Disclosure of Invention
In order to solve the problems, the application provides a three-dimensional monitoring method and system for a transformer substation based on video, which can display data acquired by a video system and analyzed conclusions in real time in a three-dimensional model mode.
In some embodiments, the following technical scheme is adopted:
a three-dimensional monitoring method of a transformer substation based on video comprises the following steps:
acquiring video image information in a transformer substation in real time, and establishing a three-dimensional model of the transformer substation;
performing appearance defect identification of transformer substation equipment, if the appearance defect of the equipment is detected, positioning the defective equipment at multiple angles to obtain coordinates of an abnormal part, establishing an equipment three-dimensional model with abnormal appearance according to the obtained abnormal equipment image, and superposing the newly-built equipment three-dimensional model to a corresponding position area of the transformer substation three-dimensional model;
and detecting abnormal states of a scene of the transformer substation, if personnel entering is detected, identifying facial features and appearance features of the personnel, establishing a human body three-dimensional model with real face images and appearance features, and placing the human body three-dimensional model at a corresponding position of the three-dimensional model of the transformer substation according to personnel position coordinates.
In other embodiments, a video-based substation three-dimensional monitoring system is disclosed, comprising:
the device is used for collecting video image information in the transformer substation in real time; the device comprises: the cameras are distributed in at least two different shooting angles in a monitoring area set by the transformer substation;
means for building a three-dimensional model of the substation; the device comprises a three-dimensional model library of a transformer substation;
means for performing an appearance defect identification of the substation equipment;
means for obtaining coordinates of an abnormal portion by multi-angle positioning of a defective device when an appearance defect of the device is detected;
means for creating a three-dimensional model of the device with an abnormal appearance from the acquired abnormal device image;
means for superimposing the newly created device three-dimensional model to the corresponding location area of the substation three-dimensional model;
the device is used for detecting abnormal states of a transformer substation scene;
means for identifying facial features and appearance features of a person when the person is detected to be entering, and creating a human body three-dimensional model with real face images and appearance features;
and the device is used for placing the human body three-dimensional model at the corresponding position of the three-dimensional model of the transformer substation according to the personnel position coordinates.
In other embodiments, a terminal device is disclosed that includes a processor for implementing instructions and a computer-readable storage medium; the computer readable storage medium is for storing a plurality of instructions adapted to be loaded by a processor and to perform the video-based substation three-dimensional monitoring method described above.
In other embodiments, a computer readable storage medium is disclosed in which are stored a plurality of instructions adapted to be loaded by a processor of a terminal device and to perform the video-based substation three-dimensional monitoring method described above.
Compared with the prior art, the application has the beneficial effects that:
the application combines the advantage of visual display of the three-dimensional transformer substation and the characteristics of omnibearing real-time monitoring and analysis of the video system, can increase the result of video analysis on the three-dimensional model of the transformer substation in real time, greatly improves the timeliness of the three-dimensional model, and ensures that patrol personnel can grasp the running information of the transformer substation more intuitively.
The application makes up the defect that the three-dimensional model system can only check the fixed model file by utilizing the real-time watching and real-time analyzing characteristics of the video system, and can more intuitively and effectively display the instant state of the transformer substation. By the technology, key data can be effectively mastered in cross-level and cross-region inspection of the unmanned inspection substation.
According to the application, through multi-camera multi-point positioning, no dead angle monitoring of the transformer substation is achieved; the three-dimensional visual tracking of the abnormal state of the transformer substation can be realized, and the real-time monitoring capability of the three-dimensional monitoring system of the transformer substation is improved.
Detailed Description
It should be noted that the following detailed description is illustrative and is intended to provide further explanation of the application. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present application. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
Example 1
With the increase of unattended substations, operation and inspection staff increasingly use a remote inspection mode to inspect various data of the substations. The display modes mainly comprise forms, graphs, video pictures, wiring diagrams and the like. With the increasing of the data volume, the traditional display mode is difficult to reflect the relevance and the position characteristics of the data, and is also difficult to extract a main interface, so that all key information can be intuitively displayed. The three-dimensional model of the transformer substation can intuitively show the actual running condition of the transformer substation by constructing a three-dimensional transformer substation which is identical with a real transformer substation and superposing real-time data which is configured in advance, but is not in a way for the condition which is not configured in advance.
Along with the increasing maturity of the video monitoring technology at present, the network cost is reduced continuously, and the video monitoring network without dead angles is easy to deploy in the transformer substation. Theoretically, the monitoring system can obtain visible data of any area through video. Therefore, what mode is adopted to display the analysis result of the video system to operation staff through a three-dimensional model is the current technical difficulty.
Based on the above, in one or more embodiments, a three-dimensional monitoring method for a transformer substation based on video is disclosed, and in the stage of video monitoring design, multiple cameras should be equipped for multi-angle monitoring in an important monitoring area so as to achieve the effect of three-dimensional positioning of equipment and faults.
In the operation and inspection stage of the video system, the camera continuously collects image information and analyzes the image information. The system is mainly composed of two intelligent analysis engines.
The device has an appearance defect recognition engine, mainly used for analyzing the appearance damage of the device, whether abnormal additives exist, abnormal light, smoke, fire light and the like.
Scene analysis engine, mainly analyze personnel's action, such as face identification, helmet monitoring, unusual action, wandering, gathering, and regional monitoring, such as foreign matter intrusion, article carry-over, crossing the warning line, etc.
Referring to fig. 1, the video-based three-dimensional monitoring method for a transformer substation specifically includes the following steps:
(1) Acquiring video image information in a transformer substation in real time, and establishing a three-dimensional model of the transformer substation;
(2) Performing appearance defect identification of transformer substation equipment, if the appearance defect of the equipment is detected, positioning the defective equipment at multiple angles to obtain coordinates of an abnormal part, establishing an equipment three-dimensional model with abnormal appearance according to the obtained abnormal equipment image, and superposing the newly-built equipment three-dimensional model to a corresponding position area of the transformer substation three-dimensional model;
the method comprises the steps of obtaining coordinates of an abnormal part according to multi-angle positioning of a camera to the abnormal region, wherein the specific process comprises the following steps:
at least two cameras near the defect equipment in the linkage transformer substation acquire images of the defect equipment from different shooting angles;
positioning coordinates of the defect equipment in the images acquired by the cameras, and adjusting the shooting angles of the cameras so that the defect position of the equipment is positioned at the center position of a shooting picture of each camera;
for each camera in linkage, a ray taking the camera as an endpoint and taking the direction corresponding to the central position of the camera as an extending direction is respectively obtained;
and in the three-dimensional model of the transformer substation, the intersection point of all rays is obtained, and the intersection point is the three-dimensional coordinate point of the equipment defect position.
According to the obtained abnormal equipment image, an equipment three-dimensional model with abnormal appearance is established, and the newly-established equipment three-dimensional model is overlapped to a corresponding position area of the transformer substation three-dimensional model, wherein the specific process comprises the following steps:
the camera recognizes the position of the appearance defect of the equipment through a video recognition technology, and captures a picture of the position. And calling cameras at other angles, and obtaining abnormal part screenshots at different angles.
Meanwhile, through the ray intersection point, the space coordinates of the abnormal part and the three-dimensional model of the equipment can be obtained. And calling the model file in the three-dimensional model library, and replacing a default normal three-dimensional model map by using the screenshot of the abnormal part to obtain the equipment three-dimensional model with abnormal appearance.
The camera recognizes an abnormal part through a video recognition technology, and captures a picture of the abnormal part. And calling other cameras, and capturing images of abnormal parts. And obtaining the space coordinates of the abnormal part by a ray intersection method, namely the coordinates of the model to be superimposed in the three-dimensional model of the transformer substation. And processing the coordinates, directions and overlapping the coordinates and directions of the three-dimensional model of the equipment with the abnormal appearance to the corresponding area of the original model through the deformation matrix.
(3) And detecting abnormal states of a scene of the transformer substation, if personnel entering is detected, identifying facial features and appearance features of the personnel, establishing a human body three-dimensional model with real face images and appearance features, and placing the human body three-dimensional model at a corresponding position of the three-dimensional model of the transformer substation according to personnel position coordinates.
If the scene analysis engine detects an abnormal state of the scene, a corresponding model is called according to the specific analyzed abnormal type, and the model is updated according to the real-time video.
For example, an area detects a person intrusion. The video monitoring system automatically invokes the standby camera, tracks the behavior of the person and walks along the route. And uploading the real-time picture of the person by the camera. The three-dimensional system calls the human body model from the three-dimensional library and performs the following processing:
1) Collecting facial features of a person, forming a map, and displaying the map on the face of the three-dimensional human body model;
specifically, the camera analyzes the person in the picture, calculates the coordinate of the person relative to the center point of the picture, controls the horizontal rotation and the vertical rotation of the camera holder, and adjusts the camera angle until the relative coordinate of the person in the picture is (0, 0).
And recognizing the face through a face recognition technology, and intercepting a face picture. And calling other cameras in the working range of the person, and capturing the facial photos of the person from multiple angles. And mapping the intercepted face photo on a three-dimensional model of the staff to obtain the three-dimensional human body model with the real face photo.
2) Collecting the appearance characteristics of personnel, if a safety helmet is worn, wearing working clothes and safety shoes, and loading corresponding parts in a human body model;
the human body model, the safety helmet model, the working clothes model and the safety shoe model are all used as material models and stored in a model library; after the video recognition camera shoots a worker, the dressing characteristics of the worker are analyzed, if the worker wears a safety helmet or wears a working suit, corresponding three-dimensional model materials are called from a model library, a complete three-dimensional model which truly reflects the dressing of the worker is assembled, and the three-dimensional model is placed in a three-dimensional model of a transformer substation.
3) Face recognition, comparing a face library, checking the authority of the person, dressing the person, and highlighting and alarming the three-dimensional model if the person has override or does not meet the requirement;
4) And solving the real-time position of the person according to the camera positioning data, and placing the human body three-dimensional model at the corresponding position of the three-dimensional model of the total station.
In addition, the model provides a clickable advanced option, and after clicking, the three-dimensional monitoring system popup window displays the real-time video of the person.
According to the three-dimensional monitoring method for the transformer substation based on the video, the advantage of visual display of the three-dimensional transformer substation is combined, and the characteristics of omnibearing real-time monitoring and analysis of a video system are combined, so that the result of video analysis can be added on a three-dimensional model of the transformer substation in real time, the timeliness of the three-dimensional model is greatly improved, and a patrol inspector can grasp the running information of the transformer substation more intuitively.
Example two
In one or more embodiments, a video-based substation three-dimensional monitoring system is disclosed, comprising:
the device is used for collecting video image information in the transformer substation in real time; the device comprises: the cameras are distributed in at least two different shooting angles in a monitoring area set by the transformer substation;
means for building a three-dimensional model of the substation; the device comprises a three-dimensional model library of a transformer substation;
means for performing an appearance defect identification of the substation equipment;
means for obtaining coordinates of an abnormal portion by multi-angle positioning of a defective device when an appearance defect of the device is detected;
means for creating a three-dimensional model of the device with an abnormal appearance from the acquired abnormal device image;
means for superimposing the newly created device three-dimensional model to the corresponding location area of the substation three-dimensional model;
the device is used for detecting abnormal states of a transformer substation scene;
means for identifying facial features and appearance features of a person when the person is detected to be entering, and creating a human body three-dimensional model with real face images and appearance features;
and the device is used for placing the human body three-dimensional model at the corresponding position of the three-dimensional model of the transformer substation according to the personnel position coordinates.
Further, the device for obtaining coordinates of an abnormal part by multi-angle positioning of the defective equipment when the appearance defect of the equipment is detected specifically includes:
the device is used for linking at least two cameras near the defect equipment in the transformer substation and acquiring images of the defect equipment from different shooting angles;
a device for positioning coordinates of the defect equipment in the images acquired by the cameras, and adjusting shooting angles of the cameras so that the defect position of the equipment is positioned at the central position of a shooting picture of each camera;
means for obtaining, for each camera of the linkage, a ray having the camera as an end point and having a direction corresponding to a center position of the camera as an extension direction, respectively;
and the device is used for solving the intersection point of all rays in the three-dimensional model of the transformer substation, wherein the intersection point is the three-dimensional coordinate point of the equipment defect position.
Example III
In one or more embodiments, a terminal device is disclosed that includes a processor for implementing instructions and a computer-readable storage medium; the computer readable storage medium is for storing a plurality of instructions adapted to be loaded by a processor and to perform the video-based substation three-dimensional monitoring method described in embodiment one.
In other embodiments, a computer readable storage medium is disclosed in which a plurality of instructions are stored, the instructions being adapted to be loaded by a processor of a terminal device and to perform the video-based substation three-dimensional monitoring method described in example one.
While the foregoing description of the embodiments of the present application has been presented in conjunction with the drawings, it should be understood that it is not intended to limit the scope of the application, but rather, it is intended to cover all modifications or variations within the scope of the application as defined by the claims of the present application.