Method and device for processing data frame, electronic equipment and storage medium

Abstract

The invention relates to a method and device for processing data frames, electronic equipment and a storage medium. In one method, a first processing unit in a collection device obtains a first position of an object to be processed in a first data frame; based on the first position, determining, by the first processing unit, a second position of the object in a second data frame after the first data frame, the first data frame and the second data frame being acquired by an acquisition unit in the acquisition device; and removing the sensitive information corresponding to the second position in the second data frame by a second processing unit in the acquisition device. By utilizing the example implementation mode of the invention, the performance of each processing unit can be fully called in the acquisition equipment to process the video data, so that the overall processing performance of removing sensitive information is improved.

Description

Technical Field

[0001] Various implementations of the present disclosure relate to data processing, and more particularly, to methods, apparatuses, electronic devices, and storage media for processing data frames by an acquisition device. Background Art

[0002] Currently, various technical solutions for performing subsequent control processes based on acquired videos have been proposed. For example, in the field of vehicle driving, video data around the vehicle can be acquired by acquisition devices installed on the vehicle and / or other locations. Subsequently, operations such as autonomous driving and / or assisted driving can be performed based on the acquired video data. However, the acquired video data may include sensitive information such as license plates and faces of surrounding vehicles and / or people. At this time, it is desirable to remove the sensitive information in the video data to ensure the security of personal information. Summary of the Invention

[0003] According to a first aspect of the present disclosure, there is provided a method for processing a data frame. The method includes: obtaining, by a first processing unit in an acquisition device, a first position of an object to be processed in a first data frame; determining, based on the first position, by the first processing unit, a second position of the object in a second data frame after the first data frame, where the first data frame and the second data frame are acquired by an acquisition unit in the acquisition device; and removing, by a second processing unit in the acquisition device, sensitive information corresponding to the second position in the second data frame.

[0004] According to a second aspect of the present disclosure, there is provided a device for processing a data frame. The device includes: an obtaining module configured to obtain, by a first processing unit in an acquisition device, a first position of an object to be processed in a first data frame; a determining module configured to determine, based on the first position, by the first processing unit, a second position of the object in a second data frame after the first data frame, where the first data frame and the second data frame are acquired by an acquisition unit in the acquisition device; and a removing module configured to remove, by a second processing unit in the acquisition device, sensitive information corresponding to the second position in the second data frame.

[0005] According to a third aspect of the present disclosure, there is provided an electronic device, including: a memory and a processor; where the memory is used to store one or more computer instructions, and one or more computer instructions are executed by the processor to implement the method according to the first aspect of the present disclosure.

[0006] According to a fourth aspect of the present disclosure, there is provided a computer-readable storage medium, on which one or more computer instructions are stored, and one or more computer instructions are executed by a processor to implement the method according to the first aspect of the present disclosure.

[0007] According to a fifth aspect of the present disclosure, there is provided a computer program product comprising computer programs / instructions which, when executed by a processor, implement the method according to the first aspect of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Features, advantages and other aspects of various implementations of the present disclosure will become more apparent by referring to the following detailed description in conjunction with the accompanying drawings, in which several implementations of the present disclosure are shown by way of example and not limitation. In the drawings:

[0009] Figure 1 A block diagram schematically showing an application environment for processing data frames;

[0010] Figure 2 A flowchart schematically showing a method for processing data frames according to an exemplary implementation of the present disclosure;

[0011] Figure 3 A block diagram schematically showing a method for determining a predicted position of an object according to an exemplary implementation of the present disclosure;

[0012] Figure 4 A block diagram schematically showing a method for processing data frames by an acquisition device according to an exemplary implementation of the present disclosure;

[0013] Figure 5 A block diagram schematically showing a method for determining a predicted position of an object according to an exemplary implementation of the present disclosure;

[0014] Figure 6 A track diagram schematically showing an interaction process for processing data frames by multiple units in an acquisition device according to an exemplary implementation of the present disclosure;

[0015] Figure 7 A flowchart schematically showing a method for processing data frames according to an exemplary implementation of the present disclosure;

[0016] Figure 8 A block diagram schematically showing a device for processing data frames according to an exemplary implementation of the present disclosure; and

[0017] Figure 9 A block diagram schematically showing a computing device / server for processing data frames according to an exemplary implementation of the present disclosure. DETAILED DESCRIPTION

[0018] The preferred implementations of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the preferred implementations of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the implementations set forth herein. On the contrary, these implementations are provided to make the present disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.

[0019] As used herein, the term "including" and its variations mean open inclusion, i.e., "including but not limited to". Unless otherwise specified, the term "or" means "and / or". The term "based on" means "at least partially based on". The terms "an example implementation" and "an implementation" mean "at least one example implementation". The term "another implementation" means "at least one additional implementation". The terms "first", "second", etc. may refer to different or the same objects. There may also be other explicit and implicit definitions hereinafter.

[0020] For the solutions described in this specification and the embodiments, if they involve personal information processing, they will all be processed on the premise of having a legal basis (such as obtaining the consent of the personal information subject, or being necessary for performing a contract, etc.), and will only be processed within the specified or agreed scope. If the user refuses to process personal information other than the necessary information required for basic functions, it will not affect the user's use of the basic functions.

[0021] Example environment

[0022] Currently, a variety of technical solutions have been proposed to perform subsequent control processes based on the collected videos. However, the collected video data may include various sensitive information, which may then endanger the security of personal data. For the sake of convenience of description, in the following, only the vehicle driving environment will be used as a specific example to describe the process of removing sensitive information from the collected data frames. Alternatively and / or additionally, the technical solutions according to an example implementation manner of the present disclosure can be implemented in other application environments.

[0023] See Figure 1 Describe the application environment according to an example implementation manner of the present disclosure, which Figure 1 Schematically shows a block diagram 100 of an application environment for processing data frames. As Figure 1As shown, the acquisition device 110 can be deployed at the vehicle, and the acquisition device 110 can be used to acquire video data of the road environment (for example, including multiple objects 120 and 122, etc.). Further, potential obstacles in the road environment can be determined from the video data, and then the vehicle's autonomous driving and / or assisted driving process can be executed. However, the video data may include sensitive information of various objects, such as the license plate of the vehicle and the face of a person, etc. At this time, directly using the acquired video data may endanger the security of personal information, so it is necessary to remove the sensitive information from the video data.

[0024] Currently, technical solutions for removing sensitive information have been proposed. For example, a computing device can receive video data from an acquisition device, and can identify sensitive information from the video data based on an image recognition algorithm and then remove the sensitive information. However, the above process involves the encoding and decoding processes of video data, and each data frame in the video data needs to be processed one by one. This may consume a large amount of processing resources and result in a long time overhead. At this time, it is desirable to remove the sensitive information in the video data in a faster and more effective manner to ensure the security of personal information.

[0025] Summary of processing data frame

[0026] In order to at least partially eliminate the deficiencies in the existing technical solutions, a technical solution for the acquisition device to process data frames is proposed. Figure 2 FIG. 200 is a flowchart schematically showing a method for processing data frames according to an exemplary implementation of the present disclosure. As Figure 2 shown, the acquisition device 110 can include multiple units. For example, the first processing unit 230 can be a processing unit in the acquisition device 110 for performing overall control (for example, a system-on-chip (abbreviated as SoC) unit), and the second processing unit 232 can be an image signal processing unit for controlling the acquisition unit 234 (for example, an image sensor) in the acquisition device 110.

[0027] According to an exemplary implementation of the present disclosure, the acquisition unit in the acquisition device acquires the first data frame 210 and the second data frame 220. The first position 212 of the object to be processed (for example, a person) in the first data frame 210 can be obtained by the first processing unit in the acquisition device. For example, the first position 212 can be determined based on object recognition and / or tracking technology. Further, the first processing unit determines the second position 222 of the object in the second data frame 220 after the first data frame 210 based on the first position. Relative to the second processing unit, the first processing unit has a higher data processing ability. At this time, the second processing unit can be used to predict in advance the second position of the object in the subsequent second data frame.

