope can be realized, the faults of the heavy load rope can be found in time, and the construction safety is improved.
It should be noted that, the sequence numbers of the steps in the foregoing embodiments do not mean the execution sequence, and the execution sequence of each process should be determined by the function and the inherent logic of the process, and should not constitute any limitation to the implementation process of the embodiments of the present application.
Referring to fig. 3, a schematic diagram of a heavy load rope monitoring device provided in the embodiment of the present application is shown, and specifically, the heavy load rope monitoring device may include an obtaining module 31, a cutting module 32, an extracting module 33, and a determining module 34, where:
the acquiring module 31 is configured to acquire a to-be-processed video sequence from a surveillance video of a heavy-load rope, where the to-be-processed video sequence includes a plurality of sample video frames;
a cropping module 32 for cropping a plurality of target images containing the heavy loading ropes from a plurality of sample video frames;
an extracting module 33, configured to respectively extract a plurality of features of the target image by using a preset feature extraction network;
a determining module 34, configured to determine a monitoring result of the heavy load rope according to a plurality of the characteristics.
In a possible implementation manner, the obtaining module 31 includes:
the monitoring video acquisition sub-module is used for acquiring a monitoring video within a preset time, wherein the monitoring video comprises a plurality of video frames;
an edge diffusion value determining submodule, configured to determine edge diffusion values of the plurality of video frames respectively, where the edge diffusion values are used to describe the degree of sharpness of the video frames;
and the sample video frame determining submodule is used for taking the video frame with the edge dispersion value higher than a preset threshold value as the sample video frame.
In a possible implementation manner, the clipping module 32 includes:
a target area determination submodule, configured to determine a plurality of target areas of the reload rope in the plurality of sample video frames, respectively, where the target areas have corresponding coordinate information;
the target coordinate information determining submodule is used for determining the target coordinate information of the heavy-load rope according to the coordinate information of the target areas;
and the cutting sub-module is used for cutting the target image from each video frame according to the target coordinate information.
In a possible implementation manner, the target area is a rectangular area, the coordinate information includes a first ordinate and a second ordinate, the second ordinate is greater than the first ordinate, the first ordinate is used to describe a lower limit position of the rectangular area, the second ordinate is used to describe an upper limit position of the rectangular area, and the target coordinate information determination submodule includes:
the first target longitudinal coordinate determination submodule is used for taking the minimum value in first longitudinal coordinates corresponding to the target areas as a first target longitudinal coordinate;
the second target longitudinal coordinate determination submodule is used for taking the maximum value in second longitudinal coordinates corresponding to the target areas as a second target longitudinal coordinate;
and the target coordinate information determining submodule is used for taking the first target vertical coordinate and the second target vertical coordinate as the target coordinate information.
In a possible implementation manner, the apparatus further includes:
the abnormal image acquisition module is used for acquiring a plurality of abnormal images of the heavy-load rope, and the heavy-load rope in each abnormal image is in an abnormal state;
and the abnormal feature extraction submodule is used for respectively extracting the abnormal features of the abnormal images, and the abnormal features are used for describing corresponding faults of the heavy-load rope.
In a possible implementation manner, the determining module 34 includes:
the calculation submodule is used for respectively calculating the feature similarity of the plurality of features and the plurality of abnormal features;
and the fault determining submodule is used for determining that the heavy-load rope is in a fault state if any one characteristic similarity is larger than a preset threshold.
In a possible implementation manner, the apparatus further includes:
the target abnormal feature determining module is used for determining a target abnormal feature corresponding to the feature similarity which is greater than a preset threshold;
and the prompt information generating module is used for generating fault prompt information of the heavy load rope according to the fault of the heavy load rope corresponding to the target abnormal characteristic.
For the apparatus embodiment, since it is substantially similar to the method embodiment, it is described relatively simply, and reference may be made to the description of the method embodiment section for relevant points.
Fig. 4 is a schematic structural diagram of a computer device according to an embodiment of the present application. As shown in fig. 4, the computer device 4 of this embodiment includes: at least one processor 40 (only one shown in fig. 4), a memory 41, and a computer program 42 stored in the memory 41 and executable on the at least one processor 40, the processor 40 implementing the steps in any of the various method embodiments described above when executing the computer program 42.
The computer device 4 may be a desktop computer, a notebook, a palm computer, a cloud computer device, or other computing devices. The computer device may include, but is not limited to, a processor 40, a memory 41. Those skilled in the art will appreciate that fig. 4 is merely an example of the computer device 4 and does not constitute a limitation of the computer device 4, and may include more or less components than those shown, or combine certain components, or different components, such as input output devices, network access devices, etc.
The Processor 40 may be a Central Processing Unit (CPU), and the Processor 40 may be other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware components, and the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 41 may in some embodiments be an internal storage unit of the computer device 4, such as a hard disk or a memory of the computer device 4. The memory 41 may also be an external storage device of the computer device 4 in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the computer device 4. Further, the memory 41 may also include both an internal storage unit and an external storage device of the computer device 4. The memory 41 is used for storing an operating system, an application program, a BootLoader (BootLoader), data, and other programs, such as program codes of the computer programs. The memory 41 may also be used to temporarily store data that has been output or is to be output.
The embodiments of the present application further provide a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the computer program implements the steps in the above-mentioned method embodiments.
The embodiments of the present application provide a computer program product, which when executed on a computer device, enables the computer device to implement the steps in the above method embodiments.
The above-mentioned embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same. Although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.
Claims (10)
1. A heavy haul rope monitoring method, comprising:
acquiring a video sequence to be processed from a monitoring video of a heavy-load rope, wherein the video sequence to be processed comprises a plurality of sample video frames;
cutting out a plurality of target images containing the heavy loading ropes from a plurality of sample video frames;
respectively extracting a plurality of characteristics of the target image by adopting a preset characteristic extraction network;
and determining a monitoring result of the heavy-load rope according to a plurality of characteristics.
2. The method of claim 1, wherein said obtaining a video sequence to be processed from surveillance video of a reloading rope comprises:
acquiring a monitoring video within a preset time, wherein the monitoring video comprises a plurality of video frames;
respectively determining edge diffusion values of a plurality of video frames, wherein the edge diffusion values are used for describing the definition of the video frames;
and taking the video frame with the edge dispersion value higher than a preset threshold value as the sample video frame.
3. The method of claim 1, wherein said cropping a plurality of target images containing said heavy load line from a plurality of said sample video frames comprises:
respectively determining a plurality of target areas of the heavy loading ropes in a plurality of sample video frames, wherein the target areas have corresponding coordinate information;
determining target coordinate information of the heavy-load rope according to the coordinate information of the target areas;
and cutting out the target image from each video frame according to the target coordinate information.
4. The method of claim 3, wherein the target area is a rectangular area, the coordinate information includes a first ordinate and a second ordinate, the second ordinate is larger than the first ordinate, the first ordinate is used to describe a lower limit position of the rectangular area, the second ordinate is used to describe an upper limit position of the rectangular area, and the determining the target coordinate information of the heavy load rope according to the coordinate information of the plurality of target areas includes:
taking the minimum value in the first vertical coordinates corresponding to the target areas as a first target vertical coordinate;
taking the maximum value in second vertical coordinates corresponding to the target areas as a second target vertical coordinate;
and taking the first target vertical coordinate and the second target vertical coordinate as the target coordinate information.
5. The method of any one of claims 1-4, further comprising:
acquiring a plurality of abnormal images of the heavy-load rope, wherein the heavy-load rope in each abnormal image is in an abnormal state;
and respectively extracting the abnormal features of the abnormal images, wherein the abnormal features are used for describing corresponding faults of the heavy-load rope.
6. The method of claim 5, wherein said determining a monitoring result of said heavy haul line based on a plurality of said characteristics comprises:
respectively calculating feature similarity of a plurality of features and a plurality of abnormal features;
and if any one characteristic similarity is larger than a preset threshold value, determining that the heavy-load rope is in a fault state.
7. The method of claim 6, wherein the method further comprises:
determining a target abnormal feature corresponding to the feature similarity larger than a preset threshold;
and generating fault prompt information of the heavy-load rope according to the fault of the heavy-load rope corresponding to the target abnormal characteristic.
8. A heavy duty rope monitoring device, comprising:
the device comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring a video sequence to be processed from a monitoring video of a heavy-load rope, and the video sequence to be processed comprises a plurality of sample video frames;
a cutting module for cutting a plurality of target images containing the heavy loading ropes from a plurality of sample video frames;
the extraction module is used for respectively extracting a plurality of characteristics of the target image by adopting a preset characteristic extraction network;
and the determining module is used for determining the monitoring result of the heavy-load rope according to a plurality of characteristics.
9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the method according to any of claims 1-7 when executing the computer program.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211627020.2A CN115797316A (en) | 2022-12-16 | 2022-12-16 | Heavy load rope monitoring method and device, computer equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211627020.2A CN115797316A (en) | 2022-12-16 | 2022-12-16 | Heavy load rope monitoring method and device, computer equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115797316A true CN115797316A (en) | 2023-03-14 |
Family
ID=85425542
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211627020.2A Pending CN115797316A (en) | 2022-12-16 | 2022-12-16 | Heavy load rope monitoring method and device, computer equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115797316A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117079218A (en) * | 2023-09-20 | 2023-11-17 | 山东省地质矿产勘查开发局第一地质大队（山东省第一地质矿产勘查院） | Dynamic monitoring method for rope position of passenger ropeway rope based on video monitoring |
-
2022
- 2022-12-16 CN CN202211627020.2A patent/CN115797316A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117079218A (en) * | 2023-09-20 | 2023-11-17 | 山东省地质矿产勘查开发局第一地质大队（山东省第一地质矿产勘查院） | Dynamic monitoring method for rope position of passenger ropeway rope based on video monitoring |
| CN117079218B (en) * | 2023-09-20 | 2024-03-08 | 山东省地质矿产勘查开发局第一地质大队（山东省第一地质矿产勘查院） | Dynamic monitoring method for rope position of passenger ropeway rope based on video monitoring |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9996762B2 (en) | Image processing method and image processing apparatus | |
| CN110781839A (en) | Sliding window-based small and medium target identification method in large-size image | |
| CN111507147A (en) | Intelligent inspection method and device, computer equipment and storage medium | |
| CN113283344A (en) | Mining conveying belt deviation detection method based on semantic segmentation network | |
| CN115797316A (en) | Heavy load rope monitoring method and device, computer equipment and medium | |
| CN111784681A (en) | Steel wire rope disorder detection method and device, computer equipment and storage medium | |
| CN110942455A (en) | Method and device for detecting missing of cotter pin of power transmission line and computer equipment | |
| KR102219809B1 (en) | Safety Work Management System by Image Analysis | |
| CN113361420A (en) | Mine fire monitoring method, device and equipment based on robot and storage medium | |
| CN116310903A (en) | Method and device for identifying fault type of photovoltaic module and electronic equipment | |
| CN116309303A (en) | Electrical equipment defect detection method and device based on infrared image and related equipment | |
| US20200388017A1 (en) | System, apparatus and method for facilitating inspection of a target object | |
| CN106706238B (en) | Steel cable core conveying belt joint overlap joint label and recognition methods | |
| US20230048649A1 (en) | Method of processing image, electronic device, and medium | |
| JP6941993B2 (en) | Work monitoring system and work monitoring method | |
| CN114091699A (en) | Power communication equipment fault diagnosis method and system | |
| CN113989286A (en) | Deep learning method, device, equipment and storage medium for belt tearing strength | |
| CN113962955A (en) | Method and device for identifying target object from image and electronic equipment | |
| CN113780178A (en) | Road detection method, road detection device, electronic equipment and storage medium | |
| CN113204455A (en) | Method, equipment and storage medium for automatically detecting user interface display abnormity | |
| KR20210067062A (en) | Vessel maintenance support method by vessel maintenance support system including mobile device and maintenance support server | |
| CN116403165B (en) | Dangerous chemical leakage emergency treatment method, dangerous chemical leakage emergency treatment device and readable storage medium | |
| CN219916365U (en) | Inspection maintenance system of oil depot equipment | |
| CN115810002A (en) | Cableway abnormity monitoring method and device, computer equipment and medium | |
| CN116128967A (en) | Risk identification method, risk identification device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |