CN112949390A - Event detection method and device based on video quality - Google Patents
Event detection method and device based on video quality Download PDFInfo
- Publication number
- CN112949390A CN112949390A CN202110115669.5A CN202110115669A CN112949390A CN 112949390 A CN112949390 A CN 112949390A CN 202110115669 A CN202110115669 A CN 202110115669A CN 112949390 A CN112949390 A CN 112949390A
- Authority
- CN
- China
- Prior art keywords
- detection
- event
- video quality
- video
- diagnosis result
- 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.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 231
- 238000003745 diagnosis Methods 0.000 claims abstract description 94
- 238000000034 method Methods 0.000 claims abstract description 32
- 238000013139 quantization Methods 0.000 claims abstract description 31
- 238000004364 calculation method Methods 0.000 claims abstract description 19
- 238000001914 filtration Methods 0.000 claims abstract description 18
- 238000004590 computer program Methods 0.000 claims description 15
- 230000005540 biological transmission Effects 0.000 claims description 13
- 230000008859 change Effects 0.000 claims description 7
- 238000013442 quality metrics Methods 0.000 claims 1
- 238000011156 evaluation Methods 0.000 abstract description 3
- 238000004458 analytical method Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008014 freezing Effects 0.000 description 1
- 238000007710 freezing Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/48—Matching video sequences
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
Abstract
The application relates to an event detection method, system, device, computer equipment and computer readable storage medium based on video quality, wherein a video to be detected is obtained; detecting the video to be detected according to the detection type, and outputting a detection event; diagnosing the video to be detected according to a preset video quality quantization index to obtain a video quality diagnosis result of the video to be detected; according to the detection event and the video quality diagnosis result, dynamically calculating the confidence coefficient of the detection event under the current video quality diagnosis result; and judging the confidence coefficient of the detection event under the current video quality diagnosis result obtained by calculation according to a preset confidence coefficient interval, and filtering the detection event of which the confidence coefficient is not in the confidence coefficient interval. The method solves the problems of simple evaluation and detection event index and higher false alarm rate of event alarm detection, and improves the accuracy rate of alarm event identification.
Description
Technical Field
The present application relates to the field of image processing, and in particular, to a method, system, apparatus, computer device, and computer-readable storage medium for detecting events based on video quality.
Background
In the case where the image information technology is widely used, evaluation of image quality becomes a wide and fundamental problem. Since image information has incomparable advantages over other information, rational processing of image information is an indispensable means in various fields. In the process of acquiring, processing, transmitting and recording images, due to the imperfection of an imaging system, a processing method, a transmission medium, recording equipment and the like, and the reasons of object motion, noise pollution and the like, certain image distortion and degradation are inevitably brought, which brings great difficulty for people to know an objective world and research and solve problems.
Intelligent analysis techniques have been widely used in video surveillance to achieve analysis of specific targets or behaviors in videos. In addition to the performance of the algorithm itself, the quality of the detected video source itself can also affect the accuracy of the detection. In order to reduce the deviation caused by the quality of a video source, a common technology adopts a scheme of performing preprocessing operation on a video before analysis so as to improve the adaptability of an analysis algorithm and the like. However, the current preprocessing scheme has the problem that the image quality evaluation accuracy is low due to the fact that the contrast characteristic information is single.
At present, no effective solution is provided for the problem of high false alarm rate of event alarm detection caused by simple evaluation of event detection indexes in the related technology.
Disclosure of Invention
Embodiments of the present application provide a method, system, apparatus, computer device, and computer-readable storage medium for detecting an event based on video quality, so as to at least solve the problems in the related art.
In a first aspect, an embodiment of the present application provides an event detection method based on video quality, including: acquiring a video to be detected;
detecting the video to be detected according to the detection type, and outputting a detection event;
diagnosing the video to be detected according to a preset video quality quantization index to obtain a video quality diagnosis result of the video to be detected;
according to the detection event and the video quality diagnosis result, dynamically calculating the confidence coefficient of the detection event under the current video quality diagnosis result;
and judging the confidence coefficient of the detection event under the current video quality diagnosis result obtained by calculation according to a preset confidence coefficient interval, and filtering the detection event of which the confidence coefficient is not in the confidence coefficient interval.
