CN113989853A - Cultural relic protection area abnormal state identification method and device, terminal equipment and medium - Google Patents
Cultural relic protection area abnormal state identification method and device, terminal equipment and medium Download PDFInfo
- Publication number
- CN113989853A CN113989853A CN202111355179.9A CN202111355179A CN113989853A CN 113989853 A CN113989853 A CN 113989853A CN 202111355179 A CN202111355179 A CN 202111355179A CN 113989853 A CN113989853 A CN 113989853A
- Authority
- CN
- China
- Prior art keywords
- protection area
- relic protection
- inspection result
- cultural relic
- abnormal state
- 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
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 79
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000007689 inspection Methods 0.000 claims abstract description 97
- 230000006399 behavior Effects 0.000 claims description 69
- 238000010586 diagram Methods 0.000 claims description 35
- 238000009412 basement excavation Methods 0.000 claims description 32
- 238000001514 detection method Methods 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 11
- 238000003062 neural network model Methods 0.000 claims description 5
- 230000009471 action Effects 0.000 description 4
- 238000013527 convolutional neural network Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000005856 abnormality Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000004321 preservation Methods 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- 206010000117 Abnormal behaviour Diseases 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 210000000746 body region Anatomy 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000007723 transport mechanism Effects 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Images
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The utility model provides a historical relic's protected area abnormal state identification method, device, terminal equipment and computer readable storage medium based on unmanned aerial vehicle to at least, solve present historical relic's protected area abnormal state identification labour cost height, easily miss examine and discern inefficiency scheduling problem, wherein, the method includes: the method comprises the steps that an unmanned aerial vehicle is used for polling personnel and objects in a cultural relic protection area to obtain a first polling result about the personnel and a second polling result about the objects; and identifying whether the cultural relic protection area has an abnormal state or not based on the first inspection result and the second inspection result, and if so, sending an abnormal warning prompt of the cultural relic protection area. The first result of patrolling and examining and the second result of patrolling and examining to the personnel that utilize the unmanned aerial vehicle technique to obtain are patrolled and examined and are carried out historical relic district abnormal state discernment, have realized the intelligent recognition of historical relic protection district abnormal state, effectively improve the efficiency and the rate of accuracy of historical relic protection district abnormal state discernment, reduce the cost of labor simultaneously.
Description
Technical Field
The present disclosure relates to the field of computer intelligence technologies, and in particular, to a method for identifying an abnormal state of a cultural relic protection area, an apparatus for identifying an abnormal state of a cultural relic protection area, a terminal device, and a computer-readable storage medium.
Background
The historical relic stealing excavation is a key striking object in China, the historical relic area has a plurality of sites and a wide range of relation in the patrol work of the historical relic area, and the patrol of the historical relic area by using an unmanned aerial vehicle becomes the work which is greatly promoted by the historical relic protection unit at present. At present, the patrol work of the cultural relic protected area mainly carries out aerial photography in the protected area through an unmanned aerial vehicle, then, the aerial photography video of the unmanned aerial vehicle is screened manually to judge whether the suspected cultural relic is stolen and excavated, and the method has the problems that the workload of video screening of workers is large, manual observation is easy to omit, the suspected cultural relic is stolen and excavated behavior and abnormal objects in the cultural relic protected area cannot be found in time, and the like.
Disclosure of Invention
The present disclosure provides a cultural relic area abnormal state identification method, device, terminal device and computer readable storage medium, so as to at least solve the problems of high labor cost, easy omission, low identification efficiency and the like in the current cultural relic area abnormal behavior and abnormal object identification.
In order to achieve the above object, the present disclosure provides a cultural relic protection area abnormal state identification method based on an unmanned aerial vehicle, including:
the method comprises the steps that an unmanned aerial vehicle is used for polling personnel and objects in a cultural relic protection area to obtain a first polling result about the personnel and a second polling result about the objects; and the number of the first and second groups,
and identifying whether the historical relic protection area has an abnormal state or not based on the first inspection result and the second inspection result, and if so, sending an abnormal warning prompt of the historical relic protection area.
