CN113191313A - Video stream discharge identification method and device based on hydraulic power plant and computer equipment - Google Patents
Video stream discharge identification method and device based on hydraulic power plant and computer equipment Download PDFInfo
- Publication number
- CN113191313A CN113191313A CN202110550718.8A CN202110550718A CN113191313A CN 113191313 A CN113191313 A CN 113191313A CN 202110550718 A CN202110550718 A CN 202110550718A CN 113191313 A CN113191313 A CN 113191313A
- Authority
- CN
- China
- Prior art keywords
- discharge
- current image
- pixel
- image
- monitoring area
- 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
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000012544 monitoring process Methods 0.000 claims abstract description 98
- 238000012545 processing Methods 0.000 claims abstract description 66
- 230000002159 abnormal effect Effects 0.000 claims abstract description 26
- 238000007599 discharging Methods 0.000 claims abstract description 13
- 238000013507 mapping Methods 0.000 claims description 14
- 238000000926 separation method Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000000877 morphologic effect Effects 0.000 claims description 5
- 230000010354 integration Effects 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000000691 measurement method Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009529 body temperature measurement Methods 0.000 description 1
- 238000007707 calorimetry Methods 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24147—Distances to closest patterns, e.g. nearest neighbour classification
-
- 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
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/48—Matching video sequences
Abstract
According to the method, the device and the computer equipment for identifying the video stream discharge based on the hydraulic power plant, the discharge monitoring area can be accurately defined by determining the foreground mask of the current image in the real-time video data and processing the foreground mask to obtain the discharge monitoring area, the monitoring range is effectively reduced, and the processing amount of related image data is reduced. By carrying out binarization processing on the current image, the highlight pixel points can be effectively distinguished, and accurate discharge area judgment based on the highlight pixel points is facilitated subsequently. The discharging phenomenon can be judged by judging whether abnormal pixel points matched with the pixel point coordinate set exist in the discharging monitoring area, and when the discharging phenomenon exists in the discharging monitoring area, the pixel point coordinates of the abnormal pixel points are clustered to obtain the position information of the discharging area. Therefore, the interference of external factors on the discharge area monitoring can be reduced as much as possible, and the real-time, accurate and reliable discharge area monitoring is realized.
Description
Technical Field
The application relates to the technical field of discharge identification of hydraulic power plants, in particular to a method, a device and computer equipment for identifying video stream discharge based on the hydraulic power plants.
Background
For discharge area monitoring of a hydropower plant area, the related art may generally include an acoustic method, a light method, an infrared heat method, and the like. The acoustic measurement method judges the position of partial discharge through sound to realize discharge monitoring, but the operation noise of related equipment in a hydropower plant area is large, and the discharge monitoring accuracy of the acoustic measurement method is difficult to ensure. The optical measurement method is to monitor the characteristics of photocurrent to realize the identification of partial discharge after the optical radiation generated by partial discharge is subjected to photoelectric conversion by the optical sensor, but the equipment for implementing the method has relatively complex structure and high manufacturing cost. In addition, the infrared calorimetry is realized based on local temperature rise caused by local discharge and a thermal infrared imager, but the temperature measurement of the thermal infrared imager is easily influenced by factors such as surface emissivity, reflectivity, ambient temperature and measurement distance of an object, so that the problem of high sensitivity exists, the local heating of equipment is easily caused by discharge misjudgment, and the discharge monitoring effect of the method applied in a water and power plant area is not ideal.
Disclosure of Invention
In order to solve the technical problems in the related art, the application provides a method, a device and computer equipment for identifying the video stream discharge based on a hydraulic power plant.
The application provides a video stream discharge identification method based on a hydraulic power plant, which comprises the following steps:
acquiring real-time video data, and determining a foreground mask of a current image in the real-time video data; processing the foreground mask of the current image to obtain a discharge monitoring area in the current image;
carrying out binarization processing on the current image to obtain a binarized image, and integrating pixel point coordinates in the binarized image to obtain a pixel point coordinate set;
mapping the pixel point coordinate set to the discharge monitoring area, and judging whether abnormal pixel points matched with the pixel point coordinate set exist in the discharge monitoring area; if so, judging that a discharge phenomenon exists in the discharge monitoring area;
and clustering the pixel point coordinates of the abnormal pixel points to obtain the position information of the discharge area.
Further, before the current image is binarized to obtain a binarized image, the method further includes:
judging whether the foreground mask of the current image meets a filtering condition;
and if the filtering condition is not met, performing binarization processing on the current image to obtain a binarized image.
Further, the acquiring the real-time video data and determining a foreground mask of a current image in the real-time video data includes:
acquiring real-time video data through a camera, and performing background information identification calculation on the real-time video data through background modeling to obtain background image data;
and obtaining a foreground mask of the current image according to the background image data.
Further, the processing the foreground mask of the current image to obtain the discharge monitoring area in the current image includes:
carrying out foreground region binarization processing on the foreground mask of the current image to obtain a foreground binarization processing result; the foreground binarization processing result comprises a white foreground area and a non-white non-foreground area;
performing morphological processing on the foreground binarization processing result to obtain a processed optimized image;
and carrying out contour coordinate identification on the optimized image by using a contour identification model to obtain contour coordinates, and combining the contour coordinates to obtain a discharge monitoring area in the current image.
Further, the binarizing the current image to obtain a binarized image includes:
performing color separation on the current image based on a preset color separation model to obtain a brightness channel matrix;
carrying out binarization processing on the brightness channel matrix to obtain a pixel brightness value set;
obtaining a brightness preset value in a preset database, and judging the size relation between each pixel brightness value in the pixel brightness value set and the brightness preset value;
for each of the pixel luminance values:
if the pixel brightness value is larger than the brightness preset value, determining a pixel point corresponding to the pixel brightness value as a high-brightness pixel point;
if the pixel brightness value is smaller than or equal to the brightness preset value, determining a pixel point corresponding to the pixel brightness value as a background pixel point;
and generating the binary image according to the pixel point coordinates corresponding to the high-brightness pixel points and/or the background pixel points.
Further, mapping the pixel coordinate set to the discharge monitoring area, and determining whether an abnormal pixel matched with the pixel coordinate set exists in the discharge monitoring area, including:
mapping the pixel point coordinate set to the discharge monitoring area to generate a binary image coordinate set, and judging whether the binary image coordinate set is an empty set;
if the coordinate set of the binary image is an empty set, judging that no discharge phenomenon exists in a discharge monitoring area in the current image;
and if the coordinate set of the binary image is not an empty set, judging that the discharge phenomenon exists in the discharge monitoring area in the current image.
Further, the method further comprises:
and outputting an early warning signal according to the position information of the discharge area.
The application provides a video stream discharge recognition device based on hydroelectric power plant, the device includes:
the device comprises a discharge area determining module, a foreground mask determining module and a display module, wherein the discharge area determining module is used for acquiring real-time video data and determining the foreground mask of a current image in the real-time video data; processing the foreground mask of the current image to obtain a discharge monitoring area in the current image;
the pixel coordinate integration module is used for carrying out binarization processing on the current image to obtain a binarized image, and integrating pixel point coordinates in the binarized image to obtain a pixel point coordinate set;
the discharging area judging module is used for mapping the pixel point coordinate set into the discharging monitoring area and judging whether abnormal pixel points matched with the pixel point coordinate set exist in the discharging monitoring area or not; if so, judging that a discharge phenomenon exists in the discharge monitoring area;
and the position information determining module is used for clustering the pixel point coordinates of the abnormal pixel points to obtain the position information of the discharge area.
The application provides a computer device, comprising:
a memory for storing a computer program;
a processor coupled to the memory for executing the computer program stored by the memory to implement the method of any of the above.
The present application provides a computer storage medium having stored thereon a computer program which, when run, implements the method of any one of the above.
The technical scheme provided by the embodiment of the application can have the following beneficial effects.
Based on the scheme, the discharge monitoring area can be accurately defined by determining the foreground mask of the current image in the real-time video data and processing the foreground mask to obtain the discharge monitoring area, so that the monitoring range is effectively reduced, and the processing amount of related image data is reduced. In addition, by carrying out binarization processing on the current image, the highlight pixel points can be effectively distinguished, so that accurate discharge area judgment based on the highlight pixel points is facilitated subsequently. Further, the pixel point coordinate set is mapped into the discharge monitoring area, whether discharge phenomenon exists in the discharge monitoring area can be judged by judging whether abnormal pixel points matched with the pixel point coordinate set exist in the discharge monitoring area, and therefore when the discharge phenomenon exists in the discharge monitoring area, the pixel point coordinates of the abnormal pixel points are clustered to obtain position information of the discharge area. Therefore, the interference of external factors on the discharge area monitoring can be reduced as much as possible, and the real-time, accurate and reliable discharge area monitoring is realized.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
Fig. 1 is a schematic structural diagram of a hydraulic power plant-based video stream discharge identification system according to an embodiment of the present invention;
fig. 2 is a flowchart of a method for identifying a video stream discharge of a hydraulic power plant according to an embodiment of the present invention;
fig. 3 is a functional block diagram of a hydraulic power plant-based video stream discharge identification apparatus according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
In order to facilitate the explanation of the video stream discharge identification method and apparatus based on a hydraulic power plant, please refer to fig. 1, which provides a schematic view of a communication architecture of a video stream discharge identification system 100 based on a hydraulic power plant according to an embodiment of the present invention. The system 100 for identifying the discharge of the hydraulic power plant-based video stream may include an image capturing device 200 and a computer device 300, wherein the image capturing device 200 is in communication connection with the computer device 300.
In particular embodiments, image capture device 200 may be a camera, video camera, or other image capture device capable of capturing relevant image data, without limitation; the computer device 300 may be a desktop computer, a tablet computer, a notebook computer, or other computer device capable of data processing and data communication, which is not limited herein.
On the basis of the above, please refer to fig. 2, which is a flowchart illustrating a method for identifying a video stream discharge based on a hydraulic power plant according to an embodiment of the present invention, where the method for identifying a video stream discharge based on a hydraulic power plant may be applied to the computer device 300 in fig. 1, and further, the method for identifying a video stream discharge based on a hydraulic power plant may specifically include the contents described in the following steps S21 to S25.
Step S21, acquiring real-time video data, and determining a foreground mask of a current image in the real-time video data.
Illustratively, the current image is used to represent each frame of image in the real-time video data.
Step S22, processing the foreground mask of the current image to obtain a discharge monitoring area in the current image.
Illustratively, the discharge monitoring area corresponds to an area in the current image where a discharge phenomenon may occur.
And step S23, performing binarization processing on the current image to obtain a binarized image, and integrating pixel point coordinates in the binarized image to obtain a pixel point coordinate set.
Step S24, mapping the pixel point coordinate set to the discharge monitoring area, and judging whether an abnormal pixel point matched with the pixel point coordinate set exists in the discharge monitoring area; and if so, judging that the discharge phenomenon exists in the discharge monitoring area.
And step S25, clustering the pixel point coordinates of the abnormal pixel points to obtain the position information of the discharge area.
It can be understood that, when the contents described in the above steps S21-S25 are executed, by determining the foreground mask of the current image in the real-time video data and processing the foreground mask to obtain the discharge monitoring area, the discharge monitoring area can be accurately defined, the monitoring range is effectively reduced, and the processing amount of the related image data is reduced. In addition, by carrying out binarization processing on the current image, the highlight pixel points can be effectively distinguished, so that accurate discharge area judgment based on the highlight pixel points is facilitated subsequently. Further, the pixel point coordinate set is mapped into the discharge monitoring area, whether discharge phenomenon exists in the discharge monitoring area can be judged by judging whether abnormal pixel points matched with the pixel point coordinate set exist in the discharge monitoring area, and therefore when the discharge phenomenon exists in the discharge monitoring area, the pixel point coordinates of the abnormal pixel points are clustered to obtain position information of the discharge area. Therefore, the interference of external factors on the discharge area monitoring can be reduced as much as possible, and the real-time, accurate and reliable discharge area monitoring is realized.
In an alternative embodiment, before the binarization processing of the current image to obtain the content of the binarized image as described in step S23, the following contents described in step q1 and step q2 may be specifically included.
And step q1, judging whether the foreground mask of the current image meets the filtering condition.
Illustratively, the filtering condition indicates that there may be situations such as walking of the relevant staff in the foreground image, which may cause certain interference, and therefore it is necessary to eliminate misjudgment caused by these situations.
And step q2, if the filtering condition is not met, performing binarization processing on the current image to obtain a binarized image.
On the basis, the specific method for judging whether the discharge monitoring interference exists may include: for continuous video stream, a position conversion target can be identified by adopting a frame difference method, the position change condition of relevant workers is judged according to the position of the target (the relevant workers) appearing in the foreground image every time, and if the position change characteristic of the relevant workers meets a certain position conversion condition, the walking interference of the relevant workers in the current image can be judged, so that the current image can be deleted.
Correspondingly, if the position change characteristics of the related workers do not meet a certain position conversion condition, the current image can be judged to have no walking interference of the related workers, and the binarization processing can be performed on the current image to obtain the binarization image.
It can be understood that, when performing the contents described in the above steps q1 and q2, by determining whether the foreground mask of the current image has the influence of human factors, the relevant image is effectively optimized, so as to ensure the accuracy of the foreground mask of the current image.
In an alternative embodiment, the step of acquiring the real-time video data and determining the foreground mask of the current image in the real-time video data described in step S231 may include the following steps described in step S211 and step S212.
Step S211, acquiring real-time video data through a camera, and performing background information identification calculation on the real-time video data through background modeling to obtain background image data.
Step S212, obtaining a foreground mask of the current image according to the background image data.
It is to be understood that, in executing the contents described in the above steps S211 and S212, the background modeling manner includes KNN (K-Nearest Neighbor) algorithm (K Nearest Neighbor algorithm). The real-time video data can be subjected to Background processing by using a create Background sub KNN function of cv2 (the processing mode comprises the mode of setting the training frame number, shadow monitoring and the like), so that the Background image data can be accurately obtained.
In general, the number of frames of KNN training may be set to 1 frame, 2 frames, or 3 frames, etc. For example, when the number of KNN training frames is 20, the processing effect on the real-time video data is the best. The accurate foreground mask of the current image can be obtained through the accurate background image data, so that the accuracy of the subsequent related image binarization processing is effectively improved.
In an alternative embodiment, the step of processing the foreground mask of the current image to obtain the discharge monitoring area in the current image, which is described in step S22, may include the following steps S221 to S223.
And step S221, carrying out foreground region binarization processing on the foreground mask of the current image to obtain a foreground binarization processing result.
Illustratively, the foreground binarization processing result includes a white foreground region and a non-white non-foreground region.
And step S222, performing morphological processing on the foreground binarization processing result to obtain a processed optimized image.
And step S223, carrying out contour coordinate identification on the optimized image by using a contour identification model to obtain a contour coordinate, and combining the contour coordinate to obtain a discharge monitoring area in the current image.
It is understood that, in executing the contents described in the above steps S221 to S223, the contour identification model performs contour calculation using the cv2.find contacts function. The morphological processing method comprises processing methods such as corrosion, expansion operation and noise elimination. The foreground mask of the current image is subjected to binarization processing and related image optimization, so that the related foreground images can be effectively distinguished, interference factors of the related foreground images are reduced, and a discharge monitoring area can be accurately determined and defined.
In an alternative embodiment, the step of performing binarization processing on the current image to obtain a binarized image, which is described in step S23, may specifically include the following steps S231-S237.
And S231, performing color separation on the current image based on a preset color separation model to obtain a brightness channel matrix.
Step S232, carrying out binarization processing on the brightness channel matrix to obtain a pixel brightness value set.
Step S233, obtaining a preset brightness value in a preset database, and determining a size relationship between each pixel brightness value in the pixel brightness value set and the preset brightness value.
Step S234, for each of the pixel luminance values:
in step S235, if the pixel brightness value is greater than the brightness preset value, determining a pixel point corresponding to the pixel brightness value as a high-brightness pixel point.
In step S236, if the pixel brightness value is less than or equal to the brightness preset value, determining a pixel point corresponding to the pixel brightness value as a background pixel point.
Step S237, generating the binarized image according to the respective pixel coordinates corresponding to the high-brightness pixel and/or the background pixel.
It is to be understood that the preset color separation model represents a separation of a channel representing luminance from an image LAB toning model, wherein L in the image LAB toning model represents luminance and a and B represent two color channels. Generally speaking, the brightness information has a certain relationship with whether discharge exists, so that the color information in the related image information needs to be removed, interference of the related color information on discharge monitoring can be effectively avoided, binarization processing is performed on the brightness information of the related image, and the coordinate point corresponding to the high-brightness pixel point can be accurately determined through the pixel brightness value set.
In an alternative embodiment, the step of mapping the pixel coordinate set to the discharge monitoring area in step S24 and determining whether there is an abnormal pixel matching the pixel coordinate set in the discharge monitoring area may include the following steps S241 to S243.
And step S241, mapping the pixel point coordinate set to the discharge monitoring area, generating a binaryzation image coordinate set, and judging whether the binaryzation image coordinate set is an empty set.
And step S242, if the coordinate set of the binarized image is an empty set, determining that no discharge phenomenon exists in the discharge monitoring area in the current image.
And step S243, if the coordinate set of the binarized image is not an empty set, determining that a discharge phenomenon exists in a discharge monitoring area in the current image.
It can be understood that, when the contents described in the above steps S241 to S243 are executed, whether the high-brightness pixel is in the discharge monitoring area can be accurately determined through the mapping relationship, so that the abnormal pixel can be quickly and accurately determined, and the discharge condition in the real-time video data can be accurately determined, so as to quickly determine the accurate discharge position corresponding to the relevant device in the discharge monitoring area in real time.
On the basis of the above, the following contents may be further included: and outputting an early warning signal according to the position information of the discharge area.
Therefore, the corresponding early warning signal can be generated and output through the discharge area position, and then related technical personnel can be rapidly prompted to handle, so that the occurrence of safety accidents and the existence of potential safety hazards can be effectively avoided.
Based on the same inventive concept, the video stream discharge identification system based on the hydraulic power plant is further provided, the system comprises image acquisition equipment and computer equipment, the image acquisition equipment is in communication connection with the computer equipment, and the computer equipment is specifically used for:
acquiring real-time video data, and determining a foreground mask of a current image in the real-time video data;
processing the foreground mask of the current image to obtain a discharge monitoring area in the current image;
carrying out binarization processing on the current image to obtain a binarized image, and integrating pixel point coordinates in the binarized image to obtain a pixel point coordinate set;
mapping the pixel point coordinate set to the discharge monitoring area, and judging whether abnormal pixel points matched with the pixel point coordinate set exist in the discharge monitoring area; if so, judging that a discharge phenomenon exists in the discharge monitoring area;
and clustering the pixel point coordinates of the abnormal pixel points to obtain the position information of the discharge area.
Further, the computer device is specifically configured to:
judging whether the foreground mask of the current image meets a filtering condition;
and if the filtering condition is not met, performing binarization processing on the current image to obtain a binarized image.
Further, the computer device is specifically configured to:
acquiring real-time video data through a camera, and performing background information identification calculation on the real-time video data through background modeling to obtain background image data;
and obtaining a foreground mask of the current image according to the background image data.
Further, the computer device is specifically configured to:
carrying out foreground region binarization processing on the foreground mask of the current image to obtain a foreground binarization processing result; the foreground binarization processing result comprises a white foreground area and a non-white non-foreground area;
performing morphological processing on the foreground binarization processing result to obtain a processed optimized image;
and carrying out contour coordinate identification on the optimized image by using a contour identification model to obtain contour coordinates, and combining the contour coordinates to obtain a discharge monitoring area in the current image.
Further, the computer device is specifically configured to:
performing color separation on the current image based on a preset color separation model to obtain a brightness channel matrix;
carrying out binarization processing on the brightness channel matrix to obtain a pixel brightness value set;
obtaining a brightness preset value in a preset database, and judging the size relation between each pixel brightness value in the pixel brightness value set and the brightness preset value;
for each of the pixel luminance values:
if the pixel brightness value is larger than the brightness preset value, determining a pixel point corresponding to the pixel brightness value as a high-brightness pixel point;
if the pixel brightness value is smaller than or equal to the brightness preset value, determining a pixel point corresponding to the pixel brightness value as a background pixel point;
and generating the binary image according to the pixel point coordinates corresponding to the high-brightness pixel points and/or the background pixel points.
Further, the computer device is specifically configured to:
mapping the pixel point coordinate set to the discharge monitoring area to generate a binary image coordinate set, and judging whether the binary image coordinate set is an empty set;
if the coordinate set of the binary image is an empty set, judging that no discharge phenomenon exists in a discharge monitoring area in the current image;
and if the coordinate set of the binary image is not an empty set, judging that the discharge phenomenon exists in the discharge monitoring area in the current image.
Further, the computer device is specifically configured to:
and outputting an early warning signal according to the position information of the discharge area.
Based on the same inventive concept, please refer to fig. 3 in combination, a functional block diagram of a hydraulic power plant-based video stream discharge identification apparatus 500 is also provided, and the following detailed description of the hydraulic power plant-based video stream discharge identification apparatus 500 is provided.
The video stream discharge recognition device 500 based on the hydraulic power plant is applied to a computer device, and the device 500 comprises:
a foreground mask determining module 510, configured to obtain real-time video data, and determine a foreground mask of a current image in the real-time video data;
a discharge area determining module 520, configured to process the foreground mask of the current image to obtain a discharge monitoring area in the current image;
a pixel coordinate integration module 530, configured to perform binarization processing on the current image to obtain a binarized image, and integrate coordinates of pixel points in the binarized image to obtain a pixel point coordinate set;
a discharge area determining module 540, configured to map the pixel coordinate set into the discharge monitoring area, and determine whether an abnormal pixel matched with the pixel coordinate set exists in the discharge monitoring area; if so, judging that a discharge phenomenon exists in the discharge monitoring area;
and a position information determining module 550, configured to cluster the pixel coordinates of the abnormal pixel to obtain position information of the discharge area.
In further embodiments, the present application provides a computer device comprising: a memory for storing a computer program; a processor coupled to the memory for executing the computer program stored by the memory to implement the method shown in fig. 2.
In a further embodiment, the present application provides a computer storage medium having stored thereon a computer program which, when run, implements the method as shown in fig. 2.
In summary, based on the hydraulic power plant video stream discharge identification method, device and computer equipment, the discharge monitoring area can be accurately defined by determining the foreground mask of the current image in the real-time video data and processing the foreground mask to obtain the discharge monitoring area, the monitoring range is effectively reduced, and the processing amount of related image data is reduced. In addition, by carrying out binarization processing on the current image, the highlight pixel points can be effectively distinguished, so that accurate discharge area judgment based on the highlight pixel points is facilitated subsequently. Further, the pixel point coordinate set is mapped into the discharge monitoring area, whether discharge phenomenon exists in the discharge monitoring area can be judged by judging whether abnormal pixel points matched with the pixel point coordinate set exist in the discharge monitoring area, and therefore when the discharge phenomenon exists in the discharge monitoring area, the pixel point coordinates of the abnormal pixel points are clustered to obtain position information of the discharge area. Therefore, the interference of external factors on the discharge area monitoring can be reduced as much as possible, and the real-time, accurate and reliable discharge area monitoring is realized.
It will be understood that the invention is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the invention is limited only by the appended claims.
Claims (10)
1. A video stream discharge identification method based on a hydraulic power plant is characterized by comprising the following steps:
acquiring real-time video data, and determining a foreground mask of a current image in the real-time video data;
processing the foreground mask of the current image to obtain a discharge monitoring area in the current image;
carrying out binarization processing on the current image to obtain a binarized image, and integrating pixel point coordinates in the binarized image to obtain a pixel point coordinate set;
mapping the pixel point coordinate set to the discharge monitoring area, and judging whether abnormal pixel points matched with the pixel point coordinate set exist in the discharge monitoring area; if so, judging that a discharge phenomenon exists in the discharge monitoring area;
and clustering the pixel point coordinates of the abnormal pixel points to obtain the position information of the discharge area.
2. The method according to claim 1, wherein before the binarizing process is performed on the current image to obtain a binarized image, the method further comprises:
judging whether the foreground mask of the current image meets a filtering condition;
and if the filtering condition is not met, performing binarization processing on the current image to obtain a binarized image.
3. The method of claim 1, wherein the obtaining real-time video data, determining a foreground mask for a current image in the real-time video data, comprises:
acquiring real-time video data through a camera, and performing background information identification calculation on the real-time video data through background modeling to obtain background image data;
and obtaining a foreground mask of the current image according to the background image data.
4. The method of claim 1, wherein the processing the foreground mask of the current image to obtain the discharge monitoring area in the current image comprises:
carrying out foreground region binarization processing on the foreground mask of the current image to obtain a foreground binarization processing result; the foreground binarization processing result comprises a white foreground area and a non-white non-foreground area;
performing morphological processing on the foreground binarization processing result to obtain a processed optimized image;
and carrying out contour coordinate identification on the optimized image by using a contour identification model to obtain contour coordinates, and combining the contour coordinates to obtain a discharge monitoring area in the current image.
5. The method according to claim 1, wherein the binarizing the current image to obtain a binarized image comprises:
performing color separation on the current image based on a preset color separation model to obtain a brightness channel matrix;
carrying out binarization processing on the brightness channel matrix to obtain a pixel brightness value set;
obtaining a brightness preset value in a preset database, and judging the size relation between each pixel brightness value in the pixel brightness value set and the brightness preset value;
for each of the pixel luminance values:
if the pixel brightness value is larger than the brightness preset value, determining a pixel point corresponding to the pixel brightness value as a high-brightness pixel point;
if the pixel brightness value is smaller than or equal to the brightness preset value, determining a pixel point corresponding to the pixel brightness value as a background pixel point;
and generating the binary image according to the pixel point coordinates corresponding to the high-brightness pixel points and/or the background pixel points.
6. The method of claim 1, wherein mapping the pixel coordinate set to the discharge monitoring area, and determining whether an abnormal pixel matching the pixel coordinate set exists in the discharge monitoring area comprises:
mapping the pixel point coordinate set to the discharge monitoring area to generate a binary image coordinate set, and judging whether the binary image coordinate set is an empty set;
if the coordinate set of the binary image is an empty set, judging that no discharge phenomenon exists in a discharge monitoring area in the current image;
and if the coordinate set of the binary image is not an empty set, judging that the discharge phenomenon exists in the discharge monitoring area in the current image.
7. The method of claim 1, further comprising:
and outputting an early warning signal according to the position information of the discharge area.
8. A hydraulic power plant-based video stream discharge identification device, the device comprising:
the foreground mask determining module is used for acquiring real-time video data and determining a foreground mask of a current image in the real-time video data;
the discharging area determining module is used for processing the foreground mask of the current image to obtain a discharging monitoring area in the current image;
the pixel coordinate integration module is used for carrying out binarization processing on the current image to obtain a binarized image, and integrating pixel point coordinates in the binarized image to obtain a pixel point coordinate set;
the discharging area judging module is used for mapping the pixel point coordinate set into the discharging monitoring area and judging whether abnormal pixel points matched with the pixel point coordinate set exist in the discharging monitoring area or not; if so, judging that a discharge phenomenon exists in the discharge monitoring area;
and the position information determining module is used for clustering the pixel point coordinates of the abnormal pixel points to obtain the position information of the discharge area.
9. A computer device, comprising:
a memory for storing a computer program;
a processor coupled to the memory for executing the computer program stored by the memory to implement the method of any of claims 1-7.
10. A computer storage medium, having stored thereon a computer program which, when executed, implements the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110550718.8A CN113191313A (en) | 2021-05-20 | 2021-05-20 | Video stream discharge identification method and device based on hydraulic power plant and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110550718.8A CN113191313A (en) | 2021-05-20 | 2021-05-20 | Video stream discharge identification method and device based on hydraulic power plant and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113191313A true CN113191313A (en) | 2021-07-30 |
Family
ID=76982707
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110550718.8A Pending CN113191313A (en) | 2021-05-20 | 2021-05-20 | Video stream discharge identification method and device based on hydraulic power plant and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113191313A (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101726693A (en) * | 2009-11-26 | 2010-06-09 | 绍兴电力局 | Method for seeking discharge regions of power devices on ultraviolet images |
| CN102236947A (en) * | 2010-04-29 | 2011-11-09 | 中国建筑科学研究院 | Flame monitoring method and system based on video camera |
| CN103543394A (en) * | 2013-10-27 | 2014-01-29 | 华北电力大学（保定） | Discharge ultraviolet imaging quantization parameter extraction method of high-voltage electric equipment |
| CN106503716A (en) * | 2016-09-13 | 2017-03-15 | 中国电力科学研究院 | A kind of safety cap recognition methods that is extracted based on color and contour feature and system |
| CN107505546A (en) * | 2017-08-25 | 2017-12-22 | 国家电网公司 | A kind of method that corona discharge is monitored using ultraviolet imager |
| CN108961247A (en) * | 2018-07-10 | 2018-12-07 | 北京环境特性研究所 | Section insulator damage diagnostic system and method based on arc image detection |
| CN110569717A (en) * | 2019-07-26 | 2019-12-13 | 深圳供电局有限公司 | partial discharge detection method, device, system, equipment and readable storage medium |
| US20200020114A1 (en) * | 2017-04-25 | 2020-01-16 | Continental Automotive France | Image-processing method for removing light zones |
| CN110930329A (en) * | 2019-11-20 | 2020-03-27 | 维沃移动通信有限公司 | Starry sky image processing method and device |
| CN111951247A (en) * | 2020-08-12 | 2020-11-17 | 国网江苏省电力有限公司电力科学研究院 | Power equipment ultraviolet image diagnosis method and system |
| CN112001327A (en) * | 2020-08-25 | 2020-11-27 | 全球能源互联网研究院有限公司 | Valve hall equipment fault identification method and system |
| CN112036320A (en) * | 2020-09-07 | 2020-12-04 | 华北电力大学（保定） | Partial discharge state identification method and device, discharge simulator and identification equipment |
| CN112288691A (en) * | 2020-10-16 | 2021-01-29 | 国电大渡河枕头坝发电有限公司 | Method for detecting water drops in hydraulic power plant based on image processing |
| CN112351247A (en) * | 2020-10-16 | 2021-02-09 | 国电大渡河枕头坝发电有限公司 | Electro-optical flash detection method in hydraulic power plant based on image processing |
| CN112801949A (en) * | 2021-01-15 | 2021-05-14 | 国网江苏省电力有限公司电力科学研究院 | Method and device for determining discharge area in ultraviolet imaging detection technology |
-
2021
- 2021-05-20 CN CN202110550718.8A patent/CN113191313A/en active Pending
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101726693A (en) * | 2009-11-26 | 2010-06-09 | 绍兴电力局 | Method for seeking discharge regions of power devices on ultraviolet images |