In one embodiment, said dynamically calculating a confidence level of said detected event at a current said video quality diagnostic result based on said detected event and said video quality diagnostic result comprises:
based on the detection event, acquiring the detection type of the detection event and the initial confidence of the detection event;
and calculating the confidence coefficient of the detection event under the current video quality diagnosis result according to the detection type of the detection event, the initial confidence coefficient of the detection event and the video quality diagnosis result. In one embodiment, the detecting type includes: face detection, tripwire detection, intrusion detection, human detection, non-motorized detection, motor vehicle detection, and/or face comparison. In an embodiment, after the determining the calculated confidence of the detection event under the current video quality diagnosis result according to a preset confidence interval, the method further includes:
and if the confidence of the detection event is in the confidence interval under the current video quality diagnosis result, determining that the detection event is an alarm event, and outputting the alarm event to a terminal.
In one embodiment, the video quality quantization index includes: one or more of lost, occluded, frozen, overexposed, overly dark, scene change, streaks, noise, color cast, blurred, low contrast, and jittered. In one embodiment, after the acquiring the video to be detected, the method further includes:
and setting the video quality quantization index and the detection type.
In a second aspect, an embodiment of the present application provides an event detection system based on video quality, including: a camera device, a transmission device, and a server device; wherein the camera device is connected to the server device through the transmission device;
the camera equipment is used for acquiring a video to be detected;
the transmission device is used for transmitting the video to the server device;
the server equipment is used for detecting the video to be detected according to the detection type and outputting a detection event; diagnosing the video to be detected according to a preset video quality quantization index to obtain a video quality diagnosis result of the video to be detected; according to the detection event and the video quality diagnosis result, dynamically calculating the confidence coefficient of the detection event under the current video quality diagnosis result; and judging the confidence coefficient of the detection event under the current video quality diagnosis result obtained by calculation according to a preset confidence coefficient interval, and filtering the detection event of which the confidence coefficient is not in the confidence coefficient interval.
In a third aspect, an embodiment of the present application provides an apparatus for image quality detection, including: the video acquisition module, the event output module, the quality diagnosis module, the confidence coefficient calculation module and the event filtering module comprise:
the video acquisition module is used for acquiring a video to be detected;
the event output module is used for detecting the video to be detected according to the detection type and outputting a detection event;
the quality diagnosis module is used for diagnosing the video to be detected according to a preset video quality quantization index to obtain a video quality diagnosis result of the video to be detected;
the confidence calculation module: the confidence coefficient of the detection event under the current video quality diagnosis result is dynamically calculated according to the detection event and the video quality diagnosis result;
the event filtering module is used for judging the confidence coefficient of the detection event under the current video quality diagnosis result according to a preset confidence coefficient interval, and filtering the detection event of which the confidence coefficient is not in the confidence coefficient interval. In a fourth aspect, the present application provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the video quality-based event detection method according to the first aspect.
In a fifth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements a video quality-based event detection method as described in the first aspect above.
Compared with the related art, the event detection method, the event detection system, the event detection device, the computer equipment and the computer readable storage medium based on the video quality provided by the embodiment of the application acquire the video to be detected; detecting the video to be detected according to the detection type, and outputting a detection event; diagnosing the video to be detected according to a preset video quality quantization index to obtain a video quality diagnosis result of the video to be detected; according to the detection event and the video quality diagnosis result, dynamically calculating the confidence coefficient of the detection event under the current video quality diagnosis result; and judging the confidence coefficient of the detection event under the current video quality diagnosis result obtained by calculation according to a preset confidence coefficient interval, and filtering the detection event of which the confidence coefficient is not in the confidence coefficient interval, so that the problem of higher false alarm rate of event alarm is solved, and the accuracy rate of identifying the alarm event is improved.
The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below to provide a more thorough understanding of the application.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 is a block diagram of a hardware structure of an application terminal according to an embodiment of the present application;
FIG. 2 is a flow chart of a method for video quality based event detection according to an embodiment of the present application;
FIG. 3 is a block diagram of an event detection architecture based on video quality according to an embodiment of the present application;
fig. 4 is a block diagram of a computer-readable storage medium according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments provided in the present application without any inventive step are within the scope of protection of the present application.
It is obvious that the drawings in the following description are only examples or embodiments of the present application, and that it is also possible for a person skilled in the art to apply the present application to other similar contexts on the basis of these drawings without inventive effort. Moreover, it should be appreciated that in the development of any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions must be made to achieve the developers' specific goals, such as compliance with system-related and business-related constraints, which may vary from one implementation to another.
Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the specification. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of ordinary skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments without conflict.
Unless defined otherwise, technical or scientific terms referred to herein shall have the ordinary meaning as understood by those of ordinary skill in the art to which this application belongs. Reference to "a," "an," "the," and similar words throughout this application are not to be construed as limiting in number, and may refer to the singular or the plural. The present application is directed to the use of the terms "including," "comprising," "having," and any variations thereof, which are intended to cover non-exclusive inclusions; for example, a process, method, system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to the listed steps or elements, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. Reference to "connected," "coupled," and the like in this application is not intended to be limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The term "plurality" as referred to herein means two or more. "and/or" describes an association relationship of associated objects, meaning that three relationships may exist, for example, "A and/or B" may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. Reference herein to the terms "first," "second," "third," and the like, are merely to distinguish similar objects and do not denote a particular ordering for the objects.
The method provided by the embodiment can be executed in a terminal, a computer or a similar operation device. Taking the example of the application running on a terminal, fig. 1 is a block diagram of a hardware structure of an application terminal of an event detection method based on video quality according to an embodiment of the present application. As shown in fig. 1, the terminal may include one or more (only one shown in fig. 1) processors 102 (the processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, and optionally, a transmission device 106 for communication functions and an input-output device 108. It will be understood by those skilled in the art that the structure shown in fig. 1 is only an illustration and is not intended to limit the structure of the terminal. For example, the terminal may also include more or fewer components than shown in FIG. 1, or have a different configuration than shown in FIG. 1.
The memory 104 can be used for storing computer programs, for example, software programs and modules of application software, such as a computer program corresponding to a method for false positive identification in the embodiment of the present invention, and the processor 102 executes various functional applications and data processing by running the computer programs stored in the memory 104, so as to implement the method described above. The memory 104 may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory located remotely from the processor 102, which may be connected to the terminal over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission device 106 is used to receive or transmit data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the terminal. In one example, the transmission device 106 includes a Network adapter (NIC) that can be connected to other Network devices through a base station to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is used to communicate with the internet in a wireless manner.
The embodiment also provides a video quality-based event detection method, and fig. 2 is a flowchart of a video quality-based event detection method according to an embodiment of the present application, and as shown in fig. 2, the flowchart includes the following steps:
step S201, a video to be detected is obtained.
The video to be detected can be collected through the camera, and then the server acquires the video to be detected from the camera. The server can also acquire the video to be detected from other image storage or acquisition equipment.
And S202, detecting the video to be detected according to the detection requirement, and outputting a detection event.
Wherein, the detection requirement refers to the intelligent detection type supported by the equipment, and may include: face detection, trip line detection, intrusion detection, human detection, non-motorized detection, motor vehicle detection, and/or face comparison configuration will enable one or more intelligent detections.
For example, if human detection is turned on, the device will detect the presence of a human in the video frame. And reporting a human body detection event when a human body appears in the video picture, wherein the detection event comprises a video panoramic screenshot and a small picture which is independently scratched out by the human body part in the picture. For another example, if a vehicle needs to be identified, the requirement for vehicle detection can be configured, and then if a vehicle appears in the video, information such as a license plate, a body color, a vehicle brand and the like of the vehicle can be reported. For another example, if a human face needs to be recognized, the requirement of vehicle detection may be configured, when a certain person appears in the video picture, the human face is first captured, and then the feature information of the human face is calculated to match with the feature information already stored in the device or the server. If the feature matching rate reaches 80% or other specified similarity, the people appearing in the picture at the moment can be confirmed to be the registered people in the database, otherwise, the people can be considered as strangers, and the detection requirement is suitable for face access control.
And step S203, diagnosing the video to be detected according to a preset video quality quantization index to obtain a video quality diagnosis result of the video to be detected.
The video quality quantization index is used for judging the quality of the video to be detected according to the set quantization index of the current video. The video quality quantization index may include: one or more of lost, occluded, frozen, overexposed, overly dark, scene change, streaks, noise, color cast, blurred, low contrast, and jittered. The video quality diagnosis result is a diagnosis result obtained by the video to be detected according to the video quality quantization index.
Step S204, according to the detection event and the video quality diagnosis result, dynamically calculating the confidence of the detection event under the current video quality diagnosis result.
The diagnosis result refers to the result of the video quality quantization index. For example, after diagnosis, the video quality at a certain moment, for example, after the current video to be detected is diagnosed, the obtained diagnosis results are loss 0, occlusion 0, freezing 0, overexposure 56, too dark 0, scene change 0, stripe 58, noise 36, color cast 1, blur 0, low contrast 0, and jitter 0.
It should be noted that a value of 0 to 100 indicates that the quality of the video is good, and a value exceeding 100 indicates that the quality of the video is not good at that time, and that relatively serious overexposure, noise, and/or streaks occur. Therefore, the accuracy of the diagnosis result can be considered to be not strong when the face detection is performed under the condition of poor video quality.
The confidence coefficient of the detection event under the current video quality diagnosis result is dynamically calculated according to the detection event and the video quality diagnosis, so that whether the detection event in the current video to be detected belongs to the detection event which is not in the confidence coefficient interval or not can be more accurately analyzed. By simultaneously associating the detection event of the video to be detected with the video quality diagnosis result and adjusting the confidence coefficient under the current video quality diagnosis result in real time according to different types of the detection event, the false alarm rate of the alarm event can be effectively reduced.
Step S205, according to a preset confidence interval, determining the calculated confidence of the detection event in the current video quality diagnosis result, and filtering the detection event whose confidence is not in the confidence interval.
Each detection event has a preset confidence interval, and the confidence of the detection event can be judged more accurately under the condition of obtaining the current video quality diagnosis result, so that the detection events which are not in the confidence intervals are filtered.
For example, when a face comparison is currently performed, the detection result of the video quality quantization index at this time is as follows: loss 0, occlusion 0, freeze 0, overexposure 56, overly dark 0, scene change 0, streak 58, noise 36, color cast 1, blur 0, low contrast 0, shake 0, weight [0.1,0.3, … 0.05.05 ] used by the face comparison rule, at which time a face comparison event is reported. The initial confidence Ti of the original face comparison event is accompanied by an event, and is assumed to be 95%, which means that the similarity between the face and the face registered in the database reaches 95%. Then, the confidence To of the detected event at the current video quality diagnosis result is 78% according To dynamic calculation. This correction process is then the correction of the confidence level by the video quality quantization index and the weights. Assuming that the effective confidence of the face detection event is defined as [ 80%, 100% ], since the confidence of the detection event is only 78%, the event can be regarded as an invalid event, an alarm cannot be triggered, and false intelligent detection due to poor picture quality is avoided.
Wherein, the preset confidence coefficient calculation formula is as follows:
wherein (0. ltoreq. Qi≤100，0≤Wi≤1)，
Q1-Q12 are detected values of 12 detection types analyzed by video quality diagnosis, and the value range is [0,100 ]]。WiIs determined according To the current detection rule, To is the confidence coefficient of the detection event under the current video quality diagnosis result, and Ti is the initial confidence coefficient of the detection event.
Through the steps S201 to S205, in the embodiment of the present application, after the video to be detected is acquired, the video to be detected needs to be detected according to the detection type, and the detection events divided according to the detection type are output. Because the judgment methods of each type of detection event are inconsistent, the corresponding type of detection event can be output only if the video to be detected needs to be divided according to the detection requirement; then, diagnosing the video to be detected according to a preset video quality quantization index, and diagnosing the video to be detected through the video quality quantization index to obtain a diagnosis result of the video to be detected so as to judge the quality of the video, wherein the confidence degrees of detection events under different video quality diagnosis results are different, so that the video to be detected needs to be diagnosed; next, according to the detection event and the video quality diagnosis result, calculating the confidence coefficient of the detection event under the current video quality diagnosis result, because the confidence coefficient of each type of detection event under different video quality is different, the confidence coefficient of the detection event under the current video quality diagnosis result needs to be dynamically calculated according to the detection event and the video quality diagnosis result, and the most accurate confidence coefficient of the current detection event can be obtained; and finally, according to a preset confidence interval, judging the confidence of the detection event under the current video quality diagnosis result obtained by calculation, filtering the detection event of which the confidence is not in the confidence interval, and screening the detection event of which the confidence is not in the confidence interval.
According to the embodiment of the application, the detection event is associated with the video quality diagnosis result, the confidence coefficient of the intelligent reporting result is adjusted in real time by pertinently acquiring the relevant video quality information, and the false alarm rate of the alarm event is effectively reduced.
In one embodiment, dynamically calculating a confidence level of the detected event at the current video quality diagnostic based on the detected event and the video quality diagnostic comprises: based on the detection event, acquiring the detection type of the detection event and the initial confidence of the detection event; and calculating the confidence coefficient of the detection event under the current video quality diagnosis result according to the detection type of the detection event, the initial confidence coefficient of the detection event and the video quality diagnosis result.
Wherein the confidence calculation can be calculated according to the following formula:
wherein (0. ltoreq. Qi≤100，0≤Wi≤1)，
Q1-Q12 are detected values of 12 detection types analyzed by video quality diagnosis, and the value range is [0,100 ]]。WiThe method is determined according to the current detection type, and when W1-W12 represent a certain detection type, the influence weight of each video quality quantization index on the detection result is weighted. For example, the current face comparison type is, the values of W1-W12 are [0.1,0.3, … 0.05]](ii) a When the detection type is changed into non-motor vehicle detection, the values of W1-W12 are [0.05,0.1, … 0.05]]. Therefore, when the detection types are changed, W1-W12 are also adjusted at the same time, and the values of W1-W12 are dynamically adjusted to adapt to different detection types.
In one embodiment, after determining the calculated confidence level of the detection event under the current video quality diagnosis result according to a preset confidence level interval, the method further includes:
and if the confidence coefficient of the detection event is in the confidence coefficient interval under the current video quality diagnosis result, determining that the detection event is an alarm event, and outputting the alarm event to the terminal.
And judging the detection event in the confidence interval as an alarm event, outputting the alarm event to the terminal, and timely reminding the detection personnel of the occurrence of the alarm event.
In one embodiment, the video quality quantization index includes: one or more of lost, occluded, frozen, overexposed, overly dark, scene change, streaks, noise, color cast, blurred, low contrast, and jittered.
The quality of the current video is judged according to the set video quantization indexes by setting the video quality quantization indexes to be one or more, so that the problem of simple indexes for evaluating the video quality in the related technology is solved, and applicable detection scenes are increased.
In one embodiment, after the acquiring the video to be detected, the method further comprises:
and setting a video quality quantization index and a detection type.
The quality and the event of the video to be detected can be better judged by setting the quality index and the detection type of the video.
The present embodiment further provides an event detection device based on video quality, which is used to implement the foregoing embodiments and preferred embodiments, and the description of the event detection device is omitted for brevity. As used hereinafter, the terms "module," "unit," "subunit," and the like may implement a combination of software and/or hardware for a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
Fig. 3 is a block diagram of an event detection structure based on video quality according to an embodiment of the present application, and as shown in fig. 3, the apparatus includes: a video acquisition module 31, a video quality analysis module 32, a quality diagnosis module 33, a confidence calculation module 34 and an event filtering module 35;
the video acquisition module 31 is used for acquiring a video to be detected;
the video event analysis module 32 is used for detecting the video to be detected according to the detection type and outputting a detection event;
the video quality analysis module 33 is configured to diagnose the video to be detected according to a preset video quality quantization index to obtain a video quality diagnosis result of the video to be detected;
a confidence calculation module 34, configured to dynamically calculate a confidence of the detection event under the current video quality diagnosis result according to the detection event and the video quality diagnosis result;
the event filtering module 35 is configured to judge the confidence of the detection event obtained by calculation under the current video quality diagnosis result according to a preset confidence interval, and filter the detection event whose confidence is not in the confidence interval.
In some embodiments, the confidence calculation module 34 is further configured to obtain, based on the detection event, a detection type of the detection event and an initial confidence of the detection event;
and calculating the confidence coefficient of the detection event under the current video quality diagnosis result according to the detection type of the detection event, the initial confidence coefficient of the detection event and the video quality diagnosis result.
In some embodiments, in the confidence calculation module 34, the type of detection includes:
face detection, tripwire detection, intrusion detection, human detection, non-motorized detection, motor vehicle detection, and/or face comparison.
In some of these embodiments, the apparatus further comprises: and the alarm module is used for determining that the detection event is an alarm event and outputting the alarm event to the terminal if the confidence coefficient of the detection event is within the confidence coefficient interval under the current video quality diagnosis result.
