Disclosure of Invention
The application provides a dangerous area personnel identification early warning system and method based on machine vision to solve the technical problems that the intellectualization level is low and the safety of workers cannot be guaranteed in the related technology at least.
The embodiment of the first aspect of this application provides a dangerous area personnel discernment early warning system based on machine vision, dangerous area personnel discernment early warning system includes: the system comprises a camera, an industrial personal computer and a display screen;
the camera is used for collecting picture information of a tunneling working face and sending the picture information to the industrial personal computer;
the industrial personal computer is used for preprocessing the picture information, identifying workers in the tunneling working face based on the preprocessed picture information, tracking and prejudging the running track of the workers at the same time to obtain prejudgment information corresponding to the running track of the workers, and then carrying out early warning based on the prejudgment information;
and the display screen is used for displaying the running track prejudgment information of the working personnel.
The embodiment of the second aspect of the application provides a dangerous area person identification and early warning method based on machine vision, and the method comprises the following steps:
collecting picture information of a driving face;
preprocessing the picture information, and identifying workers in the tunneling working face based on the preprocessed picture information;
tracking the running track of a worker and prejudging to obtain running track prejudging information of the worker;
and early warning the operation track of the worker based on the prejudgment information.
An embodiment of a third aspect of the present application provides an electronic device, including: a memory, a processor and a computer program stored on the memory and executable on the processor, when executing the program, implementing the method as described in the second aspect above.
A computer-readable storage medium is proposed in an embodiment of the fourth aspect of the present application, on which a computer program is stored, which, when executed by a processor, implements the method as described in the second aspect above.
The technical scheme provided by the embodiment of the application at least has the following beneficial effects:
the application provides a dangerous area personnel discernment early warning system and method based on machine vision, wherein, dangerous area personnel discernment early warning system includes: the system comprises a camera, an industrial personal computer and a display screen; the camera is used for collecting picture information of a tunneling working face and sending the picture information to the industrial personal computer; the industrial personal computer is used for preprocessing the picture information, identifying workers in the tunneling working face based on the preprocessed picture information, tracking and prejudging the running track of the workers at the same time to obtain prejudgment information corresponding to the running track of the workers, and then carrying out early warning based on the prejudgment information; and the display screen is used for displaying the operation track prejudgment information of the working personnel. The technical scheme provided by the application ensures the safety of the workers of the tunneling working face and effectively improves the intelligent level of the tunneling working face.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative and intended to explain the present application and should not be construed as limiting the present application.
The application provides a dangerous area personnel discernment early warning system and method based on machine vision, wherein, dangerous area personnel discernment early warning system includes: the system comprises a camera, an industrial personal computer and a display screen; the camera is used for collecting picture information of a tunneling working face and sending the picture information to the industrial personal computer; the industrial personal computer is used for preprocessing the picture information, identifying workers in the tunneling working face based on the preprocessed picture information, tracking and prejudging the running track of the workers at the same time to obtain prejudgment information corresponding to the running track of the workers, and then carrying out early warning based on the prejudgment information; and the display screen is used for displaying the operation track prejudgment information of the working personnel. The technical scheme provided by the application ensures the safety of the working personnel of the tunneling working face and effectively improves the intelligent level of the tunneling working face.
The following describes a dangerous area person identification early warning system and method based on machine vision according to an embodiment of the present application with reference to the accompanying drawings.
Example one
Fig. 1 is a block diagram of a hazardous area personnel identification and early warning system based on machine vision according to an embodiment of the present application, and as shown in fig. 1, the hazardous area personnel identification and early warning system may include: the system comprises a camera 1, an industrial personal computer 2 and a display screen 3;
the camera 1 is used for collecting picture information of a tunneling working face and sending the picture information to the industrial personal computer 2;
the industrial personal computer 2 is used for preprocessing the picture information, identifying workers in the tunneling working face based on the preprocessed picture information, tracking and prejudging the running track of the workers at the same time to obtain prejudgment information corresponding to the running track of the workers, and then carrying out early warning based on the prejudgment information;
and the display screen 3 is used for displaying the running track prejudgment information of the working personnel.
In the embodiment of the present disclosure, as shown in fig. 2, the system for identifying and warning people in a dangerous area further includes: a vision box 4;
the vision box 4 covers the outer side of the industrial personal computer 2 and is used for protecting the industrial personal computer 2 from being corroded by the severe environment of the driving working face.
In the embodiment of the disclosure, as shown in fig. 3, an image preprocessing module 2-1, a personnel identification module 2-2 and a tracking early warning module 2-3 are arranged in the industrial personal computer 2;
the image preprocessing module 2-1 is used for performing definition enhancement processing on the picture information;
a pre-trained personnel identification model is arranged in the personnel identification module 2-2 and is used for inputting the pre-processed picture information into the pre-trained personnel identification model and then identifying the working personnel tunneling the working face in the picture information;
the tracking early warning module 2-3 is provided with a pre-established motion model and an early warning boundary line, and is used for tracking the operation track of the worker, pre-judging the operation action of the worker at the next moment to obtain pre-judgment information corresponding to the operation track of the worker, then determining whether the operation track of the worker needs to be early warned according to the pre-judgment information and the early warning boundary line, and sending an early warning signal to the worker when the operation track of the worker needs to be early warned.
It should be noted that the early warning boundary line is defined on an upper computer in the industrial personal computer 2 by using an infrared thermal imager.
Further, the image preprocessing module 2-1 is specifically configured to:
and performing brightness enhancement processing on the picture information or performing image enhancement processing on the picture information based on a single-scale Retinex algorithm.
The person identification model 2-2 is obtained by training the initial YOLOV3 model based on training sample data formed by image information of the heading face having the worker mark information.
Illustratively, picture information of a tunneling working face in a historical period is acquired, 80% of the picture information is marked with personnel information to form training sample data, and 20% of the pictures are preprocessed to form test sample data;
carrying out optimization training on the initial Yolov3 model by using training sample data, adjusting model parameters until the error of a loss function is smaller than a set value, outputting a positioning identification result of a worker, testing the identification accuracy of the model by using test sample data, and continuously adjusting the model parameters; the mean square error loss MSE loss function is used in the training of the model, and the AdamaOptimizer is adopted in the optimizer.
In an embodiment of the present disclosure, the process of establishing the motion model includes:
establishing an initial motion model based on the motion trail of the working personnel in the historical period of the tunneling working face;
and learning the initial motion model according to a preset motion rule and a machine learning method to obtain a well-learned motion model.
Wherein the preset motion rule comprises:
behavior inference rule, interaction rule with others and influence rule of surrounding environment
Exemplary, the prediction of downhole pedestrian trajectories based on GAN includes: by combining the sequence prediction model and the GAN countermeasure network, the countermeasure idea is introduced into the task of pedestrian trajectory prediction, and the sample space of all possible solutions is shown.
In summary, the present invention provides a dangerous area personnel identification and early warning system based on machine vision, including: the system comprises a camera, an industrial personal computer and a display screen; the camera is used for collecting picture information of a tunneling working face and sending the picture information to the industrial personal computer; the industrial personal computer is used for preprocessing the picture information, identifying workers in the tunneling working face based on the preprocessed picture information, tracking and prejudging the running track of the workers at the same time to obtain prejudgment information corresponding to the running track of the workers, and then carrying out early warning based on the prejudgment information; the display screen is used for displaying the operation track prejudgment information of the workers, the safety of the workers on the tunneling working face is guaranteed, and the intelligent level of the tunneling working face is effectively improved.
Example two
Fig. 4 is a flowchart of a method for identifying and warning people in a dangerous area based on machine vision according to an embodiment of the present application, where as shown in fig. 4, the method may include:
step 1: collecting picture information of a driving face;
and 2, step: preprocessing the picture information, and identifying workers in the tunneling working face based on the preprocessed picture information;
and step 3: tracking and pre-judging the running track of a worker to obtain the running track pre-judging information of the worker;
and 4, step 4: and early warning the operation track of the worker based on the prejudgment information.
In conclusion, the dangerous area personnel identification and early warning method based on machine vision guarantees the safety of the tunneling working face workers and effectively improves the intelligent level of the tunneling working face.
Example 3
In order to implement the above embodiments, the present disclosure further provides an electronic device.
The electronic device provided by the embodiment comprises: memory, processor and computer program stored on the memory and executable on the processor, which when executed by the processor implements the method of embodiment 2.
Example 4
In order to implement the above embodiments, the present disclosure also proposes a computer-readable storage medium.
The present embodiment provides a computer device having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method of embodiment 2.
In the description of the present specification, reference to the description of "one embodiment," "some embodiments," "an example," "a specific example," or "some examples" or the like means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.
Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.