In one embodiment, an object detection algorithm is deployed in an onboard terminal of the unmanned aerial vehicle,
utilize unmanned aerial vehicle to patrol and examine personnel and object in the historical relic protected area, obtain the first result of patrolling and examining about personnel and the second result of patrolling and examining about the object, include:
shooting a patrol video in the cultural relic protection area by using an airborne camera of the unmanned aerial vehicle; and the number of the first and second groups,
and detecting personnel and objects in the inspection video in the cultural relic protection area by using a target detection algorithm deployed in an airborne terminal of the unmanned aerial vehicle to obtain a first inspection result about the personnel and a second inspection result about the objects.
Whether the historical relic protection area has an abnormal state is identified based on the first inspection result and the second inspection result, including:
judging whether human body excavation behaviors exist in the cultural relic protection area or not based on the first routing inspection result;
if yes, judging that the historical relic protection area has an abnormal state;
if not, judging whether the historical relic protection area has abnormal objects or not based on the second inspection result, and if so, judging that the historical relic protection area has an abnormal state.
In one embodiment, the judging whether human body excavation behaviors exist in the cultural relic protection area or not based on the first routing inspection result comprises the following steps:
obtaining human skeleton key points from the first inspection result;
generating a human body skeleton space-time diagram based on the human body skeleton key points;
inputting the human body skeleton space-time diagram into a space-time diagram convolution neural network model for human body behavior recognition to obtain a behavior recognition result;
and judging whether human body excavation behaviors exist in the cultural relic protection area or not based on the behavior recognition result.
In one embodiment, the method for obtaining the human skeleton key points from the first inspection result specifically comprises the following steps:
and acquiring the key points of the human skeleton from the first inspection result by using a human posture estimation OpenPose algorithm.
In one embodiment, the judging whether human body excavation behaviors exist in the cultural relic protection area or not based on the first routing inspection result comprises the following steps:
sending the first inspection result to a background server so that the background server obtains human skeleton key points from the first inspection result by using a human posture estimation OpenPose algorithm, then generating a human skeleton space-time diagram based on the human skeleton key points, and inputting the human skeleton space-time diagram into a space-time diagram convolution neural network model for human behavior recognition to obtain a behavior recognition result;
acquiring the behavior recognition result from a background server; and the number of the first and second groups,
and judging whether human body excavation behaviors exist in the cultural relic protection area or not based on the behavior recognition result.
In one embodiment, the historical relic protection area abnormity warning prompt carries the first inspection result and the second inspection result.
In order to realize above-mentioned purpose, this disclosure still provides a historical relic protected area abnormal state recognition device based on unmanned aerial vehicle correspondingly, includes:
the inspection module is used for inspecting personnel and objects in the cultural relic protection area by using the unmanned aerial vehicle to obtain a first inspection result about the personnel and a second inspection result about the objects; and the number of the first and second groups,
the identification module is arranged for identifying whether the cultural relic protection area has an abnormal state or not based on the first inspection result and the second inspection result;
and the prompting module is set to send out an abnormal warning prompt of the cultural relic protection area when the identification module identifies that the abnormal state exists.
In order to achieve the above object, the present disclosure also provides a terminal device, which includes a memory and a processor, where the memory stores a computer program, and when the processor runs the computer program stored in the memory, the processor executes the method for identifying abnormal states in a cultural relic protection area based on an unmanned aerial vehicle.
In order to achieve the above object, the present disclosure also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the processor executes the method for identifying abnormal states of a cultural relic protection area based on an unmanned aerial vehicle.
According to the cultural relic protection area abnormal state identification method, the cultural relic protection area abnormal state identification device, the terminal equipment and the computer readable storage medium, the unmanned aerial vehicle is used for polling personnel and objects in the cultural relic protection area to obtain a first polling result about the personnel and a second polling result about the objects, whether the cultural relic protection area has an abnormal state or not is identified based on the first polling result and the second polling result, and if yes, an abnormal warning prompt of the cultural relic protection area is sent. This disclosure utilizes unmanned aerial vehicle technique, patrol and examine the first result of patrolling and examining and the second result of patrolling and examining of obtaining personnel and object through unmanned aerial vehicle, then patrol and examine the discernment that the result carries out the foreign state in historical relic district based on first result of patrolling and examining and the second, realized the intelligent recognition of historical relic protection district foreign state, need not the manual work and carry out the foreign state screening to the video, the problem of examining neglected of having avoided artifical screening to lead to has been avoided, its efficiency and the rate of accuracy that can effectively improve historical relic protection district foreign state discernment at least, reduce the cost of labor simultaneously.
Additional features and advantages of the disclosure will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the disclosure. The objectives and other advantages of the disclosure may be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
The accompanying drawings are included to provide a further understanding of the disclosed embodiments and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the example serve to explain the principles of the disclosure and not to limit the disclosure.
Fig. 1 is a schematic flow chart of a cultural relic protection area abnormal state identification method based on an unmanned aerial vehicle according to an embodiment of the present disclosure;
FIG. 2 is a schematic flowchart of step S101 in FIG. 1;
FIG. 3 is a schematic flowchart of step S102 in FIG. 1;
fig. 4 is a schematic flowchart of a cultural relic protection area abnormal state identification method based on an unmanned aerial vehicle according to another embodiment of the present disclosure;
FIG. 5 is an exemplary illustration of a human skeleton space-time diagram in another embodiment of the disclosure;
FIG. 6 is a schematic flow chart of ST-GCN model identification according to another embodiment of the present disclosure;
fig. 7 is a schematic structural diagram of a cultural relic protection area abnormal state identification device based on an unmanned aerial vehicle according to an embodiment of the present disclosure;
fig. 8 is a schematic structural diagram of a terminal device according to an embodiment of the present disclosure.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present disclosure more apparent, specific embodiments of the present disclosure are described below in detail with reference to the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating the present disclosure, are given by way of illustration and explanation only, not limitation.
It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order; also, the embodiments and features of the embodiments in the present disclosure may be arbitrarily combined with each other without conflict.
In the following description, suffixes such as "module", "component", or "unit" used to denote elements are used only for the convenience of explanation of the present disclosure, and have no specific meaning in themselves. Thus, "module", "component" or "unit" may be used mixedly.
In order to solve the problems, the embodiment of the disclosure provides an unmanned aerial vehicle-based cultural relic preservation area abnormal state identification method, which utilizes an unmanned aerial vehicle technology to intelligently identify abnormal objects and suspected excavation behaviors in the cultural relic preservation area, so that the suspected cultural relic excavation stealing behavior of the cultural relic preservation area can be accurately detected, the excavation stealing behavior can be efficiently found, the labor cost is reduced, and the risk of the cultural relic excavation stealing is reduced.
Referring to fig. 1, fig. 1 is a schematic flow chart of a cultural relic protection area abnormal state identification method based on an unmanned aerial vehicle according to an embodiment of the present disclosure, where the method is applied to a cultural relic protection area abnormal state identification device based on an unmanned aerial vehicle, and includes step S101 and step S102.
In step S101, the unmanned aerial vehicle is used to inspect the personnel and the objects in the cultural relic protection area, and a first inspection result about the personnel and a second inspection result about the objects are obtained.
In one embodiment, people and objects in the cultural relic protection area are quickly identified by deploying a target detection algorithm in a recording terminal of an unmanned aerial vehicle, wherein the target detection algorithm is deployed in an onboard terminal of the unmanned aerial vehicle, as shown in fig. 2, step S101 includes step S1011 and step S1012.
S1011, shooting a patrol video in the cultural relic protection area by using an airborne camera of the unmanned aerial vehicle; and the number of the first and second groups,
s1012, detecting personnel and objects in the inspection video in the cultural relic protection area by using a target detection algorithm deployed in an airborne terminal of the unmanned aerial vehicle, and obtaining a first inspection result about the personnel and a second inspection result about the objects.
Specifically, the staff starts the unmanned aerial vehicle, for example, an unmanned aerial vehicle control program may be provided on the cultural relic protection area abnormal state recognition device, the staff starts the unmanned aerial vehicle on the device, the unmanned aerial vehicle shoots an inspection video in the cultural relic protection area through an onboard camera, the inspection video shot by the camera is input into a target detection algorithm, the target detection algorithm is used for detecting the personnel and the abnormal objects in the cultural relic protection area, a first inspection result about the personnel and a second inspection result about the objects are obtained, and the first inspection result and the second inspection result include a detection result and a current frame image of the abnormal objects or suspected excavation behaviors.
In this embodiment, the resolution of the selected camera may be 1080P, and the frame rate is 60 fps; and an android system is carried on the airborne terminal, and the GPU computing power is not less than 10 TOPS. The target detection algorithm can use YOLOv4-tiny to train a YOLOv4-tiny model, realize the target detection of abnormal objects and personnel such as excavators and dump trucks, and deploy the trained model to an airborne terminal. In one embodiment, when the unmanned aerial vehicle airborne camera detects people through the target detection algorithm model, the focal length of the unmanned aerial vehicle camera is adjusted to require that a human body in a shooting video is placed in a middle area, and the occupation ratio of the people in a picture in a video frame is larger than 1/4; the resolution of the shot video is not less than 1080P, the video frame rate is 60fps, namely the proportion of people in the current frame image in the picture is more than 1/4; the shooting video resolution is not less than 1080P, and the video frame rate is 60 fps.
It should be noted that, in the cultural relic protection area, not only the suspected excavation behavior of the person but also the abnormal object threatens the safety of the cultural relic protection area, for example, the excavation person performs the preparatory work before excavation, and the excavation tool is placed in the cultural relic protection area in advance, and the excavation tool may include an excavator, a dump truck and other objects which may damage the cultural relic protection area. In some embodiments, the cultural relic information can be stored in the on-board terminal, and if an object other than the cultural relic information is identified in the inspection, the abnormal object can be determined.
In step S102, whether the cultural relic protection area has an abnormal state is identified based on the first inspection result and the second inspection result, if yes, step S103 is executed, otherwise, the process is ended.
Further, the embodiment determines whether human body excavation behavior (abnormal behavior of people) exists in the cultural relic protection area based on the first inspection result, and determines whether an abnormal object exists in the cultural relic protection area based on the second inspection result, specifically, step S102, as shown in fig. 3, includes the following steps:
s1021, judging whether human body excavation behaviors exist in the cultural relic protection area or not based on the first inspection result, if so, executing a step S1022, otherwise, executing a step S1023;
s1022, judging that the historical relic protection area has an abnormal state;
and S1023, judging whether the cultural relic protection area has an abnormal object or not based on the second inspection result, if so, executing the step S1022 to judge that the cultural relic protection area has an abnormal state, and if not, ending the process.
Specifically, if the person behavior abnormality is identified in the first inspection result or the body abnormality is identified in the second inspection result, it is determined that the abnormal state exists. Compared with the prior art, the identification of the abnormal state of the cultural relic protection area can be effectively improved by distinguishing the abnormal state identification of the personnel and the objects in the embodiment.
It should be noted that, in some embodiments, it may also be determined whether an abnormal object exists in the cultural relic protection area first, so as to determine the human excavation behavior, or to perform synchronous determination, and the above sequence of steps in this embodiment is not a limitation to the present disclosure.
In step S103, a cultural relic protected area abnormality warning prompt is issued.
In one embodiment, the historical relic protection area abnormity warning prompt carries the first inspection result and the second inspection result.
Through carrying first inspection result and second inspection result in the warning suggestion of historical relic district's anomaly, the user can be used for staff's manual inspection after receiving the warning suggestion of historical relic protection district's anomaly to confirm unusual action or object fast, ensure historical relic protection district safety.
Compared with the prior art, the embodiment of the disclosure is suitable for workers in the cultural relic protection area to carry out daily patrol work by utilizing the unmanned aerial vehicle, can effectively assist the workers in patrolling the cultural relic protection area, reduces manual participation links, realizes quick and accurate detection of suspected cultural relic digging stealing behavior in the cultural relic protection area, and reduces the risk of the cultural relic digging stealing.
Referring to fig. 4, fig. 4 is a schematic flow chart of a cultural relic protection area abnormal state identification method based on an unmanned aerial vehicle according to another embodiment of the present disclosure, based on the previous embodiment, in this embodiment, techniques such as an OpenPose algorithm and a space-time convolutional neural network ST-GCN model are used to perform human body behavior identification, so as to obtain clearer physical body behavior actions of people and improve detection efficiency of suspected excavation behaviors, specifically, whether a human body excavation behavior exists in the cultural relic protection area is determined based on the first inspection result (step S1021), which includes steps S401 to S404.
In step S401, the human skeleton key points are obtained from the first inspection result.
Further, human skeleton key points are obtained from the first inspection result (step S401), which specifically includes:
and acquiring the key points of the human skeleton from the first inspection result by using a human posture estimation OpenPose algorithm.
It is understood that human pose estimation is a fundamental problem in computer vision, which can be understood as the position estimation of the pose of the "human body" (key points such as head, left hand, right foot, etc.). Human posture estimation can be divided into two ideas: 1) top-down, which means detecting the human body area first and then detecting the human body key points in the area; 2) "bottom-up" refers to detecting all key points of human body in picture, and then corresponding these key points to different individual persons. The first scheme needs to perform forward keypoint detection on each detected human body region, so that the speed is low, and the second scheme is adopted by openpos.
In step S402, a human skeleton space-time diagram is generated based on the human skeleton key points.
Specifically, each frame of the human activity video is input into an OpenPose algorithm, and human skeleton key points of the frame are obtained. And then obtaining a human body skeleton space-time diagram G (V, E) by using the key points of the human body skeleton, wherein the human body skeleton space-time diagram is shown in fig. 5, and the construction process of the human body skeleton space-time diagram comprises the following substeps:
1) within each frame, a human skeleton space diagram is constructed according to the natural skeleton connection relation of the human body, wherein the edge is represented as ES＝{vtivtjL (i, j) belongs to H, wherein H is a group of naturally connected human joints;
2) the same key points of two adjacent frames are connected to form a time sequence edge. These edges are denoted as EF＝{vtiv(t+1)i}；
3) All the key points in the input frame constitute a node set V ═ Vti|t＝1,...,T,i＝1,...N}；
4) All the edges in steps 1) and 2) form an edge set E, that is, the required space-time diagram G is formed as (V, E).
In step S403, the human skeleton space-time diagram is input into the space-time diagram convolutional neural network model for human behavior recognition, so as to obtain a behavior recognition result.
Specifically, a human skeleton space-time diagram is input into a trained ST-GCN model for behavior recognition, the ST-GCN model recognition process is shown in FIG. 6, input data are subjected to batch standardization, then are subjected to global pooling and global clustering to obtain 256-dimensional feature vectors of each sequence after passing through 9 ST-GCN units, and finally are classified by a SoftMax function to obtain a final behavior recognition result.
In step S404, it is determined whether there is a human body excavation behavior in the cultural relic protection area based on the behavior recognition result.
In an embodiment, a certain number of human behaviors may be intelligently analyzed to generate a human digging behavior sample, where in step S304, it is determined whether a human digging behavior exists, that is, it is determined that a similarity between a behavior recognition result and the human digging behavior sample exists, and once the similarity reaches a preset threshold, it is determined that a human (suspected) digging behavior exists in the cultural relic protection area.
In the related art, a mode of extracting key points of the human body skeleton to generate a human body skeleton space-time diagram and then inputting the human body skeleton space-time diagram into a convolutional network for feature extraction is provided to complete human body behavior identification, but the human body behavior identification is usually performed on a common figure picture and is not performed on mining behaviors and abnormal objects in a text area.
In one embodiment, in order to relieve the cache pressure of the device and reduce the computing capacity, the method comprises the following steps of sending data to a background server, identifying human behavior by using the background server, and identifying whether an abnormal state exists in the cultural relic protection area based on the first inspection result and the second inspection result:
sending the first inspection result to a background server so that the background server obtains human skeleton key points from the first inspection result by using a human posture estimation OpenPose algorithm, then generating a human skeleton space-time diagram based on the human skeleton key points, and inputting the human skeleton space-time diagram into a space-time diagram convolution neural network model for human behavior recognition to obtain a behavior recognition result;
acquiring the behavior recognition result from a background server; and the number of the first and second groups,
and judging whether the cultural relic protection area has human body excavation behaviors or not based on the behavior identification result, and if so, judging that the cultural relic protection area has an abnormal state.
Based on the same technical concept, the embodiment of the present disclosure correspondingly provides an abnormal state identification device for a cultural relic protection area based on an unmanned aerial vehicle, as shown in fig. 7, the device includes an inspection module 61, an identification module 71 and a prompt module 73, wherein,
the inspection module 71 is configured to inspect personnel and objects in the cultural relic protection area by using an unmanned aerial vehicle to obtain a first inspection result about the personnel and a second inspection result about the objects; and the number of the first and second groups,
the identification module 72 is configured to identify whether an abnormal state exists in the cultural relic protection area based on the first inspection result and the second inspection result;
and the prompting module 73 is configured to send out a cultural relic protection area abnormity warning prompt when the identification module identifies that the abnormal state exists.
In one embodiment, an object detection algorithm is deployed in an onboard terminal of the drone, and the patrol module 71 includes:
the shooting unit is arranged to shoot a patrol video in the cultural relic protection area by utilizing an airborne camera of the unmanned aerial vehicle; and the number of the first and second groups,
and the detection unit is arranged to detect the personnel and the object in the inspection video in the cultural relic protection area by using a target detection algorithm deployed in an airborne terminal of the unmanned aerial vehicle, so as to obtain a first inspection result about the personnel and a second inspection result about the object.
In one embodiment, the identification module 72 includes:
the first judging unit is arranged for judging whether human body excavation behaviors exist in the cultural relic protection area or not based on the first routing inspection result, and if yes, judging that the cultural relic protection area has an abnormal state;
and the second judging unit is arranged for judging whether the historical relic protection area has abnormal objects or not based on the second inspection result when the first judging unit judges that the human body excavation behavior does not exist, and judging that the historical relic protection area has an abnormal state if the historical relic protection area has the abnormal objects.
In one embodiment, the first judging unit includes:
a first obtaining element configured to obtain a human skeleton key point from the first inspection result;
a generating element configured to generate a human skeleton space-time diagram based on the human skeleton key points;
the recognition element is used for inputting the human body skeleton space-time diagram into a space-time diagram convolutional neural network model to perform human body behavior recognition so as to obtain a behavior recognition result;
and the first judging element is arranged for judging whether human body excavation action exists in the cultural relic protection area or not based on the action identification result.
In an embodiment, the obtaining element is specifically configured to obtain the human skeleton key points from the first inspection result by using a human posture estimation openpos algorithm.
In one embodiment, the first judging unit includes:
a sending element, configured to send the first inspection result to a background server, so that the background server obtains human skeleton key points from the first inspection result by using a human posture estimation OpenPose algorithm, then generates a human skeleton space-time diagram based on the human skeleton key points, and inputs the human skeleton space-time diagram into a space-time diagram convolutional neural network model for human behavior recognition, so as to obtain a behavior recognition result;
a second obtaining element configured to obtain the behavior recognition result from a background server; and the number of the first and second groups,
and the second judging element is arranged to judge whether human body excavation behaviors exist in the cultural relic protection area or not based on the behavior recognition result.
In one embodiment, the historical relic protection area abnormity warning prompt carries the first inspection result and the second inspection result.
Based on the same technical concept, the embodiment of the present disclosure correspondingly provides a terminal device, as shown in fig. 8, the terminal device includes a memory 81 and a processor 82, a computer program is stored in the memory 81, and when the processor 82 runs the computer program stored in the memory 81, the processor 82 executes the method for identifying the abnormal state of the cultural relic protection area based on the unmanned aerial vehicle.
Based on the same technical concept, the embodiment of the present disclosure correspondingly provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the processor executes the method for identifying abnormal states of the cultural relic protection area based on the unmanned aerial vehicle.
It will be understood by those of ordinary skill in the art that all or some of the steps of the methods, systems, functional modules/units in the devices disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. In a hardware implementation, the division between functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be performed by several physical components in cooperation. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as is well known to those of ordinary skill in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, Digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can accessed by a computer. In addition, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media as known to those skilled in the art.
Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the present disclosure, and not for limiting the same; while the present disclosure has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art will understand that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present disclosure.
Claims (10)
1. The cultural relic protection area abnormal state identification method based on the unmanned aerial vehicle is characterized by comprising the following steps:
the method comprises the steps that an unmanned aerial vehicle is used for polling personnel and objects in a cultural relic protection area to obtain a first polling result about the personnel and a second polling result about the objects; and the number of the first and second groups,
and identifying whether the historical relic protection area has an abnormal state or not based on the first inspection result and the second inspection result, and if so, sending an abnormal warning prompt of the historical relic protection area.
2. The method of claim 1, wherein an object detection algorithm is deployed in an onboard terminal of the drone,
utilize unmanned aerial vehicle to patrol and examine personnel and object in the historical relic protected area, obtain the first result of patrolling and examining about personnel and the second result of patrolling and examining about the object, include:
shooting a patrol video in the cultural relic protection area by using an airborne camera of the unmanned aerial vehicle; and the number of the first and second groups,
and detecting personnel and objects in the inspection video in the cultural relic protection area by using a target detection algorithm deployed in an airborne terminal of the unmanned aerial vehicle to obtain a first inspection result about the personnel and a second inspection result about the objects.
3. The method according to claim 1 or 2, wherein identifying whether the cultural relic protection area has an abnormal state based on the first and second inspection results comprises:
judging whether human body excavation behaviors exist in the cultural relic protection area or not based on the first routing inspection result;
if yes, judging that the historical relic protection area has an abnormal state;
if not, judging whether the historical relic protection area has abnormal objects or not based on the second inspection result, and if so, judging that the historical relic protection area has an abnormal state.
4. The method according to claim 3, wherein judging whether human body excavation behaviors exist in the cultural relic protection area or not based on the first routing inspection result comprises the following steps:
obtaining human skeleton key points from the first inspection result;
generating a human body skeleton space-time diagram based on the human body skeleton key points;
inputting the human body skeleton space-time diagram into a space-time diagram convolution neural network model for human body behavior recognition to obtain a behavior recognition result;
and judging whether human body excavation behaviors exist in the cultural relic protection area or not based on the behavior recognition result.
5. The method according to claim 4, characterized in that the human skeleton key points are obtained from the first inspection result, specifically:
and acquiring the key points of the human skeleton from the first inspection result by using a human posture estimation OpenPose algorithm.
6. The method according to claim 3, wherein judging whether human body excavation behaviors exist in the cultural relic protection area or not based on the first routing inspection result comprises the following steps:
sending the first inspection result to a background server so that the background server obtains human skeleton key points from the first inspection result by using a human posture estimation OpenPose algorithm, then generating a human skeleton space-time diagram based on the human skeleton key points, and inputting the human skeleton space-time diagram into a space-time diagram convolution neural network model for human behavior recognition to obtain a behavior recognition result;
acquiring the behavior recognition result from a background server; and the number of the first and second groups,
and judging whether human body excavation behaviors exist in the cultural relic protection area or not based on the behavior recognition result.
7. The method according to claim 1, wherein the first inspection result and the second inspection result are carried in the historical relic protection area abnormity warning prompt.
8. The utility model provides a historical relic's protected area abnormal state recognition device based on unmanned aerial vehicle, its characterized in that includes:
the inspection module is used for inspecting personnel and objects in the cultural relic protection area by using the unmanned aerial vehicle to obtain a first inspection result about the personnel and a second inspection result about the objects; and the number of the first and second groups,
the identification module is arranged for identifying whether the cultural relic protection area has an abnormal state or not based on the first inspection result and the second inspection result;
and the prompting module is set to send out an abnormal warning prompt of the cultural relic protection area when the identification module identifies that the abnormal state exists.
9. A terminal device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor runs the computer program stored in the memory, the processor executes the unmanned aerial vehicle-based cultural relic protection area abnormal state identification method according to any one of claims 1 to 7.
10. A computer-readable storage medium, having a computer program stored thereon, which when executed by a processor, performs the unmanned aerial vehicle-based cultural relic protection area abnormal state identification method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111355179.9A CN113989853A (en) | 2021-11-16 | 2021-11-16 | Cultural relic protection area abnormal state identification method and device, terminal equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111355179.9A CN113989853A (en) | 2021-11-16 | 2021-11-16 | Cultural relic protection area abnormal state identification method and device, terminal equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113989853A true CN113989853A (en) | 2022-01-28 |
Family
ID=79748777
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111355179.9A Pending CN113989853A (en) | 2021-11-16 | 2021-11-16 | Cultural relic protection area abnormal state identification method and device, terminal equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113989853A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102547241A (en) * | 2011-12-31 | 2012-07-04 | 深圳市永达电子股份有限公司 | Home anomaly detection method and home anomaly detection device as well as home anomaly detection system on basis of wireless network camera |
| CN106534323A (en) * | 2016-11-16 | 2017-03-22 | 四川川大智胜***集成有限公司 | Mobile patrol system and patrol method based on protection of historical relics |
| CN111783744A (en) * | 2020-07-31 | 2020-10-16 | 上海仁童电子科技有限公司 | Operation site safety protection detection method and device |
| CN112183317A (en) * | 2020-09-27 | 2021-01-05 | 武汉大学 | Live working field violation behavior detection method based on space-time diagram convolutional neural network |
| US20210009266A1 (en) * | 2019-07-10 | 2021-01-14 | Coretronic Corporation | Unmanned aerial vehicle patrol system and unmanned aerial vehicle patrol method |
| CN112329691A (en) * | 2020-11-17 | 2021-02-05 | 珠海大横琴科技发展有限公司 | Monitoring video analysis method and device, electronic equipment and storage medium |
-
2021
- 2021-11-16 CN CN202111355179.9A patent/CN113989853A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102547241A (en) * | 2011-12-31 | 2012-07-04 | 深圳市永达电子股份有限公司 | Home anomaly detection method and home anomaly detection device as well as home anomaly detection system on basis of wireless network camera |
| CN106534323A (en) * | 2016-11-16 | 2017-03-22 | 四川川大智胜***集成有限公司 | Mobile patrol system and patrol method based on protection of historical relics |
| US20210009266A1 (en) * | 2019-07-10 | 2021-01-14 | Coretronic Corporation | Unmanned aerial vehicle patrol system and unmanned aerial vehicle patrol method |
| CN111783744A (en) * | 2020-07-31 | 2020-10-16 | 上海仁童电子科技有限公司 | Operation site safety protection detection method and device |
| CN112183317A (en) * | 2020-09-27 | 2021-01-05 | 武汉大学 | Live working field violation behavior detection method based on space-time diagram convolutional neural network |
| CN112329691A (en) * | 2020-11-17 | 2021-02-05 | 珠海大横琴科技发展有限公司 | Monitoring video analysis method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20130279758A1 (en) | Method and system for robust tilt adjustment and cropping of license plate images | |
| CN111898581B (en) | Animal detection method, apparatus, electronic device, and readable storage medium | |
| KR101708547B1 (en) | Event detection apparatus and event detection method | |
| KR102217253B1 (en) | Apparatus and method for analyzing behavior pattern | |
| CN107944382B (en) | Method for tracking target, device and electronic equipment | |
| US11727578B2 (en) | Crowd type classification system, crowd type classification method and storage medium for storing crowd type classification program | |
| CN109360362A (en) | A kind of railway video monitoring recognition methods, system and computer-readable medium | |
| CN110490171B (en) | Dangerous posture recognition method and device, computer equipment and storage medium | |
| US10789502B2 (en) | Extraneous-matter detecting apparatus and extraneous-matter detecting method | |
| CN111767915A (en) | License plate detection method, device, equipment and storage medium | |
| CN104573680A (en) | Image detection method, image detection device and traffic violation detection system | |
| CN112949439A (en) | Method and system for monitoring invasion of personnel in key area of oil tank truck | |
| KR20170125470A (en) | Method and system for detecting damaged tree blight with using aviation image | |
| KR102540208B1 (en) | Fire detection method using deep learning | |
| CN111666848B (en) | Method, device and equipment for detecting arrival of transport vehicle and storage medium | |
| CN112836683A (en) | License plate recognition method, device, equipment and medium for portable camera equipment | |
| CN110276315A (en) | Airport monitoring method, apparatus and system | |
| CN112507760A (en) | Method, device and equipment for detecting violent sorting behavior | |
| CN111126411B (en) | Abnormal behavior identification method and device | |
| CN113971829A (en) | Intelligent detection method, device, equipment and storage medium for wearing condition of safety helmet | |
| CN113139419B (en) | Unmanned aerial vehicle detection method and device | |
| CN116403162B (en) | Airport scene target behavior recognition method and system and electronic equipment | |
| CN113160272A (en) | Target tracking method and device, electronic equipment and storage medium | |
| CN110188645B (en) | Face detection method and device for vehicle-mounted scene, vehicle and storage medium | |
| CN113989853A (en) | Cultural relic protection area abnormal state identification method and device, terminal equipment and 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 |