In some embodiments, in the quality diagnosis module 33, the video quality quantization index includes: one or more of lost, occluded, frozen, overexposed, overly dark, scene change, streaks, noise, color cast, blurred, low contrast, and jittered.
In some of these embodiments, the apparatus further comprises: and the setting module is used for setting the video quality quantization index and the detection type.
The above modules may be functional modules or program modules, and may be implemented by software or hardware. For a module implemented by hardware, the modules may be located in the same processor; or the modules can be respectively positioned in different processors in any combination.
The present embodiment also provides a computer device comprising a memory having a computer program stored therein and a processor arranged to run the computer program to perform the steps of any of the method embodiments described above.
Optionally, the electronic apparatus may further include a transmission device and an input/output device, wherein the transmission device is connected to the processor, and the input/output device is connected to the processor.
Optionally, in this embodiment, the processor may be configured to execute the following steps by a computer program:
step S1, acquiring a video to be detected;
step S2, detecting the video to be detected according to the detection type, and outputting a detection event;
step S3, diagnosing the video to be detected according to a preset video quality quantization index to obtain a video quality diagnosis result of the video to be detected;
step S4, according to the detection event and the video quality diagnosis result, dynamically calculating the confidence of the detection event under the current video quality diagnosis result;
step S5, according to a preset confidence interval, determining the calculated confidence of the detection event in the current video quality diagnosis result, and filtering the detection event whose confidence is not in the confidence interval.
It should be noted that, for specific examples in this embodiment, reference may be made to examples described in the foregoing embodiments and optional implementations, and details of this embodiment are not described herein again.
In an embodiment, a computer-readable storage medium is provided, fig. 4 is a block diagram of a computer-readable storage medium according to an embodiment of the present application, and fig. 4 shows a computer program stored thereon, where the computer program is executed by a processor to implement the steps in a video quality-based event detection method provided by the embodiments, where the steps are as follows:
step S1, acquiring a video to be detected;
step S2, detecting the video to be detected according to the detection type, and outputting a detection event;
step S3, diagnosing the video to be detected according to a preset video quality quantization index to obtain a video quality diagnosis result of the video to be detected;
step S4, according to the detection event and the video quality diagnosis result, dynamically calculating the confidence of the detection event under the current video quality diagnosis result;
step S5, according to a preset confidence interval, determining the calculated confidence of the detection event in the current video quality diagnosis result, and filtering the detection event whose confidence is not in the confidence interval.
Those skilled in the art will appreciate that the architecture shown in fig. 4 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to serve as a limitation on the computer-readable storage media on which the disclosed aspects may be implemented, as a particular computing device may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above examples only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. An event detection method based on video quality, comprising:
acquiring a video to be detected;
detecting the video to be detected according to the detection requirement, and outputting a detection event;
diagnosing the video to be detected according to a preset video quality quantization index to obtain a video quality diagnosis result of the video to be detected;
according to the detection event and the video quality diagnosis result, dynamically calculating the confidence coefficient of the detection event under the current video quality diagnosis result;
and judging the confidence coefficient of the detection event under the current video quality diagnosis result obtained by calculation according to a preset confidence coefficient interval, and filtering the detection event of which the confidence coefficient is not in the confidence coefficient interval.
2. The method of claim 1, wherein dynamically calculating a confidence level of the detection event at the current video quality diagnosis based on the detection event and the video quality diagnosis comprises:
based on the detection event, acquiring the detection type of the detection event and the initial confidence of the detection event;
and calculating the confidence coefficient of the detection event under the current video quality diagnosis result according to the detection type of the detection event, the initial confidence coefficient of the detection event and the video quality diagnosis result.
3. The method of claim 2, wherein the detecting the type comprises:
face detection, tripwire detection, intrusion detection, human detection, non-motorized detection, motor vehicle detection, and/or face comparison.
4. The method according to any one of claims 1 to 3, wherein after the determining the calculated confidence level of the detected event at the current video quality diagnosis result according to a preset confidence level interval, the method further comprises:
and if the confidence of the detection event is in the confidence interval under the current video quality diagnosis result, determining that the detection event is an alarm event, and outputting the alarm event to a terminal.
