CN115239670A - Method and device for detecting supporting leg base plate - Google Patents
Method and device for detecting supporting leg base plate Download PDFInfo
- Publication number
- CN115239670A CN115239670A CN202210901772.7A CN202210901772A CN115239670A CN 115239670 A CN115239670 A CN 115239670A CN 202210901772 A CN202210901772 A CN 202210901772A CN 115239670 A CN115239670 A CN 115239670A
- Authority
- CN
- China
- Prior art keywords
- image
- detected
- base plate
- supporting leg
- detection result
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the field of image recognition, and provides a method and a device for detecting a supporting leg base plate, wherein the method comprises the following steps: acquiring an image to be detected in a supporting point area of a supporting leg; analyzing the image to be detected and outputting a detection result of the support leg base plate of the image to be detected; and receiving the detection result, and determining whether to send out a prompt signal based on the detection result. The support leg detection method and the support leg detection device can detect the support leg of the concrete pump truck by using an image identification method through the computing device, can accurately identify whether the support leg base plate exists or not, and can prompt in time according to a detection result.
Description
Technical Field
The invention relates to the technical field of image recognition, in particular to a method and a device for detecting a supporting leg base plate.
Background
The concrete pump truck supporting legs have the functions of ensuring that the concrete pump truck has sufficient safety and stability in the working process and preventing the whole concrete pump truck from tipping. However, in actual work progress, on the one hand, because workman's safety consciousness is not enough, do not use the landing leg backing plate, it is firm inadequately when pump truck landing leg supports ground, need not the backing plate will increase the risk that the pump truck emptys. For the detection of whether the support leg has a base plate, no relevant method is proposed in the industry at present.
Therefore, how to detect the outriggers of the concrete pump truck in an image recognition mode is a technical problem which needs to be solved urgently at present.
Disclosure of Invention
The invention provides a method and a device for detecting a support leg base plate, which are used for solving the defect that the support leg of a concrete pump truck is not detected in the prior art and realizing the support leg detection of the concrete pump truck in an image recognition mode.
The invention provides a method for detecting a supporting leg base plate, which comprises the following steps:
acquiring an image to be detected in a supporting point area of a supporting leg;
analyzing the image to be detected and outputting a detection result of the support leg base plate of the image to be detected;
and receiving the detection result, and determining whether to send out a prompt signal based on the detection result.
The invention provides a method for detecting a support leg base plate, which determines whether to send out a prompt signal or not based on a detection result, and comprises the following steps:
if the detection results are abnormal within the continuous preset time, the controller controls the alarm to send out a prompt signal.
The invention provides a method for detecting a supporting leg base plate, which is used for analyzing an image to be detected and outputting a detection result of the supporting leg base plate of the image to be detected and comprises the following steps:
inputting the image to be detected into computing equipment for decoding, inputting the decoded image data into a supporting leg state detection model, detecting whether a supporting leg base plate exists in the image to be detected, and outputting the detection result of the image to be detected.
The invention provides a method for detecting a supporting leg base plate, which is used for detecting whether the supporting leg base plate exists in an image to be detected and outputting a detection result of the image to be detected and comprises the following steps:
and under the condition that the support leg base plate does not exist in the image to be detected, outputting a first detection result of the image to be detected.
The invention provides a method for detecting a supporting leg base plate, which is used for detecting whether the supporting leg base plate exists in an image to be detected and outputting a detection result of the image to be detected and comprises the following steps:
under the condition that a supporting leg base plate exists in the image to be detected, judging whether the coordinates of the supporting leg base plate in the image to be detected are located in a preset region of interest or not;
and if the coordinates are located in the preset region of interest, outputting a second detection result of the image to be detected.
The invention provides a method for detecting a supporting leg base plate, which is used for detecting whether the supporting leg base plate exists in an image to be detected and outputting a detection result of the image to be detected and comprises the following steps:
under the condition that a supporting leg base plate exists in the image to be detected, judging whether the coordinates of the supporting leg base plate in the image to be detected are located in a preset region of interest or not;
and if the coordinates are not located in the preset region of interest, outputting a third detection result of the image to be detected.
According to the method for detecting the supporting leg base plate, the supporting leg state detection model comprises a day detection model and a night detection model;
inputting the image to be detected into a computing device for decoding, inputting the decoded image data into a supporting leg state detection model, detecting whether a supporting leg base plate exists in the image to be detected, and including:
inputting the image to be detected into computing equipment for decoding, and selecting a target model from a daytime detection model and a night detection model for the decoded data based on the acquisition time of the image to be detected;
inputting the decoded image data into the target model, and detecting whether a supporting leg base plate exists in the image to be detected.
According to the method for detecting the support leg base plate, the training process of the support leg state detection model comprises the following steps:
acquiring an image sample of a support leg base plate, and dividing the image sample into a day sample and a night sample;
labeling the daytime samples as a first training set and a first testing set, and labeling the nighttime samples as a second training set and a second testing set;
and establishing a day detection model and a night detection model, inputting the day sample into the day detection model and inputting the night sample into the night detection model for iterative training, and repeatedly adjusting the parameters of the day detection model and the night detection model until the models converge.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the steps of the leg base plate detection method.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when being executed by a processor, carries out the steps of the leg rest detection method according to any one of the above-mentioned claims.
The invention also provides a leg base plate detection device, which comprises:
the acquisition module is used for acquiring an image to be detected in a supporting point area of the supporting leg;
the detection module is used for analyzing the image to be detected and outputting a detection result of the support leg base plate of the image to be detected;
and the prompting module is used for receiving the detection result and determining whether to send out a prompting signal or not based on the detection result.
The present invention also provides a work machine comprising: the leg plate detection device is described above.
According to the working machine provided by the invention, the image acquisition equipment for acquiring the image to be detected is arranged at the tail end of the supporting leg of the working machine or on the side surface of the working machine.
According to the method and the device for detecting the supporting leg base plate, the image to be detected in the supporting leg supporting point area is obtained, the image to be detected is analyzed, the detection result of the supporting leg base plate of the image to be detected is output, then the detection result is received, and whether a prompt signal is sent or not is determined based on the detection result. The support leg detection method and the support leg detection device can detect the support leg of the concrete pump truck by using an image identification method through the computing device, can accurately identify whether the support leg base plate exists or not, and can prompt in time according to a detection result.
Drawings
In order to more clearly illustrate the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a schematic flow chart of a method for inspecting a leg plate according to the present invention;
FIG. 2 is a schematic diagram of rectangular coordinates of an image to be detected by the method for detecting the support leg base plate provided by the invention;
FIG. 3 is a second schematic flow chart of the method for detecting a leg plate according to the present invention;
FIG. 4 is a schematic view of an image capturing device for the leg plate inspection method of the present invention;
FIG. 5 is a third schematic flow chart of the method for inspecting a leg plate according to the present invention;
FIG. 6 is a schematic structural diagram of a leg plate detection device provided by the present invention;
FIG. 7 is a second schematic structural view of a leg plate detection device provided in the present invention;
fig. 8 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The leg mat detection method and apparatus of the present invention will be described with reference to fig. 1 to 8.
Referring to fig. 1, the method for detecting the support leg base plate provided by the invention comprises the following steps:
specifically, the present embodiment obtains an image through an image capturing device, which may be an image capturing device such as a camera or a video camera. It should be noted that the resolution of the image acquired by the image acquisition device should be no lower than 1080P. The image to be detected in the embodiment is an image of a supporting point of a supporting leg of the pump truck, which is acquired by the image acquisition equipment in real time, and the acquisition time can be determined according to specific conditions.
specifically, the analysis of the image to be detected is performed on the basis of a computing device, i.e. an AI computing device, which is provided with a trained AI detection model, i.e. a leg state detection model. The model detects and identifies the input image to be detected, so as to obtain the detection result and obtain whether the landing leg base plate exists in the image to be detected.
