Image transmission, image blurring processing method and device, equipment, storage medium

Abstract

The application provides an image transmission method, an image blurring processing method and device, equipment and a storage medium. The image transmission method is applied to a first processor and includes: segmenting a to-be-blurred image; determining depth information of segmented image regions; and sequentially transmitting the segmented image regions and corresponding depth information to a second processor. In response to receiving at least one image region and corresponding depth information, the second processor performs blurring processing on a target image region according to the depth information. The at least one image region constitutes a partial region of the to-be-blurred image.

Description

TECHNICAL FIELD

[0001] The present application relates to the image technology field, and in particular, relates to an image transmission method and device, an image blurring processing method and device, equipment and a storage medium. BACKGROUND

[0002] With the development of science and technology, camera, video camera and other camera devices are widely used in people's daily life, work and study, and play an increasingly important role in people's life. When an image is captured by using a camera device, in order to highlight the shooting subject and make the shooting subject clearly displayed, blurring processing is often used for the background area of the shooting.

[0003] Considering the trend of image or video development to high frame rate and high resolution in the future, if the relationship between the blurring effect and the blurring processing speed cannot be well balanced, the application of the blurring processing method in the high frame rate and / or high resolution scene will be directly affected. SUMMARY

[0004] Therefore, the image transmission method and device, the image blurring processing method and device, the equipment and the storage medium provided by the present application can help improve the blurring processing speed of the whole image without affecting the blurring effect of the image.

[0005] According to an aspect of an embodiment of the present application, an image transmission method is provided, which is applied to a first processor, and the method comprises: segmenting a to-be-blurred image; determining depth information of the segmented image region; and transmitting the segmented image region and the corresponding depth information to a second processor in sequence; wherein the second processor performs blurring processing on a target image region according to the depth information in response to receiving at least one image region and the corresponding depth information; and the at least one image region constitutes a partial region of the to-be-blurred image.

[0006] In this way, the to-be-blurred image is segmented so as to transmit the segmented image region and the corresponding depth information to the second processor in sequence; in this way, the second processor can perform blurring processing after receiving the partial region of the to-be-blurred image and the corresponding depth information, without waiting for receiving all image data of the to-be-blurred image to perform blurring processing, thereby effectively shortening the overall processing time of the to-be-blurred image.

[0007] According to another aspect of the embodiments of the present application, provided is an image blurring processing method, which is applied to a second processor, and includes: in response to at least one image region and corresponding depth information transmitted by a first processor, performing blurring processing on a target image region according to the depth information, to obtain a blurred image region; wherein the at least one image region is obtained by segmenting a to-be-blurred image by the first processor, and the at least one image region constitutes part of the to-be-blurred image.

[0008] According to still another aspect of the embodiments of the present application, provided is an image blurring processing method, which includes: segmenting a to-be-blurred image by a first processor, and determining depth information of segmented image regions; transmitting the segmented image regions and corresponding depth information to a second processor in sequence by the first processor; and in response to receiving at least one image region and corresponding depth information, performing blurring processing on a target image region according to the depth information by the second processor; wherein the at least one image region constitutes part of the to-be-blurred image.

[0009] According to still another aspect of the embodiments of the present application, provided is an image transmission device, which includes: a segmentation module configured to segment a to-be-blurred image; a determination module configured to determine depth information of segmented image regions; and a transmission module configured to transmit the segmented image regions and corresponding depth information to an image blurring processing device in sequence; wherein in response to receiving at least one image region and corresponding depth information, the image blurring processing device performs blurring processing on a target image region according to the depth information, and the at least one image region constitutes part of the to-be-blurred image.

[0010] According to still another aspect of the embodiments of the present application, provided is an image blurring processing device, which includes: a blurring processing module configured to, in response to at least one image region and corresponding depth information transmitted by an image transmission device, perform blurring processing on a target image region according to the depth information, to obtain a blurred image region; wherein the at least one image region is obtained by segmenting a to-be-blurred image by the image transmission device, and the at least one image region constitutes part of the to-be-blurred image.

[0011] According to another aspect of the embodiments of the present application, provided is an electronic device including the image transmission device and the image blurring processing device according to the embodiments of the present application.

[0012] According to another aspect of the embodiments of the present application, an electronic device is provided, which comprises a first memory, a first processor, a second memory and a second processor, the first memory stores a computer program which can be run on the first processor, the second memory stores a computer program which can be run on the second processor, the first processor implements the image transmission method according to the embodiments of the present application when running the program, and the second processor implements the image blurring processing method according to the embodiments of the present application when running the program.

[0013] According to an aspect of the embodiments of the present application, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the image transmission method and / or the image blurring processing method according to the embodiments of the present application.

[0014] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and are not limiting to the present application. BRIEF DESCRIPTION OF DRAWINGS

[0015] The drawings incorporated in the specification and constituting a part of the specification illustrate embodiments consistent with the present application and, together with the specification, serve to explain the technical solutions of the present application. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort on the basis of these drawings.

[0016] The flowcharts shown in the drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor do they have to be executed in the order described. For example, some operations / steps can be further divided, and some operations / steps can be combined or partially combined, so the actual execution order may be changed according to the actual situation.

[0017] Figure 1 Structure schematic diagram of the electronic device provided by the embodiments of the present application;

[0018] Figure 2 Implementation flowchart of the image blurring processing method provided by the embodiments of the present application;

[0019] Figure 3 Principle schematic diagram of the image blurring processing provided by the embodiments of the present application;

[0020] Figure 4 System workflow schematic diagram provided by the embodiments of the present application;

[0021] Figure 5 Multi-level segmentation schematic diagram provided by the embodiments of the present application;

[0022] Figure 6A system module schematic diagram provided by an embodiment of the present application is shown in the following figure;

[0023] Figure 7 A structure schematic diagram of an image transmission device provided by an embodiment of the present application is shown in the following figure;

[0024] Figure 8 A structure schematic diagram of an image virtualization processing device provided by an embodiment of the present application is shown in the following figure;

[0025] Figure 9 A structure schematic diagram of an electronic device provided by an embodiment of the present application is shown in the following figure;

[0026] Figure 10 A structure schematic diagram of an electronic device provided by an embodiment of the present application is shown in the following figure. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the following will combine the figures in the embodiments of the present application to make a further detailed description of the specific technical solutions of the present application. The following embodiments are used to illustrate the present application, but not to limit the scope of the present application.

[0028] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application, and are not intended to limit the present application.

[0029] In the following description, “some embodiments”, “the embodiment”, “the embodiments of the present application” and the like describe a subset of all possible embodiments, and “some embodiments” can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict.

[0030] It should be noted that the terms “first”, “second”, “third”, “fourth”, “fifth” and the like involved in the embodiments of the present application are used to distinguish similar or different objects, and do not represent a specific order of the objects. Understandably, “first”, “second”, “third”, “fourth” and “fifth” can be interchanged with a specific order or sequence as allowed, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0031] The embodiments of the present application provide an image transmission and image virtualization processing method, which is applied to an electronic device. The electronic device can be various types of devices with information processing capability in the implementation process, for example, the electronic device can include a mobile phone, a tablet computer, a smart watch, etc. Figure 1 As shown in the figure, the electronic device 10 includes a first processor 101 and a second processor 102.

[0032] Figure 2An implementation flowchart of the image blurring processing method provided in the embodiments of the present application is shown in FIG. 1, which can include the following steps 201 to 204: Figure 2

[0033] In step 201, the first processor 101 segments the image to be blurred and determines the depth information of the segmented image regions.

[0034] In step 202, the first processor 101 transmits the segmented image regions and the corresponding depth information to the second processor 102 in sequence.

[0035] In step 203, the second processor 102 performs blurring processing on the target image region according to the depth information in response to receiving at least one of the image regions and the corresponding depth information; wherein the at least one image region constitutes a partial region of the image to be blurred.

[0036] In step 204, the second processor 102 splices the at least two blurred image regions.

[0037] In the embodiments of the present application, the first processor 101 segments the image to be blurred so as to transmit the segmented image regions and the corresponding depth information to the second processor 102 in batches in sequence; in this way, the second processor 102 can perform blurring processing upon receiving the partial region of the image to be blurred and the corresponding depth information, without waiting for receiving all the image data of the image to be blurred before performing blurring processing, thereby effectively shortening the overall processing time of the image to be blurred.

[0038] The further optional implementation modes of the above steps and related terms are described below.

[0039] In step 201, the first processor 101 segments the image to be blurred and determines the depth information of the segmented image regions.

[0040] In the embodiments of the present application, the segmentation algorithm is not limited and can be various, as long as it can segment the image to be blurred into at least two image regions.

[0041] In some embodiments, the first processor 101 can implement step 201 in the following way: determining the segmentation level according to the scene parameters of the image to be blurred and / or the performance parameters of the second processor 102; and segmenting the image to be blurred according to the segmentation level; wherein the segmentation level refers to the total number of image regions to be segmented; the scene parameters are used to represent the complexity of the content of the image to be blurred, and the performance parameters are used to represent the processing capability of the second processor 102.

[0042] ​Further, in some embodiments, the dividing the image to be blurred according to the division level comprises: determining a depth threshold for the division according to the division level and depth information of the image to be blurred; dividing the depth information of the image to be blurred according to the depth threshold to obtain image range parameters (i.e. corresponding position points in the image to be blurred) corresponding to the divided depth information; and dividing the corresponding image region from the image to be blurred according to the image range parameters. In this way, the depth threshold for the division is determined according to the division level and the depth information of the image to be blurred, so that position points with consistent depth or within a certain range of difference are divided into the same image region. Thus, the second processor 102 can use the same blurring calculation for all or most position points in the image region, without the need for more different blurring calculations, thereby saving the power consumption caused by blurring calculation and shortening the blurring processing time.

[0043] In the embodiments of the present application, the types of the scene parameters and the performance parameters are not limited and can be various types of parameters. For example, in some embodiments, the scene parameters can include at least one of the following: whether it is a high motion scene, whether it includes complex color blocks (such as plaid shirts, checkerboards, etc.), and the number of planes; and the performance parameters can include at least one of the following: the occupancy rate of the second processor 102 and the blurring processing speed of the second processor 102; wherein the blurring processing speed is equivalent to the average length of time for blurring processing of the image region.

[0044] It can be understood that in the embodiments of the present application, the division level is adapted to the performance parameters of the second processor 102 and / or the scene parameters of the image to be blurred. In this way, on the one hand, the processing capacity of the second processor 102 can be utilized as much as possible according to the performance parameters, thereby improving the blurring processing efficiency; on the other hand, a proper number of image regions are divided according to the scene parameters, thereby being beneficial to reducing the division processing load of the first processor 101 and reducing the splicing processing load of the second processor 102.

[0045] For example, when the occupancy of the second processor 102 is small (e.g., less than the first threshold) and / or the blurring processing speed of the second processor 102 is fast (e.g., greater than the second threshold), the image to be blurred can be divided into a smaller number of image regions, which can reduce the division processing load of the first processor 101 and also reduce the number of image regions to be spliced by the second processor 102, thereby reducing the splicing processing load. When the occupancy of the second processor 102 is large (e.g., greater than or equal to the first threshold) or the blurring processing speed of the second processor 102 is slow (e.g., less than or equal to the second threshold), the image to be blurred can be divided into a larger number of image regions, which makes the number of pixels in each image region smaller, so that the first processor 101 can process an image region in a shorter time, thereby shortening the waiting time of the next image region to be processed, which shortens the overall processing time of the image to be blurred and improves the blurring processing efficiency.

[0046] It can be understood that the greater the number of image regions to be divided, the greater the division workload of the first processor 101, and correspondingly, the more image regions to be spliced by the second processor 102. Conversely, the smaller the number of image regions to be divided, the smaller the division workload of the first processor 101, and correspondingly, the fewer image regions to be spliced by the second processor 102. It can be seen that selecting an appropriate image region according to the performance parameters of the second processor 102 and the scene parameters of the image to be blurred is beneficial to reducing the division processing load of the first processor 101 and the splicing processing load of the second processor 102.

[0047] In some embodiments, a mapping relationship between different scene parameters and / or different performance parameters and different division levels can be predefined, so that the first processor 101 can determine the division level suitable for the image to be blurred according to the mapping relationship.

[0048] In the embodiments of the present application, the determination method of the scene parameter is not limited, which can be a parameter directly issued by the second processor 102 to the first processor 101. The second processor 102 can perform scene recognition on the image to be blurred according to a standard that can affect the image blurring effect, so as to obtain the scene parameter (e.g., the scene parameter is used to represent whether it is a high motion scene and / or whether it contains complex color blocks, etc.). Of course, the scene recognition task can also be performed by the first processor 101 or other processors, and the present application does not limit the implementation subject of the scene recognition.

[0049] In some embodiments, the scene parameter can also be determined by the first processor 101 according to depth information of the image to be blurred and / or content recognition result of the image to be blurred. Of course, the scene parameter can also be determined by the second processor 102 or other processors.

[0050] It can be understood that the scene parameter is determined based on the depth information of the image to be blurred, which is beneficial for subsequent segmentation of position points with the same or similar depth into the same image region, and accordingly, if the depth of the position points in an image region is the same or similar, the workload of the blurring processing of the second processor 102 can be reduced, thereby improving the blurring processing efficiency.

[0051] In some embodiments, the depth information of the image to be blurred can be one of the following: depth information of a previous adjacent frame, depth information of a previous non-adjacent frame, and depth information of a current frame; and the depth information of the image region is obtained based on a corresponding part of the image region in the depth information of the image to be blurred.

[0052] Considering that the corresponding depth information can not have been calculated or the calculation speed is relatively slow when the first processor 101 performs segmentation processing on the image to be processed, in some embodiments, the depth information of the previous adjacent frame or the depth information of the previous non-adjacent frame can be used as the depth information of the image to be blurred of the current frame, so that the depth information of the segmented image region can be transmitted to the second processor 102 earlier, thereby shortening the overall processing time of the image to be blurred and improving the blurring processing efficiency.

[0053] In the embodiments of the present application, the depth information of the previous adjacent frame or the depth information of the previous non-adjacent frame can be used as the depth information of the image to be blurred of the current frame with or without a precondition. For embodiments with a precondition, for example, the first processor 101 can first determine a motion parameter representing the degree of scene change; in response to the motion parameter satisfying a first condition, the depth information of the previous adjacent frame or the depth information of the previous non-adjacent frame is used as the depth information of the image to be blurred; otherwise, the depth information of the current frame is used as the image to be blurred of the current frame.

[0054] It can be understood that for a scene in which the motion parameter satisfies the first condition, i.e., a low-motion scene in which the scene change is relatively stable, the difference between the depth information of the previous adjacent frame or the depth information of the previous non-adjacent frame and the depth information of the current frame is relatively small; therefore, in this scene, the depth information of the previous adjacent frame or the depth information of the previous non-adjacent frame is used as the depth information of the image to be blurred of the current frame, and the transmission of the depth information is based on this, which can enable the second processor 102 to improve the blurring processing efficiency while ensuring the blurring processing effect.

[0055] In some embodiments, the depth information of the image region transmitted to the second processor 102 can include the depth of each position point of the image region; in other embodiments, the depth information of the image region transmitted to the second processor 102 can also be an average depth value of the depth of each position point of the image region. Especially for the image region with consistent depth values, the depth value of any position point of the region can be transmitted to the second processor 102, instead of the depth of each position point of the region, thereby saving the bandwidth overhead of data transmission.

[0056] In step 202, the first processor 101 transmits the segmented image region and the corresponding depth information to the second processor 102 in sequence.

[0057] When implementing step 202, the first processor 101 can transmit the current segmented image region and the corresponding depth information to the second processor 102 while segmenting; or the first processor 101 can transmit the segmented image region and the corresponding depth information to the second processor 102 in batches after the image to be blurred is segmented. Compared with the latter, the strategy of transmitting while segmenting can transmit the image region and the corresponding depth information to the second processor 102 as early as possible, so that the second processor 102 can start the blurring processing of the image region as early as possible, that is, as soon as the second processor 102 receives an image region and the corresponding depth information, the second processor 102 can start the blurring processing of the image region according to the depth information, thereby improving the overall blurring efficiency of the image to be blurred.

[0058] For the strategy of transmitting while segmenting, specifically, in some embodiments, the first processor 101 can transmit at least one image region and the corresponding depth information to the second processor 102 when the at least one image region is segmented; wherein the at least one image region constitutes part of the image to be blurred. That is, in the embodiments of the present application, it is not limited to whether to transmit one segmented image region to the second processor 102 or to transmit multiple segmented image regions to the second processor 102. In summary, the image regions of the image to be blurred are transmitted to the second processor 102 in batches, thereby achieving the beneficial effect that the second processor 102 can start the blurring processing of the image region as early as possible.

[0059] It should be further noted that in the embodiments of the present application, the transmission strategy is not limited, the first processor 101 can first transmit all image regions of the image to be blurred, and then transmit the depth information corresponding to the image regions in batches, or transmit an image region in one data packet and transmit the depth information corresponding to the image region in another adjacent data packet; the first processor 101 can also package the at least one image region and the corresponding depth information into one data packet; then transmit the data packet to the second processor 102; so that the second processor 102 receives the data packet, analyzes the data packet, obtains the at least one image region and the corresponding depth information, and then performs blurring processing on the target image region according to the depth information; the first processor 101 can also package the image region and the corresponding depth information into one data packet and transmit it to the second processor 102 after segmenting an image region.

[0060] In summary, regardless of the packaging and transmission method, compared with starting the blurring processing after receiving all image data and corresponding depth information of the image to be blurred, as long as the blurring processing time of the second processor 102 is advanced.

[0061] Further, in some embodiments, the first processor 101 can package the at least one image region, the corresponding depth information, and the frame identifier and the region identifier of the at least one image region into one data packet; in this way, on the one hand, the second processor 102 can accurately splice the corresponding blurred image region according to the frame identifier and the region identifier, thereby avoiding the situation that the splicing is misaligned or spliced with the image region of other frames; on the other hand, compared with the splicing method based on content recognition, this splicing method has a simple algorithm, thereby saving the calculation overhead and shortening the overall blurring time of the image to be blurred.

[0062] Considering that users are more sensitive and concerned about the visual effects of the focal plane region and the secondary focal plane, during the blurring processing, it is expected to spend more time to process these regions more finely, but it is not expected to sacrifice more processing time.

[0063] Therefore, in some embodiments, the first image region and the corresponding depth information are transmitted to the second processor 102 earlier than the second image region and the corresponding depth information. The first processor 101 preferentially transmits the first image region and the corresponding depth information to the second processor 102 compared with the second image region, so that the second processor 102 can perform the blurring processing on the first image region as early as possible. The first image region includes an image region whose absolute value of the depth difference from the focal plane of the image to be blurred is less than or equal to a difference threshold and / or an image region including the focal plane, and the second image region refers to the image region whose absolute value of the depth difference from the focal plane is greater than the difference threshold.

[0064] In this way, the image region that needs more time for blurring processing is preferentially transmitted to the second processor 102, so that the next image region is transmitted while the second processor 102 is processing the blurring of the image region, and the second processor 102 can immediately process the blurring of the transmitted image region after completing the current blurring processing task without waiting for the next image region, thereby improving the blurring processing efficiency of the second processor 102.

[0065] In other embodiments, the first processor 101 can also transmit the image regions and the corresponding depth information to the second processor 102 in order of the absolute value of the depth difference from the focal plane from small to large. That is, the image region close to the focal plane and the corresponding depth information are preferentially transmitted to the second processor 102, which is beneficial to improve the blurring processing efficiency of the second processor 102.

[0066] In step 203, the second processor 102 performs blurring processing on the target image region according to the depth information in response to receiving at least one image region and the corresponding depth information. The at least one image region constitutes a partial region of the image to be blurred. The target image region is the image region corresponding to the depth information.

[0067] It can be understood that once the second processor 102 receives an image region and the depth information corresponding to the image region, the blurring processing on the image region can be performed without waiting for the arrival of other image regions.

[0068] In some embodiments, the second processor 102 receives a data packet transmitted by the first processor 101, and parses the data packet to obtain the at least one image region and the corresponding depth information.

[0069] In step 204, the second processor 102 splices the at least two blurred image regions.

[0070] In some embodiments, the second processor 102 parses the data packet to further obtain the frame identifier and the region identifier of the at least one image region; then, the second processor 102 can stitch the at least two blurred image regions according to the frame identifier and the region identifier of the at least two blurred image regions.

[0071] The image blurring scheme includes a single-camera-based blurring scheme and a double-camera-based blurring scheme; wherein the single-camera-based image blurring is mainly achieved by blurring algorithm processing on the regions other than the focusing region. However, due to the use of only one camera, it is difficult to obtain the depth information of the lens and the shooting region, resulting in similar blurring degrees of different regions when the algorithm is processed. More complex algorithm processing can use deep learning for background segmentation. A neural network is trained using a data set to achieve foreground and background segmentation. After segmentation, it is determined which objects are the main objects that are expected to be clearly focused, and which objects are the background that is expected to be blurred. However, if the blurring is performed only according to the foreground and background segmentation results, the blurred photo is not natural. The main reason is still the lack of depth data, which cannot be used for distance-dependent blurring, and the segmentation algorithm may make errors in judging the foreground and background.

[0072] In some embodiments, a depth map (Depth Map) of the to-be-blurred image, i.e., depth information of the to-be-blurred image, is constructed using a double camera to infer the foreground and background relationship of the scene, and the blurring degree of different scenes is controlled based on this. The double camera can calculate the distance of each pixel point from the focus plane using the perspective difference of the two cameras, and then calculate the blurring degree according to the focus plane distance.

[0073] For image blurring processing, as shown in Figure 3 Fig. 3, in theory, the farther away from the focus plane 301, the larger the dispersion circle, and the more blurred the image. That is, the closer to the focus plane 301, the clearer the image. The ideal effect of blurring is that although everything outside the depth of field is blurred, the blurring degree is different, the closer to the focus plane, the clearer, and the farther away from the focus plane, the more blurred.

[0074] In the embodiments of the present application, although it is a single-camera-based blurring scheme, due to the presence of the front-end NPU, depth information calculation based on a single camera can be performed using corresponding algorithms, rather than the method of directly blurring other regions based on matting when a single camera is used. Therefore, the blurring effect of the embodiments of the present application is relatively close to the blurring effect of the double camera, and at the same time, since a single camera is used, the data amount can be greatly reduced, the transmission and processing pressure of the system can be reduced, and power consumption can be saved.

[0075] Considering the subsequent development trend of high frame rate and high resolution, if the relationship between effect and processing speed cannot be well balanced, it will directly affect the application of blurring in high frame rate and high resolution scenarios. Therefore, in the embodiments of the present application, the processing speed of blurring is accelerated from the direction of segmentation processing.

[0076] In some embodiments, whether it is a dual-camera blurring solution used on a large scale or a single-camera blurring solution used, further processing is based on the collection of the entire image; that is, further blurring processing is started only after the entire image or the depth information corresponding to the entire image is received. The time consumption of processing a frame is the transmission time plus the image processing time. If synchronous image blurring processing is performed at the same time as transmission, a part of the time and data transmission can be parallel, thereby reducing the relative processing time of the entire image, which is particularly beneficial for scenarios with large resolution.

[0077] Based on this, the exemplary application of the embodiments of the present application in an actual application scenario will be described below.

[0078] In the embodiments of the present application, a multi-level segmentation blurring solution based on depth information and scene characteristics is provided, and the main idea is as follows: through the segmentation processing of the entire image (i.e., the image to be blurred) combined with the obtained depth information in the front end (for example, the position points with consistent or certain range of differences in depth information are segmented into the same image region, and the number of segmentation levels can be set according to the performance of the system and the processing speed of the AP side), after the segmentation is completed, the different image regions after segmentation and the corresponding depth information are transmitted to the AP side (i.e., an example of the second processor 102) in batches; the AP side can perform blurring processing on the received part of the image data synchronously after receiving it; in this way, after the depth information calculation and transmission of the entire image are completed, the AP side can have completed the blurring processing of most of the image regions, and finally the blurring results are merged to obtain the complete blurred image.

