Image storage method, image reconstruction method, image reconstruction device, image reconstruction equipment, image reconstruction system and steaming and baking equipment
By determining the reference frame and target area in image processing, only the data of the intercepted area is stored, the problem of large space occupancy of image compression data in the prior art is solved, and more efficient storage and transmission are achieved.
Patent Information
- Application Number
- CN202410971726.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-19
- Publication Date
- 2024-11-22
AI Technical Summary
The compressed data obtained by the existing image compression method still takes up a relatively large space, which is not conducive to storage and network transmission, especially in scenarios such as steam ovens and other scenarios to store and transfer continuously images during long-term cooking.
By determining one frame from the multi-frame picture to be stored as a reference frame, determining the target object and the target area based on the reference frame, selecting the intercept area, and only the target image data in the intercept area is stored, and combining the reference frame and the target image data for storage , the pictures are supplemented according to the non-intercepted area and target image data during reconstruction.
It greatly reduces the stored image size, improves storage and network transmission efficiency, and ensures the consistency and integrity of image effects.
Smart Images

Figure CN119011846A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of image processing, and in particular to an image storage method, a reconstruction method, a device, a equipment and a system, and a steaming and baking device. Background Art
[0002] Taking a steam oven as an example, in order to more conveniently understand the condition of the food in the steam oven, a camera is usually set up to obtain continuous images of the food in the steam oven, such as videos or multi-frame pictures. However, when the cooking time of the food in the steam oven is long, the continuous images are large, which will cause a large space to be occupied when stored, and the transmission time is long.
[0003] Therefore, in order to solve the above problems, the existing technology compresses continuous images to reduce the size of the data, thereby reducing the space occupied during storage and reducing the time required for transmission.
[0004] However, the current common compression method for continuous images is to extract key frames of continuous images and then splice the key frames together to achieve video compression. However, the compressed data obtained by this scheme still occupies a relatively large space, which is not conducive to storage and network transmission. Summary of the invention
[0005] The present invention provides an image storage method, a reconstruction method, a device, a equipment and a system as well as a steaming and baking device, which are used to solve the problem that the compressed data obtained by the existing image compression method still occupies a relatively large space and is not conducive to storage and network transmission.
[0006] In a first aspect, an embodiment of the present application provides an image storage method, wherein the image is a plurality of frames of pictures to be stored, the image shooting area of each frame of the picture is the same and includes a target object in a target area of the image shooting area, and the image storage method comprises:
[0007] Determine a frame of picture in the image as a reference frame;
[0008] Determine the position information of the target object and the target area based on the reference frame;
[0009] determining a clipping area based on the position information of the target area, wherein the clipping area includes the target area;
[0010] The target image data in the cut-out area of the remaining frames is obtained, and the reference frame and the target image data are stored, wherein the remaining frames are all pictures in the image except the reference frame.
[0011] In one embodiment, determining the position information of the target object and the target area based on the reference frame includes:
[0012] Using an image recognition algorithm to identify the target object in the reference frame;
[0013] The area where the target object is located is taken as the target area, or the minimum preset graphic where the target object is located is taken as the target area, and the minimum preset graphic includes a rectangle or a circle.
[0014] In one embodiment, determining the interception area based on the position information of the target area includes:
[0015] An area that is n times larger than the target area is used as a cut-off area, where n is greater than or equal to 1.
[0016] In one embodiment, the method further includes: obtaining the type of the target object, obtaining an expansion coefficient m of the target object based on the type of the target object, and determining n based on the expansion coefficient m, where m is less than or equal to n.
[0017] In one embodiment, determining the interception area based on the position information of the target area includes:
[0018] Dividing the image capturing area into a plurality of sub-areas;
[0019] All sub-regions containing the target region are taken as the clipped regions.
[0020] In one embodiment, dividing the image capturing area into a plurality of sub-areas includes:
[0021] Acquiring the resolution of the reference frame;
[0022] The number of pixels in the sub-region is determined based on the resolution, and the size of each sub-region is the same.
[0023] In a second aspect, an embodiment of the present application provides an image reconstruction method, comprising:
[0024] Acquire data stored in the image storage method according to any one of the implementations of the first aspect, wherein the data includes a reference frame and target image data;
[0025] Acquire a non-cut region based on a reference frame, wherein the non-cut region is a region of the reference frame other than the cut region;
[0026] The target image data is supplemented into the non-cropped area to obtain a reconstructed picture.
[0027] In a third aspect, an embodiment of the present application provides an image storage device, wherein the image is a plurality of frames of pictures to be stored, the image shooting area of each frame of the picture is the same and includes a target object in a target area of the image shooting area, and the image storage device includes:
[0028] A reference frame acquisition module, used to determine a frame of picture in the image as a reference frame;
[0029] A target area determination module, used to determine the position information of the target object and the target area based on the reference frame;
[0030] A clipping area selection module, configured to determine a clipping area based on the position information of the target area, wherein the clipping area includes the target area;
[0031] The image data storage module is used to obtain the target image data in the cut-out area of the remaining frames, and store the reference frame and the target image data. The remaining frames are all pictures in the image except the reference frame.
[0032] In a fourth aspect, an embodiment of the present application provides an image reconstruction device, comprising:
[0033] A data acquisition module, used to acquire data stored in the image storage method according to any one of the implementations of the first aspect, wherein the data includes a reference frame and target image data;
[0034] A non-intercepted area acquisition module, used to acquire a non-intercepted area based on a reference frame, wherein the non-intercepted area is an area of the reference frame other than the intercepted area;
[0035] The image reconstruction module is used to supplement the target image data into the non-cropped area to obtain a reconstructed image.
[0036] In a fifth aspect, an embodiment of the present application provides an image storage device, including:
[0037] The image storage device includes a memory and a processor, the memory stores a program code that can be run on the processor, and when the program code is executed by the processor, the image storage method as described in any one of the embodiments of the first aspect is implemented.
[0038] In a sixth aspect, an embodiment of the present application provides an image reconstruction device, including:
[0039] The image reconstruction device includes a memory and a processor, the memory stores a program code that can be run on the processor, and when the program code is executed by the processor, the image reconstruction method as described in any embodiment of the second aspect is implemented.
[0040] In a seventh aspect, an embodiment of the present application provides an image processing system, including:
[0041] An image storage device as described in any one of the embodiments of the fifth aspect;
[0042] And an image reconstruction device as described in any embodiment of the sixth aspect.
[0043] In an eighth aspect, an embodiment of the present application provides a steaming and baking device, applying the image storage method described in any one of the embodiments of the first aspect, and / or, applying the image reconstruction method described in any one of the embodiments of the second aspect.
[0044] The image storage method, reconstruction method, device, equipment, system and steaming and baking equipment provided by the technical solution of the present application have at least the following beneficial effects compared with the prior art:
[0045] First, a frame is determined from the image to be stored as a reference frame, and then the target object and target area are determined based on the reference frame; the interception area is selected based on the target area, and then the target image data in the interception area of the remaining frames is obtained, and finally the reference frame and the target image data are stored. Since the image shooting area of each frame in the image is the same, and the target objects are all in the target area, when storing the image, only one complete frame is stored, and the remaining frames only store the image data of the interception area for storage. Compared with storing each frame, the storage amount is greatly reduced. When reconstructing, the image can be restored only by combining the data of the non-intercepted area of the reference frame with the target image data. While ensuring the image effect, the size of the image to be stored is reduced, which is conducive to storage and network transmission.
[0046] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0047] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0048] Figure 1 is a flow chart of an image storage method in an embodiment of the present invention;
[0049] Figure 2 is a specific flow chart of an image storage method in an embodiment of the present invention;
[0050] Figure 3 is a schematic diagram of dividing an image into sub-regions in an embodiment of the present invention;
[0051] Figure 4 is a flow chart of an image reconstruction method in an embodiment of the present invention;
[0052] Figure 5 is a schematic diagram of the structure of an image storage device in an embodiment of the present invention;
[0053] Figure 6 is a schematic structural diagram of an image reconstruction device in an embodiment of the present invention;
[0054] Figure 7 is a schematic diagram of the structure of an image storage device in an embodiment of the present invention;
[0055] Figure 8 is a schematic diagram of the structure of an image reconstruction device in an embodiment of the present invention;
[0056] Fig. 9 It is a schematic diagram of the structure of an image processing system in an embodiment of the present invention. DETAILED DESCRIPTION
[0057] In order to make the purpose, technical scheme and advantages of the present application clearer, the technical scheme of the present application is described in detail below in conjunction with the accompanying drawings and embodiments. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other implementation methods obtained by ordinary technicians in the field without making creative work belong to the scope of protection of the present application.
[0058] In the prior art, for compressed videos, specific video frames are extracted and then all the video frames are stored. Although the size of the video is indeed reduced compared to the uncompressed state, the compressed data is still relatively large.
[0059] For videos or multiple frames of pictures recorded in scenes such as steam ovens, the image acquisition device, such as the camera, is fixed in position, and the scene position is fixed, that is, the image capture area is the same. Moreover, since it only focuses on the changes of the steaming and baking object (i.e., the target object), it does not care about the changes in other areas. Therefore, based on this, the embodiment of the present application proposes an image storage method to further reduce the size of the compressed image on the basis of image compression.
[0060] like Figure 1 As shown, the embodiment of the present application provides an image storage method, wherein the image is a plurality of frames of pictures to be stored, the image may be a video, or a plurality of frames of pictures acquired at a preset interval, the image capture area of each frame of the picture is the same and includes a target object in the target area of the image capture area, the image capture area is the same, that is, the position and shooting angle of the image acquisition device remain unchanged. The target object will not move, but may undergo certain deformation, such as expansion or contraction, and the image storage method includes:
[0061] S110: Determine a frame of picture in the image as a reference frame; optionally, use the first frame of picture as the reference frame. Alternatively, select a frame from multiple frames of the image as the reference frame according to actual needs.
[0062] S120: Determine the position information of the target object and the target area based on the reference frame; preferably, use an image recognition algorithm to identify the target object in the reference frame. Exemplarily, the reference frame is arbitrarily divided into multiple areas, and the similarity between each area and a preset target object image is calculated, and the area with the highest similarity and greater than a threshold is used as the target object. Alternatively, a standard image without the target object is stored, and then the reference frame is subtracted from the standard image, and then the area where the pixels are not 0 after the subtraction is used as the target object. Because the pixels in the background area do not change after the target object is placed and before it is placed, the pixels in the background area become 0 after the subtraction, and the pixels in the area where the target object is placed are different from those before it is placed, and the pixels are not 0 after the subtraction.
[0063] In one embodiment, the area where the target object is located is directly used as the target area, and there is no need to re-determine the target area, but it is not convenient for subsequent calculations.
[0064] Therefore, in another embodiment, the minimum preset graphic where the target object is located is used as the target area, and the minimum preset graphic includes a rectangle or a circle. The minimum preset graphic refers to an area that can not only include the target area and the graphic is in a preset form, but also has the smallest graphic area. The minimum area is to reduce the size of the data stored subsequently as much as possible.
[0065] S130: Determine a clipping area based on the position information of the target area, where the clipping area includes the target area.
[0066] Since the target object may be deformed during the process of the image acquisition device acquiring the image, when selecting the cutout area, the entire target area may be included compared to the target area.
[0067] As an optional implementation of the present application, determining the interception area based on the position information of the target area includes: taking an area that is n times larger than the target area as the interception area, where n is greater than or equal to 1. It should be noted that when n is equal to 1, it is a special case, that is, the target object will not be deformed, or even if the target object is deformed, it will shrink instead of expand.
[0068] In one embodiment, n is a fixed value, that is, the same n is used regardless of the target object. This method is simple to control, but may cause the image of some target objects to occupy a relatively large storage space after processing.
[0069] Therefore, in another embodiment, n is adjusted according to the type of the target object. Specifically, the type of the target object is obtained, the expansion coefficient m of the target object is obtained based on the type of the target object, and n is determined based on the expansion coefficient m, where m is less than or equal to n.
[0070] The type of the target object can be identified according to a pre-trained image recognition model. After the target object is identified in the reference frame, the target object is input into the image recognition model to obtain the type of the target object, and then the expansion coefficient m of the target object is obtained based on the pre-stored correspondence between the type of the target object and the expansion coefficient. When m is greater than 1, it indicates that the target object will be deformed and the outline will become larger (or the viewing area based on the viewing angle of the image acquisition device will become larger); when m is equal to 1, it indicates that the target object will not be deformed, or even if it is deformed, its outline will not change (or the viewing area based on the viewing angle of the image acquisition device will remain unchanged); when m is less than 1, it indicates that the target object will be deformed and its outline will become smaller (or the viewing area based on the viewing angle of the image acquisition device will become smaller).
[0071] Exemplarily, n is determined based on the expansion coefficient m, when m is less than or equal to 1, n is 1, and when m is greater than 1, n is m. Of course, in order to ensure the error tolerance, n can be appropriately set to be slightly larger on this basis to ensure that the target object is still within the interception area after deformation.
[0072] In actual use, if a frame of picture is randomly selected as a reference frame, there is a possibility that the picture with the largest outline of the target object is selected as the reference frame, and the selected interception area will be too large. Therefore, in order to ensure that the interception area can include the target object and the interception area is minimized, in a preferred embodiment, the first frame is selected as the reference frame, at which time the target object is generally not deformed. The expansion coefficient can be used to better select a suitable interception area.
[0073] As another optional implementation of the embodiment of the present application, determining the interception area based on the position information of the target area includes:
[0074] The image shooting area is divided into a plurality of sub-areas, that is, the entire picture of the reference frame is divided into a plurality of sub-areas in advance, and then each sub-area where the target area is located is found.
[0075] All sub-regions containing the target region are taken as the intercepted region. The intercepted region selected in this way only needs to be divided into sub-regions in advance. Since all sub-regions where the target region is located cannot all be the target region, some sub-regions must be stored as the target region, so the intercepted region obtained at this time will be larger than the target region.
[0076] In one embodiment, dividing the image capturing area into a plurality of sub-areas includes determining a number a of sub-areas according to actual needs, and dividing the image capturing area equally into a sub-areas regardless of the type of image.
[0077] In another embodiment, the image capture area is divided into a plurality of sub-areas, including: obtaining a resolution of the reference frame; determining the number of pixels in the sub-areas based on the resolution, and each sub-area has the same size. The pixels in the sub-areas divided in this way are complete.
[0078] Regardless of the method used to divide the sub-regions, although the obtained intercepted area may be larger, the reconstruction efficiency will be reduced if the sub-regions are not divided during the subsequent reconstruction due to the change in the position of the target image data. After dividing the sub-regions, the sub-regions can be reconstructed in parallel, which greatly improves the reconstruction efficiency.
[0079] S140: Obtain target image data in the intercepted area of the remaining frames, store the reference frame and the target image data, and the remaining frames are all pictures in the image except the reference frame. That is, only the reference frame and the data in the intercepted area are stored, and the data outside the intercepted area of other frames will not be stored repeatedly, which greatly reduces the data size.
[0080] The image storage method provided by the embodiment of the present application first determines a frame from the image to be stored as a reference frame, and then determines the target object and target area based on the reference frame; selects a cutout area based on the target area, and then obtains the target image data in the cutout area of the remaining frames, and finally stores the reference frame and the target image data. Since the image shooting area of each frame in the image is the same, and the target objects are all in the target area, when storing the image, only one complete frame is stored, and the remaining frames only store the image data of the cutout area for storage, which greatly reduces the storage amount compared to storing each frame. The size of the image that needs to be stored is reduced, which is beneficial to storage and network transmission.
[0081] In order to more clearly illustrate the present application scheme, the present application embodiment also provides a specific image storage method, such as Figure 2 As shown, this method is mainly aimed at scenes such as videos of steaming ovens, which have clear targets, and the target will not move, and the position of the camera for taking pictures will not change. It is mainly divided into four steps: capturing the initial image, obtaining the position occupied by the target in the image, capturing a partial area for compressing the video, and reconstructing the complete video. The embodiment scheme of the present application aims to achieve accurate extraction and compressed storage of specific targets in video frames through precise target recognition technology. When the camera starts recording, the system will first extract a complete video frame as the initial reference, i.e., the reference frame. This step is crucial because it provides basic data for subsequent target recognition and area division.
[0082] Next, the system will use advanced image recognition algorithms to perform detailed target recognition on this reference frame to obtain the target object. During this process, the algorithm can accurately identify the target object to be photographed in the reference frame and obtain the precise position and size information of the target object in the picture. This information is crucial for subsequent area division and compression processing.
[0083] After completing the target recognition, the embodiment of the present application further divides the reference frame into multiple regions of fixed size. Taking a 1080p video as an example, its pixel points are 1920*1080, which can be divided into several regions of 160*60 as needed. This division method not only simplifies the processing process, but also helps to improve the compression efficiency.
[0084] In another embodiment, if Figure 3 As shown in the figure, the largest image is the complete video image of the reference frame. The image is divided into 4*4 rectangular areas. The small black box in the middle is the target area where the target object is located, and the video area to be intercepted is the box outside the target area. Of course, Figure 3 This is just an example, and in actual division, it is not necessarily divided into 4*4 rectangular areas, but can be divided into any number of sub-areas according to actual needs.
[0085] Subsequently, the system determines the number of sub-regions occupied by the target object in the reference frame based on the previously acquired location information of the target object. This step enables the system to accurately locate the area where the target is located, facilitating subsequent compression processing.
[0086] When compressing video, the embodiment of the present application adopts an innovative frame extraction method. It only extracts the frame information of the target area where the target object is located, and the frames of non-target areas will not be stored. This targeted extraction method greatly reduces the storage space occupied while ensuring the integrity of the target information.
[0087] It should be noted that when reconstructing the compressed video, the system will use the first complete key reference frame to fill in the non-target area. This step allows the reconstructed video to maintain visual coherence and integrity while avoiding information loss caused by compression.
[0088] The specific image storage method provided by the embodiment of the present application divides the video screen into different areas of fixed size, and divides the video into an area for shooting the target and an area for shooting the background by confirming the position and size of the target. In addition to storing the first complete picture, only the target area for shooting is stored. This storage method can greatly reduce the size of the compressed video. In general, the embodiment of the present application realizes the accurate extraction and efficient compression of specific targets in the video frame through accurate target recognition and area division technology. This method not only improves the efficiency of video processing, but also reduces the occupancy of storage space, and provides new ideas and technical support for the development of the field of video processing.
[0089] like Figure 4 As shown, the embodiment of the present application also provides an image reconstruction method, including:
[0090] S410: Acquire data stored based on the image storage method provided by the above embodiment, the data including reference frame and target image data; the image storage method provided by the above embodiment can determine a frame from the image to be stored as a reference frame, and then determine the target object and target area based on the reference frame; select a cutout area based on the target area, and then obtain the target image data in the cutout area of the remaining frames, and finally store the reference frame and the target image data. Since the image shooting area of each frame in the image is the same, and the target objects are all in the target area, when storing the image, only one complete frame is stored, and the remaining frames only store the image data of the cutout area for storage, which greatly reduces the storage amount compared to storing each frame.
[0091] S420: Acquire a non-clipped area based on a reference frame, wherein the non-clipped area is an area of the reference frame excluding the clipped area; that is, the non-clipped area can be obtained by removing the clipped area from the reference frame.
[0092] S430: Supplement the target image data to the non-cut region to obtain a reconstructed image. The non-cut region is supplemented using a reference frame. This step allows the reconstructed image to maintain visual coherence and integrity while avoiding information loss caused by compression.
[0093] The image reconstruction method provided in the embodiment of the present application first obtains the reference frame and the target image data; then obtains the non-intercepted area based on the reference frame; and finally supplements the target image data into the non-intercepted area to obtain a reconstructed image. When reconstructing the solution of the embodiment of the present application, it is only necessary to combine the data of the non-intercepted area of the reference frame with the target image data to restore the image. The reconstructed image maintains visual coherence and integrity while avoiding information loss caused by compression. While ensuring the image effect, the size of the image that needs to be stored is reduced, which is beneficial to storage and network transmission.
[0094] like Figure 5 As shown, an embodiment of the present application provides an image storage device 500, wherein the image is a plurality of frames of pictures to be stored, the image shooting area of each frame of the picture is the same and includes a target object in a target area of the image shooting area, and the image storage device 500 includes:
[0095] The reference frame acquisition module 510 is used to determine a frame in the image as a reference frame; optionally, the reference frame acquisition module 510 uses the first frame as the reference frame. Alternatively, the reference frame acquisition module 510 selects a frame from multiple frames of the image as a reference frame according to actual needs.
[0096] The target area determination module 520 is used to determine the position information of the target object and the target area based on the reference frame; preferably, the target area determination module 520 uses an image recognition algorithm to identify the target object in the reference frame. Exemplarily, the reference frame is arbitrarily divided into multiple areas, and the similarity between each area and a preset target object image is calculated, and the area with the highest similarity and greater than a threshold is used as the target object. Alternatively, a standard image without the target object is stored, and then the reference frame is subtracted from the standard image, and then the area where the pixels are not 0 after the subtraction is used as the target object. Because the pixels in the background area do not change after the target object is placed and before it is placed, the pixels in the background area become 0 after the subtraction, and the pixels in the area where the target object is placed are different from those before it is placed, and the pixels are not 0 after the subtraction.
[0097] In one embodiment, the area where the target object is located is directly used as the target area, and there is no need to re-determine the target area, but it is not convenient for subsequent calculations.
[0098] Therefore, in another embodiment, the minimum preset graphic where the target object is located is used as the target area, and the minimum preset graphic includes a rectangle or a circle. The minimum preset graphic refers to an area that can not only include the target area and the graphic is in a preset form, but also has the smallest graphic area. The minimum area is to reduce the size of the data stored subsequently as much as possible.
[0099] The clipping area selection module 530 is used to determine a clipping area based on the position information of the target area, where the clipping area includes the target area.
[0100] Since the target object may be deformed during the process of the image acquisition device acquiring the image, when selecting the cutout area, the entire target area may be included compared to the target area.
[0101] As an optional implementation of the present application, the clipping region selection module 530 uses the region obtained by expanding the target region by n times as the clipping region, where n is greater than or equal to 1. It should be noted that when n is equal to 1, it is a special case, that is, the target object will not be deformed, or even if the target object is deformed, it will shrink instead of expand.
[0102] In one embodiment, n is a fixed value, that is, the same n is used regardless of the target object. This method is simple to control, but may cause the image of some target objects to occupy a relatively large storage space after processing.
[0103] Therefore, in another embodiment, n is adjusted according to the type of the target object. Specifically, the type of the target object is obtained, the expansion coefficient m of the target object is obtained based on the type of the target object, and n is determined based on the expansion coefficient m, where m is less than or equal to n.
[0104] The type of the target object can be identified according to a pre-trained image recognition model. After the target object is identified in the reference frame, the target object is input into the image recognition model to obtain the type of the target object, and then the expansion coefficient m of the target object is obtained based on the pre-stored correspondence between the type of the target object and the expansion coefficient. When m is greater than 1, it indicates that the target object will be deformed and the outline will become larger (or the viewing area based on the viewing angle of the image acquisition device will become larger); when m is equal to 1, it indicates that the target object will not be deformed, or even if it is deformed, its outline will not change (or the viewing area based on the viewing angle of the image acquisition device will remain unchanged); when m is less than 1, it indicates that the target object will be deformed and its outline will become smaller (or the viewing area based on the viewing angle of the image acquisition device will become smaller).
[0105] Exemplarily, n is determined based on the expansion coefficient m, when m is less than or equal to 1, n is 1, and when m is greater than 1, n is m. Of course, in order to ensure the error tolerance, n can be appropriately set to be slightly larger on this basis to ensure that the target object is still within the interception area after deformation.
[0106] In actual use, if a frame of picture is randomly selected as a reference frame, there is a possibility that the picture with the largest outline of the target object is selected as the reference frame, and the selected interception area will be too large. Therefore, in order to ensure that the interception area can include the target object and the interception area is minimized, in a preferred embodiment, the first frame is selected as the reference frame, at which time the target object is generally not deformed. The expansion coefficient can be used to better select a suitable interception area.
[0107] As another optional implementation of the embodiment of the present application, the clipping area selection module 530 divides the image shooting area into multiple sub-areas, that is, divides the entire picture of the reference frame into multiple sub-areas in advance, and then finds each sub-area where the target area is located.
[0108] All sub-regions containing the target region are taken as the intercepted region. The intercepted region selected in this way only needs to be divided into sub-regions in advance. Since all sub-regions where the target region is located cannot all be the target region, some sub-regions must be stored as the target region, so the intercepted region obtained at this time will be larger than the target region.
[0109] In one embodiment, dividing the image capturing area into a plurality of sub-areas includes determining a number a of sub-areas according to actual needs, and dividing the image capturing area equally into a sub-areas regardless of the type of image.
[0110] In another embodiment, the image capture area is divided into a plurality of sub-areas, including: obtaining a resolution of the reference frame; determining the number of pixels in the sub-areas based on the resolution, and each sub-area has the same size. The pixels in the sub-areas divided in this way are complete.
[0111] Regardless of the method used to divide the sub-regions, although the obtained intercepted area may be larger, the reconstruction efficiency will be reduced if the sub-regions are not divided during the subsequent reconstruction due to the change in the position of the target image data. After dividing the sub-regions, the sub-regions can be reconstructed in parallel, which greatly improves the reconstruction efficiency.
[0112] The image data storage module 540 is used to obtain the target image data in the intercepted area of the remaining frames, and store the reference frame and the target image data. The remaining frames are all pictures in the image except the reference frame. That is, only the reference frame and the data in the intercepted area are stored, and the data outside the intercepted area of other frames will not be stored repeatedly, which greatly reduces the data size.
[0113] The image storage device provided in the embodiment of the present application first determines a frame from the image to be stored as a reference frame, then determines the target object and target area based on the reference frame; selects a clipping area based on the target area, then obtains the target image data in the clipping area of the remaining frames, and finally stores the reference frame and the target image data. Since the image shooting area of each frame in the image is the same, and the target objects are all in the target area, when storing the image, only one complete frame is stored, and the remaining frames only store the image data of the clipping area for storage, which greatly reduces the storage amount compared to storing each frame.
[0114] like Figure 6 As shown, the embodiment of the present application provides an image reconstruction device 600, including:
[0115] The data acquisition module 610 is used to acquire data stored based on the image storage method provided by the above embodiment, wherein the data includes a reference frame and target image data; the image storage method provided by the above embodiment can determine a frame from the image to be stored as a reference frame, and then determine the target object and target area based on the reference frame; select a cut-out area based on the target area, and then acquire the target image data in the cut-out area of the remaining frames, and finally store the reference frame and the target image data. Since the image shooting area of each frame in the image is the same, and the target objects are all in the target area, when storing the image, only one complete frame is stored, and the remaining frames only store the image data of the cut-out area for storage, which greatly reduces the storage amount compared to storing each frame.
[0116] The non-clipped area acquisition module 620 is used to acquire the non-clipped area based on the reference frame, wherein the non-clipped area is the area of the reference frame excluding the clipped area; that is, the non-clipped area can be obtained by removing the clipped area from the reference frame.
[0117] The image reconstruction module 630 is used to supplement the target image data into the non-cut area to obtain a reconstructed image. The non-cut area is supplemented using a reference frame. This step allows the reconstructed image to maintain visual coherence and integrity while avoiding information loss caused by compression.
[0118] The image reconstruction device provided in the embodiment of the present application first obtains the reference frame and the target image data; then obtains the non-intercepted area based on the reference frame; and finally supplements the target image data into the non-intercepted area to obtain a reconstructed image. When reconstructing according to the scheme of the embodiment of the present application, it is only necessary to combine the data of the non-intercepted area of the reference frame with the target image data to restore the image. The reconstructed image maintains visual coherence and integrity while avoiding information loss caused by compression. While ensuring the image effect, the size of the image that needs to be stored is reduced, which is beneficial to storage and network transmission.
[0119] like Figure 7 As shown, the embodiment of the present application provides an image storage device 700, including:
[0120] The image storage device 700 includes a memory 710 and a processor 720. The memory 710 stores program codes that can be run on the processor 720. When the program codes are executed by the processor 720, the image storage method provided in the above embodiment is implemented.
[0121] The image storage device provided by the embodiment of the present application stores the program code running on the processor through the memory. When the program code is executed by the processor, the processor can first determine a frame from the image to be stored as a reference frame, and then determine the target object and target area based on the reference frame; select the interception area based on the target area, and then obtain the target image data in the interception area of the remaining frames, and finally store the reference frame and the target image data. Since the image shooting area of each frame in the image is the same, and the target objects are all in the target area, when storing the image, only one complete frame is stored, and the remaining frames only store the image data of the interception area for storage, which greatly reduces the storage amount compared to storing each frame of the image.
[0122] like Figure 8 As shown, the embodiment of the present application provides an image reconstruction device 800, including:
[0123] The image reconstruction device 800 includes a memory 810 and a processor 820. The memory 810 stores program codes that can be executed on the processor 820. When the program codes are executed by the processor 820, the image reconstruction method provided in the above embodiment is implemented.
[0124] The image reconstruction device provided by the embodiment of the present application stores the program code running on the processor through the memory. When the program code is executed by the processor, the processor can first obtain the reference frame and the target image data; then obtain the non-intercepted area based on the reference frame; and finally, supplement the target image data into the non-intercepted area to obtain a reconstructed picture. When reconstructing according to the scheme of the embodiment of the present application, it is only necessary to combine the data of the non-intercepted area of the reference frame with the target image data to restore the picture. The reconstructed picture maintains visual coherence and integrity, while avoiding information loss caused by compression. While ensuring the image effect, the size of the image that needs to be stored is reduced, which is conducive to storage and network transmission.
[0125] like Fig. 9 As shown, the embodiment of the present application provides an image processing system 900, including:
[0126] The image storage device 700 provided in the above embodiment;
[0127] And the image reconstruction device 800 provided by the above embodiment.
[0128] In the image processing system provided by the embodiment of the present application, the image storage device first determines a frame from the image to be stored as a reference frame, and then determines the target object and the target area based on the reference frame; selects the interception area based on the target area, and then obtains the target image data in the interception area of the remaining frames, and finally stores the reference frame and the target image data. Since the image shooting area of each frame of the image is the same, and the target objects are all in the target area, when storing the image, only one complete frame is stored, and the remaining frames only store the image data of the interception area for storage, which greatly reduces the storage volume compared to storing each frame of the image. The image reconstruction device first obtains the reference frame and the target image data; then obtains the non-intercepted area based on the reference frame; and finally supplements the target image data to the non-intercepted area to obtain a reconstructed image. When reconstructing the scheme of the embodiment of the present application, it is only necessary to combine the data of the non-intercepted area of the reference frame with the target image data to restore the image. The reconstructed image maintains visual coherence and integrity, while avoiding information loss caused by compression. While ensuring the image effect, the size of the image to be stored is reduced, which is conducive to storage and network transmission.
[0129] The embodiment of the present application also provides a steaming and baking device, which uses the image storage method provided in the above embodiment, and / or the image reconstruction method provided in the above embodiment. The size of the video recording the steaming and baking scene of the steaming and baking device such as the steaming oven can be greatly reduced, which is conducive to storage and network transmission, and greatly reduces resource waste when recording the steaming and baking scene of the steaming and baking device.
[0130] Although the present invention has been described with reference to the preferred embodiments, various modifications may be made thereto and parts thereof may be replaced by equivalents without departing from the scope of the present invention. In particular, as long as there is no structural conflict, the various technical features mentioned in the various embodiments may be combined in any manner. The present invention is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims. It should be noted that in the description of the present application, the terms "first", "second", etc. are used only for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of the present application, unless otherwise specified, the meaning of "multiple" refers to at least two.
[0131] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.
[0132] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.
[0133] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.
[0134] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.
[0135] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.
[0136] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.
[0137] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.
Claims
1. An image storage method, characterized in that: The image is a plurality of frames of pictures to be stored, the image shooting area of each frame of the picture is the same and includes a target object in a target area of the image shooting area, and the image storage method includes: Determine a frame of picture in the image as a reference frame; Determine the position information of the target object and the target area based on the reference frame; determining a clipping area based on the position information of the target area, wherein the clipping area includes the target area; The target image data in the cut-out area of the remaining frames is obtained, and the reference frame and the target image data are stored, wherein the remaining frames are all pictures in the image except the reference frame.
2. The image storage method according to claim 1, characterized in that: The determining the position information of the target object and the target area based on the reference frame includes: Using an image recognition algorithm to identify the target object in the reference frame; The area where the target object is located is taken as the target area, or the minimum preset graphic where the target object is located is taken as the target area, and the minimum preset graphic includes a rectangle or a circle.
3. The image storage method according to claim 1, characterized in that: The determining of the interception area based on the position information of the target area includes: An area that is n times larger than the target area is used as a cut-off area, where n is greater than or equal to 1.
4. The image storage method according to claim 3, characterized in that: Also includes: The type of the target object is obtained, an expansion coefficient m of the target object is obtained based on the type of the target object, and n is determined based on the expansion coefficient m, where m is less than or equal to n.
5. The image storage method according to claim 1, characterized in that: The determining of the interception area based on the position information of the target area includes: Dividing the image capturing area into a plurality of sub-areas; All sub-regions containing the target region are taken as the clipped regions.
6. The image storage method according to claim 5, characterized in that: The step of dividing the image capturing area into a plurality of sub-areas comprises: Acquiring the resolution of the reference frame; The number of pixels in the sub-region is determined based on the resolution, and the size of each sub-region is the same.
7. An image reconstruction method, characterized in that: include: Acquire data stored based on the image storage method according to any one of claims 1 to 6, wherein the data includes a reference frame and target image data; Acquire a non-cut region based on a reference frame, wherein the non-cut region is a region of the reference frame other than the cut region; The target image data is supplemented into the non-cropped area to obtain a reconstructed picture.
8. An image storage device, characterized in that: The image is a plurality of frames of pictures to be stored, the image shooting area of each frame of the picture is the same and includes a target object in a target area of the image shooting area, and the image storage device includes: A reference frame acquisition module, used to determine a frame of picture in the image as a reference frame; A target area determination module, used to determine the position information of the target object and the target area based on the reference frame; A clipping area selection module, configured to determine a clipping area based on the position information of the target area, wherein the clipping area includes the target area; The image data storage module is used to obtain the target image data in the cut-out area of the remaining frames, and store the reference frame and the target image data. The remaining frames are all pictures in the image except the reference frame.
9. An image reconstruction device, characterized in that: include: A data acquisition module, used to acquire data stored based on the image storage method according to any one of claims 1 to 6, wherein the data includes reference frame and target image data; A non-intercepted area acquisition module, used to acquire a non-intercepted area based on a reference frame, wherein the non-intercepted area is an area of the reference frame other than the intercepted area; The image reconstruction module is used to supplement the target image data into the non-cropped area to obtain a reconstructed image.
10. An image storage device, characterized in that: include: The image storage device comprises a memory and a processor, wherein the memory stores a program code executable on the processor, and when the program code is executed by the processor, the image storage method according to any one of claims 1 to 6 is implemented.
11. An image reconstruction device, characterized in that: include: The image reconstruction device comprises a memory and a processor, wherein the memory stores a program code executable on the processor, and when the program code is executed by the processor, the image reconstruction method as claimed in claim 7 is implemented.
12. An image processing system, characterized in that: include: The image storage device as claimed in claim 10; And the image reconstruction device as claimed in claim 11.
13. A steaming and baking device, characterized in that: Apply the image storage method described in any one of claims 1 to 6, and / or apply the image reconstruction method described in claim 7.
