Image processing result display method and related device
By acquiring and matching the feature data of the two video streams and aligning the time differences of the video streams using specific timestamps, the problem of inaccurate display of the detection frame in the video stream is solved, and the accurate display of the image processing results is achieved.
Patent Information
- Application Number
- CN202510733281.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-03
- Publication Date
- 2025-09-16
AI Technical Summary
In the prior art, when image processing results are displayed in a video stream, especially when the position of a target changes dramatically between frames, it is difficult for the detection frame to accurately frame the target, resulting in inaccurate display.
By obtaining the feature data of the first and second video streams, aligning the time difference between the two video streams using specific timestamps, matching the target feature data, and displaying the image processing results in the second video stream.
It achieves accurate display of image processing results in video streams, improves the accuracy of detection frames, and is applicable to various video stream formats without increasing the computational burden.
Smart Images
Figure CN120658912A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of image processing technology, and in particular to a method for displaying image processing results and related devices. Background Art
[0002] The artificial intelligence algorithm can process real-time video streams and obtain processing results. For example, target tracking processing is performed on at least part of the video stream. An example of a target may be a license plate, that is, the target license plate is identified from a video stream of a parking lot and tracked. The result of identification and tracking means that the identified target license plate is framed with a detection frame, and the detection frame moves as the target license plate moves in the video frame.
[0003] This method of displaying processing results in the video currently has some problems. For example, when the position of the identified target changes dramatically between frames in the video stream, that is, when the identified target moves quickly, the processing results cannot be accurately displayed in the video stream. For example, the target license plate cannot be accurately framed by the detection frame, and the detection frame may frame other license plates or deviate from the target license plate.
[0004] It can be seen that the accuracy of the display of image processing results needs to be improved. Summary of the Invention
[0005] In view of the above problems, this application provides a method and related device for displaying image processing results to achieve the purpose of improving the accuracy of displaying image processing results. The specific solution is as follows:
[0006] The first aspect of the present application provides a method for displaying image processing results, comprising:
[0007] Obtain first characteristic data of a first video stream and second characteristic data of a second video stream, where the first video stream and the second video stream have the same content and a playback time deviation, the first characteristic data including a first total data amount, time data corresponding to the first total data amount, and an image processing result of the first video stream, the second characteristic data including a second total data amount, the total data amount including a total data amount of an I frame and M frames following the I frame, where M is an integer greater than or equal to 1;
[0008] By matching the first feature data with the second feature data, target feature data matching the second feature data in the first feature data is obtained;
[0009] Based on the target feature data, the image processing result is displayed in the second video stream.
[0010] In a possible implementation, M is the number of frames within the deviation of the playback time of the first video stream and the second video stream.
[0011] In a possible implementation, the first video stream is a real-time stream, and the second video stream is obtained by storing the real-time stream.
[0012] In a possible implementation, before obtaining the first feature data of the first video stream and the second feature data of the second video stream, the method further includes:
[0013] Inserting a specific timestamp into each frame in the first video stream, wherein the specific timestamp of a target frame is an absolute time when an I frame of the target frame is received, and the target frame is any frame;
[0014] The time data includes the specific time stamp.
[0015] In a possible implementation, the method further includes:
[0016] The corresponding relationship between the specific timestamp and the first total quantity is recorded to obtain a record text.
[0017] In a possible implementation, the total data volume includes: the total data volume in H265 / H264 encoding format.
[0018] A second aspect of the present application provides a device for displaying image processing results, comprising:
[0019] an acquisition module, configured to acquire first characteristic data of a first video stream and second characteristic data of a second video stream, wherein the first video stream and the second video stream have the same content and a play time deviation, the first characteristic data including a first total data amount, time data corresponding to the first total data amount, and an image processing result of the first video stream, the second characteristic data including a second total data amount, the total data amount including a total data amount of an I frame and M frames following the I frame, where M is an integer greater than or equal to 1;
[0020] a matching module, configured to obtain target feature data in the first feature data that matches the second feature data by matching the first feature data with the second feature data;
[0021] A display module is used to display the image processing result in the second video stream based on the target feature data.