[0079] The specific implementation scheme is as follows: the image data (i.e. the image to be blurred) of the current frame obtained at the front end is subjected to depth information calculation to obtain corresponding depth information; the appropriate number of levels is determined according to the obtained scene parameters (including the scene parameters obtained by using the scene recognition algorithm owned by the front end) and the scene characteristics; the entire image (i.e. the image to be blurred) is segmented according to the depth information and in combination with the determined number of levels (at the same time, the depth information is subjected to corresponding segmentation processing); the image data (i.e. the image region) after segmentation and the corresponding depth information are packaged and transmitted together, so as to facilitate real-time blurring processing of the AP side after receiving the data; the AP side receives the data and performs blurring processing (the image data close to the focal plane can be transmitted first, so that the AP side has more time to obtain better image blurring effect); finally, the image data after blurring processing is spliced to form a complete image data after blurring.

[0080] The specific implementation process is as shown in Figure 4 and includes the following steps 401 to 408:

[0081] Step 401, the camera is opened;

[0082] Step 402, the sensor (Sensor) of the camera acquires image data (i.e. the image to be blurred);

[0083] Step 403, the depth information corresponding to the current frame (i.e. the image to be blurred) is obtained by calculation, and the scene information (i.e. the scene parameter) given by the AP side is acquired; in some embodiments, the AP side sends the scene information to the front end module together with the data request (request) information;

[0084] Step 404, the complete image data (i.e. the image to be blurred) is subjected to multi-level segmentation processing based on the current scene characteristics and in combination with the depth information; and the depth information (i.e. the data reflecting the depth of different regions of the entire image) is subjected to the same segmentation processing based on the segmentation result, so that the segmented depth information and the segmented image data correspond to each other;

[0085] Step 405, the segmented image data (i.e. the image region) and the corresponding depth information are packaged and transmitted;

[0086] Step 406, the AP side performs real-time blurring processing on the received depth information and image data;

[0087] Step 407, after the processing of multiple data packets is completed (i.e. the data blurring processing corresponding to one frame is completed), the obtained blurring result is spliced and fused to obtain a complete image data after blurring;

[0088] Step 408, subsequent image post-processing is performed, and image recording or preview is continued.

[0089] For image stitching after segmentation, the same frame ID and corresponding region ID can be added during the front-end segmentation and packaging. This will allow for accurate determination of the image's position within the entire image during subsequent stitching, avoiding mis-stitching or incorrect stitching with other frames (if the same frame ID is not available, a piece of data from the current frame may be stitched together with the next frame).

[0090] When performing multi-level segmentation, the front end primarily determines the number of levels (i.e., the number of segmentation levels) based on the characteristics of the scene (scene complexity can also be determined based on the number of planes where objects reside, as reflected by depth information) and the changes in the power consumption and performance parameters of the current system. Then, it segments the current image data based on the depth information corresponding to the current frame. After segmentation, the depth data corresponding to different regions and the corresponding segmented image data are sent together to subsequent modules for processing.

[0091] For example, Figure 5 As shown, when the objects in the scene are found to be mainly concentrated in three planes based on depth information, namely the focal plane region, the subfocal plane region, and the background region, the segmentation level can be set to 3.

[0092] In some embodiments, such as Figure 6 As shown, this illustrates the system architecture applicable to the embodiments of this application. The YUV format image to be blurred is transmitted via a resizing module (i.e., a resize module) 601, then one path is sent to a depth information calculation module 602 for depth information calculation; the other path is sent to a Pre-ISP image analysis and segmentation module 603 for segmentation based on the depth information. Module 603 sends the segmented image region and corresponding depth information to a data packaging module 604, which packages the image region and corresponding depth information and then transmits it via MIPI to an image blurring processing module 605. Module 605 blurs the corresponding image region based on the depth information and then transmits the blurred image region to a blurring post-processing module 606. Module 606 stitches and merges the blurred image region, and after obtaining the stitched and merged complete image, it transmits it to an image post-processing module 607. Module 607 performs post-processing on the received image and transmits the post-processing result to a camera scene management module 608 for image display and preview. The camera scene management module 608 identifies the scene information and sends it to module 603.

[0093] The identification and use of the scene information can be directly based on the scene parameters determined by the AP side, or a scene analysis and identification module can be added in the front end to identify the scene according to the standards that can affect the blurring effect. For example, for the present scheme, it can be: whether it is a high motion scene and / or whether it is a scene with complex color blocks (such as plaid shirts), etc. Then, the scene characteristics are combined with the depth information to perform segmentation processing.

[0094] When performing segmentation processing in the front end, the depth information of the current frame can not have been calculated (or the calculation speed is slow), so the depth information of the previous frame can be used at the same time as the depth information of the current frame is calculated (the depth information of the adjacent two frames generally has small differences, especially for low motion scenes with stable scene changes). The front end module performs image segmentation and processing for the current frame based on the depth information of the previous frame, which can better speed up the blurring processing speed.

[0095] In the embodiments of the present application, the depth information calculation and image segmentation are first performed in the front end (i.e., the first processor 101), so the entire image data can be segmented into multiple different regions for real-time transmission and processing. Compared with performing blurring processing after receiving the entire image data, the blurring speed of the entire image can be greatly improved, i.e., when the last piece of image data is received, the image data transmitted in the early stage has been basically blurred. Therefore, the embodiments of the present application are particularly suitable for subsequent high-resolution and high-frame-rate scenes.

[0096] In the embodiments of the present application, by performing segmentation transmission on the image to be blurred based on the scene information and the depth information corresponding to the current frame in the front end, real-time transmission and blurring processing of the image data are realized:

[0097] (1) The front end performs depth information calculation and segmentation of the corresponding image region on the image to be blurred in a region-by-region manner, and transmits the segmented image region to the AP side for blurring processing in a transmission manner;

[0098] (2) The AP side performs blurring on the image data according to the predetermined blurring strategy, and blurs the image with different depth differences to a corresponding degree. The blurring of the entire image is completed in real time by processing a part of the image according to the received image data, and the final blurred image is generated. Compared with serial processing, the relative processing time of the entire image can be saved.

[0099] When the multi-level segmentation of the image to be blurred is performed at the front end (i.e., the first processor 101), the number of levels of segmentation can be determined according to the characteristics of the scene and the current state of the system (for example, more levels of segmentation can be used when the system has low power consumption and the current scene is complex); the complexity of the scene can be determined according to the recognition result of the objects in the scene, or can be determined according to the depth information corresponding to the current image; for example, when the depth information finds that the objects in the scene are mainly concentrated on three planes, the number of levels of segmentation can be set to 3; and finally, the image is segmented according to the depth information of different regions.