The supporting leg state detection model is a detection model which is trained by inputting a large number of image samples of supporting leg base plates into the model for training, generating identification labels of the image samples and adjusting model parameters through multiple times of iterative training.
And step 130, receiving the detection result, and determining whether to send out a prompt signal based on the detection result.
Specifically, the controller in this embodiment receives a detection result of the computing device and responds to the detection result. When the detection result is abnormal, prompting the user through an alarm; and when the detection result is normal, the equipment keeps a normal running state and does not send prompt information.
The method for detecting the supporting leg base plate comprises the steps of obtaining an image to be detected in a supporting point area of a supporting leg, analyzing the image to be detected, outputting a detection result of the supporting leg base plate of the image to be detected, receiving the detection result, and determining whether to send a prompt signal or not based on the detection result. The support leg detection method and the support leg detection device can detect the support leg of the concrete pump truck by using an image identification method through the computing device, can accurately identify whether the support leg base plate exists or not, and can prompt in time according to a detection result.
Based on the above embodiment, the determining whether to send out a prompt signal based on the detection result includes:
if the detection results are abnormal within the continuous preset time, the controller controls the alarm to send out a prompt signal.
Specifically, in this embodiment, the computing device transmits the detected state of the leg back to the pumping truck controller in real time through the CAN bus or the network cable, and the frequency of the returned information is not less than 1HZ, that is, the returned information is transmitted at least once per second. And if the received state information of the support leg base plate in the continuous 3S is abnormal, the controller triggers the acousto-optic alarm and displays a prompt signal on a remote control center control screen of the pump truck to remind an operator of the pump truck.
According to the embodiment, the detection result is judged according to the set continuous time, so that the prompt signal is sent out under the condition of meeting the continuous preset time, the prompt signal is more accurate, and the condition of misjudgment on the detection result is effectively avoided.
Based on above embodiment, the analysis wait to detect the image, the detection result of the landing leg backing plate of waiting to detect the image is exported, include:
inputting the image to be detected into computing equipment for decoding, inputting the decoded image data into a supporting leg state detection model, detecting whether a supporting leg base plate exists in the image to be detected, and outputting the detection result of the image to be detected.
1. And outputting a first detection result of the image to be detected under the condition that the support leg base plate does not exist in the image to be detected.
And under the condition that a supporting leg base plate exists in the image to be detected, judging whether the coordinates of the supporting leg base plate in the image to be detected are positioned in a preset region of interest.
2. And if the coordinates are located in a preset region of interest, outputting a second detection result of the image to be detected.
3. And if the coordinates are not located in the preset region of interest, outputting a third detection result of the image to be detected.
Specifically, the embodiment decodes an input image to be detected through the computing device, and then transmits the decoded data into the leg state detection model for detection. If a leg pad is detected, the model outputs rectangular coordinates of the leg pad in the image.
Referring to fig. 2, the rectangular coordinates of the pad are determined by four vertices (x 1, y 1), (x 2, y 2), (x 3, y 3), and (x 4, y 4) of the rectangle. And when the support leg base plate is detected and the coordinate of the base plate is within the range of the preset value of the system, the support leg base plate is determined to be normal at the current moment, namely the support leg base plate is the second detection result. The region of interest is ROI information preset by the system, and is used for eliminating false detection caused by the existence of similar base plates in other regions in the image. And when the support leg base plate is not detected or the coordinate of the base plate is not in the range of the preset value of the system, determining that the support leg base plate is abnormal, namely a first detection result or a third detection result. Wherein the leg backing plate abnormal conditions include: no leg mat or mat sinking into the earth.
In the embodiment, the ROI information is set in the computing equipment in advance, and the detection result of the image to be detected is compared with the set ROI information, so that the normal or abnormal condition of the support leg base plate can be obtained to give an alarm in time.
Based on the above embodiment, the leg state detection model comprises a day detection model and a night detection model;
inputting the image to be detected into a computing device for decoding, inputting the decoded image data into a supporting leg state detection model, detecting whether a supporting leg base plate exists in the image to be detected, and including:
inputting the image to be detected into computing equipment for decoding, and selecting a target model from a daytime detection model and a night detection model for the decoded data based on the acquisition time of the image to be detected;
and inputting the decoded image data into the target model, and detecting whether a support leg base plate exists in the image to be detected.
Specifically, the leg state detection model in this embodiment includes two models: the daytime detection model and the night detection model are respectively used for detecting images acquired by the image acquisition equipment at different times of the daytime and the night.
According to the embodiment, an appropriate model is selected as the target model to be detected according to the acquisition time of the image to be detected, so that the detection of the supporting leg base plate of the image to be detected is more efficient.
Based on the above embodiment, the training process of the leg state detection model includes:
acquiring an image sample of a support leg base plate, and dividing the image sample into a day sample and a night sample;
labeling the daytime samples as a first training set and a first testing set, and labeling the nighttime samples as a second training set and a second testing set;
and establishing a day detection model and a night detection model, inputting the day sample into the day detection model and inputting the night sample into the night detection model for iterative training, and repeatedly adjusting the parameters of the day detection model and the night detection model until the models converge.
The embodiment is a training process of a leg state detection model, namely a process of obtaining the model. Firstly, image acquisition equipment is pre-installed on pump trucks of different models and used for acquiring image data of the supporting leg pads. The pump truck data return capacity is utilized, a certain amount of landing leg base plate image data in different shapes, colors and different construction sites are collected, and the collected landing leg base plate image data are used as image samples.
The collected image samples are classified because the images shot by the image samples in the day and at night are greatly different, one group of image data under the scene of the day is the day sample, and the other group of image data under the scene of the night is the night sample.
The day-of-the-day samples and night-time samples are then labeled using a labeling tool (such as LabelImg), with each set of labeled data divided into a training set and a test set.
And finally, training two different leg base plate detection models, namely a daytime detection model and a night detection model, respectively based on training set data of daytime and night scenes through a deep learning Faster-RCNN algorithm. And testing the recall rate and the accuracy rate of the model on the corresponding test set, and if the recall rate and the accuracy rate simultaneously meet certain requirements, determining that the detection model is trained. And if the test result does not meet the requirements, adjusting the algorithm parameters and then training.
Referring to fig. 3, the training method of the leg base plate detection model specifically includes the following steps:
Based on the above embodiment, before the image to be detected of the supporting point region of the supporting leg is obtained, the method further includes:
and the image acquisition equipment is arranged at the tail end of a supporting leg of the pump truck or the side surface of the pump truck, and the focal length of a lens of the image acquisition equipment is adjusted.
Referring to fig. 4, the image capturing device 410 in this embodiment may be installed below the end of the leg 420, or may be installed on the side of the pump truck near the source end of the leg, so as to facilitate real-time monitoring and capturing of an image of the leg region. After the image acquisition equipment is installed, the focal length of the lens is adjusted properly, and the fact that the acquired video image covers the supporting leg base plate area is guaranteed.
Based on the above embodiment, the acquiring an image to be detected of the supporting point region of the supporting leg includes:
under the condition that the acquisition time of the image to be detected is daytime, acquiring the image to be detected in the daytime in the supporting point area of the supporting leg of the pump truck through image acquisition equipment;
wait to examine under the condition that the acquisition time of examining the image is night, combine the light filling effect of light filling lamp night through image acquisition equipment, wait to examine the image of examining night that obtains the pump truck landing leg strong point region.
Specifically, the present embodiment performs image acquisition in different ways through an image acquisition device for the acquisition time of an image to be detected. Sufficient light during the daytime, directly lead to image acquisition equipment alright acquire the higher image of definition, and light is more weak during night, needs carry out the collection of image under the light filling effect of light filling lamp at night to combine the light filling lamp to acquire the higher image of definition.