[0028] Further, the first processing unit may send the predicted second position to the second processing unit, and then the second processing unit in the acquisition device may remove the sensitive information corresponding to the second position from the second data frame. It should be understood that when the second position has been determined, removing the sensitive information at the second position does not require invoking a large amount of processing resources. Thus, the above process can be directly executed by the second processing unit with relatively low processing capabilities.

[0029] Using the exemplary implementation manners of the present disclosure, the performance of each processing unit can be fully utilized inside the acquisition device to process video data. In this way, sensitive information can be removed before the encoding operation of the data frame, and further, the resource overhead and time overhead involved in encoding and decoding the data frame including sensitive information can be eliminated, thereby improving the data processing efficiency.

[0030] Detailed process of processing data frame

[0031] The general idea of processing the data frame has been described. More details regarding the data frame processing will be described below with reference to the accompanying drawings. According to an exemplary implementation manner of the present disclosure, the first processing unit may include a system-on-chip unit in the acquisition device. The system-on-chip unit may include multiple types. For example, a general-purpose processing unit (CPU) for performing conventional processing functions and an image processing unit (GPU) for performing dedicated image processing functions. Compared with the second processing unit, the first processing unit has a higher processing capability. Thus, various algorithms known in the past and / or to be developed in the future may be executed at the first processing unit to determine the first position of the object in the first data frame.

[0032] According to an exemplary implementation manner of the present disclosure, during the process of obtaining the first position, the acquisition unit may capture video data and send each data frame to the first processing unit. When the first processing unit receives the first data frame, the first processing unit may, based on an object recognition process, identify the position of the object from the data frame. For example, when the object is a person, a predetermined person recognition process may be executed, and the area to be recognized may be specified (for example, the face area, or the entire person area, etc.), and then the position of the person may be identified from the data frame. Alternatively and / or additionally, when the object is a vehicle, the license plate area may be specified, and then the position of the license plate may be identified from the data frame. Specifically, a circular area, an elliptical area, etc. may be used to represent the face position, and a rectangular area, a quadrilateral area, etc. may be used to represent the license plate position, etc.

[0033] Further, an object tracking process that is currently known and / or will be developed in the future can be executed at the first processing unit to determine the position of the object in subsequent data frames. Specifically, machine learning techniques and / or other algorithms can be used to track the position of the object in each subsequent data frame. According to an example implementation of the present disclosure, to determine the second position, the second time point of the second data frame can be determined based on the first time point of the first data frame and the acquisition interval of the acquisition unit. Further, based on the object tracking process, the second position can be determined based on the first position and the second time point. Refer to Figure 3 for more details, the Figure 3 block diagram 300 for determining the predicted position of an object according to an exemplary implementation of the present disclosure is schematically shown.

[0034] As Figure 3 shown, the acquisition interval of the acquisition device can be obtained. For example, assuming the acquisition frequency is f, the acquisition interval can be expressed as ΔT = 1 / f. Further, the first time point T1 of the first data frame can be determined, and the second time point T2 of the second data frame can be determined as T2 = T1 + 1 / f. Assuming the acquisition frequency is 25 frames per second, the acquisition interval is 1 / 25 = 40 ms. Using the example implementation of the present disclosure, the time points of each subsequent data frame can be determined based on simple mathematical operations, and then the position of the object at this time point can be determined. As Figure 3 shown, the first position and the second position can be compared, and then the trajectory 310 of the object can be determined.

[0035] It should be understood that Figure 3 only the case where there is one subsequent data frame after the first data frame is schematically shown. Alternatively and / or additionally, based on the object tracking process, the predicted position of the object in one or more subsequent data frames after the first data frame can be determined, and then a longer motion trajectory of the object can be predicted. It should be understood that the predicted positions here are determined based on a mature and reliable object tracking process, so the predicted positions have high accuracy, and it can be considered that the probability of these predicted positions including sensitive information is relatively high. As Figure 3 shown, the image at the second position can be directly subjected to a predetermined processing process to remove the sensitive information at these predicted positions. Using the example implementation of the present disclosure, it is not necessary to perform an object recognition process for each data frame one by one. In this way, the overall workload of the acquisition device can be reduced, and then the performance of eliminating sensitive information can be improved.