[0100] The blurring of the image at the back end (i.e., the second processor 102) is performed according to the edge processing method (since the image data after segmentation is transmitted together with the depth information of the corresponding region, the real-time blurring condition at the back end (AP side) is met), and the blurring is basically completed after the transmission of the entire image is completed, and finally the image is spliced and fused to form a complete image.

[0101] In the embodiment of the present application, for the real-time processing of the image after segmentation, since the segmentation of the image to be blurred is based on depth information, the focal plane region or the background region can be distinguished, and the focal plane region and the region of the secondary focal plane can be transmitted first, so that the AP side can spend more time to process the key regions more finely when performing subsequent algorithm processing and blurring processing.

[0102] For the blurring processing and image splicing, in order to reduce the influence on the post-processing algorithm, the two processing modules can be moved to an earlier node for processing, so that the subsequent image processing algorithm processes the complete image data frame, and does not need to be real-time adapted and updated due to the change of image segmentation; that is, the change of the blurring scheme does not affect the flow and strategy of the image post-processing.

[0103] It should be noted that although the steps of the method in the present application are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired result. In addition or alternatively, some steps can be omitted, a plurality of steps can be combined into one step, and / or one step can be divided into a plurality of steps, etc.; or, the steps in different embodiments can be combined into a new technical solution.

[0104] Based on the foregoing embodiments, the embodiments of the present application provide an image transmission device and an image blurring processing device, which include respective modules and units included in the respective modules, and can be implemented by a processor; of course, the embodiments can also be implemented by a specific logic circuit; in the implementation process, the processor can be a central processing unit (CPU), an ISP, a Pre-ISP, a GPU, an NPU, a microprocessor (MPU), a digital signal processor (DSP), or a field programmable gate array (FPGA), etc.

[0105] Figure 7 A structural schematic diagram of an image transmission device provided by the embodiments of the present application is shown in FIG. 7, which includes: Figure 7

[0106] A segmentation module 701 configured to segment a to-be-blurred image.

[0107] A determination module 702 configured to determine depth information of an image region segmented.

[0108] A transmission module 703 configured to transmit the segmented image region and corresponding depth information to an image blurring processing device in sequence; wherein the image blurring processing device performs blurring processing on a target image region according to the depth information in response to receiving at least one image region and corresponding depth information; wherein the at least one image region constitutes a partial region of the to-be-blurred image.

[0109] In some embodiments, the transmission module 703 is configured to transmit the at least one image region and corresponding depth information to the image blurring processing device 80 in response to segmenting the at least one image region.

[0110] In some embodiments, the transmission module 703 is configured to package the at least one image region and corresponding depth information into a data packet; and transmit the data packet to the image blurring processing device 80.

[0111] In some embodiments, the segmentation module 701 is configured to: determine a segmentation level according to a scene parameter of the to-be-blurred image and / or a performance parameter of the image blurring processing device; and segment the to-be-blurred image according to the segmentation level; wherein the scene parameter is used to represent the complexity of the content of the to-be-blurred image, and the performance parameter is used to represent the processing capability of the image blurring processing device.

[0112] In some embodiments, the determination module 702 is further configured to determine the scene parameter of the to-be-blurred image according to depth information of the to-be-blurred image and / or a content recognition result of the to-be-blurred image.

[0113] ​In some embodiments, the segmentation module 701 is configured to: determine a depth threshold for segmentation according to the segmentation level and depth information of the image to be blurred; segment the depth information of the image to be blurred according to the depth threshold to obtain image range parameters corresponding to the segmented depth information; and segment the corresponding image region from the image to be blurred according to the image range parameters.

[0114] In some embodiments, the depth information of the image to be blurred is one of: depth information of a previous adjacent frame, depth information of a previous non-adjacent frame, and depth information of a current frame; and the depth information of the image region is obtained based on a corresponding part of the image region in the depth information of the image to be blurred.

[0115] In some embodiments, the determination module 702 is further configured to: determine a motion parameter representing a degree of scene change; and in response to the motion parameter satisfying a first condition, use the depth information of the previous adjacent frame or the previous non-adjacent frame as the depth information of the image to be blurred.

[0116] In some embodiments, the transmission module 703 is configured to: transmit the first image region and corresponding depth information to the image blurring processing apparatus at an earlier time than the second image region and corresponding depth information; the first image region includes an image region with an absolute value of a depth difference from a focal plane of the image to be blurred less than or equal to a difference threshold and / or an image region including the focal plane; and the second image region refers to the image region with an absolute value of the depth difference from the focal plane greater than the difference threshold.

[0117] In some embodiments, the transmission module 703 is configured to sequentially transmit the image regions and corresponding depth information to the image blurring processing apparatus in order of absolute values of depth differences from the focal plane from small to large.

[0118] In some embodiments, the transmission module 703 is configured to package the at least one image region, corresponding depth information, and frame identifier and region identifier of the at least one image region into a data packet, so that the image blurring processing apparatus splices the corresponding blurred image region according to the frame identifier and the region identifier.

[0119] Figure 8 A structural schematic diagram of an image blurring processing apparatus provided by an embodiment of the present application is shown in FIG. 8. Figure 8 As shown in FIG. 8, the image blurring processing apparatus 80 includes:

[0120] The receiving module 801 is configured to receive at least one image region and corresponding depth information transmitted by the image transmission apparatus 70.

[0121] The blurring processing module 802 is configured to, in response to the received at least one image region and corresponding depth information, perform blurring processing on the target image region according to the depth information to obtain a blurred image region; wherein the at least one image region is obtained by the image transmission device 70 segmenting the image to be blurred, and the at least one image region constitutes a partial region of the image to be blurred.

[0122] In some embodiments, the image blurring processing device 80 further comprises a splicing module configured to splice the at least two blurred image regions.

[0123] In some embodiments, the image blurring processing device 80 further comprises a receiving module configured to receive a data packet transmitted by the image transmission device 70; and parse the data packet to obtain the at least one image region and corresponding depth information.

[0124] In some embodiments, the receiving module parses the data packet to further obtain frame identifiers and region identifiers of the at least one image region; and the splicing module is configured to splice the at least two blurred image regions according to the frame identifiers and region identifiers of the at least two blurred image regions.

[0125] The above description of the device embodiments is similar to the description of the method embodiments, and has similar beneficial effects. For technical details not disclosed in the device embodiments of the present application, please refer to the description of the method embodiments for understanding.

[0126] The division of the modules of the device in the embodiments of the present application is illustrative, and is only a logical functional division. In actual implementation, another division mode can be used. In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or can be physically separated, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware, or in the form of a software functional unit. It can also be realized in the form of a combination of software and hardware.

[0127] It should be noted that, in the embodiments of the present application, if the above-mentioned method is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present application can be embodied in the form of a software product in essence or the part that contributes to the related art, and the computer software product is stored in a storage medium, including a plurality of instructions for causing an electronic device to execute all or part of the method described in the embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (Read Only Memory, ROM), a magnetic disk or an optical disk, and various media that can store program codes. Thus, the embodiments of the present application are not limited to any specific hardware and software combination.

[0128] Figure 9 The structural schematic diagram of the electronic device provided in the embodiments of the present application is shown in FIG. 1. Figure 9 As shown in FIG. 1, the electronic device 90 includes an image transmission device 70 and an image blurring processing device 80.

[0129] The embodiments of the present application further provide an electronic device, Figure 10 The hardware entity schematic diagram of the electronic device in the embodiments of the present application is shown in FIG. 2. Figure 10 As shown in FIG. 2, the electronic device 100 includes a first memory 1001, a first processor 101, a second memory 1002 and a second processor 102, the first memory 1001 stores a computer program executable on the first processor 101, the second memory 1002 stores a computer program executable on the second processor 102, the first processor 101 executes the program to implement the steps involved in the foregoing embodiments, and the second processor 102 executes the program to implement the steps involved in the foregoing embodiments.

[0130] It should be noted that the first memory 1001 is configured to store instructions and applications executable by the first processor 101, and can also buffer data (for example, image data, audio data, voice communication data and video communication data) to be processed or having been processed in the first processor 101 and each module of the electronic device 100, which can be implemented by a flash memory (FLASH) or a random access memory (Random Access Memory, RAM). The second memory 1002 is configured to store instructions and applications executable by the second processor 102, and can also buffer data (for example, image data, audio data, voice communication data and video communication data) to be processed or having been processed in the second processor 102 and each module of the electronic device 100, which can be implemented by a flash memory (FLASH) or a random access memory (Random Access Memory, RAM).

[0131] The embodiment of the present application provides a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the steps in the method provided in the above embodiment.

[0132] The embodiment of the present application provides a computer program product containing instructions which, when run on a computer, cause the computer to perform the steps in the method provided in the above method embodiment.

[0133] It should be noted that the description of the above storage medium and device embodiments is similar to the description of the above method embodiments, and has similar beneficial effects to the method embodiments. For technical details not disclosed in the storage medium, storage medium and device embodiments of the present application, please refer to the description of the method embodiments of the present application.

[0134] It should be understood that the "one embodiment" or "an embodiment" or "some embodiments" mentioned throughout the specification means that the specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" or "in some embodiments" appearing throughout the specification does not necessarily mean the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present application, the size of the sequence number of the above processes does not mean the execution order, and the execution order of the processes should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. The sequence number of the above embodiments of the present application is only for description, not representing the advantages and disadvantages of the embodiments. The above description of each embodiment tends to emphasize the differences between each embodiment, and the same or similar parts can be referred to each other. For the sake of brevity, this paper will not repeat here.

[0135] The term "and / or" in this paper is only a description of the association relationship of the associated objects, which means that there can be three kinds of relationships, for example, object A and / or object B, which can represent three cases of the existence of object A, the existence of object A and object B, and the existence of object B.

[0136] It should be noted that in this paper, the term "include", "contain" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or includes elements inherent to such process, method, article or device. Without more limitations, the element defined by the sentence "including a" does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0137] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other manners. The above described embodiments are merely exemplary, and for example, the division of the modules is merely logical function division, and there can be another division manner in actual implementation, for example, a plurality of modules or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the various components shown or discussed can be indirect coupling or communication connection through some interfaces, devices or modules, and can be electrical, mechanical or other forms.

[0138] The modules described above as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules; they can be located in one place or distributed on multiple network units; and some or all of the modules can be selected according to actual needs to achieve the purpose of the embodiments.

[0139] In addition, each functional module in each embodiment of the present application can be integrated into one processing unit, or each module can be a separate unit, or two or more modules can be integrated into one unit; the integrated module can be realized in the form of hardware or in the form of hardware plus software functional unit.

[0140] Those skilled in the art can understand that all or part of the steps of the above-mentioned method embodiments can be completed by program instruction related hardware, and the above-mentioned program can be stored in a computer readable storage medium, and the program executes the steps including the above-mentioned method embodiments when executed; and the above-mentioned storage medium includes mobile storage device, read only memory (ROM), magnetic disc or optical disc and various storage program codes. Or, when the above-mentioned integrated unit is realized in the form of software functional module and sold or used as an independent product, it can also be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present application can be embodied in the form of software products, and the computer software products are stored in a storage medium, including a plurality of instructions for making an electronic device execute all or part of the methods described in the embodiments of the present application. And the above-mentioned storage medium includes mobile storage device, ROM, magnetic disc or optical disc and various storage program codes.

[0141] The methods disclosed in the several method embodiments of the present application can be combined arbitrarily without conflict to obtain new method embodiments. The features disclosed in the several product embodiments of the present application can be combined arbitrarily without conflict to obtain new product embodiments. The features disclosed in the several method or device embodiments of the present application can be combined arbitrarily without conflict to obtain new method embodiments or device embodiments.

[0142] The above merely illustrates the embodiments of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An image transmission method characterized by, The method is applied to a first processor, and the method comprises: determining a segmentation level according to a scene parameter of the image to be blurred and / or a performance parameter of a second processor; wherein the scene parameter is used to represent the complexity of the content of the image to be blurred, and the performance parameter is used to represent the processing capability of the second processor; segmenting the image to be blurred according to the segmentation level; determining depth information of the segmented image region; transmitting the segmented image region and the corresponding depth information to the second processor in sequence; wherein the second processor performs blurring processing on a target image region according to the depth information in response to receiving at least one image region and the corresponding depth information, and the at least one image region constitutes a partial region of the image to be blurred.

2. The method of claim 1, wherein in response to segmenting the at least one image region, the at least one image region and the corresponding depth information are transmitted to the second processor.

3. The method of claim 1 or 2, wherein the at least one image region and the corresponding depth information are packaged into a data packet; the data packet is transmitted to the second processor.

4. The method of claim 1, wherein, The method further comprises: determining the scene parameter of the image to be blurred according to the depth information of the image to be blurred and / or a content recognition result of the image to be blurred.

5. The method of claim 1, wherein a depth threshold value used for segmentation is determined according to the segmentation level and the depth information of the image to be blurred; the depth information of the image to be blurred is segmented according to the depth threshold value to obtain an image range parameter corresponding to the segmented depth information; the corresponding image region is segmented from the image to be blurred according to the image range parameter.

6. The method of claim 4, wherein, The depth information of the image to be blurred is one of the depth information of a previous adjacent frame, the depth information of a previous non-adjacent frame, and the depth information of a current frame; and the depth information of the image region is obtained based on the corresponding part of the image region in the depth information of the image to be blurred.

7. The method of claim 6, wherein, The method further comprises: determining a motion parameter representing the degree of scene change; in response to the motion parameter satisfying a first condition, the depth information of the previous adjacent frame or the previous non-adjacent frame is used as the depth information of the image to be blurred.

8. The method of claim 1 or 2, wherein the transmission time of a first image region and the corresponding depth information to the second processor is earlier than the transmission time of a second image region and the corresponding depth information; wherein the first image region includes an image region with an absolute value of depth difference from a focal plane of the image to be blurred less than or equal to a difference threshold value and / or includes an image region of the focal plane, and the second image region refers to an image region with an absolute value of depth difference from the focal plane greater than the difference threshold value; or the image regions and the corresponding depth information are sequentially transmitted to the second processor in order of absolute value of depth difference from the focal plane from small to large.

9. The method of claim 3, wherein packaging the at least one image region, depth information of the at least one image region, and frame identification and region identification of the at least one image region into a data packet; wherein the second processor splices the corresponding blurred image region according to the frame identification and the region identification.

10. An image blurring processing method characterized by comprising: The method is applied to a second processor, and the method comprises: in response to at least one image region and corresponding depth information transmitted by a first processor, performing blurring processing on a target image region according to the depth information, to obtain a blurred image region; wherein the at least one image region is obtained by segmenting a to-be-blurred image by the first processor, and the at least one image region constitutes part of the to-be-blurred image; the first processor segments the to-be-blurred image, comprising: determining a segmentation level according to scene parameters of the to-be-blurred image and / or performance parameters of the second processor; wherein the scene parameters are used to represent complexity of content of the to-be-blurred image, and the performance parameters are used to represent processing capability of the second processor; segmenting the to-be-blurred image according to the segmentation level.

11. The method of claim 10, wherein, The method further comprises: splicing the at least two blurred image regions.

12. The method of claim 11, wherein, The method further comprises: receiving a data packet transmitted by the first processor; parsing the data packet to obtain the at least one image region and corresponding depth information.

13. The method of claim 12, wherein, The method further comprises: parsing the data packet to further obtain frame identification and region identification of the at least one image region; Correspondingly, the splicing of the at least two blurred image regions comprises: splicing the at least two blurred image regions according to frame identification and region identification of the at least two blurred image regions.

14. An image blurring processing method characterized by comprising: The method comprises: a first processor determines a segmentation level according to scene parameters of a to-be-blurred image and / or performance parameters of a second processor, and segments the to-be-blurred image according to the segmentation level; wherein the scene parameters are used to represent complexity of content of the to-be-blurred image, and the performance parameters are used to represent processing capability of the second processor; the first processor determines depth information of the segmented image region; the first processor transmits the segmented image region and corresponding depth information to the second processor in sequence; the second processor performs blurring processing on a target image region according to the depth information in response to receiving at least one image region and corresponding depth information; wherein the at least one image region constitutes part of the to-be-blurred image.

15. An image transmission apparatus characterized by comprising: The device comprises: a segmentation module configured to determine a segmentation level according to scene parameters of a to-be-blurred image and / or performance parameters of an image blurring processing device, and to segment the to-be-blurred image according to the segmentation level; wherein the scene parameters are used to represent complexity of content of the to-be-blurred image, and the performance parameters are used to represent processing capability of the image blurring processing device; a determination module configured to determine depth information of the segmented image region; The transmission module is configured to transmit the segmented image region and the corresponding depth information to the image blurring processing device in sequence; wherein the image blurring processing device performs blurring processing on the target image region according to the depth information in response to receiving at least one image region and the corresponding depth information; wherein the at least one image region constitutes a partial region of the image to be blurred.

16. An image blurring processing apparatus characterized by comprising: The device comprises: The blurring processing module is configured to perform blurring processing on the target image region according to the depth information in response to at least one image region and the corresponding depth information transmitted by the image transmission device, to obtain a blurred image region; wherein the at least one image region is obtained by segmenting the image to be blurred by the image transmission device, and the at least one image region constitutes a partial region of the image to be blurred. The image transmission device segments the image to be blurred, comprising: According to the scene parameters of the image to be blurred and / or the performance parameters of the image blurring processing device, determine the segmentation level; wherein the scene parameters are used to represent the complexity of the content of the image to be blurred, and the performance parameters are used to represent the processing capability of the image blurring processing device; According to the segmentation level, segment the image to be blurred.

17. An electronic device, comprising: The image transmission device of claim 15 and the image blurring processing device of claim 16 are included.

18. An electronic device comprising a first memory, a first processor, a second memory, and a second processor, the first memory storing a computer program executable on the first processor, the second memory storing a computer program executable on the second processor, wherein, The first processor executes the program to implement the method of any one of claims 1 to 9, and the second processor executes the program to implement the method of any one of claims 10 to 13.

19. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the method of any one of claims 1 to 9, or the computer program is executed by the processor to implement the method of any one of claims 10 to 13.

Images