The following describes the leg pad detecting device provided by the present invention, and the leg pad detecting device described below and the leg pad detecting method described above can be referred to correspondingly.
Referring to fig. 5, the flow of the complete embodiment of the leg pad detection method provided by the present invention is as follows:
Referring to fig. 6, the leg pad detecting apparatus provided by the present invention includes:
the acquisition module 610 is used for acquiring an image to be detected of a supporting point area of the supporting leg;
the detection module 620 is used for analyzing the image to be detected and outputting a detection result of the supporting leg base plate of the image to be detected;
and a prompt module 630, configured to receive the detection result, and determine whether to send a prompt signal based on the detection result.
Based on the above embodiment, the training process of the leg state detection model includes:
the device comprises a sample acquisition module, a support leg base plate and a support leg base plate, wherein the sample acquisition module is used for acquiring an image sample of the support leg base plate and dividing the image sample into a daytime sample and a night sample;
the marking module is used for marking the daytime samples as a first training set and a first testing set and marking the nighttime samples as a second training set and a second testing set;
and the training module is used for establishing a day detection model and a night detection model, inputting the day sample into the day detection model and inputting the night sample into the night detection model for iterative training, and repeatedly adjusting the parameters of the day detection model and the night detection model until the models converge.
Based on the above embodiment, the detection module is specifically configured to:
inputting the image to be detected into computing equipment for decoding, inputting the decoded image data into a supporting leg state detection model, detecting whether a supporting leg base plate exists in the image to be detected, and outputting a detection result of the image to be detected;
under the condition that the support leg base plate does not exist in the image to be detected, outputting a first detection result of the image to be detected;
under the condition that a supporting leg base plate exists in the image to be detected, judging whether the coordinates of the supporting leg base plate in the image to be detected are located in a preset region of interest or not;
if the coordinates are located in a preset region of interest, outputting a second detection result of the image to be detected;
and if the coordinates are not located in the preset region of interest, outputting a third detection result of the image to be detected.
Based on the above embodiment, the leg state detection model comprises a day detection model and a night detection model; the detection module is specifically configured to:
inputting the image to be detected into computing equipment for decoding, and selecting a target model from a daytime detection model and a night detection model for the decoded data based on the acquisition time of the image to be detected;
and inputting the decoded image data into the target model, and detecting whether a support leg base plate exists in the image to be detected.
Based on the above embodiment, the acquisition module is specifically configured to:
under the condition that the acquisition time of the image to be detected is daytime, acquiring the image to be detected in the daytime in the supporting point area of the supporting leg of the pump truck through image acquisition equipment;
wait to examine under the condition that the acquisition time of examining the image is night, combine the light filling effect of light filling lamp night through image acquisition equipment, wait to examine the image of examining night that obtains the pump truck landing leg strong point region.
Referring to fig. 7, the leg mat detection apparatus provided by the present invention includes:
an image capture device 710, an AI computing device 720, a controller 730, and an audible and visual alarm 740. The image acquisition device 710 corresponds to the acquisition module of fig. 6, the AI calculation device corresponds to the detection module of fig. 6, and the controller 730 and the acousto-optic alarm 740 correspond to the prompt module of fig. 6.
The present invention also provides a work machine comprising: the leg mat detection device is described above.
Here, the working machine may be a working machine such as a crane, an excavator, a pile machine, or a working vehicle such as a climbing truck, a fire truck, a mixer truck.
Based on the above embodiment, the image pickup apparatus for acquiring an image to be detected is mounted at the end of the leg of the working machine or the side of the working machine.
Fig. 8 illustrates a physical structure diagram of an electronic device, which may include, as shown in fig. 8: a processor (processor) 810, a communication Interface 820, a memory 830 and a communication bus 840, wherein the processor 810, the communication Interface 820 and the memory 830 communicate with each other via the communication bus 840. The processor 810 may invoke logic instructions in the memory 830 to perform a leg pad detection method comprising:
acquiring an image to be detected in a supporting point area of a supporting leg;
analyzing the image to be detected and outputting a detection result of the support leg base plate of the image to be detected;
and receiving the detection result, and determining whether to send out a prompt signal based on the detection result.
In addition, the logic instructions in the memory 830 may be implemented in software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk, and various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, which when executed by a computer, enable the computer to perform the leg pad detection method provided by the above methods, the method comprising:
acquiring an image to be detected in a supporting point area of a supporting leg;
analyzing the image to be detected and outputting a detection result of the support leg base plate of the image to be detected;
and receiving the detection result, and determining whether to send out a prompt signal based on the detection result.
In still another aspect, the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, the computer program being implemented by a processor to perform the leg pad detection method provided in the above aspects, the method including:
acquiring an image to be detected in a supporting point area of a supporting leg;
analyzing the image to be detected and outputting a detection result of the support leg base plate of the image to be detected;
and receiving the detection result, and determining whether to send out a prompt signal based on the detection result.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment may be implemented by software plus a necessary general hardware platform, and may also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will 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; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (13)
1. A method for detecting a support leg base plate is characterized by comprising the following steps:
acquiring an image to be detected in a supporting point area of a supporting leg;
analyzing the image to be detected and outputting a detection result of the support leg base plate of the image to be detected;
and receiving the detection result, and determining whether to send out a prompt signal based on the detection result.
2. The method for detecting the leg base plate according to claim 1, wherein the determining whether to send out a prompt signal based on the detection result comprises:
if the detection results are abnormal within the continuous preset time, the controller controls the alarm to send out a prompt signal.
3. The method for detecting a leg plate according to claim 1, wherein the analyzing the image to be detected and outputting the detection result of the leg plate of the image to be detected comprises:
inputting the image to be detected into a computing device for decoding, inputting the decoded image data into a supporting leg state detection model, detecting whether a supporting leg base plate exists in the image to be detected, and outputting the detection result of the image to be detected.
4. The method for detecting the supporting leg base plate according to claim 3, wherein the detecting whether the supporting leg base plate exists in the image to be detected or not and outputting the detection result of the image to be detected comprises the following steps:
and under the condition that the support leg base plate does not exist in the image to be detected, outputting a first detection result of the image to be detected.
5. The method for detecting the supporting leg base plate according to claim 3, wherein the step of detecting whether the supporting leg base plate exists in the image to be detected and outputting a detection result of the image to be detected comprises the steps of:
under the condition that a supporting leg base plate exists in the image to be detected, judging whether the coordinates of the supporting leg base plate in the image to be detected are located in a preset region of interest or not;
and if the coordinates are located in a preset region of interest, outputting a second detection result of the image to be detected.
6. The method for detecting the supporting leg base plate according to claim 3, wherein the detecting whether the supporting leg base plate exists in the image to be detected or not and outputting the detection result of the image to be detected comprises the following steps:
under the condition that a supporting leg base plate exists in the image to be detected, judging whether the coordinates of the supporting leg base plate in the image to be detected are located in a preset region of interest;
and if the coordinates are not located in the preset region of interest, outputting a third detection result of the image to be detected.
7. The leg base plate detection method according to claim 3, wherein the leg state detection model includes a day detection model and a night detection model;
inputting the image to be detected into computing equipment for decoding, inputting the decoded image data into a supporting leg state detection model, and detecting whether a supporting leg base plate exists in the image to be detected, wherein the method comprises the following steps:
inputting the image to be detected into computing equipment for decoding, and selecting a target model from a daytime detection model and a night detection model for the decoded data based on the acquisition time of the image to be detected;
inputting the decoded image data into the target model, and detecting whether a supporting leg base plate exists in the image to be detected.
8. The leg mat detection method according to claim 3, wherein the training process of the leg state detection model comprises:
acquiring an image sample of a support leg base plate, and dividing the image sample into a day sample and a night sample;
labeling the daytime samples as a first training set and a first testing set, and labeling the nighttime samples as a second training set and a second testing set;
and establishing a day detection model and a night detection model, inputting the day sample into the day detection model and inputting the night sample into the night detection model for iterative training, and repeatedly adjusting the parameters of the day detection model and the night detection model until the models converge.
9. An electronic device comprising a memory, a processor and a computer program stored on said memory and executable on said processor, wherein said processor when executing said program performs the steps of the method of detecting a landing pad according to any of claims 1 to 8.
10. A non-transitory computer-readable storage medium, on which a computer program is stored, wherein the computer program, when being executed by a processor, implements the steps of the leg pad detection method according to any one of claims 1 to 8.
11. A leg pad detection device, comprising:
the acquisition module is used for acquiring an image to be detected in a supporting point area of the supporting leg;
the detection module is used for analyzing the image to be detected and outputting a detection result of the support leg base plate of the image to be detected;
and the prompting module is used for receiving the detection result and determining whether to send a prompting signal or not based on the detection result.
12. A work machine, comprising: the leg mat detecting device according to claim 11.
13. The work machine of claim 12, wherein the image capturing device for capturing the image to be detected is mounted at the end of a leg of the work machine or at the side of the work machine.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210901772.7A CN115239670A (en) | 2022-07-28 | 2022-07-28 | Method and device for detecting supporting leg base plate |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210901772.7A CN115239670A (en) | 2022-07-28 | 2022-07-28 | Method and device for detecting supporting leg base plate |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115239670A true CN115239670A (en) | 2022-10-25 |
Family
ID=83677858
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210901772.7A Pending CN115239670A (en) | 2022-07-28 | 2022-07-28 | Method and device for detecting supporting leg base plate |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115239670A (en) |
-
2022
- 2022-07-28 CN CN202210901772.7A patent/CN115239670A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105390021B (en) | The detection method and device of parking space state | |
| RU2380758C2 (en) | Method and device for smoke detection | |
| CN107561737B (en) | Method, device and tool for automatically adjusting IPC (International Process control) parameters of AOI (automatic Option identification) system | |
| CN110231642B (en) | Method and device for constructing radiation field map and robot | |
| CN106373336A (en) | Fall detection method and device | |
| CN113554004B (en) | Detection method and detection system for material overflow of mixer truck, electronic equipment and mixing station | |
| CN115376000A (en) | Underwater measurement method, device and computer readable storage medium | |
| CN113470018A (en) | Hub defect identification method, electronic device, device and readable storage medium | |
| CN110392239B (en) | Designated area monitoring method and device | |
| JP2021060888A (en) | Inspection method of utility work and inspection system of utility work | |
| CN114419038A (en) | Method and device for identifying surface defects of hub, storage medium and electronic equipment | |
| CN115239670A (en) | Method and device for detecting supporting leg base plate | |
| JP2008041017A (en) | Monitoring system and monitoring device | |
| CN112070748A (en) | Metal oil pipe defect detection method and device | |
| CN116091503A (en) | Method, device, equipment and medium for discriminating panel foreign matter defects | |
| CN111709360B (en) | Safety rope wearing identification method and system | |
| CN115438945A (en) | Risk identification method, device, equipment and medium based on power equipment inspection | |
| CN117372321A (en) | Defect detection method, device, equipment and storage medium | |
| CN111504608B (en) | Brightness uniformity detection system and brightness uniformity detection method | |
| CN114283377A (en) | Escalator safety detection method, device, equipment and storage medium | |
| CN113449617A (en) | Track safety detection method, system, device and storage medium | |
| CN111649804A (en) | Oil level monitoring method and device with storage function | |
| CN116403165B (en) | Dangerous chemical leakage emergency treatment method, dangerous chemical leakage emergency treatment device and readable storage medium | |
| JP2001014571A (en) | Fire detector, fire detection system and fire detection method | |
| CN117115926B (en) | Human body action standard judging method and device based on real-time image processing |
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 |