[0036] According to an exemplary implementation of the present disclosure, the first processing unit may transmit a second position to the second processing unit. Further, the second processing unit may update a portion corresponding to the second position in the second data frame based on a predetermined processing procedure to remove sensitive information. It should be understood that although the performance of the second processing unit is lower than that of the first processing unit, the process of removing sensitive information does not involve excessive workload, so the second processing unit can successfully complete this process, thereby sharing the workload of the first processing unit.

[0037] According to an exemplary implementation of the present disclosure, sensitive information can be removed based on various methods. For example, the predetermined processing procedure may include at least any one of the following: a scaling process, a scrambling process, a filtering process, a noise process, and a distortion process. Specifically, the resolution of the image at the second position can be reduced and the facial features of the person can be blurred. A scrambling process can be performed. For example, the individual pixels within the facial region of the person can be rearranged to blur the facial features of the person. A filter can be applied to the facial region of the person to blur the facial features of the person. Noise can be added to the facial region of the person. For example, the facial features of the person can be blurred by adding mosaics or the like. A distortion process such as warping can be performed on the facial region of the person, and so on.

[0038] According to an exemplary implementation of the present disclosure, assuming that the performance of the second processing unit is low, the pixels within the face region can be directly set to a single white color or other color. Again, for example, assuming that the performance of the second processing unit is high, the resolution of the face region can be reduced through a scaling process, thereby providing a more matching person image with the surrounding environment. In this way, a suitable processing procedure can be selected based on the performance of the second processing unit to eliminate sensitive information in the data frame.

[0039] According to an exemplary implementation of the present disclosure, the acquisition unit may continuously acquire new data frames, and the first processing unit and the second processing unit may continuously repeat the process described above to remove sensitive information from each acquired data frame. Refer to Figure 4 for more details. The Figure 4 schematically shows a block diagram 400 for processing a data frame by an acquisition device according to an exemplary implementation of the present disclosure.

[0040] As Figure 4 shown, the acquisition unit 234 may acquire a first data frame 210 in the initial stage, and the first processing unit 230 may determine a first position 212 based on an identification algorithm. The first processing unit 230 may predict a second position 222 and send the second position 222 to the second processing unit. At this time, the second processing unit may remove sensitive information from the second position 222 in the second data frame 220, and then generate an updated second data frame 410.

[0041] Further, the first processing unit 230 may determine a third position of the object in a third data frame (collected by the collection unit in the collection device) after the second data frame based on the second position 222. The first processing unit may send the third position to the second processing unit so that the second processing unit removes the sensitive information corresponding to the third position in the third data frame. According to an example implementation of the present disclosure, the process described above may be iteratively executed. At this time, the first processing unit may be responsible for determining the predicted position and sending the predicted position to the second processing unit, and the second processing unit may be responsible for removing the sensitive information at the predicted position. In this way, the first processing unit and the second processing unit may share the workload of the entire processing flow according to their respective processing performances, thereby improving the performance of the overall workflow.

[0042] According to an example implementation of the present disclosure, in the initial stage of collection, the first data frame includes the original data frame collected by the collection unit. As the collection process progresses, the first data frame received by the first processing unit may also include the updated original data frame with sensitive information removed. At this time, the process described above may be continuously executed in an iterative manner, so that the two processing units share the workload in the process of eliminating sensitive information.

[0043] It should be understood that the above only schematically shows the process of performing processing on a single data frame after the first data frame. Alternatively and / or additionally, the position of the object in multiple (e.g., k) subsequent frames may be predicted in a similar manner. For example, the performance of the first processing unit and the second processing unit may be compared, and then the value of k may be determined. During the object tracking performed by the first processing unit, assuming that the second processing unit can remove sensitive information from 3 data frames, k = 3 may be set at this time. In this way, the first processing unit may determine the predicted positions of the object in multiple subsequent data frames at one time, so that the processing times of the first processing unit and the second processing unit are matched, thereby improving the overall performance of removing sensitive information.

[0044] It should be understood that the object tracking process may reduce the waiting time for determining the predicted position. However, using the object tracking process for a long time may reduce the prediction accuracy. At this time, the first processing unit may execute the object recognition process at a predetermined time interval and use the latest recognition result as the basis for subsequent object tracking, that is, the basis for calibrating the object tracking process. For example, the calibration process may be executed at intervals of two frames, three frames (and / or other quantities). In other words, during the regular object tracking, the first position may be a predicted value determined based on the object tracking process; and during the calibration, the first position may be an actual measurement value determined during the object recognition process. In this way, the overall accuracy of the object position may be determined.

[0045] The process of determining the object position is described by taking the execution of calibration at an interval of two frames as an example. Refer to Figure 5 For more details, the Figure 5 FIG. 500 is a block diagram schematically showing an exemplary implementation according to the present disclosure for determining the predicted position of an object. As Figure 5 shown, for the i-th frame 510, the object position (i.e., the recognition position) can be determined based on the object recognition process; for the (i + 1)-th frame 512, the object position (i.e., the predicted position) can be determined based on the object tracking process; for the (i + 2)-th frame 514, the object position (i.e., the recognition position) can be determined based on the object recognition process; for the (i + 3)-th frame 516, the object position (i.e., the predicted position) can be determined based on the object tracking process; for the (i + 4)-th frame 518, the object position (i.e., the recognition position) can be determined based on the object recognition process, and so on.

[0046] Using the exemplary implementation of the present disclosure, the object recognition process and the object tracking process can be alternately executed. At this time, the object recognition process can provide an accurate basis for object tracking, and the object tracking process can greatly reduce the overall workload of the first processing unit. Alternatively and / or additionally, the calibration process can be executed at an interval of three frames (or other quantities). In this way, the speed of determining the object position can be improved as a whole.

[0047] The above steps for removing sensitive information have been described separately. In the following, refer to Figure 6 Describe the overall interaction process executed by each unit in the acquisition device. Figure 6 FIG. 600 is an orbit diagram schematically showing an exemplary implementation according to the present disclosure for the interaction process of processing data frames by multiple units in an acquisition device. As Figure 6 shown, the first processing unit 230 can send a notification 601 to the second processing unit 232 to start the acquisition process. Subsequently, the second processing unit 232 can send a notification 602 to the acquisition unit 234 to trigger the acquisition unit 234 to acquire each video frame in the application environment. Assuming that the acquisition unit 234 acquires 603 the i-th data frame, the acquisition unit 234 can send (as shown by arrows 604 and 604') the i-th video frame to the first processing unit 230 via the second processing unit 232.

[0048] Upon receiving the i-th data frame, the first processing unit 230 may determine 605 the position of the object in the i-th data frame. Specifically, the sensitive position may be identified from the i-th data frame based on the object recognition process. Alternatively and / or additionally, the sensitive position may be predicted based on the object tracking process. The first processing unit 230 may send 606 the sensitive position to the second processing unit 232, and the second processing unit may remove 607 the sensitive information from the sensitive position in the i-th frame. At this time, a data frame after removing the sensitive information can be obtained.

[0049] Continue to refer to Figure 6 , in parallel with or in sequence with the step shown by arrow 607, the acquisition unit 234 may acquire the subsequent (i + 1)-th data frame, and then send it to the first processing unit 230 via the second processing unit (as shown by arrows 609 and 609’). The (i + 1)-th data frame and each subsequent data frame can be processed in a similar manner, thereby removing the sensitive information from each acquired data frame.

[0050] It should be understood that although the process of eliminating sensitive information has been described above by taking the removal of face data as an example, alternatively and / or additionally, each object in the acquired data frame can be processed in a similar manner. For example, in a vehicle environment, similar processing can be performed for each face and each license plate in the data frame. At this time, the faces and license plates in each data frame are blurred, thereby ensuring the security of personal sensitive information.

[0051] According to an example implementation of the present disclosure, an encoding operation may be performed at the acquisition device based on the updated data frame from which the sensitive information has been removed. Specifically, the updated i-th data frame, (i + 1)-th data frame, (i + 1)-th data frame, etc. can be continuously encoded, and then a data stream of real-time acquisition can be generated using the updated data frame from which the sensitive information has been eliminated.

[0052] Using the example implementation of the present disclosure, the performance of each processing unit can be fully utilized inside the acquisition device to process video data. Specifically, the first processing unit may perform tasks that require strong processing performance, such as object recognition and object tracking; the second processing unit may perform tasks that only require weak processing performance, such as removing sensitive information. In this way, multiple processing units can share the video processing tasks, thereby improving the overall processing performance.

[0053] Example process

[0054] Figure 7A flowchart of a method 700 for processing data frames according to some implementations of the present disclosure is shown. At block 710, a first processing unit in an acquisition device obtains a first position of an object to be processed in a first data frame; at block 720, based on the first position, the first processing unit determines a second position of the object in a second data frame after the first data frame, where the first data frame and the second data frame are acquired by an acquisition unit in the acquisition device; and at block 730, a second processing unit in the acquisition device removes sensitive information corresponding to the second position from the second data frame.

[0055] According to an example implementation of the present disclosure, determining the second position includes: determining a second time point of the second data frame based on a first time point of the first data frame and an acquisition interval of the acquisition unit; and determining the second position based on the first position and the second time point based on an object tracking process.

[0056] According to an example implementation of the present disclosure, removing sensitive information includes: transmitting the second position from the first processing unit to the second processing unit; and based on a predetermined processing process, the second processing unit updates a part corresponding to the second position in the second data frame to remove sensitive information.

[0057] According to an example implementation of the present disclosure, the predetermined processing process includes at least any one of the following: a scaling process, a confusion process, a filtering process, a noise process, and a deformation process.

[0058] According to an example implementation of the present disclosure, obtaining the first position includes: in response to the first processing unit receiving the first data frame, the first processing unit obtains the first position based on an object recognition process.

[0059] According to an example implementation of the present disclosure, the method further includes: based on the second position, the first processing unit determines a third position of the object in a third data frame after the second data frame, where the third data frame is acquired by the acquisition unit in the acquisition device; and the second processing unit removes sensitive information corresponding to the third position from the third data frame.

[0060] According to an example implementation of the present disclosure, the second position is obtained based on at least any one of an object recognition process and an object tracking process.

[0061] According to an example implementation of the present disclosure, the first data frame includes at least any one of the following: an original data frame acquired by the acquisition unit; and an updated original data frame with sensitive information removed.

[0062] According to an example implementation of the present disclosure, the method further includes: performing encoding on the first data frame and the updated second data frame to generate encoded data.

[0063] According to an exemplary implementation of the present disclosure, the first processing unit includes a system-on-chip unit in the acquisition device; and the second processing unit includes an image signal processing unit for controlling the acquisition unit.

[0064] Example device and equipment

[0065] According to an exemplary implementation of the present disclosure, there is provided an apparatus 800 for processing data frames. Figure 8 A block diagram of an apparatus 800 for processing data frames according to an exemplary implementation of the present disclosure is schematically shown. The apparatus includes: an obtaining module 810 configured to obtain a first position of an object to be processed in a first data frame by a first processing unit in an acquisition device; a determining module 820 configured to determine a second position of the object in a second data frame after the first data frame based on the first position by the first processing unit, where the first data frame and the second data frame are acquired by an acquisition unit in the acquisition device; and a removing module 830 configured to remove sensitive information corresponding to the second position in the second data frame by a second processing unit in the acquisition device.

[0066] According to an exemplary implementation of the present disclosure, the determining module includes: a time point determining module configured to determine a second time point of the second data frame based on a first time point of the first data frame and an acquisition interval of the acquisition unit; and a tracking module configured to determine the second position based on an object tracking process, based on the first position and the second time point.

[0067] According to an exemplary implementation of the present disclosure, the removing module includes: a transmitting module configured to transmit the second position from the first processing unit to the second processing unit; and a sensitive information removing module configured to update a part corresponding to the second position in the second data frame by the second processing unit based on a predetermined processing process to remove the sensitive information.

[0068] According to an exemplary implementation of the present disclosure, the predetermined processing process includes at least any one of the following: a scaling process, a confounding process, a filtering process, a noise process, and a deformation process.

[0069] According to an exemplary implementation of the present disclosure, the obtaining module includes: an identifying module configured to obtain the first position by the first processing unit based on an object identification process in response to the first processing unit receiving the first data frame.

[0070] According to an exemplary implementation of the present disclosure, the determining module is further configured to determine, by a first processing unit, a third position of the object in a third data frame after a second data frame based on a second position, where the third data frame is acquired by an acquisition unit in an acquisition device; and the removing module is further configured to remove, by a second processing unit, sensitive information corresponding to the third position in the third data frame.

[0071] According to an exemplary implementation of the present disclosure, the second position is obtained based on at least any one of an object recognition process and an object tracking process.

[0072] According to an exemplary implementation of the present disclosure, the first data frame includes at least any one of the following: an original data frame acquired by an acquisition unit; and an updated original data frame from which sensitive information has been removed.

[0073] According to an exemplary implementation of the present disclosure, the device further includes: an encoding module configured to perform encoding on the first data frame and the updated second data frame to generate encoded data.

[0074] According to an exemplary implementation of the present disclosure, the first processing unit includes a system-on-chip unit in an acquisition device; and the second processing unit includes an image signal processing unit for controlling the acquisition unit.

[0075] Figure 9 A block diagram of a computing device / server for processing data frames according to an exemplary implementation of the present disclosure is schematically shown. It should be understood that Figure 9 The computing device / server 900 shown is merely exemplary and should not impose any limitation on the functions and scope of the embodiments described herein.

[0076] As Figure 9 shown, the computing device / server 900 is in the form of a general-purpose computing device. The components of the computing device / server 900 may include, but are not limited to, one or more processors or processing units 910, a memory 920, a storage device 930, one or more communication units 940, one or more input devices 950, and one or more output devices 960. The processing unit 910 may be an actual or virtual processor and is capable of performing various processes according to programs stored in the memory 920. In a multi-processor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing ability of the computing device / server 900.

[0077] The computing device / server 900 generally includes multiple computer storage media. Such media can be any available media accessible to the computing device / server 900, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 920 can be volatile memory (such as registers, caches, random access memory (RAM)), non-volatile memory (such as read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 930 can be removable or non-removable media and can include machine-readable media, such as a flash drive, a magnetic disk, or any other medium that can be capable of storing information and / or data (such as training data for training) and can be accessed within the computing device / server 900.

[0078] The computing device / server 900 can further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown in Figure 9 it, a disk drive for reading from or writing to a removable, non-volatile magnetic disk (such as a "floppy disk") and an optical disk drive for reading from or writing to a removable, non-volatile optical disk can be provided. In these cases, each drive can be connected to a bus (not shown) by one or more data media interfaces. The memory 920 can include a computer program product 925 having one or more program modules that are configured to execute the various methods or actions of the various embodiments of the present disclosure.

[0079] The communication unit 940 enables communication with other computing devices via a communication medium. Additionally, the functions of the components of the computing device / server 900 can be implemented in a single computing cluster or multiple computer machines that are capable of communicating via a communication connection. Thus, the computing device / server 900 can operate in a networked environment using a logical connection with one or more other servers, network personal computers (PCs), or another network node.

[0080] The input device 950 can be one or more input devices, such as a mouse, a keyboard, a trackball, etc. The output device 960 can be one or more output devices, such as a display, a speaker, a printer, etc. The computing device / server 900 can also communicate with one or more external devices (not shown) as needed via the communication unit 940, such as storage devices, display devices, etc., communicate with one or more devices that enable a user to interact with the computing device / server 900, or communicate with any device that enables the computing device / server 900 to communicate with one or more other computing devices (such as a network card, a modem, etc.). Such communication can be performed via an input / output (I / O) interface (not shown).

[0081] According to an exemplary implementation of the present disclosure, there is provided a computer-readable storage medium having one or more computer instructions stored thereon, and when the one or more computer instructions are executed by a processor, the methods described above are implemented.

[0082] Aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0083] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine, such that when the instructions are executed by the processing unit of the computer or other programmable data processing apparatus, an apparatus is produced that implements the functions / acts specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, which causes a computer, a programmable data processing apparatus, and / or other devices to operate in a particular manner, so that the computer-readable medium storing the instructions includes a manufacture including instructions for implementing various aspects of the functions / acts specified in one or more blocks of the flowchart and / or block diagram.

[0084] The computer-readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device, such that a series of operation steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, so that the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions / acts specified in one or more blocks of the flowchart and / or block diagram.

[0085] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various implementations of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of code, or a portion of an instruction, which contains one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions noted in the blocks may occur in a different order than that noted in the accompanying drawings. For example, two consecutive blocks may in fact be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending upon the functionality involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or acts, or by a combination of dedicated hardware and computer instructions.

[0086] The various implementations of the present disclosure have been described above. The above description is exemplary, not exhaustive, and is not limited to the disclosed implementations. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described implementations. The choice of terms used herein is intended to best explain the principles of the implementations, the practical application, or improvements made to the technology in the marketplace, or to enable other ordinary skill in the art to understand the implementations disclosed herein.

Claims

1. A method for processing data frames, comprising: obtaining, by a first processing unit in an acquisition device, a first position of an object to be processed in a first data frame; determining, based on the first position, by the first processing unit, a second position of the object in a second data frame after the first data frame, where the first data frame and the second data frame are acquired by an acquisition unit in the acquisition device; and removing, by a second processing unit in the acquisition device, sensitive information corresponding to the second position in the second data frame.

2. The method according to claim 1, wherein determining the second position comprises: determining a second time point of the second data frame based on a first time point of the first data frame and an acquisition interval of the acquisition unit; and determining the second position based on an object tracking process, based on the first position and the second time point.

3. The method according to claim 1, wherein removing the sensitive information comprises: transmitting the second position from the first processing unit to the second processing unit; and updating, by the second processing unit, a part corresponding to the second position in the second data frame based on a predetermined processing process to remove the sensitive information.

4. The method according to claim 3, wherein the predetermined processing process comprises at least any one of the following: a scaling process, a scrambling process, a filtering process, a noise process, and a deformation process.

5. The method according to claim 1, wherein obtaining the first position comprises: In response to the first processing unit receiving the first data frame, the first processing unit obtains the first position based on an object recognition process.

6. The method according to claim 1, further comprising: determining, based on the second position, by the first processing unit, a third position of the object in a third data frame after the second data frame, where the third data frame is acquired by the acquisition unit in the acquisition device; and removing, by the second processing unit, sensitive information corresponding to the third position in the third data frame.

7. The method according to claim 6, wherein the second position is obtained based on at least any one of an object recognition process and an object tracking process.

8. The method according to claim 1, wherein the first data frame comprises at least any one of the following: an original data frame acquired by the acquisition unit; and an updated original data frame with sensitive information removed.

9. The method according to claim 1, further comprising: Performing encoding on the first data frame and the updated second data frame to generate encoded data.

10. The method according to claim 1, wherein the first processing unit comprises a system-on-chip unit in the acquisition device; and the second processing unit comprises an image signal processing unit for controlling the acquisition unit.

11. A device for processing data frames, comprising: an obtaining module configured to obtain, by a first processing unit in an acquisition device, a first position of an object to be processed in a first data frame; A determination module, configured to determine, by the first processing unit based on the first position, a second position of the object in a second data frame after the first data frame, where the first data frame and the second data frame are acquired by an acquisition unit in the acquisition device; and A removal module, configured to remove, by a second processing unit in the acquisition device, sensitive information corresponding to the second position in the second data frame.

12. An electronic device, comprising: A memory and a processor; wherein the memory is used to store one or more computer instructions, and the one or more computer instructions are executed by the processor to implement the method according to any one of claims 1 to 10.

13. A computer-readable storage medium, on which one or more computer instructions are stored, and the one or more computer instructions are executed by a processor to implement the method according to any one of claims 1 to 10.

14. A computer program product, comprising computer programs / instructions, and when the computer programs / instructions are executed by a processor, the method according to any one of claims 1 to 10 is implemented.

Images