[0022] The third aspect of the present application provides a computer program product, including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements the method for displaying the image processing results of the above-mentioned first aspect or any implementation method of the first aspect.
[0023] A fourth aspect of the present application provides an electronic device, comprising at least one processor and a memory connected to the processor, wherein:
[0024] The memory is used to store computer programs;
[0025] The processor is used to execute the computer program so that the electronic device can implement the method for displaying image processing results of the above-mentioned first aspect or any implementation manner of the first aspect.
[0026] In a fifth aspect, the present application provides a computer storage medium, which carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can display the image processing results of the above-mentioned first aspect or any implementation method of the first aspect.
[0027] By means of the above-mentioned technical scheme, the display and device of image processing results provided by the present application obtain the first feature data of the first video stream and the second feature data of the second video stream, and obtain the target feature data in the first feature data that matches the second feature data by matching the first feature data with the second feature data. Based on the target feature data, the image processing result is displayed in the second video stream. Because the content of the first video stream and the second video stream are the same and there is a deviation in the playback time, and the first feature data includes the first total data volume, the time data corresponding to the first total data volume, and the image processing result of the first video stream, the second feature data includes the second total data volume of the first video stream, and the total data volume includes the total data volume of I frame and M frames after I frame. Therefore, by matching the first feature data with the second feature data, that is, using the total data volume as a medium, the first video stream and the first video stream in the second video stream are temporally aligned. Therefore, the image processing result of the first video stream can be accurately displayed in the second video stream. BRIEF DESCRIPTION OF THE DRAWINGS
[0028] The above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that the originals and elements are not necessarily drawn to scale.
[0029] Figure 1 This is an example diagram showing how to identify targets from a video stream based on an artificial intelligence algorithm and display the recognition results.
[0030] Figure 2 A flowchart of a method for displaying image processing results provided in this application;
[0031] Figure 3This is an example diagram of the matching of real-time stream and recorded video stream in the method for displaying image processing results provided by this application;
[0032] Figure 4 A flowchart of another method for displaying image processing results provided by this application;
[0033] Figure 5 A structural example diagram of a device for displaying image processing results provided in an embodiment of the present application;
[0034] Figure 6 This is a structural example diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0035] The following describes the embodiments of the present application in conjunction with the accompanying drawings. The terms used in the implementation methods of the present application are only used to explain the specific embodiments of the present application and are not intended to limit the present application.
[0036] The embodiments of the present application are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.
[0037] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, and this is merely a way of distinguishing the objects of the same attributes when describing them in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.
[0038] Figure 1 This example shows an AI-based algorithm identifying a target in a video stream and displaying the recognition results. The video stream consists of multiple frames, arranged in descending order of acquisition time. The AI algorithm processes the video stream and identifies the target in each frame.
[0039] In practice, it is necessary to display the recognized target in the video stream, such as the image frame where the recognized target license plate is located and its position in the image frame.
[0040] It is understandable that the image processing result includes the output result of the image processing algorithm (such as an artificial intelligence algorithm). For example, the image processing algorithm is to identify and track the target license plate, and the image processing result is a detection frame used to frame the target license plate in the video stream.
[0041] like Figure 1 As shown, it is assumed that the detection frame is recognized in the 2nd frame, the 3rd frame, the nth frame, and the n+1th frame, but when the detection frame is displayed in the video stream, the detection frame is not displayed in the 2nd frame, and in the 3rd frame, the detection frame does not accurately frame the target license plate.
[0042] The embodiments of the present application provide a method for displaying image processing results, the purpose of which is to accurately display image processing results in a video stream.
[0043] The following example uses the method of identifying and tracking a target license plate in a video stream collected from a parking lot, and displays the identification and tracking results in the video stream.
[0044] Figure 2 This is a method for displaying image processing results provided by an embodiment of the present application. Figure 2 The medium video platform obtains a real-time video stream (referred to as a real-time stream) from a camera deployed in the parking lot. The video platform records the real-time stream to obtain a recorded video stream. The video platform provides a download interface for the recorded video stream.