| CN102236947A (en) * | 2010-04-29 | 2011-11-09 | 中国建筑科学研究院 | Flame monitoring method and system based on video camera |
| CN103543394A (en) * | 2013-10-27 | 2014-01-29 | 华北电力大学（保定） | Discharge ultraviolet imaging quantization parameter extraction method of high-voltage electric equipment |
| CN106503716A (en) * | 2016-09-13 | 2017-03-15 | 中国电力科学研究院 | A kind of safety cap recognition methods that is extracted based on color and contour feature and system |
| US20200020114A1 (en) * | 2017-04-25 | 2020-01-16 | Continental Automotive France | Image-processing method for removing light zones |
| CN107505546A (en) * | 2017-08-25 | 2017-12-22 | 国家电网公司 | A kind of method that corona discharge is monitored using ultraviolet imager |
| CN108961247A (en) * | 2018-07-10 | 2018-12-07 | 北京环境特性研究所 | Section insulator damage diagnostic system and method based on arc image detection |
| CN110569717A (en) * | 2019-07-26 | 2019-12-13 | 深圳供电局有限公司 | partial discharge detection method, device, system, equipment and readable storage medium |
| CN110930329A (en) * | 2019-11-20 | 2020-03-27 | 维沃移动通信有限公司 | Starry sky image processing method and device |
| CN111951247A (en) * | 2020-08-12 | 2020-11-17 | 国网江苏省电力有限公司电力科学研究院 | Power equipment ultraviolet image diagnosis method and system |
| CN112001327A (en) * | 2020-08-25 | 2020-11-27 | 全球能源互联网研究院有限公司 | Valve hall equipment fault identification method and system |
| CN112036320A (en) * | 2020-09-07 | 2020-12-04 | 华北电力大学（保定） | Partial discharge state identification method and device, discharge simulator and identification equipment |
| CN112288691A (en) * | 2020-10-16 | 2021-01-29 | 国电大渡河枕头坝发电有限公司 | Method for detecting water drops in hydraulic power plant based on image processing |
| CN112351247A (en) * | 2020-10-16 | 2021-02-09 | 国电大渡河枕头坝发电有限公司 | Electro-optical flash detection method in hydraulic power plant based on image processing |
| CN112801949A (en) * | 2021-01-15 | 2021-05-14 | 国网江苏省电力有限公司电力科学研究院 | Method and device for determining discharge area in ultraviolet imaging detection technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105956618B (en) | Converter steelmaking blowing state identification system and method based on image dynamic and static characteristics | |
| JP6305171B2 (en) | How to detect objects in a scene | |
| CN106886216B (en) | Robot automatic tracking method and system based on RGBD face detection | |
| CN110033431B (en) | Non-contact detection device and detection method for detecting corrosion area on surface of steel bridge | |
| CN110910350B (en) | Nut loosening detection method for wind power tower cylinder | |
| EP3376433B1 (en) | Image processing apparatus, image processing method, and image processing program | |
| US11200681B2 (en) | Motion detection method and motion detection system with low computational complexity and high detection accuracy | |
| CN113920097A (en) | Power equipment state detection method and system based on multi-source image | |
| CN116797977A (en) | Method and device for identifying dynamic target of inspection robot and measuring temperature and storage medium | |
| Afifah et al. | Hotspot detection in photovoltaic module using Otsu thresholding method | |
| CN116703895B (en) | Small sample 3D visual detection method and system based on generation countermeasure network | |
| KR101779040B1 (en) | Method and apparatus for extracting panel area from thermal infrared images of photovoltaic array | |
| CN113191313A (en) | Video stream discharge identification method and device based on hydraulic power plant and computer equipment | |
| CN116310274A (en) | State evaluation method for power transmission and transformation equipment | |
| CN115643471A (en) | Infrared thermal imaging detection system for power equipment | |
| CN112255141B (en) | Thermal imaging gas monitoring system | |
| KR20150033047A (en) | Method and Apparatus for Preprocessing Image for Detecting Objects | |
| CN112651276A (en) | Power transmission channel early warning system based on double-light fusion and early warning method thereof | |
| JP2008040724A (en) | Image processing device and image processing method | |
| Xiaoxiao et al. | A new method of digital number recognition for substation inspection robot | |
| TWI793901B (en) | Smoke detection system and smoke detection method | |
| CN213241250U (en) | Miner safety helmet detection system | |
| CN117333675B (en) | Monitoring and early warning method and system for GIS expansion joint | |
| CN114792417B (en) | Model training method, image recognition method, device, equipment and storage medium | |
| JP2010097289A (en) | Moving object tracking device |
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 |