WO2023179161A1

WO2023179161A1 - Video frame rate control method and apparatus, and electronic device and storage medium

Info

Publication number: WO2023179161A1
Application number: PCT/CN2022/143524
Authority: WO
Inventors: 曾卫东
Original assignee: 深圳云天励飞技术股份有限公司
Priority date: 2022-03-22
Filing date: 2022-12-29
Publication date: 2023-09-28
Also published as: CN114679607A; CN114679607B

Abstract

The present invention relates to the technical field of video detection, and in particular to a video frame rate control method and apparatus, and an electronic device and a storage medium. The video frame rate control method comprises: performing frame extraction on a video stream on the basis of an initial frame extraction frequency, so as to obtain video frame data; performing coding processing on the video frame data, so as to generate picture coding data; identifying current event data which is comprised in the picture coding data; and performing primary modification on the initial frame extraction frequency according to the current event data, so as to determine a target frame extraction frequency for performing frame extraction on the video stream. By means of the present invention, an algorithm can be called according to the current event data of a video stream to dynamically redefine a frame extraction interval duration, such that not only can resources which are occupied by low-frequency events be reduced, but the identification quantity of high-frequency events can also be increased; and frame extraction is performed on the subsequent video stream according to a target frame extraction frequency which is obtained after modification, such that an algorithm identification rate of an algorithm training platform can be improved in different application scenarios.

Description

A video frame rate control method, device, electronic equipment and storage medium

Technical field

This application requests the priority of the Chinese patent application submitted to the China Patent Office on March 22, 2022, with the application number 202210283048.2 and the invention title "A video frame rate control method, device, electronic equipment and storage medium", all of which The contents are incorporated into this application by reference.

The present invention relates to the field of video detection technology, and in particular to a video frame rate control method, device, electronic equipment and storage medium.

Background technique

Video structured description technology refers to extracting key information through intelligent analysis of the original video, and performing semantic description of the text to obtain the structured semantic information of the video. Through video structured description technology, video data can be used for target classification and recognition, target posture recognition, target object segmentation, etc.

In the existing technology, the mainstream camera video streaming service frame extraction method is to extract frames once every few seconds by default or manually configured, and when using different algorithms at the same time, resources are repeatedly consumed for different algorithms. In fact, in different application scenarios, the status of objects in the video stream is different. Therefore, using a fixed frame frequency is not conducive to object recognition. It can be seen that in the existing video frame extraction, there are problems of small difference and low recognition efficiency.

Technical solutions

Embodiments of the present invention provide a video frame rate control method, aiming to solve the problems of small differences and low recognition efficiency in existing video frame rate control methods.

In a first aspect, an embodiment of the present invention provides a video frame rate control method. The method includes the following steps:

Extract frames from the video stream based on the initial frame extraction frequency to obtain video frame data;

identifying current event data included in the picture encoded data;

The initial frame decimation frequency is initially modified according to the current event data to determine a target frame decimation frequency for decimating the video stream.

In a second aspect, an embodiment of the present invention also provides a video frame rate control device, including:

The frame extraction module is used to extract frames from the video stream based on the initial frame extraction frequency to obtain video frame data;

An identification module, used to identify the current event data included in the picture encoding data;

A modification module, configured to perform an initial modification to the initial frame extraction frequency according to the current event data to determine a target frame extraction frequency for extracting frames on the video stream.

In a third aspect, embodiments of the present invention further provide an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the computer program. When implementing the steps in the video frame rate control method provided by the embodiment of the present invention.

In a fourth aspect, embodiments of the present invention also provide a computer-readable storage medium. A computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, the video frame rate provided by the embodiment of the present invention is achieved. Control the steps in the method.

In the embodiment of the present invention, the video stream is extracted based on the initial frame extraction frequency to obtain video frame data; the video frame data is encoded to generate picture encoded data; and the current frame included in the picture encoded data is identified. Event data: perform an initial modification to the initial frame extraction frequency according to the current event data to determine a target frame extraction frequency for extracting frames on the video stream. Therefore, the embodiment of the present invention can mobilize the algorithm to dynamically redefine the frame interval duration according to the current event data of the video stream, which can not only reduce the resources occupied by low-frequency events, but also increase the number of identifications of high-frequency events, thereby achieving Quickly obtain algorithm materials, and extract frames from subsequent video streams based on the modified target frame frequency. For application in different scenarios, it can improve the algorithm recognition rate of the algorithm training platform.

Description of the drawings

The drawings needed to be used in the embodiments of this application will be introduced below.

Figure 1 is a schematic structural diagram of a system provided by an embodiment of the present invention;

Figure 2 is a flow chart of a video frame rate control method provided by an embodiment of the present invention;

Figure 3a is a flow chart of another video frame rate control method provided by an embodiment of the present invention;

Figure 3b is a flow chart of another video frame rate control method provided by an embodiment of the present invention;

Figure 3c is a flow chart of another video frame rate control method provided by an embodiment of the present invention;

Figure 3d is a flow chart of another video frame rate control method provided by an embodiment of the present invention;

Figure 4 is a schematic structural diagram of a video frame rate control device provided by an embodiment of the present invention;

Figure 5 is a schematic structural diagram of a modification module provided by an embodiment of the present invention;

Figure 6 is a schematic structural diagram of another video frame rate control device provided by an embodiment of the present invention;

Figure 7 is a schematic structural diagram of another video frame rate control device provided by an embodiment of the present invention;

Figure 8 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention.

Embodiments of the invention

The embodiments of the present application are described below with reference to the accompanying drawings.

As shown in Figure 1, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is a medium used to provide communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

Users can use terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages, etc. The terminal devices 101, 102, and 103 may be collection devices. The terminal devices 101, 102, and 103 may be cameras with video collection functions, passenger flow cameras, etc. A camera, also known as a computer camera, computer eye, electronic eye, etc., is a video input device that is widely used in video conferencing, telemedicine, and real-time monitoring.

The server 105 may be a server that provides various services, such as a background server that provides support for video streams and image information collected by the terminal devices 101, 102, and 103.

It should be noted that the video frame rate control method provided by the embodiments of the present application is generally executed by a server. Correspondingly, a video frame rate control device is generally provided in the server.

It should be understood that the number of terminal devices, networks and servers in Figure 1 is only illustrative. Depending on implementation needs, there can be any number of end devices, networks, and servers.

As shown in Figure 2, Figure 2 is a flow chart of a video frame rate control method provided by an embodiment of the present invention. As shown in Figure 2, it includes the following steps:

S201. Extract frames from the video stream based on the initial frame extraction frequency to obtain video frame data.

Among them, the video frame rate control method provided in this embodiment uses electronic devices in scenarios including but not limited to urban governance, such as road monitoring, personnel identification, environmental monitoring, etc. Among them, the above video stream can be collected through a collection device, specifically, it can be a video collected online in real time, or a video saved offline. Collection equipment includes cameras, passenger flow cameras and other image collection equipment that can perform video collection, picture storage and processing. In this embodiment, the above-mentioned collection device refers to a camera as an example. The above-mentioned video stream may refer to a video stream that requires frame extraction, decoding, encoding, recognition analysis, etc. Video streaming refers to the transmission of video data. For example, video streaming can be processed as a stable and continuous stream through the network.

After the video stream is obtained through the camera, video frames can be extracted from the video stream, and frame extraction will obtain the above-mentioned video frame data. Specifically, each video will first form a frame number before extracting frames. The number of frames in a video refers to the amount of pictures transmitted in 1 second. It can also be understood as how many times the graphics processor can refresh per second. It is usually expressed in terms of fps (Frames). Per Second) said. The above-mentioned video frame extraction is to extract several frames at certain intervals from a video, simulating the process of taking a photo at regular intervals and joining them together to form a video. Initially, you can pre-set the initial frame extraction frequency area of the camera to control frame extraction, and use the set initial frame extraction frequency to extract frames from the video stream and cache them at the same time. Caching the data after frame extraction can save resources when calling multiple algorithms for the same camera at the same time. It does not need to be obtained from the video stream every time. Obtaining it directly from the cache can save resources.

S202. Encode the video frame data to generate image encoding data.

Specifically, the above-mentioned picture coded data can be obtained after coding the video frame data. The above image encoding data may be data obtained based on base64 encoding. Base64 encoding is a method of encoding data with 64 printable characters. The underlying implementation of any data is binary, so base64 encoding can be performed. Base64 encoding is mainly used in the data transmission process (encoding, decoding).

S203. Identify the current event data included in the picture encoding data.

Among them, the algorithm warehouse can be called, and the corresponding algorithm can be retrieved from the algorithm warehouse according to the picture encoding data for identification, so as to obtain the current event data included in the picture encoding data. The current event data may refer to the results obtained after analyzing the video stream, such as roads included in the video stream, people and vehicles on the road, road conditions, etc.

S204. Modify the initial frame extraction frequency for the first time according to the current event data to determine the target frame extraction frequency for extracting frames on the video stream.

Among them, the initial frame sampling frequency may also refer to the frame sampling frequency when the camera was last used. The above-mentioned current event data may include specific event content, and the event content may include recognition target, recognition time, recognition location, recognition result, frame extraction frequency during recognition, etc. According to the event content, the corresponding identification can be called to modify the initial frame extraction frequency according to the event content, and finally determine the appropriate target frame extraction frequency to modify and adjust the initial frame extraction frequency, and at the same time record the data of each modification. For example, if the event content is road damage detection, and the frame frequency of the image frames to be obtained is small, the corresponding road damage detection algorithm is modified to obtain a longer time interval for each image frame, because the long-term images of road damage detection are consistent. , the change rate is low. Of course, when the event content includes data with high fluidity and high degree of transformation, the corresponding algorithm will increase the frequency of frame extraction for identification. Another example: when the camera is set in a shopping mall or urban traffic scene, and a large number of people appear in the video stream or a large number of vehicles appear in the video stream through the recognition algorithm in a short period of time, the initial frame extraction can be improved. frequency.

In the embodiment of the present invention, the video stream is extracted based on the initial frame frequency to obtain video frame data; the video frame data is encoded to generate picture encoded data; the current event data included in the picture encoded data is identified; according to The current event data makes an initial modification to the initial decimation frequency to determine the target decimation frequency for decimating the video stream. Therefore, the embodiment of the present invention can mobilize the algorithm to dynamically redefine the frame interval duration according to the current event data of the video stream, which can not only reduce the resources occupied by low-frequency events, but also increase the number of identifications of high-frequency events, thereby achieving Quickly obtain algorithm materials, and extract frames from subsequent video streams based on the modified target frame frequency. For application in different scenarios, it can improve the algorithm recognition rate of the algorithm training platform.

As shown in Figure 3a, Figure 3a is a flow chart of another video frame rate control method provided by an embodiment of the present invention. As shown in Figure 3, it includes the following steps:

S301. Extract frames from the video stream based on the initial frame extraction frequency to obtain video frame data.

S302. Encode the video frame data to generate image encoding data.

S303. Identify the current event data included in the picture encoding data.

S304. Obtain the historical event content in the historical event data.

The above historical event data may include image data of video streams previously acquired by the camera, and each image data is matched with a corresponding frame rate. The above historical event content may include person identification, road identification, animal identification, etc.

S305. Calculate the matching degree between the event content and the historical event content.

Among them, after obtaining the current event content, in order to facilitate modification of the corresponding frame extraction frequency, the current event content can be compared with the historical event content. The amount of historical event data is large. When performing identification and comparison, it is best to determine the event type to which the current event content belongs, and then lock the corresponding historical event content of the same type in the historical event data according to the event type, and then add the current event content Compare it one by one with historical event content of the same type and filter out the historical event content with the highest matching degree.

More specifically, event content and historical event content correspond to different recognition algorithms. The recognition algorithms are included in the algorithm bin. Different recognition algorithms can correspond to different recognition objects. For example, when used for person recognition, it can include human body key point recognition algorithms. , human feature recognition algorithms, etc., which can include license plate recognition algorithms when used for road vehicle detection. The above event types may include but are not limited to person identification, vehicle identification, road condition identification, animal identification, etc. Historical event information can be cached in a preset cache area in the background. Of course, the cache time can be set, for example, historical event information within 1 month can be cached.

S306. If the matching degree meets the matching degree threshold, modify the initial frame extraction frequency of the current event data according to the frame extraction frequency of the historical event content to determine the target frame extraction frequency for extracting frames for the video stream.

Among them, after filtering out the historical event content with the highest matching degree, it can be compared with the preset matching degree threshold. If the matching degree threshold is met, the current time data can be extracted based on the frame extraction frequency corresponding to the historical event content with the highest matching degree. The initial decimation frequency is modified to determine the target decimation frequency for decimating the video stream. In this way, when the same type of event content is encountered again, the recognition speed and accuracy of the algorithm can be accelerated.

S308. If the matching degree does not meet the matching degree threshold, modify the frame extraction frequency based on the preset frame extraction frequency to determine the target frame extraction frequency for extracting frames for the video stream.

Of course, if the matching degree of the historical event content with the highest matching degree still does not meet the matching degree threshold, it may mean that the same camera has not yet been recognized/the recognition data is small. In this case, the initial frame sampling frequency can be based on the preset frame sampling frequency. to modify.

As another possible embodiment, as shown in FIG. 3b , FIG. 3b is a flow chart of another video frame rate control method provided by an embodiment of the present invention. After the above step S305, it also includes:

308. Obtain the environmental parameters of the collection device that collects the video stream.

Among them, due to the different application scenarios of the collection equipment (camera), the environmental parameters of the camera can refer to the environment where the camera is used, including: day, night, indoors, outdoors, tourist attractions, restaurants, schools, shopping malls, garages, etc. Therefore, the environmental parameters of the camera that collects the video stream can be obtained, and the initial frame rate can be modified based on the environmental parameters.

309. According to the matching degree between the event content and the historical event content, and the environmental parameters of the collection device, the initial frame extraction frequency of the video stream is modified again to determine the target frame extraction frequency for the video stream.

After obtaining the environmental parameters of the camera, the initial frame rate of the video stream can be modified again by combining the environmental parameters of the camera with the obtained frame rate of the historical event content with the highest matching degree. In this way, adjusting the initial frame extraction frequency in combination with multiple dimensions will help improve the recognition rate of the algorithm in the background, and enable more efficient recognition in the future.

As another possible embodiment, as shown in FIG. 3c , another video frame rate control method flow chart provided by an embodiment of the present invention, after the above step S305, also includes:

310. Obtain the built-in performance parameters of the collection device that collects video streams.

Among them, the camera's built-in performance parameters may refer to the camera's own parameters. Because they are set in different environments, the built-in performance parameters of the corresponding cameras will be adjusted to a certain extent, and the built-in performance parameters corresponding to different models of cameras are also inconsistent, such as: the resolution and video quality of the camera in day and night environments. When it is set up in a garage with lighting conditions, you can choose a relatively low-resolution camera, and when it is used in a shopping mall, you can choose some high-definition cameras.

311. Based on the matching degree between the event content and the historical event content and the built-in performance parameters of the collection device, modify the initial frame extraction frequency of the video stream again to determine the target frame extraction frequency for the video stream.

After obtaining the built-in performance parameters of the camera, the initial frame rate of the video stream can be modified again by combining the built-in performance parameters of the camera with the frame rate of the historical event content obtained above with the highest matching degree. In this way, adjusting the initial frame extraction frequency in combination with multiple dimensions will help improve the recognition rate of the algorithm in the background, and enable more efficient recognition in the future.

As another possible embodiment, as shown in FIG. 3d , FIG. 3d is a flow chart of another video frame rate control method provided by an embodiment of the present invention. It is also possible to modify the initial frame frequency of the video stream by combining the matching degree between the event content of the current event data and the historical event content, the built-in performance parameters of the camera, and the environmental parameters of the camera. By quantifying each modification condition (matching degree, built-in performance parameters and environmental parameters), the quantized value is matched to each of the above conditions, and the initial frame frequency is modified based on the quantized value through the characteristics of the corresponding algorithm. In this way, adjusting the initial frame extraction frequency in combination with more dimensional conditions is more conducive to improving the recognition rate of the algorithm in the background, and allows for more efficient recognition in the future.

In addition, the recognition time of the algorithm can also be combined. For example, when using the animal recognition algorithm to identify animals in the video stream at night, the initial frame extraction frequency of the video stream is increased. When running algorithms related to human activities during the day, the frequency of the corresponding video stream is increased. Initial decimation frequency. In this way, the frame extraction frequency of the video stream can be increased for application scenarios with a large amount of activity; the frame extraction frequency of the video stream can be reduced for application scenarios with a small amount of activity.

Optionally, the method also includes: re-adjusting the target frame extraction frequency based on the multiple modification data.

When the initial frame frequency is modified multiple times, each modification data will be recorded. Different modification parameters (historical event data, environmental parameters, built-in parameters, etc.) can be matched with a weight, and modifications can also be set. The target frame frequency is adjusted again based on the priority of the comparison parameter, combined with the modification of the weight and/or priority of the comparison parameter, and then used as the final modification data for frame rate modification. This can improve the recognition accuracy of the algorithm.

Optionally, as shown in Figure 3d, the method also includes: obtaining the event type and event content of the current event data, and adjusting the resolution of the collection device based on the event type and event content of the current event data.

Among them, the corresponding event type and event content can be analyzed based on the current time data obtained by extracting frames from the video stream. For example, the current camera c is recognized for license plate recognition, and the recognition content includes vehicle entry and exit management in the community at 20 o'clock in the evening. The resolution of camera c can be enhanced to address the impact of the environment on license plate recognition at night. If the same camera c recognizes content at 12 noon, the resolution can be reduced compared to that at night, because the environment itself provides a certain brightness.

In the embodiment of the present invention, the historical event content with the highest matching degree is obtained by comparing the event content of the current event data with the historical event content, and the frame extraction frequency of the historical event content with the highest matching degree is used as the event content of the current event data. Modify the data to mobilize the algorithm to dynamically redefine the frame interval duration, which can not only reduce the resources occupied by low-frequency events, but also increase the number of identifications of high-frequency events, thereby achieving rapid acquisition of algorithm materials. According to the modified The target frame extraction frequency is used to extract frames for subsequent video streams, which can improve the algorithm recognition rate of the algorithm training platform for use in different scenarios. Secondly, by extracting frames from the video stream based on the initial frame extraction frequency and caching it, when multiple algorithms are called for the same camera at the same time, there is no need to obtain them from the video stream each time. Obtaining them directly from the cache can save resources. . In addition, the initial frame frequency is modified again by combining the matching degree between the event content of the current event data and the historical event content, the environmental parameters of the camera and/or the built-in parameters of the camera, combining multiple dimensions and using various methods. Realize automatic modification of the initial frame extraction frequency. By dynamically adjusting the frame extraction frequency of the video stream, it can automatically reduce low-frequency repetitive algorithm identification and improve high-frequency algorithm identification for use in different scenarios, greatly improving The algorithm recognition rate of the algorithm training platform is improved.

As shown in Figure 4, Figure 4 is a module structure diagram of a video frame rate control device provided by an embodiment of the present invention. As shown in Figure 4, the device includes:

The frame extraction module 401 is used to extract frames from the video stream based on the initial frame extraction frequency to obtain video frame data;

Encoding module 402 is used to encode video frame data and generate picture encoded data;

The identification module 403 is used to identify the current event data included in the picture encoding data;

The modification module 404 is configured to first modify the initial frame extraction frequency according to the current event data to determine the target frame extraction frequency for extracting frames on the video stream.

Optionally, the current event data includes event content, and different event content corresponds to different frame extraction frequencies. As shown in Figure 5, Figure 5 is a schematic structural diagram of a modification module provided by an embodiment of the present invention. Among them, the frame extraction module modification module 404 includes:

Acquisition unit 4041, used to obtain historical event content in historical event data;

Identification unit 4042, used to calculate the matching degree between event content and historical event content;

The first modification unit 4043 is configured to modify the initial frame extraction frequency of the current event data according to the frame extraction frequency of the historical event content if the matching degree meets the matching degree threshold, so as to determine the target frame extraction frequency for extracting frames for the video stream. ;

The second modification unit 4044 is used to perform modifications based on the preset frame extraction frequency if the matching degree does not meet the matching degree threshold.

Optionally, as shown in Figure 6, Figure 6 is a schematic structural diagram of another video frame rate control device provided by an embodiment of the present invention. Device 400 also includes:

The first acquisition module 405 is used to acquire the environmental parameters of the collection device where the video stream is collected;

The first calculation module 406 is used to modify the initial frame extraction frequency of the video stream again according to the matching degree between the event content and the historical event content and the environmental parameters of the collection device to determine the target frame extraction for the video stream. frequency.

Optionally, as shown in Figure 7, Figure 7 is a schematic structural diagram of another video frame rate control device provided by an embodiment of the present invention. Device 400 also includes:

The second acquisition module 408 is used to acquire the built-in performance parameters of the collection device that collects the video stream;

The second calculation module 408 is used to modify the initial frame extraction frequency of the video stream again based on the matching degree between the event content and the historical event content and the built-in performance parameters of the collection device to determine the target frame extraction frequency of the video stream. frame rate.

The video frame rate control device provided by the embodiment of the present invention can realize the above-mentioned various implementations of the video frame rate control method, as well as the corresponding beneficial effects. To avoid duplication, they will not be described again here.

As shown in FIG. 8 , FIG. 8 is a structural diagram of an electronic device provided by an embodiment of the present invention. As shown in Figure 8, it includes: a processor 801, a memory 802, a network interface 803, and a computer program stored on the memory 802 and capable of running on the processor 801, wherein:

The processor 801 is used to call the computer program stored in the memory 802 and perform the following steps:

Encode the video frame data to generate image encoding data;

Identify current event data included in the picture encoding data;

The initial frame decimation frequency is initially modified based on the current event data to determine the target frame decimation frequency for decimating the video stream.

Optionally, the current event data includes event content. Different event contents correspond to different frame extraction frequencies. The processor 801 performs an initial modification of the initial frame extraction frequency based on the current event data to determine the target of frame extraction for the video stream. Frame frequency, including:

Obtain historical event content in historical event data;

Calculate the matching degree between event content and historical event content;

If the matching degree meets the matching degree threshold, the initial frame extraction frequency of the current event data is modified according to the frame extraction frequency of the historical event content to determine the target frame extraction frequency for the video stream;

If the matching degree does not meet the matching degree threshold, modifications are made based on the preset frame extraction frequency to determine the target frame extraction frequency for extracting frames for the video stream.

Optionally, after the processor 801 calculates the matching degree between the event content and the historical event content, it also includes:

Obtain the environmental parameters of the collection device that collects the video stream;

Based on the matching degree between the event content and the historical event content and the environmental parameters of the collection device, the initial frame extraction frequency of the video stream is modified again to determine the target frame extraction frequency for the video stream.

Obtain the built-in performance parameters of the collection device that collects the video stream;

Based on the matching degree between the event content and the historical event content, and the built-in performance parameters of the collection device, the initial frame extraction frequency of the video stream is modified again to determine the target frame extraction frequency for the video stream.

Optionally, the processor 801 is also configured to re-adjust the target frame frequency based on the multiple modification data.

Optionally, the processor 801 is also configured to obtain the event type and event content of the current event data, and adjust the resolution of the collection device based on the event type and event content of the current event data.

Embodiments of the present invention also provide a computer-readable storage medium. A computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, each process of the video frame rate control method embodiment provided by the embodiment of the present invention is implemented. , and can achieve the same technical effect, so to avoid repetition, they will not be described again here.

It should be noted that only 801-803 with components are shown in the figure, but it should be understood that implementation of all illustrated components is not required, and more or fewer components may be implemented instead. Among them, those skilled in the art can understand that the electronic device here is a device that can automatically perform numerical calculations and/or information processing according to preset or stored instructions. Its hardware includes but is not limited to microprocessors, special-purpose Integrated circuit (Application Specific Integrated Circuit (ASIC), Programmable Gate Array (Field-Programmable GateArray, FPGA), Digital Signal Processor (DSP), embedded devices, etc.

The electronic device 800 may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The electronic device 800 can perform human-computer interaction with the customer through a keyboard, mouse, remote control, touch pad, or voice-activated device.

The memory 802 includes at least one type of readable storage medium. The readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory ( SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disks, optical disks, etc. In some embodiments, memory 802 may be an internal storage unit of the electronic device, such as a hard drive or memory of the electronic device. In other embodiments, the memory 802 may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), or a secure digital (Secure Digital) device equipped on the electronic device. SD) card, Flash Card, etc. Of course, the memory 802 may also include both the internal storage unit of the electronic device and its external storage device. In this embodiment, the memory 802 is usually used to store operating systems and various application software installed on electronic devices, such as program codes for video frame rate control methods, etc. In addition, the memory 802 can also be used to temporarily store various types of data that have been output or will be output.

Processor 801 may be a central processing unit (Central Processing Unit) in some embodiments. Processing Unit (CPU), controller, microcontroller, microprocessor, or other data processing chip. The processor 801 is typically used to control the overall operation of the electronic device. In this embodiment, the processor 801 is used to run the program code or process data stored in the memory 801, for example, run the program code of the video frame rate control method.

The network interface 803 may include a wireless network interface or a wired network interface. The network interface 803 is generally used to establish a communication connection between the electronic device 800 and other electronic devices.

Embodiments of the present invention also provide a computer-readable storage medium. A computer program is stored on the computer-readable storage medium. When the computer program is executed by the processor 801, each of the video frame rate control method embodiments provided by the embodiment of the present invention is implemented. The process can achieve the same technical effect. To avoid repetition, it will not be described again here.

Those of ordinary skill in the art can understand that all or part of the process of implementing the video frame rate control method of the embodiment can be completed by instructing relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it may include processes such as the embodiments of each method. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory (Read-Only Memory, ROM) or a random access memory 802 (Random Access Memory, RAM for short), etc.

The terms "first", "second", etc. in the description and claims of this application or the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific sequence. Reference herein 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 present application. The appearances of this 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 skilled in the art understand, both explicitly and implicitly, that the embodiments described herein may be combined with other embodiments.

What is disclosed above is only the preferred embodiment of the present invention. Of course, it cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention still fall within the scope of the present invention.

Claims

A video frame rate control method, characterized in that the method includes the following steps:

Extract frames from the video stream based on the initial frame extraction frequency to obtain video frame data;

Encoding the video frame data to generate picture encoding data;

identifying current event data included in the picture encoded data;

The initial frame decimation frequency is initially modified according to the current event data to determine a target frame decimation frequency for decimating the video stream.
The method of claim 1, wherein the current event data includes event content, different event contents correspond to different frame extraction frequencies, and the initial frame extraction frequency is determined according to the current event data. Make an initial modification to determine the target frame frequency for decimating the video stream, including:

Obtain historical event content in historical event data;

Calculate the matching degree between the event content and the historical event content;

If the matching degree meets the matching degree threshold, the initial frame extraction frequency of the current event data is modified according to the frame extraction frequency of the historical event content to determine the target frame extraction frequency for extracting frames for the video stream. ;

If the matching degree does not meet the matching degree threshold, modification is made based on the preset frame extraction frequency to determine the target frame extraction frequency for extracting frames on the video stream.
The method of claim 2, wherein after calculating the matching degree between the event content and historical event content, it further includes:

Obtain the environmental parameters of the collection device that collects the video stream;

According to the matching degree between the event content and the historical event content, and the environmental parameters of the collection device, the initial frame extraction frequency of the video stream is modified again to determine the frame extraction frequency of the video stream. The target frame frequency.
The method of claim 2, wherein after calculating the matching degree between the event content and historical event content, it further includes:

Obtain the built-in performance parameters of the collection device that collects the video stream;

According to the matching degree between the event content and the historical event content and the built-in performance parameters of the collection device, the initial frame extraction frequency of the video stream is modified again to determine the frame extraction frequency of the video stream. The target frame frequency.
The method of claim 1, further comprising:

The target frame frequency is adjusted again based on the multiple modification data.
The method of claim 2, further comprising:

Obtain the event type and event content of the current event data, and adjust the resolution of the collection device based on the event type and event content of the current event data.
A video frame rate control device, characterized by including:

The frame extraction module is used to extract frames from the video stream based on the initial frame extraction frequency to obtain video frame data;

An encoding module, used to encode the video frame data and generate picture encoding data;

An identification module, used to identify the current event data included in the picture encoding data;

A modification module, configured to perform an initial modification to the initial frame extraction frequency according to the current event data to determine a target frame extraction frequency for extracting frames on the video stream.
The device of claim 7, wherein the modification module includes:

The acquisition unit is used to obtain the historical event content in the historical event data;

An identification unit, used to calculate the matching degree between the event content and the historical event content;

A first modification unit configured to modify the initial frame extraction frequency of the current event data according to the frame extraction frequency of the historical event content if the matching degree satisfies the matching degree threshold, to determine whether to perform processing on the video stream. The target frame sampling frequency;

The second modification unit is configured to modify the matching degree based on the preset frame extraction frequency if the matching degree does not meet the matching degree threshold.
An electronic device, characterized in that it includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements claim 1 The steps in a video frame rate control method described in any one of to 6.
A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the method of any one of claims 1 to 6 is implemented. Steps in the video frame rate control method.