[0045] Because there is a time difference between the real-time stream and the recorded video stream downloaded from the download interface, the detection frame identified based on the real-time stream may be inaccurate when displayed in the recorded video stream, such as Figure 1 As shown, the detection frame does not completely frame the target license plate. For another example, the detection frame frames non-target license plates. The purpose of the method provided in this embodiment is to accurately mark the target license plate with a detection frame in the video stream.
[0046] Figure 2 The following steps are included:
[0047] S201: Configure a specific timestamp for each frame in a real-time stream.
[0048] Exemplarily, the real-time stream includes multiple video streams.
[0049] It is understandable that each frame in a video stream usually has a timestamp, but this type of timestamp is usually a relative timestamp, and it is possible that the timestamp will change after being processed by other entities. Therefore, this type of timestamp cannot be applied to the subsequent frame matching of this embodiment. Therefore, in this step, a specific timestamp is configured for each frame in the first video stream.
[0050] A specific timestamp is an absolute timestamp that does not change with the processing of the real-time stream. The specific timestamp is set specifically for the subsequent steps of this embodiment. To distinguish it from other timestamps, the specific timestamp is exemplarily formatted in a specific format, such as using the Supplemental Enhancement Information (SEI) field of the H264 / H265 protocol to insert a specific timestamp into each frame in the real-time stream. Alternatively, the specific timestamp may also have a unique identifier that is used to distinguish it from other types of timestamps.
[0051] The specific timestamp configured for any frame is the moment when the execution subject of this process (such as a processor) receives the frame.
[0052] The absolute timestamp of each frame is denoted as ts, for example, the absolute timestamp of the first frame is ts_1, and the absolute timestamp of the second frame is ts_2.
[0053] S202: Process the real-time stream based on an image processing algorithm to obtain an image processing result.
[0054] Exemplarily, the image processing algorithm is to identify and track the target license plate from the real-time stream, and the image processing result is a detection frame of the target license plate in the real-time stream.
[0055] The image processing result can be called structured data. Taking the image processing result as the detection frame of the target license plate in the real-time stream as an example, the structured data is recorded as (ts:rects), where ts represents a specific timestamp, rects represents the information of the detection frame, such as the size and position data of the detection frame, etc. ts:rects represents the correspondence between the absolute timestamp and the detection window. It can be understood that the specific timestamp of any frame corresponds to the detection frame in the frame. For example, if the target vehicle is identified in the first frame, the detection frame of the target vehicle in the first frame corresponds to the specific timestamp ts_1 of the first frame.
[0056] S203: Extract feature data of the real-time stream.
[0057] In this embodiment, feature data is extracted based on the I-frame and P-frame of the Group of Pictures (GOP). Therefore, if the real-time stream is not in the GOP format, the real-time stream must first be converted into a GOP video stream.
[0058] A GOP video stream includes I frames and P frames. I frames are key frames of the first video stream, which contain complete picture information and therefore have a large data volume. P frames contain inter-frame difference information and therefore have a small data volume.
[0059] In this step, an I frame and M P frames are extracted. For example, M is 5, i.e., an I frame and 5 P frames. The sequence of absolute timestamps is used, and the corresponding relationship between the data volume (i.e., size) of the sequence and the specific timestamps of the I frame constitutes the feature data. The data volume of the sequence is denoted as pkt_size1, and the feature data can be recorded as (ts:pkt_size1). For example, the feature data of the real-time stream is recorded in text form to obtain recorded text.
[0060] In this step, the data volume is the frame size in the H265 / H264 encoding mode. In other words, after encoding a GOP in the H265 / H264 encoding mode, the data volume of the I frame and M P frames is counted. The H265 / H264 encoding mode does not use any information in the encapsulation format. Therefore, it is applicable to a variety of scenarios.
[0061] It should be noted that the larger M is, the more P frames it contains, and the more it can reflect the characteristics of the video. Therefore, the matching results will be more accurate and the display results will be more accurate. However, the amount of calculation is large. Therefore, in practice, the value of M should be selected by comprehensively considering the accuracy of the display results and the amount of calculation.
[0062] It is understandable that the real-time stream may include multiple video streams, and feature data can be obtained for each video stream.
[0063] S204: Based on the download interface of the recorded video stream of the video platform, download the recorded video stream of the real-time stream.
[0064] S205: Extract matching features of the first segment of the recorded video stream.
[0065] The first recorded video stream refers to the first GOP video stream in the recorded video stream.
[0066] The matching feature is the data size of the sequence consisting of an I frame and M P frames. The value of M is the same as the value of M in S203. The matching feature is recorded as pkt_size2.
[0067] S206 : Compare the matching feature pkt_size2 with the data volume pkt_size1 in the feature data of the real-time stream to determine feature data that matches the matching feature.
[0068] Exemplarily, pkt_size1 whose difference with pkt_size2 is within a preset range is pkt_size1 that matches the matching feature, and feature data of pkt_size1 that matches the matching feature is feature data that matches the matching feature.
[0069] It can be understood that when searching for pkt_size1, because the time deviation between the recorded video stream and the real-time stream is usually small, for example, no more than 5 seconds, when matching pkt_size2 and pkt_size1, the search range can be within 5 seconds before and after the target time (i.e., ts corresponding to pkt_size1) to search for a matching pkt_size2, that is, feature matching that meets the accuracy requirements can be achieved within a smaller frame range, with a smaller amount of computation while ensuring matching accuracy and success rate.
[0070] S207: Use the specific timestamp included in the feature data that matches the matching feature as the target timestamp.
[0071] For ease of explanation, the target timestamp is denoted as ts_P.
[0072] S208: Display the detection frame in the recorded video stream based on the image processing result and the target timestamp.
[0073] It can be understood that in the structured data (ts:rects), the target timestamp ts_P is searched, and the detection frame corresponding to the target timestamp ts_P is displayed in the first recorded video stream, that is, the target timestamp ts_P is used as the timestamp of the first recorded video stream, and the recorded video streams after the first recorded video stream are sorted in chronological order, corresponding to the specific timestamps after the target timestamp in the structured data, and based on the correspondence between the specific timestamps and the detection frames, the detection frames are displayed in subsequent recorded video streams in turn.
[0074] by Figure 3 For example, the real-time stream contains 5 GOP video streams, and the specific timestamps are ts_1, ts_2, ts_3, ts_4 and ts_5 respectively. Each GOP video stream consists of an I frame and several P frames.
[0075] The structured data of the GOP video stream with a specific time stamp of ts_2 is (ts_2:rects_2).
[0076] Assume that the matching feature pkt_size2 of the first GOP video stream in the recorded video stream matches pkt_size1 in the feature data of the GOP video stream with a specific timestamp of ts_2. Then the detection box to be displayed for the first GOP video stream in the recorded video stream is rects_2. Similarly, the detection box to be displayed for the second GOP video stream in the recorded video stream is rects_3 corresponding to the specific timestamp ts_3, and so on. The detection box to be displayed for the fifth GOP video stream in the recorded video stream is rects_5 corresponding to the specific timestamp ts_5. Figure 3 The other video streams in the recorded video stream except the first GOP video stream are not shown).
[0077] from Figure 2 It can be seen from the illustrated embodiment that, when there is a time difference between the recorded video stream used to display the detection frame and the real-time stream for identifying the position of the detection frame, the real-time stream with time alignment of the recorded video stream is determined by searching for the real-time stream that matches the matching features of the recorded video stream, that is, the specific timestamp of the recorded video stream is determined, and then based on the correspondence between the specific timestamp and the detection frame, and the fact that the recorded video stream is obtained by recording the real-time stream, the exact position of the detection frame in the recorded video stream can be determined, thereby achieving accurate display of the detection frame.
[0078] It is understandable that Figure 2 The real-time stream and recorded video stream shown are examples of two related videos, and the detection box is an example of the image processing result to be displayed, and the above example is not intended to be limiting. Figure 2 The process shown can be summarized as Figure 4 The process shown.
[0079] Figure 4 This is another method for displaying image processing results provided by an embodiment of the present application, which is applied in a processor (or processing module, processing chip), and the processor (or processing module, processing chip) is set in an electronic device.
[0080] Figure 4 The following steps are included:
[0081] S11. Obtain first characteristic data of a first video stream and second characteristic data of a second video stream.
[0082] The first video stream has the same content as the second video stream, but there is a time offset between the two streams. This time offset can be understood as a mismatch in the start time of playback, meaning that playback can start in the background or in the foreground. In other words, the first and second video streams have the same content, but there is a time offset between them.
[0083] In this embodiment, the first video stream is a video stream processed by an image processing algorithm, such as the real-time stream described in the aforementioned embodiment. The second video stream is a video stream used to display the image processing results, such as the recorded video stream described above. Exemplarily, the first video stream is the processing object of the image processing algorithm, played in the background, and processed during playback. The second video stream is played in the foreground and displays the processing results during playback. It is understood that the first video stream and the second video stream only need to meet the above-mentioned conditions of having the same content but a deviation in playback time, and are not limited to real-time streams and recorded video streams of real-time streams.
[0084] The first feature data includes the total data volume of I frame and M frames after I frame, referred to as the first total data volume, such as the aforementioned pkt_size1, the time data corresponding to the first total data volume, such as the aforementioned specific timestamp ts, and the image processing result. The image processing result varies based on different image processing algorithms. Examples of image processing results include the aforementioned detection box.
[0085] It can be understood that an example of M frames is M P frames.
[0086] The second feature data includes the total data volume of the I frame and the M P frames following the I frame of the first video stream, referred to as the second total data volume, such as the aforementioned matching feature pkt_size2.
[0087] For example, in this embodiment, M is an integer greater than or equal to 1. The maximum value of M is the number of frames within the play time deviation between the first video and the second video. In practice, the value of M can be set as needed to reduce the amount of calculation while meeting the matching accuracy.
[0088] S12. Acquire target feature data in the first feature data that matches the second feature data by matching the first feature data with the second feature data.
[0089] The target feature data is feature data including a target timestamp.
[0090] Exemplarily, the first feature data includes pkt_size1, ts and rects, and the second feature data includes pkt_size2. Matching the first feature data with the second feature data means comparing pkt_size1 with pkt_size2 one by one. The pkt_size1 whose difference is within a preset range is the target pkt_size1, and the first feature data including the target pkt_size1 is the target feature data.
[0091] S13. Based on the target feature data, display the image processing result in the second video stream.
[0092] Exemplarily, the image processing result contained in the target feature data is displayed in the first video stream in the second video stream, and by aligning the first video stream with the time data contained in the target feature data, the time data of other video streams after the first video stream in the second video stream are determined, which are sequentially the time data after the time data of the target feature data, thereby aligning the other video streams with the video streams in the first video stream one by one in time, and then based on the corresponding relationship between the time data and the image processing results, the image processing results are sequentially displayed in the second video stream, such as Figure 3 Example.
[0093] The method provided in this embodiment can accurately display image processing results, and since matching feature data does not need to be obtained from the encapsulation structure, it is applicable to a variety of video streams, including but not limited to Real Time Streaming Protocol (RTSP) streams, GB28181 protocol real-time streams, GB28181 protocol historical streams, and Motion Picture Experts Group 4 (MP4). Furthermore, the method does not introduce codec performance consumption on the central processing unit (CPU) or graphics processing unit (GPU); it only records key information such as frame sequence size characteristics, whether it is a key frame, and timestamps, resulting in low hard disk usage.
[0094] Figure 5 An embodiment of the present application provides a display device for image processing results, including: an acquisition module, a matching module and a display module.
[0095] The acquisition module is used to obtain first characteristic data of a first video stream and second characteristic data of a second video stream. The content of the first video stream and the second video stream are the same and there is a deviation in the playback time. The first characteristic data includes a first total data volume, time data corresponding to the first total data volume, and an image processing result of the first video stream. The second characteristic data includes a second total data volume. The total data volume includes the total data volume of I frame and M frames after the I frame, and M is an integer greater than or equal to 1.
[0096] The matching module is used to obtain target feature data in the first feature data that matches the second feature data by matching the first feature data with the second feature data.
[0097] The display module is used to display the image processing result in the second video stream based on the target feature data.
[0098] In some implementations, the maximum value of M is the number of frames within the playback time deviation between the first video stream and the second video stream.
[0099] In some implementations, the first video stream is a real-time stream, and the second video stream is obtained by storing the real-time stream.
[0100] In some implementations, before obtaining the first feature data of the first video stream and the second feature data of the second video stream, it also includes: inserting a specific timestamp into each frame in the first video stream, the specific timestamp of the target frame is the absolute time of receiving the I frame of the target frame, the target frame is any frame, and accordingly, the time data includes the specific timestamp.
[0101] In some implementations, the method further includes: recording a correspondence between a specific timestamp and the first total quantity to obtain a record text.
[0102] In some implementations, the total data volume includes: the total data volume in H265 / H264 encoding format.
[0103] The specific implementation of the functions of the above modules can be found in the above method embodiments.
[0104] The device can improve the accuracy of displaying image processing results and has the advantages of high versatility and high efficiency.
[0105] As mentioned above, the method and apparatus provided in the embodiments of the present application run in a processor, and the processor is set in an electronic device. The electronic device can be a mobile phone, a tablet computer, a wearable device, a vehicle-mounted device, an augmented reality (AR) / virtual reality (VR) device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA) and other terminals, or a server, etc. The embodiments of the present application do not impose any restrictions on this.
[0106] As mentioned above, the electronic device can obtain the video stream from the video platform, and the image processing algorithm can be executed by the electronic device or by other entities, which is not limited here.
[0107] Taking the electronic device as a terminal as an example, the terminal includes: at least one processor and a memory connected to the processor.
[0108] The memory can be used to store instructions and data. The memory may primarily include an instruction storage area and a data storage area. The data storage area can store various data, such as multimedia files and text. The instruction storage area can store software units such as the operating system, applications, and instructions required for at least one function, or subsets or extensions thereof. It may also include non-volatile random access memory (RAM). It provides the processor with management capabilities for the hardware, software, and data resources within the computing and processing device, supporting control software and applications. It is also used to store multimedia files and running programs and applications.
[0109] The processor is the terminal's control center, connecting all components of the terminal using various interfaces and circuits. By running or executing instructions stored in memory and accessing data stored in memory, it performs various terminal functions and processes data, thereby providing overall control of the terminal device. Optionally, the processor may include one or more processing units; preferably, the processor may integrate an application processor and a modem processor, where the application processor primarily handles the operating system, user interface, and application programs, while the modem processor primarily handles wireless communications. It is understood that the modem processor may not be integrated into the processor. In some embodiments, the processor and memory may be implemented on a single chip; in some embodiments, they may be implemented on separate chips. The processor may also be used to generate corresponding operational control signals and send them to corresponding components of the computing and processing device, read and process data in the software, particularly data and programs in memory, to enable the various functional modules therein to perform their corresponding functions, thereby controlling the corresponding components to act as instructed.
[0110] The memory may be used to store software codes related to the method for displaying image processing results, and the processor may execute the steps of the method for displaying image processing results by running the software codes.
[0111] Exemplarily, the terminal may further include components such as an input unit, a display unit, a camera, an audio circuit, a speaker, and a microphone, and the processor may also schedule these components to implement corresponding functions.
[0112] Take the electronic device as an example, where the server is Figure 6 As shown, the server 200 includes a bus 201, a processor 202, a communication interface 203, and a memory 204. The processor 202, the memory 204, and the communication interface 203 communicate with each other via the bus 201.
[0113] The bus 201 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.
[0114] The processor 202 may be any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).
[0115] The memory 204 may include volatile memory, such as random access memory (RAM). The memory 204 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state drive (SSD).
[0116] The memory 204 may be used to store software codes related to the method for displaying image processing results, and the processor 202 may execute the steps of the method for displaying image processing results, and may also schedule other units to implement corresponding functions.
[0117] It should be understood that the above-mentioned terminal or server 200 can be a centralized or distributed device, and the processor in the above-mentioned terminal or server 200 can be a hardware circuit (such as an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a general-purpose processor, a digital signal processor (DSP), a microprocessor or a microcontroller, etc.), or a combination of these hardware circuits. For example, the processor can be a hardware system with an instruction execution function, such as a CPU, DSP, etc., or a hardware system without an instruction execution function, such as an ASIC, FPGA, etc., or a combination of the above-mentioned hardware systems without an instruction execution function and hardware systems with an instruction execution function.
[0118] An embodiment of the present application also provides a computer program product including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements any method for displaying image processing results provided in the embodiment of the present application.
[0119] A computer-readable storage medium is also provided in an embodiment of the present application. The storage medium carries one or more computer programs. When one or more computer programs are executed by an electronic device, the electronic device can implement any method for displaying image processing results provided in an embodiment of the present application.
[0120] It should also be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed across multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. In addition, in the drawings of the device embodiments provided in this application, the connection relationship between the modules indicates that there is a communication connection between them, which can be specifically implemented as one or more communication buses or signal lines.
[0121] Through the description of the above embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course can also be implemented by special hardware including application-specific integrated circuits, special CPUs, special memories, special components, etc. In general, all functions performed by computer programs can be easily implemented with corresponding hardware, and the specific hardware structures used to implement the same function can also be diverse, such as analog circuits, digital circuits or special circuits, etc. However, for the present application, software program implementation is a better implementation method in most cases. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer's floppy disk, USB flash drive, mobile hard disk, ROM, RAM, magnetic disk or optical disk, etc., and includes a number of instructions to enable a computer device (which can be a personal computer, training equipment, or network equipment, etc.) to execute the methods described in each embodiment of the present application.
[0122] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware, or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.
[0123] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, a computer, a training device or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website, a computer, a training device or a data center. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a training device, a data center, etc. that includes one or more available media integrations. The available medium can be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).
Claims
1. A method for displaying image processing results, characterized in that: include: Obtain first feature data of a first video stream and second feature data of a second video stream, where the first video stream and the second video stream have the same content and a playback time deviation, the first feature data including a first total data amount, time data corresponding to the first total data amount, and an image processing result of the first video stream, the second feature data including a second total data amount of the first video stream, the total data amount including the total data amount of I frame and M frames after the I frame, where M is an integer greater than or equal to 1; By matching the first feature data with the second feature data, target feature data matching the second feature data in the first feature data is obtained; Based on the target feature data, the image processing result is displayed in the second video stream.
2. The method according to claim 1, characterized in that The maximum value of M is the number of frames within the playback time deviation between the first video stream and the second video stream.
3. The method according to claim 1 or 2, characterized in that The first video stream is a real-time stream, and the second video stream is obtained by storing the real-time stream.
4. The method according to claim 1 or 2, characterized in that Before obtaining the first characteristic data of the first video stream and the second characteristic data of the second video stream, the method further includes: Inserting a specific timestamp into each frame in the first video stream, wherein the specific timestamp of a target frame is an absolute time when an I frame of the target frame is received, and the target frame is any frame; The time data includes the specific time stamp.
5. The method according to claim 4, characterized in that Also includes: The corresponding relationship between the specific timestamp and the first total quantity is recorded to obtain a record text.
6. The method according to claim 1 or 2, characterized in that The total data volume includes: the total data volume under the H265 / H264 encoding format.
7. A device for displaying image processing results, characterized in that: include: an acquisition module, configured to acquire first characteristic data of a first video stream and second characteristic data of a second video stream, wherein the first video stream and the second video stream have the same content and a play time deviation, the first characteristic data including a first total data amount, time data corresponding to the first total data amount, and an image processing result of the first video stream, the second characteristic data including a second total data amount, the total data amount including a total data amount of an I frame and M frames following the I frame, where M is an integer greater than or equal to 1; a matching module, configured to obtain target feature data in the first feature data that matches the second feature data by matching the first feature data with the second feature data; A display module is used to display the image processing result in the second video stream based on the target feature data.
8. A computer program product, characterized in that The method comprises computer-readable instructions, which, when executed on an electronic device, enable the electronic device to implement the method for displaying image processing results as claimed in any one of claims 1 to 6.
9. An electronic device, characterized in that: comprising at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is configured to execute the computer program so that the electronic device can implement the method for displaying image processing results as described in any one of claims 1 to 6.
10. A computer storage medium, characterized in that The storage medium carries one or more computer programs, and when the one or more computer programs are executed by an electronic device, the electronic device can implement the method for displaying image processing results as described in any one of claims 1 to 6.