5. The method according to any one of claims 1 to 3, wherein the video quality metrics comprise: one or more of lost, occluded, frozen, overexposed, overly dark, scene change, streaks, noise, color cast, blurred, low contrast, and jittered.
6. The method according to any one of claims 1 to 3, wherein after said acquiring the video to be detected, the method further comprises:
and setting the video quality quantization index and the detection type.
7. An event detection system based on video quality, comprising: a camera device, a transmission device, and a server device; wherein the camera device is connected to the server device through the transmission device;
the camera equipment is used for acquiring a video to be detected;
the transmission device is used for transmitting the video to the server device;
the server equipment is used for detecting the video to be detected according to the detection type and outputting a detection event; diagnosing the video to be detected according to a preset video quality quantization index to obtain a video quality diagnosis result of the video to be detected; according to the detection event and the video quality diagnosis result, dynamically calculating the confidence coefficient of the detection event under the current video quality diagnosis result; and judging the confidence coefficient of the detection event under the current video quality diagnosis result obtained by calculation according to a preset confidence coefficient interval, and filtering the detection event of which the confidence coefficient is not in the confidence coefficient interval.
8. An apparatus for image quality detection, comprising: the video acquisition module, the event output module, the quality diagnosis module, the confidence coefficient calculation module and the event filtering module comprise:
the video acquisition module is used for acquiring a video to be detected;
the event output module is used for detecting the video to be detected according to the detection type and outputting a detection event;
the quality diagnosis module is used for diagnosing the video to be detected according to a preset video quality quantization index to obtain a video quality diagnosis result of the video to be detected;
the confidence calculation module: the confidence coefficient of the detection event under the current video quality diagnosis result is dynamically calculated according to the detection event and the video quality diagnosis result;
the event filtering module is used for judging the confidence coefficient of the detection event under the current video quality diagnosis result according to a preset confidence coefficient interval, and filtering the detection event of which the confidence coefficient is not in the confidence coefficient interval.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements a video quality based event detection method according to any of claims 1 to 6 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out a video quality based event detection method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110115669.5A CN112949390B (en) | 2021-01-28 | 2021-01-28 | Event detection method and device based on video quality |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110115669.5A CN112949390B (en) | 2021-01-28 | 2021-01-28 | Event detection method and device based on video quality |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112949390A true CN112949390A (en) | 2021-06-11 |
| CN112949390B CN112949390B (en) | 2024-03-15 |
Family
ID=76238446
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110115669.5A Active CN112949390B (en) | 2021-01-28 | 2021-01-28 | Event detection method and device based on video quality |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112949390B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114332915A (en) * | 2021-12-02 | 2022-04-12 | 深圳云天励飞技术股份有限公司 | Human body attribute detection method and device, computer equipment and storage medium |
| CN114928740A (en) * | 2021-11-25 | 2022-08-19 | 广东利通科技投资有限公司 | Video quality detection method, device, equipment, storage medium and program product |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070092143A1 (en) * | 2005-10-21 | 2007-04-26 | The Boeing Company | System, method and computer program product for adaptive video processing |
| CN102395043A (en) * | 2011-11-11 | 2012-03-28 | 北京声迅电子股份有限公司 | Video quality diagnosing method |
| CN104780361A (en) * | 2015-03-27 | 2015-07-15 | 南京邮电大学 | Quality evaluation method for urban video monitoring system |
| US20150288874A1 (en) * | 2012-10-23 | 2015-10-08 | Ishay Sivan | Real time assessment of picture quality |
| CN105430384A (en) * | 2015-12-10 | 2016-03-23 | 青岛海信网络科技股份有限公司 | Video quality diagnosis method and system |
| CN105740758A (en) * | 2015-12-31 | 2016-07-06 | 上海极链网络科技有限公司 | Internet video face recognition method based on deep learning |
| CN106851263A (en) * | 2017-03-30 | 2017-06-13 | 安徽四创电子股份有限公司 | Video quality diagnosing method and system based on timing self-learning module |
| CN108182444A (en) * | 2017-12-08 | 2018-06-19 | 深圳英飞拓科技股份有限公司 | The method and device of video quality diagnosis based on scene classification |
| CN112241696A (en) * | 2020-09-28 | 2021-01-19 | 深圳市商汤科技有限公司 | Image processing method and device, electronic device and storage medium |
-
2021
- 2021-01-28 CN CN202110115669.5A patent/CN112949390B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070092143A1 (en) * | 2005-10-21 | 2007-04-26 | The Boeing Company | System, method and computer program product for adaptive video processing |
| CN102395043A (en) * | 2011-11-11 | 2012-03-28 | 北京声迅电子股份有限公司 | Video quality diagnosing method |
| US20150288874A1 (en) * | 2012-10-23 | 2015-10-08 | Ishay Sivan | Real time assessment of picture quality |
| CN104780361A (en) * | 2015-03-27 | 2015-07-15 | 南京邮电大学 | Quality evaluation method for urban video monitoring system |
| CN105430384A (en) * | 2015-12-10 | 2016-03-23 | 青岛海信网络科技股份有限公司 | Video quality diagnosis method and system |
| CN107071398A (en) * | 2015-12-10 | 2017-08-18 | 青岛海信网络科技股份有限公司 | A kind of video quality diagnosing method and system |
| CN105740758A (en) * | 2015-12-31 | 2016-07-06 | 上海极链网络科技有限公司 | Internet video face recognition method based on deep learning |
| CN106851263A (en) * | 2017-03-30 | 2017-06-13 | 安徽四创电子股份有限公司 | Video quality diagnosing method and system based on timing self-learning module |
| CN109167997A (en) * | 2017-03-30 | 2019-01-08 | 安徽四创电子股份有限公司 | A kind of video quality diagnosis system and method |
| CN108182444A (en) * | 2017-12-08 | 2018-06-19 | 深圳英飞拓科技股份有限公司 | The method and device of video quality diagnosis based on scene classification |
| CN112241696A (en) * | 2020-09-28 | 2021-01-19 | 深圳市商汤科技有限公司 | Image processing method and device, electronic device and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 赵薇;: "基于模糊Petri网的监控视频事件建模与识别", 中国科技信息, no. 17 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114928740A (en) * | 2021-11-25 | 2022-08-19 | 广东利通科技投资有限公司 | Video quality detection method, device, equipment, storage medium and program product |
| CN114332915A (en) * | 2021-12-02 | 2022-04-12 | 深圳云天励飞技术股份有限公司 | Human body attribute detection method and device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112949390B (en) | 2024-03-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109166261B (en) | Image processing method, device and equipment based on image recognition and storage medium | |
| US9497425B2 (en) | Motion detection method and device using the same | |
| CN112291520B (en) | Abnormal event identification method and device, storage medium and electronic device | |
| CN111163259A (en) | Image capturing method, monitoring camera and monitoring system | |
| US20180144476A1 (en) | Cascaded-time-scale background modeling | |
| CN111210399B (en) | Imaging quality evaluation method, device and equipment | |
| CN112949390A (en) | Event detection method and device based on video quality | |
| CN111723773B (en) | Method and device for detecting carryover, electronic equipment and readable storage medium | |
| CN111354024B (en) | Behavior prediction method of key target, AI server and storage medium | |
| WO2022041484A1 (en) | Human body fall detection method, apparatus and device, and storage medium | |
| CN109960969B (en) | Method, device and system for generating moving route | |
| CN109145771A (en) | A kind of face snap method and device | |
| CN111654700A (en) | Privacy mask processing method and device, electronic equipment and monitoring system | |
| CN102740121A (en) | Video quality diagnosis control system and method applied to video monitoring network | |
| CN111444758A (en) | Pedestrian re-identification method and device based on spatio-temporal information | |
| CN108174198B (en) | Video image quality diagnosis analysis detection device and application system | |
| CN113869137A (en) | Event detection method and device, terminal equipment and storage medium | |
| CN115346060A (en) | Picture abnormity identification method and device, electronic equipment and storage medium | |
| CN115909215A (en) | Edge intrusion early warning method and system based on target detection | |
| CN111814776A (en) | Image processing method, device, server and storage medium | |
| CN110795998A (en) | People flow detection method and device, electronic equipment and readable storage medium | |
| CN113657198A (en) | Binocular living body face recognition method and device, electronic device and storage medium | |
| CN115082326A (en) | Processing method for deblurring video, edge computing equipment and central processor | |
| US10916016B2 (en) | Image processing apparatus and method and monitoring system | |
| CN114359828A (en) | Target behavior recording method, device, storage medium and electronic device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |