CN111586356B - Violation monitoring method, device and system, electronic equipment and storage medium - Google Patents
Violation monitoring method, device and system, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN111586356B CN111586356B CN202010383391.5A CN202010383391A CN111586356B CN 111586356 B CN111586356 B CN 111586356B CN 202010383391 A CN202010383391 A CN 202010383391A CN 111586356 B CN111586356 B CN 111586356B
- Authority
- CN
- China
- Prior art keywords
- video frame
- target object
- position area
- video
- monitoring
- 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.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 272
- 238000000034 method Methods 0.000 title claims abstract description 61
- 230000006399 behavior Effects 0.000 claims description 64
- 238000004891 communication Methods 0.000 claims description 21
- 238000001514 detection method Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 13
- 230000009471 action Effects 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 4
- 238000012806 monitoring device Methods 0.000 abstract description 4
- 230000008859 change Effects 0.000 description 15
- 230000008569 process Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 238000003708 edge detection Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000005530 etching Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
- Alarm Systems (AREA)
Abstract
The embodiment of the invention provides a video-based violation monitoring method, a video-based violation monitoring device, a video-based violation monitoring system, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring a current monitoring video frame; the current monitoring video frame is: monitoring video frames shot at present in a target monitoring scene; performing image monitoring on the current monitoring video frame, and judging whether the current monitoring video frame contains a human body image; if the current monitoring video frame contains a human body image, extracting a position area of a feature point of a preset part of the human body image; obtaining a position area of a target object in a prestored reference video frame when the target object does not bear an object, wherein the reference video frame is obtained from a historical monitoring video frame, and the target object is a part bearing the object; and judging whether the current monitoring video has an illegal behavior or not based on whether the position area of the feature point is located in the position area of the target object when the target object does not bear the object. The embodiment of the invention can improve the accuracy of monitoring the illegal behavior.
Description
Technical Field
The invention relates to the technical field of video monitoring, in particular to a method, a device and a system for monitoring violation behaviors based on videos, electronic equipment and a storage medium.
Background
At present, in order to realize safe production, monitoring equipment is installed in a production scene in many industries so as to monitor illegal behaviors of personnel. For example: in express delivery or commodity circulation trade, be provided with the transportation center. A plurality of conveying belts are arranged in the transfer center to convey the packages in different areas for sorting the packages. During the sorting process, if the operators have illegal behaviors such as crossing or walking on the conveyor belt, the behaviors can cause the safety hazard of the operators. Therefore, it is necessary to monitor violations such as crossing or walking on the conveyor.
In the prior art, a current monitoring video in a transit center is acquired, edges of a conveyor belt and human body images in a video frame are monitored from a current monitoring video frame, whether the human body images of the frame are located in a plurality of detected edges is judged, and whether violation behaviors of operators occur in the video frame is further determined.
Because the conveyor belt is in the process of conveying the parcels, the placed parcels can bring certain interference to the edge detection of the conveyor belt. For example, when a parcel is placed on the edge area of the conveyor belt and a part of the parcel exceeds the conveyor belt, the detected edge of the conveyor belt will exceed the actual edge of the conveyor belt, and it may be determined that the human body image overlaps the parcel placed on the conveyor belt, and thus the violation occurs.
Therefore, in the method for judging whether the human body image has the violation behavior in the prior art, the condition that the monitoring result is not accurate enough can occur.
Disclosure of Invention
The embodiment of the invention aims to provide a video-based violation monitoring method, device and system, electronic equipment and a storage medium, so as to improve the accuracy of violation monitoring. The specific technical scheme is as follows:
in a first aspect of the present invention, there is provided a method for monitoring violation based on video, where the method includes:
acquiring a current monitoring video frame; the current monitoring video frame is as follows: monitoring video frames shot at present in a target monitoring scene;
performing image monitoring on the current monitoring video frame, and judging whether the current monitoring video frame contains a human body image;
if the current monitoring video frame contains a human body image, extracting a position area of a feature point of a preset part of the human body image;
obtaining a position area of a target object in a prestored reference video frame when the target object does not bear an object, wherein the reference video frame is obtained from a historical monitoring video frame, and the target object is a part bearing the object;
and judging whether the violation behavior exists in the current monitoring video or not based on whether the position area of the feature point is located in the position area of the target object when the target object does not bear the object.
In a second aspect of the present invention, there is also provided a video-based violation monitoring apparatus, including:
the current monitoring video frame acquisition module is used for acquiring a current monitoring video frame; the current monitoring video frame is as follows: monitoring video frames shot at present in a target monitoring scene;
the human body image judging module is used for carrying out image monitoring on the current monitoring video frame and judging whether the current monitoring video frame contains a human body image;
a feature point position region extraction module, configured to extract a position region of a feature point of a preset portion of the human body image if the current monitoring video frame includes the human body image;
a first target object position area obtaining module, configured to obtain a position area of a target object in a pre-stored reference video frame when the target object does not carry an object, where the reference video frame is obtained from a historical monitoring video frame, and the target object is a component carrying the object;
and the illegal behavior judging module is used for judging whether the illegal behavior exists in the current monitoring video or not based on whether the position area of the characteristic point is positioned in the position area of the target object when the target object does not bear the object.
In another aspect of the present invention, there is also provided a video-based violation monitoring system, including: the system comprises video acquisition equipment and a monitoring host;
the video acquisition equipment is arranged in a target monitoring scene and is used for shooting a monitoring video of the target monitoring scene;
the monitoring host is in communication connection with the video acquisition equipment and is used for any one of the above video-based violation monitoring methods.
In another aspect of the present invention, there is also provided an electronic device, including a processor, a communication interface, a memory and a communication bus, where the processor, the communication interface, and the memory complete communication with each other through the communication bus;
a memory for storing a computer program;
and the processor is used for realizing any one of the above illegal behavior monitoring methods based on the video when executing the program stored in the memory.
In yet another aspect of the present invention, there is also provided a computer-readable storage medium, in which a computer program is stored, and the computer program, when executed by a processor, implements any one of the above-mentioned video-based violation monitoring methods.
In yet another aspect of the present invention, there is also provided a computer program product containing instructions which, when run on a computer, cause the computer to perform any of the above-described video-based violation monitoring methods.
According to the method, the device, the electronic equipment and the storage medium for monitoring the illegal behaviors based on the video, the current monitoring video frame is obtained, if the current monitoring video frame comprises a human body image, the position area of the feature point of the preset part of the human body image is extracted, the position area of a target object in a prestored reference video frame when the target object does not bear an object is obtained, whether the illegal behaviors exist in the current monitoring video is judged based on whether the position area of the feature point is located in the position area of the target object when the target object does not bear the object or not, namely, when the position area of the feature point is located in the position area of the target object when the target object does not bear the object, the illegal behaviors exist in the current monitoring video is judged. The position area of the target object which is stored in advance when the object is not carried is the same as the actual position area of the target object, and the target object is not influenced by other objects, so that whether the violation occurs in the current monitoring video or not is judged by using the position area, and the accuracy of monitoring the violation can be improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below.
FIG. 1 is a schematic view of a positional relationship of a conveyor belt, an object and a human body;
fig. 2 is a first flowchart of a video-based violation monitoring method according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating a process of pre-saving a location area of a target object in a reference video frame according to an embodiment of the present invention;
FIG. 4 is a schematic flow chart of S301 in the embodiment shown in FIG. 3;
fig. 5 is a second flowchart of a video-based violation monitoring method according to an embodiment of the present invention;
fig. 6 is a third flowchart illustrating a video-based violation monitoring method according to an embodiment of the present invention;
FIG. 7 is a schematic flow chart of S203 in the embodiment shown in FIG. 2;
FIG. 8 is a schematic flow chart of S701 in the embodiment shown in FIG. 7;
fig. 9 is a fourth flowchart illustrating a video-based violation monitoring method according to an embodiment of the present invention;
fig. 10 is a schematic structural diagram of a video-based violation monitoring apparatus according to an embodiment of the present invention;
fig. 11 is a schematic structural diagram of a video-based violation monitoring system according to an embodiment of the present invention;
fig. 12 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention.
In the prior art, after a current monitoring video frame in a transit center is acquired, edges of a conveyor belt and human body images in the video frame are identified from the current monitoring video frame, whether the human body images of the frame are located in a plurality of detected edges is judged, and whether violation behaviors of operators occur in the video frame is further determined. Because the conveyor belt is in the process of conveying the parcels, the placed parcels can bring certain interference to the edge detection of the conveyor belt. As shown in fig. 1, when a parcel is placed in the edge area of the conveyor belt and a part of the parcel exceeds the conveyor belt, the detected edge of the conveyor belt will exceed the actual edge of the conveyor belt, and the human body image and the parcel may be overlapped, and it is determined that an illegal action occurs.
In view of this, the video-based violation monitoring method provided in the embodiment of the present invention is, in general, applied to a monitoring host of a video-based violation monitoring system, and after extracting a position region of a feature point of a preset portion of a human body image in a current video frame to be processed, obtains a position region of a target object in a reference video frame, which is stored in advance, when the target object does not carry an object, and determines whether a violation occurs in a current monitoring video based on whether the position region of the feature point is located in the position region of the target object when the target object does not carry the object. The position area of the target object which is stored in advance when the object is not carried is the same as the actual position area of the target object, and the target object is not influenced by other objects, so that whether the violation occurs in the current monitoring video or not is judged by using the position area, and the accuracy of monitoring the violation can be improved.
As shown in fig. 2, the present invention provides a video-based violation monitoring method, which may include:
s201, acquiring a current monitoring video frame.
The current surveillance video frame may be: for a surveillance video frame currently shot in a target surveillance scene, the target scene can be a transit center in the logistics industry or the express industry, and the currently detected video frame can be obtained in real time, namely, one video frame is obtained as the current surveillance video frame when one video frame is shot.
S202, image monitoring is carried out on the current monitoring video frame, and whether the current monitoring video frame contains a human body image or not is judged.
In the embodiment of the invention, whether the violation behaviors such as that an operator crosses a target object or walks on the target object exist in the current monitoring video frame needs to be judged. Therefore, after the current monitoring video frame is acquired, image monitoring can be performed on the current monitoring video frame, whether the current monitoring video frame contains a human body image or not is judged, and if the current monitoring video frame contains the human body image and the current monitoring video frame possibly has an illegal behavior, whether the current monitoring video frame has the illegal behavior or not can be continuously judged according to the human body image. If the human body image is not contained, the current monitoring video frame cannot have illegal behaviors, so that the next monitoring video frame can be obtained without subsequent processing, and the image monitoring is carried out on the next monitoring video frame.
The current video frame to be monitored can be subjected to image monitoring by adopting the existing general object detection model to obtain an image monitoring result, and the image monitoring result can comprise: the position areas of a plurality of rectangular frames, and the classification of each rectangular frame. The position area of the rectangular frame may be represented by the coordinate position of the center point of the rectangular frame, and the length and width of the rectangular frame. The classification of the rectangular box may be: and a human body, an object and the like can know whether the current monitoring video frame contains a human body image or not according to the classification in the obtained image monitoring result.
S203, if the current monitoring video frame contains the human body image, extracting the position area of the feature point of the preset part of the human body image.
If the current monitoring video frame contains the human body image, the position area of the feature point of the preset part of the human body image can be extracted. Since it is necessary to detect whether there is an illegal behavior that an operator crosses a target object or walks on the target object in the current monitoring video frame, the preset portion may be a foot portion in the human body image. That is, the position areas of a plurality of feature points of the foot in the human body image may be acquired, for example, the position areas of 2-4 feature points per foot may be acquired, for example, the position areas of two feature points of the center of the toe and the center of the heel may be acquired, or the position areas of four feature points of the center of the toe, the center of the heel, the center of the inner side of the sole, and the center of the outer side of the sole may be acquired. Further, the location area may refer to a coordinate location of the feature point.
S204, obtaining the position area of the target object in the prestored reference video frame when the target object does not bear the object.
In an embodiment of the present invention, the target object may be a component carrying an object, which may be used for transporting the object and is in motion during the transportation of the object, for example, a conveyor belt in a transit center, a transport cart, or another component that may be used for transporting the object.
The reference video frame may be obtained from a plurality of historical surveillance video frames, which have been obtained in advance before the current surveillance video frame is obtained, and thus, the reference video frame may be obtained from the plurality of historical surveillance video frames. Since the position area of the target object in the reference video frame when the object is not carried needs to be obtained, it can be understood that the target object in the reference video frame does not carry the object, and the obtained position area can be a standard position area of the target object, and the position area is more accurate because the object is not carried thereon.
Specifically, a video frame not carrying an object in the target object can be monitored from the historical monitoring video frames by a manual monitoring method, and is used as a reference video frame, and then the monitoring host acquires the reference video frame, so that the position area where the target object does not carry the object is manually framed. The method for obtaining the reference video frame may also be a method for calculating a video scene variation between two video frames of a preset interval duration in the historical surveillance video, and obtaining the reference video frame by using whether the video scene variation is smaller than a preset variation threshold, where the method for obtaining the reference video frame is described in detail below.
The target object is usually a polygon in the reference video frame, and therefore, the shape of the position area of the target object when the target object is not carrying the object may also be a polygon, and the coordinate positions of a plurality of vertices of the position area may be obtained while the position area of the target object in the reference video frame is obtained.
S205, judging whether the current monitoring video has an illegal behavior based on whether the position area of the feature point is located in the position area of the target object when the target object does not bear the object.
Whether the illegal behavior exists in the current monitoring video can be judged based on whether the position area of the feature point is located in the position area of the target object when the target object does not bear the object, and when the position area of the feature point is located in the position area of the target object when the target object does not bear the object, the illegal behavior exists, namely, the illegal behavior that an operator crosses the target object or walks on the target object exists. Otherwise, no violation is present.
The video-based violation monitoring method provided by the embodiment of the invention comprises the steps of obtaining a current monitoring video frame, extracting a position area of a feature point of a preset part of a human body image if the current monitoring video frame contains the human body image, obtaining a position area of a target object in a prestored reference video frame when the target object does not bear an object, and judging whether violation behaviors exist in the current monitoring video based on whether the position area of the feature point is located in the position area of the target object when the target object does not bear the object, namely judging that the violation behaviors exist in the current monitoring video when the position area of the feature point is located in the position area of the target object when the target object does not bear the object. The position area of the target object which is stored in advance when the object is not carried is the same as the actual position area of the target object, and the target object is not influenced by other objects, so that whether the violation occurs in the current monitoring video or not is judged by using the position area, and the accuracy of monitoring the violation can be improved.
As an optional implementation manner of the embodiment of the present invention, as shown in fig. 3, the position area of the target object in the reference video frame may be pre-saved by adopting the following steps:
s301, detecting the video scene variation between two video frames with preset interval duration in the historical monitoring video.
The preset interval duration may be a preset duration, and the preset interval duration may be determined according to the movement speed of the target object during object transportation and the interval duration between every two adjacent video frames in the historical monitoring video. For example, when the moving speed of the target object is slow, the amount of motion is small in the interval period between two adjacent video frames, and the preset interval period may be set to a large value. Of course, the preset interval duration may also be set as the interval duration between two video frames, that is, the video scene variation between two adjacent video frames in the historical surveillance video is detected.
And S302, taking the video frame with the video scene variation smaller than the preset variation threshold value as a reference video frame, acquiring a position area where a target object in the reference video frame is located, and storing the position area as the position area when the target object does not bear the object.
Since the target object carries an object during the transportation of the object, the video frames are different, that is, the amount of change in the video scene between the two video frames is greater than 0, and the amount of change in the video scene between the two video frames is smaller when the target object carries fewer objects, the preset change threshold can be set to a smaller value. When the video scene variation is smaller than the preset variation threshold, it indicates that neither of the target objects in the two video frames carries an object, or the carried objects are fewer, one of the two video frames may be used as a reference video frame.
After the reference video frame is determined, the position area where the target object is located in the reference video frame may be obtained and stored as the position area when the target object does not carry an object. The existing example segmentation model can be adopted to segment the reference video frame to obtain the position area of the target object. An example segmentation model may be, for example, Mask RCNN (Mask Region-conditional Neural Networks). In the process of obtaining the position area of the target object, a background or other objects with colors close to the color of the target object may exist at the edge of the target object, so that a black hole exists in the obtained position area, or burrs exist at the edge of the position area, and therefore, after the position area of the target object is obtained, the position area may be subjected to expansion processing to fill the black hole therein. The location area may also be subjected to an etching operation to remove burrs therefrom.
When a target object bears more objects, the video scene variation between two video frames of the preset interval duration is larger in the moving process of the target object, and the video frame with the video scene variation smaller than the preset variation threshold indicates that the target object bears fewer objects or does not bear objects, so that the position area of the target object can be more accurate by adopting the steps S301 to S303 in the embodiment of the present invention.
As an optional implementation manner of the embodiment of the present invention, as shown in fig. 4, in step S301 of the embodiment shown in fig. 3, the step of detecting a video scene change amount between two video frames of a preset interval duration in a historical surveillance video may include:
s401, performing motion detection on the two video frames by adopting a preset motion detection method to obtain a motion area in the video frames.
The motion detection may be performed on the two video frames by using a preset motion detection method to obtain a motion region in the video frames, and specifically, the motion detection may be performed on the two video frames by using a time difference method to obtain the motion region in the video frames. Since the motion region may be a polygon, the coordinate positions of a plurality of vertices of the motion region may be acquired. In addition, after completing the motion detection of the two video frames, a comparison thermal map of the two video frames may be obtained, where the comparison thermal map includes a motion region and a non-motion region, and pixel values of pixel points in the two different regions may be different, where the pixel value of the pixel point in the motion region may be 255, and the pixel value of the pixel point in the non-motion region may be 0.
S402, calculating the ratio of the number of the pixel points in the motion area to the number of all the pixel points in the video frame as the video scene variation.
The number of the pixels in the motion area can be counted, the number of all the pixels in the video frame can be counted, the ratio of the number of the pixels in the motion area to the number of all the pixels can be calculated, and the ratio is used as the video scene variable quantity of the two video frames. In the embodiment of the invention, the method for calculating the variable quantity of the two video scenes is simpler.
As an optional implementation manner of the embodiment of the present invention, as shown in fig. 5, before the step of obtaining a position area of a target object in a pre-stored reference video frame when the target object does not carry an object in step S204 of the embodiment flowchart shown in fig. 2, the method for monitoring an illegal behavior based on a video according to the embodiment of the present invention may further include:
s501, acquiring the current position area of the target object in the current monitoring video frame.
After the current surveillance video frame is acquired, a current location area of the target object in the current surveillance video frame may be acquired. The current surveillance video frame can be segmented by adopting the existing instance segmentation model to obtain the current position area of the target object. And then, expanding and corroding the current position area to fill the black hole and remove the burrs in the current position area to obtain the expanded and corroded current position area.
S502, the position area of the target object in the reference video frame and the amount of position change between the current position areas are calculated.
The position area of the target object in the reference video frame can be compared with the current position area, and if the difference between the position areas is larger, the monitoring visual angle of the monitoring equipment of the transit center is possibly changed. In comparing the position area of the target object in the reference video frame with the current position area, a position change amount between the position area of the target object in the reference video frame and the current position area may be calculated, and the position change amount may be a ratio of an intersection to a union between the position area of the target object in the reference video frame and the current position area. Specifically, when the position variation is calculated, the intersection between the position region of the target object in the reference video frame and the current position region, that is, the number of pixels of the intersection between the position region and the current position region may be calculated first; calculating a union set between the position area of the target object in the reference video frame and the current position area, namely the number of pixel points in a combined area formed by combining the two position areas; then, the ratio of the number of the intersected pixels to the number of the pixels in the merging area is used as the position variation.
S503, receiving a next frame of video frame when the position variation is greater than the preset position variation threshold.
A preset position change threshold may be preset, and the preset position change threshold may be set according to a position change amount of a position area of a target object in two video frames before and after a change in the monitoring angle of view is obtained under the condition that the transfer center scene is the same. Specifically, the preset position change threshold may be set as follows: and in the same transfer center, the target object does not bear an object, the position areas of the target object of the video frames under two different monitoring visual angles are obtained, the position variation between the two video frames is calculated, and the calculated position variation is used as a preset position variation threshold.
Under the condition that the position variation is larger than the preset position variation threshold, it is indicated that the monitoring view angle of the transit center may be changed, and the position area of the target object in the prestored reference video frame when the target object does not bear the object needs to be updated, so that the situation that whether the illegal behavior judgment is wrong exists in the current video frame due to the fact that the position area of the target object of the reference video frame determined before the change is still used after the monitoring view angle is changed is avoided.
In this case, the next frame of video frame may be received for calculation of the video scene change amount with the current monitoring video frame.
S504, calculating the video scene variable quantity between the next frame of video frame and the current monitoring video frame.
Referring to the method for calculating the video scene variation in steps S401 to S402 in the embodiment shown in fig. 4, the video scene variation between the current monitored video frame and the next frame of video frame may be calculated, which is not described again in this embodiment of the present invention.
And S505, taking the video frame with the video scene variation smaller than the preset variation threshold value as a reference video frame, acquiring a position area where the target object in the reference video frame is located, and storing the position area as the position area when the updated target object does not bear the object.
If the video scene variation between the current monitoring video frame and the next frame of video frame is larger than or equal to the preset variation threshold, continuously acquiring the second frame of video frame after the current monitoring video frame, calculating the video scene variation between the next frame of video frame and the second frame of video frame, judging whether the video scene variation is smaller than the preset variation threshold, and so on until the video scene variation is smaller than the preset variation threshold, taking the video frame smaller than the variation threshold as a reference video frame, and acquiring a position area where a target object in the reference video frame is located, and storing the position area as the position area when the updated target object does not bear the object.
As an optional implementation manner of the embodiment of the present invention, as shown in fig. 6, the method for monitoring violation based on video according to the embodiment of the present invention may further include:
s601, when the area of the current position area is smaller than that of the position area of the target object in the reference video frame and the position variation between the next frame of video frame and the current monitoring video frame is smaller than a preset position variation threshold value, the current position area is used as the position area when the updated target object does not bear the object to be stored.
On the basis that the monitoring visual angle is not changed when the position variation between the next frame of video frame and the current monitoring video frame is smaller than the preset position variation threshold, if the area of the current position area is smaller than the area of the position area of the target object in the reference video frame, the current position area is more accurate than the position area of the target object in the reference video frame, and therefore the current position area can be used as the updated position area when the target object does not bear the object to be stored.
As an optional implementation manner of the embodiment of the present invention, as shown in fig. 7, in step S203 of the embodiment shown in fig. 2, if the current monitoring video frame includes a human body image, the step of extracting a position region of a feature point of a preset part of the human body image may include:
s701, if the current monitoring video frame contains the human body image, the position area of the human body image is obtained.
After the general object detection model performs image monitoring on the current video frame to be monitored, the image monitoring result may include: the position areas of a plurality of rectangular frames, and the classification of each rectangular frame. The classification of the rectangular box may be: and a human body, an object and the like can know whether the current monitoring video frame contains a human body image or not according to the classification in the obtained detection result. Therefore, if the current monitoring video includes the human body image, the position area of the rectangular frame classified as the human body can be obtained from the image monitoring result, and the position area is the position area of the human body image.
S702, determining whether the suspected violation exists in the current monitoring video frame according to the coincidence degree between the position area of the human body image and the position area of the target object in the reference video frame.
After the position area of the human body image is obtained, whether suspected violation behaviors exist in the current monitoring video frame can be determined by using the coordinate positions of all vertexes in the position area and the coincidence degree between the position areas of the target objects in the reference video frame. When the coincidence degree between the position area of the human body image and the position area of the target object in the reference video frame is high, the suspected violation behavior may exist in the current monitoring video frame.
And S703, under the condition that the suspected violation behavior exists in the current monitoring video frame, extracting the position area of the feature point of the preset part of the human body image.
If the suspected violation exists in the current monitoring video frame, then the position area of the feature point of the preset part of the human body image can be extracted, so that whether the violation exists in the video to be processed or not can be judged conveniently according to whether the position area is located in the position area of the target object in the reference video frame or not.
In the embodiment of the invention, whether the suspected violation behavior exists in the current video frame to be processed is judged by acquiring the human body image in the current video frame to be processed and utilizing the contact ratio between the human body image and the position area of the target object in the reference video frame, the position area of the feature point of the preset part of the human body image is extracted under the condition that the suspected violation behavior exists, and whether the violation behavior exists in the current monitoring video frame is further judged according to the position area of the feature point. Therefore, the condition that the illegal behavior judgment is wrong due to the fact that the characteristic point detection is wrong in the process of directly judging whether the illegal behavior exists by adopting the characteristic points can be avoided, and the accuracy of judging whether the illegal behavior exists in the video to be processed can be further improved.
As an optional implementation manner of the embodiment of the present invention, as shown in fig. 8, in step S701 of the embodiment flowchart shown in fig. 7, the step of determining whether there is a suspected violation in the current surveillance video according to a coincidence ratio between the position region of the human body image and the position region of the target object in the reference video frame may include:
s801, determining a position area of the human body image and a superposition area between the position area of the target object in the reference video frame.
The coordinate position of each vertex of the position area of the human body image and the coordinate position of each vertex of the position area of the target object in the reference video frame can be calculated according to the coordinate positions of the vertices of the position area of the human body image and the coordinate positions of the vertices of the position area of the target object in the reference video frame, and the coordinate positions of the vertices of the overlapping area can be obtained.
S802, calculating the area of the overlapped area.
The area of the overlap region can be calculated from the coordinate position of each vertex in the overlap region. After the coordinate position is obtained, the length of each edge in the overlapping area can be calculated by using the pixel points in the overlapping area, and the area of the overlapping area can be calculated by using the length of each edge.
And S803, determining that the suspected violation exists in the current monitoring video under the condition that the area of the overlapping area is larger than the preset area threshold.
The preset area threshold value can be determined according to the condition that a half area of the human body image coincides with the target object under a fixed monitoring visual angle. In the embodiment of the invention, the method for determining whether the suspected violation exists in the current monitoring video is simpler.
As an optional implementation manner of the embodiment of the present invention, as shown in fig. 9, in step S205 of the embodiment shown in fig. 2, based on whether the location area of the feature point is located in the location area of the target object when the target object does not carry an object, the step of determining whether there is an illegal action in the current monitoring video may include:
s901, judging whether the position area of the characteristic point is located in the position area of the target object when the target object does not bear the object.
The method comprises the steps of judging whether a position area of a feature point of a preset part of a human body image in a current monitoring video frame is located in a position area of a target object when the target object does not bear an object, if so, indicating that possible illegal behaviors exist in the current monitoring video frame, and the possibility that the illegal behaviors exist in the current monitoring video is high. However, in order to further improve the accuracy of monitoring the illegal behavior in the current monitoring video, a plurality of video frames after the current monitoring video frame in the current monitoring video may be monitored to comprehensively determine whether the illegal behavior exists in the current monitoring video. If not, it indicates that there is no violation in the current surveillance video frame, and step S201 of the embodiment shown in fig. 2 is executed.
And S902, if so, acquiring the position area of the feature point of the preset part of the human body image in each video frame of the preset number of video frames.
If so, a preset number of video frames can be obtained, the preset number of video frames can be video frames which are adjacent to the current monitoring video frame in the current monitoring video, and for each video frame in the preset number of video frames, the position area of the feature point of the preset part of the human body image in the video frame can be obtained.
And S903, judging whether the position area of the characteristic point in each video frame in the preset number of video frames is located in the position area of the target object in the reference video frame when the object is not carried.
The method can judge whether the position area of the feature point in each video frame is positioned in the position area of the target object in the reference video frame when the object is not carried in the preset number of video frames.
And S904, calculating the ratio of the number of the video frames in which the position areas of the feature points are located in the position area of the target object in the reference video frame in the preset number of video frames to the preset number.
The number of video frames in which the position area of the feature point is located in the position area of the target object in the reference video frame in the preset number of video frames can be counted, and the ratio between the counted number and the preset number is calculated, so that whether the violation behavior exists in the current monitoring video or not can be determined by using whether the ratio is larger than a preset ratio threshold or not.
And S905, if the ratio is larger than a preset ratio threshold, the current monitoring video has violation.
The preset number and the preset proportion threshold value can be values preset according to experience, the preset proportion threshold value and the preset number can be determined according to the time length for an operator to cross a target object or walk in the target object, and if the calculated ratio is greater than the preset proportion threshold value, it is indicated that the current monitoring video has illegal behaviors.
In the embodiment of the present invention, the number of video frames in which the position area of the feature point is located in the position area of the target object in the reference video frame can be used, whether the ratio of the number of the video frames to the preset number is larger than a preset ratio threshold value or not is judged, whether the current monitoring video has violation behaviors or not is judged, because the current monitoring video frame is used for judging whether the video frame to be processed has the condition that the illegal action can cause the false detection, when the human body usually does the illegal action, the violation may last for a period of seconds or even minutes, which is longer than the interval between two video frames, and, therefore, whether the violation behavior exists in the current monitoring video can be judged by judging the ratio of the video frames with the violation behavior in the preset number of video frames, so that the method and the device can further improve the accuracy of violation behavior monitoring.
As an optional implementation manner of the embodiment of the present invention, the target monitoring scenario may be: a logistics transfer center; the target object may be: a conveyor belt used for conveying the packages in the logistics transfer center; the feature points of the preset portion may be: characteristic points of human feet.
An embodiment of the present invention provides a specific embodiment of a video-based violation monitoring device, which corresponds to the flow shown in fig. 2, and referring to fig. 10, fig. 10 is a schematic structural diagram of a video-based violation monitoring device according to an embodiment of the present invention, and may include:
a current surveillance video frame acquiring module 1001 configured to acquire a current surveillance video frame; the current monitoring video frame is: and monitoring video frames currently shot in the target monitoring scene.
The human body image determining module 1002 is configured to perform image monitoring on a current monitoring video frame, and determine whether the current monitoring video frame includes a human body image.
A feature point position region extraction module 1003, configured to extract a position region of a feature point of a preset part of a human body image if the current monitoring video frame includes the human body image.
A first target object position area obtaining module 1004, configured to obtain a position area of a target object in a pre-stored reference video frame when the target object does not carry an object, where the reference video frame is obtained from a historical monitoring video frame, and the target object is a component carrying an object.
And an illegal behavior determining module 1005, configured to determine whether an illegal behavior exists in the current monitoring video based on whether the position area of the feature point is located in the position area of the target object when the target object does not carry the object.
The video-based violation monitoring device provided by the embodiment of the invention extracts the position area of the feature point of the preset part of the human body image by acquiring the current monitoring video frame, if the current monitoring video frame contains the human body image, obtains the position area of the target object in the prestored reference video frame when the target object does not bear the object, and judges whether violation exists in the current monitoring video based on whether the position area of the feature point is located in the position area of the target object when the target object does not bear the object, namely, judges that the violation exists in the current monitoring video when the position area of the feature point is located in the position area of the target object when the target object does not bear the object. The position area of the target object which is stored in advance when the object is not carried is the same as the actual position area of the target object, and the target object is not influenced by other objects, so that whether the violation occurs in the current monitoring video or not is judged by using the position area, and the accuracy of monitoring the violation can be improved.
As an optional implementation manner of the embodiment of the present invention, the device for monitoring violation behaviors based on video according to the embodiment of the present invention may further include:
and the video scene variable quantity detection module is used for detecting the video scene variable quantity between two video frames with preset interval duration in the historical monitoring video.
And the second target object position area acquisition module is used for taking the video frame with the video scene variation smaller than the preset variation threshold value as a reference video frame, acquiring a position area where the target object in the reference video frame is located, and storing the position area as the position area when the target object does not bear the object.
As an optional implementation manner of the embodiment of the present invention, the video scene change amount detection module may include:
and the motion detection submodule is used for performing motion detection on the two video frames by adopting a preset motion detection method to obtain a motion area in the video frames.
And the video scene variable quantity calculating submodule is used for calculating the ratio of the number of the pixel points in the motion area to the number of all the pixel points in the video frame to be used as the video scene variable quantity.
As an optional implementation manner of the embodiment of the present invention, the device for monitoring violation behaviors based on video according to the embodiment of the present invention may further include:
and the current position area acquisition module is used for acquiring the current position area of the target object in the current monitoring video frame.
And the position variation acquiring module is used for calculating the position areas of the target objects in the reference video frame and the position variation between the current position areas, and the position variation is the ratio of intersection and union between the position areas of the target objects in the reference video frame and the current position areas.
And the video frame receiving module is used for receiving the next frame of video frame under the condition that the position variation is larger than the preset position variation threshold.
And the video scene variable quantity calculating module is used for calculating the video scene variable quantity between the next frame of video frame and the current monitoring video frame and between the two video frames.
And the third target object position area acquisition module is used for taking the video frame with the video scene variation smaller than the preset variation threshold as a reference video frame, acquiring a position area where the target object in the reference video frame is located, and storing the position area as the position area when the updated target object does not bear the object.
As an optional implementation manner of the embodiment of the present invention, the device for monitoring an illegal behavior based on a video according to the embodiment of the present invention may further include:
and the position area updating module is used for taking the current position area as the position area for storing the updated target object when the object is not carried by the target object under the condition that the area of the current position area is smaller than that of the position area of the target object in the reference video frame and the position variation between the next frame of video frame and the current monitoring video frame is smaller than a preset position variation threshold value.
As an optional implementation manner of the embodiment of the present invention, the feature point position area extracting module 1003 may include:
and the human body image position area obtaining submodule is used for obtaining the position area of the human body image if the current monitoring video frame contains the human body image.
And the suspected violation behavior determining submodule is used for determining whether the suspected violation behavior exists in the current monitoring video according to the coincidence degree between the position area of the human body image and the position area of the target object in the reference video frame.
And the characteristic point position area extraction submodule is used for extracting the position area of the characteristic point of the preset part of the human body image under the condition that the suspected violation behavior exists in the current monitoring video.
As an optional implementation manner of the embodiment of the present invention, the suspected violation determining sub-module may include:
and the coincidence region determining unit is used for determining the coincidence region between the position region of the human body image and the position region of the target object in the reference video frame.
And the area calculation unit is used for calculating the area of the overlapped area.
And the suspected violation determining unit is used for determining that the suspected violation exists in the current monitoring video under the condition that the area of the overlapping area is larger than the preset area threshold value in violation.
As an optional implementation manner of the embodiment of the present invention, the violation behavior determining module 1005 may include:
and the first position area judgment submodule is used for judging whether the position area of the characteristic point is positioned in the position area of the target object when the target object does not bear the object.
And the characteristic point position area obtaining submodule is used for obtaining the position area of the characteristic point of the preset part of the human body image in the video frame aiming at each video frame in the preset number of video frames if the characteristic point position area is in the preset position, and the preset number of video frames are the video frames which are adjacent to the current monitoring video frame and behind the current monitoring video frame in the current monitoring video.
And the second position area judgment submodule is used for judging whether the position area of the characteristic point in each video frame is positioned in the position area of the target object in the reference video frame when the object is not carried in the preset number of video frames.
And the quantity ratio calculation submodule is used for calculating the ratio between the quantity of the video frames in which the position areas of the characteristic points are positioned in the position area of the target object in the reference video frame and the preset quantity in the preset quantity of video frames.
And the violation behavior determining submodule is used for determining that the violation behavior exists in the current monitoring video if the ratio is larger than the preset ratio threshold.
As shown in fig. 11, an embodiment of the present invention further provides a video-based violation monitoring system, which includes: video acquisition equipment and monitoring host computer.
The video capture device 1101 is installed in the target monitoring scene and is used for shooting a monitoring video of the target monitoring scene. For example, the video capture device 1101 may be a camera installed in a transit center, and the camera may adjust an angle according to a shooting requirement, that is, shooting a monitoring video of a target monitoring scene at different viewing angles.
The monitoring host 1102 is communicatively connected to the video capture device 1101, and can obtain a current monitoring video from the video capture device 1101, so as to perform the following steps:
acquiring a current monitoring video frame; the current monitoring video frame is: and monitoring video frames currently shot in the target monitoring scene.
And monitoring the image of the current monitoring video frame, and judging whether the current monitoring video frame contains a human body image.
And if the current monitoring video frame contains the human body image, extracting the position area of the feature point of the preset part of the human body image.
And obtaining the position area of a target object in a prestored reference video frame when the target object does not bear the object, wherein the reference video frame is obtained from the historical monitoring video frame, and the target object is a part bearing the object.
And judging whether the current monitoring video has an illegal behavior or not based on whether the position area of the feature point is located in the position area of the target object when the target object does not bear the object.
An embodiment of the present invention further provides an electronic device, as shown in fig. 12, including a processor 1201, a communication interface 1202, a memory 1203, and a communication bus 1204, where the processor 1201, the communication interface 1202, and the memory 1203 complete mutual communication through the communication bus 1204.
A memory 1203 is used for storing the computer program.
The processor 1201 is configured to implement the following steps when executing the program stored in the memory 1203:
acquiring a current monitoring video frame; the current monitoring video frame is: and monitoring video frames currently shot in the target monitoring scene.
And monitoring the image of the current monitoring video frame, and judging whether the current monitoring video frame contains a human body image.
And if the current monitoring video frame contains the human body image, extracting the position area of the feature point of the preset part of the human body image.
And obtaining the position area of a target object in a prestored reference video frame when the target object does not bear the object, wherein the reference video frame is obtained from the historical monitoring video frame, and the target object is a part bearing the object.
And judging whether the current monitoring video has an illegal behavior or not based on whether the position area of the feature point is located in the position area of the target object when the target object does not bear the object.
The communication bus mentioned in the above terminal may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface is used for communication between the terminal and other equipment.
The Memory may include a Random Access Memory (RAM) or a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component.
In another embodiment of the present invention, a computer-readable storage medium is further provided, in which a computer program is stored, and the computer program, when executed by a processor, implements the video-based violation monitoring method according to any of the above embodiments.
In yet another embodiment, a computer program product containing instructions is provided, which when run on a computer, causes the computer to perform the video-based violation monitoring method of any of the above embodiments.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.
Claims (8)
1. A video-based violation monitoring method, the method comprising:
acquiring a current monitoring video frame; the current monitoring video frame is as follows: monitoring video frames shot at present in a target monitoring scene;
performing image monitoring on the current monitoring video frame, and judging whether the current monitoring video frame contains a human body image;
if the current monitoring video frame contains a human body image, extracting a position area of a feature point of a preset part of the human body image;
obtaining a position area of a target object in a prestored reference video frame when the target object does not bear an object, wherein the reference video frame is obtained from a historical monitoring video frame, and the target object is a part bearing the object;
judging whether the violation behavior exists in the current monitoring video or not based on whether the position area of the feature point is located in the position area of the target object when the target object does not bear the object or not;
the position area of the target object in the reference video frame is preserved in advance by adopting the following steps:
detecting the video scene variation between two video frames with preset interval duration in the historical monitoring video;
taking the video frame with the video scene variation smaller than a preset variation threshold value as a reference video frame, acquiring a position area where a target object in the reference video frame is located, and storing the position area as a position area when the target object does not bear the object;
before the step of obtaining the location area of the target object in the pre-saved reference video frame when the target object does not carry an object, the method further includes:
acquiring a current position area of a target object in the current monitoring video frame;
calculating a position area of a target object in the reference video frame and a position variation between the current position areas, wherein the position variation is a ratio of intersection and union between the position area of the target object in the reference video frame and the current position area;
receiving a next frame of video frame under the condition that the position variation is larger than a preset position variation threshold value;
calculating the video scene variable quantity between the next frame of video frame and the current monitoring video frame and between the two video frames;
and taking the video frame with the video scene variation smaller than the preset variation threshold value as a reference video frame, acquiring a position area where a target object in the reference video frame is located, and storing the position area as the position area when the updated target object does not bear the object.
2. The method of claim 1, further comprising:
and under the condition that the area of the current position area is smaller than that of a position area of a target object in the reference video frame and the position variation between the next frame of video frame and the current monitoring video frame is smaller than the preset position variation threshold, taking the current position area as the position area when the updated target object does not bear an object for storage.
3. The method according to claim 1, wherein the step of extracting the position area of the feature point of the preset portion of the human body image if the current monitoring video frame contains the human body image comprises:
if the current monitoring video frame contains a human body image, acquiring a position area of the human body image;
determining whether a suspected violation exists in the current monitoring video according to the coincidence ratio between the position area of the human body image and the position area of the target object in the reference video frame;
and under the condition that the suspected violation behavior exists in the current monitoring video, extracting the position area of the feature point of the preset part of the human body image.
4. The method according to claim 1, wherein the step of determining whether there is an illegal action in the current surveillance video based on whether the location area of the feature point is located in the location area of the target object when the target object does not carry an object comprises:
judging whether the position area of the characteristic point is positioned in the position area of the target object when the target object does not bear the object;
if yes, acquiring a position area of a feature point of a preset part of a human body image in each video frame of a preset number of video frames, wherein the preset number of video frames are video frames which are adjacent to the current monitoring video frame and behind the current monitoring video frame in the current monitoring video;
judging whether the position area of the feature point in each video frame in the preset number of video frames is located in the position area of the target object in the reference video frame when the object is not carried;
calculating the ratio of the number of video frames in which the position areas of the feature points are located in the position area of the target object in the reference video frame to the preset number in the preset number of video frames;
and if the ratio is larger than a preset ratio threshold, the current monitoring video has violation behaviors.
5. A video-based violation monitoring apparatus, the apparatus comprising:
the current monitoring video frame acquisition module is used for acquiring a current monitoring video frame; the current monitoring video frame is as follows: monitoring video frames shot at present in a target monitoring scene;
the human body image judging module is used for carrying out image monitoring on the current monitoring video frame and judging whether the current monitoring video frame contains a human body image;
a feature point position region extraction module, configured to extract a position region of a feature point of a preset portion of the human body image if the current monitoring video frame includes the human body image;
a first target object position area obtaining module, configured to obtain a position area of a target object in a pre-stored reference video frame when the target object does not carry an object, where the reference video frame is obtained from a historical monitoring video frame, and the target object is a component carrying the object;
the illegal behavior judging module is used for judging whether the illegal behavior exists in the current monitoring video or not based on whether the position area of the feature point is positioned in the position area of the target object when the target object does not bear the object or not;
the video scene variation detection module is used for detecting the video scene variation between two video frames with preset interval duration in the historical monitoring video;
the second target object position area acquisition module is used for taking a video frame with the video scene variation smaller than a preset variation threshold as a reference video frame, acquiring a position area where a target object in the reference video frame is located, and storing the position area as a position area when the target object does not bear an object;
the current position area acquisition module is used for acquiring the current position area of the target object in the current monitoring video frame;
the position variation acquiring module is used for calculating the position areas of the target objects in the reference video frame and the position variation between the current position areas, and the position variation is the ratio of intersection and union between the position areas of the target objects in the reference video frame and the current position areas;
the video frame receiving module is used for receiving the next frame of video frame under the condition that the position variation is larger than a preset position variation threshold;
the video scene variable quantity calculating module is used for calculating the video scene variable quantity between the next frame of video frame and the current monitoring video frame and between the two video frames;
and the third target object position area acquisition module is used for taking the video frame with the video scene variation smaller than the preset variation threshold as a reference video frame, acquiring a position area where the target object in the reference video frame is located, and storing the position area as the position area when the updated target object does not bear the object.
6. A video-based violation monitoring system, comprising: the system comprises video acquisition equipment and a monitoring host;
the video acquisition equipment is arranged in a target monitoring scene and is used for shooting a monitoring video of the target monitoring scene;
the monitoring host computer is connected with the video acquisition equipment in a communication mode and is used for realizing the method steps of any one of claims 1-4.
7. An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing mutual communication by the memory through the communication bus;
a memory for storing a computer program;
a processor for implementing the method steps of any of claims 1 to 4 when executing a program stored in the memory.
8. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which computer program, when being executed by a processor, carries out the method steps of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010383391.5A CN111586356B (en) | 2020-05-08 | 2020-05-08 | Violation monitoring method, device and system, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010383391.5A CN111586356B (en) | 2020-05-08 | 2020-05-08 | Violation monitoring method, device and system, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111586356A CN111586356A (en) | 2020-08-25 |
| CN111586356B true CN111586356B (en) | 2021-07-20 |
Family
ID=72125391
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010383391.5A Active CN111586356B (en) | 2020-05-08 | 2020-05-08 | Violation monitoring method, device and system, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111586356B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112800849A (en) * | 2020-12-31 | 2021-05-14 | 熊猫汽车(上海)有限公司 | Video monitoring method, video monitoring device, electronic equipment and storage medium |
| CN112822460B (en) * | 2021-02-01 | 2023-02-03 | 深圳市瑞驰文体发展有限公司 | Billiard game video monitoring method and system |
| CN112926443B (en) * | 2021-02-24 | 2021-12-07 | 北京优创新港科技股份有限公司 | Method and device for judging whether people exist on tobacco leaf purchasing conveyor belt |
| CN113705370B (en) * | 2021-08-09 | 2023-06-30 | 百度在线网络技术（北京）有限公司 | Method and device for detecting illegal behaviors of live broadcasting room, electronic equipment and storage medium |
| CN113673503B (en) * | 2021-08-25 | 2024-03-26 | 浙江大华技术股份有限公司 | Image detection method and device |
| CN113610072B (en) * | 2021-10-11 | 2022-01-25 | 精英数智科技股份有限公司 | Method and system for identifying person crossing belt based on computer vision |
| CN115273395B (en) * | 2022-05-31 | 2024-03-12 | 歌尔股份有限公司 | Monitoring method, device, equipment, system and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20150001305A (en) * | 2013-06-27 | 2015-01-06 | 와이드브릿지 주식회사 | Crime Prevention System Capable of 360 degree Video Monitoring and Warning for Crime Prevention |
| CN105959624A (en) * | 2016-05-03 | 2016-09-21 | 方筠捷 | Examination room monitoring data processing method and automatic monitoring system thereof |
| CN106101647A (en) * | 2016-07-29 | 2016-11-09 | 国网河南省电力公司郑州供电公司 | The method for managing security of the object space movement locus feature of view-based access control model and system |
| CN109961014A (en) * | 2019-02-25 | 2019-07-02 | 中国科学院重庆绿色智能技术研究院 | A kind of coal mine conveying belt danger zone monitoring method and system |
| CN110490125A (en) * | 2019-08-15 | 2019-11-22 | 成都睿晓科技有限公司 | A kind of fueling area service quality detection system detected automatically based on gesture |
-
2020
- 2020-05-08 CN CN202010383391.5A patent/CN111586356B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20150001305A (en) * | 2013-06-27 | 2015-01-06 | 와이드브릿지 주식회사 | Crime Prevention System Capable of 360 degree Video Monitoring and Warning for Crime Prevention |
| CN105959624A (en) * | 2016-05-03 | 2016-09-21 | 方筠捷 | Examination room monitoring data processing method and automatic monitoring system thereof |
| CN106101647A (en) * | 2016-07-29 | 2016-11-09 | 国网河南省电力公司郑州供电公司 | The method for managing security of the object space movement locus feature of view-based access control model and system |
| CN109961014A (en) * | 2019-02-25 | 2019-07-02 | 中国科学院重庆绿色智能技术研究院 | A kind of coal mine conveying belt danger zone monitoring method and system |
| CN110490125A (en) * | 2019-08-15 | 2019-11-22 | 成都睿晓科技有限公司 | A kind of fueling area service quality detection system detected automatically based on gesture |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111586356A (en) | 2020-08-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111586356B (en) | Violation monitoring method, device and system, electronic equipment and storage medium | |
| CN107358149B (en) | Human body posture detection method and device | |
| Hu et al. | Moving object detection and tracking from video captured by moving camera | |
| US7778445B2 (en) | Method and system for the detection of removed objects in video images | |
| US20080181499A1 (en) | System and method for feature level foreground segmentation | |
| KR101735365B1 (en) | The robust object tracking method for environment change and detecting an object of interest in images based on learning | |
| CN111523510A (en) | Behavior recognition method, behavior recognition device, behavior recognition system, electronic equipment and storage medium | |
| JP6044522B2 (en) | Slow change detection system | |
| US20110280478A1 (en) | Object monitoring system and method | |
| US10692225B2 (en) | System and method for detecting moving object in an image | |
| CN111814776B (en) | Image processing method, device, server and storage medium | |
| CN110910355A (en) | Package blocking detection method and device and computer storage medium | |
| Lim et al. | River flow lane detection and Kalman filtering-based B-spline lane tracking | |
| CN112270253A (en) | High-altitude parabolic detection method and device | |
| KR101690050B1 (en) | Intelligent video security system | |
| EP3044734B1 (en) | Isotropic feature matching | |
| CN113505643A (en) | Violation target detection method and related device | |
| JP6772059B2 (en) | Electronic control devices, electronic control systems and electronic control methods | |
| US10916016B2 (en) | Image processing apparatus and method and monitoring system | |
| CN113947795B (en) | Mask wearing detection method, device, equipment and storage medium | |
| CN112802112B (en) | Visual positioning method, device, server and storage medium | |
| CN115423795A (en) | Static frame detection method, electronic device and storage medium | |
| JP2001091246A (en) | Obstacle detecting device | |
| CN114699702A (en) | Fire fighting equipment detection method and related device | |
| CN114387544A (en) | High-altitude parabolic detection method and system, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |