Method, device, apparatus and computer-readable medium for generating region of interest

Abstract

The embodiments of the present disclosure disclose a method, device, equipment and computer-readable medium for generating a region of interest. A specific implementation of the method includes: selecting a first target image and a second target image; determining the imaging time of the first target image and the second target image; performing grayscale processing to generate a first grayscale image and a second grayscale image; determining the coordinates of each pixel; determining the grayscale value of each first grayscale image pixel coordinate and the grayscale value of each second grayscale image pixel coordinate to generate a first grayscale value and a second grayscale value; performing data fusion processing to obtain a first grayscale image pixel information set and a second grayscale image pixel information set; performing instantaneous speed generation processing on each first grayscale image pixel information to generate a region of interest. This implementation realizes the generation of a region of interest for an image before inputting the image into a neural network model, thereby improving the efficiency of generating the region of interest and reducing the waste of computing resources.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular to a method, device, apparatus, and computer-readable medium for generating a region of interest. Background Art

[0002] Region of interest generation is a basic technology in the field of computer vision. At present, the method of generating region of interest is usually to use deep learning algorithm to process the image and extract feature information, and then process the extracted feature information to generate the region of interest.

[0003] However, when the above method is adopted, the following technical problems often occur:

[0004] First, extracting features from the image and calculating feature points, and then generating regions of interest based on the feature points, will take a long time, thereby reducing the efficiency of generating regions of interest;

[0005] Second, the region of interest in the image needs to be processed, and the background information in the image also needs to be processed, which results in a waste of computing resources. Summary of the invention

[0006] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0007] Some embodiments of the present disclosure propose a method, an apparatus, a device and a computer-readable medium for generating a region of interest to solve one or more of the technical problems mentioned in the above background technology section.

[0008] In a first aspect, some embodiments of the present disclosure provide a region of interest method, the method comprising: randomly selecting two adjacent target images from a pre-acquired target image sequence as a first target image and a second target image respectively; determining the imaging time of the first target image and the second target image respectively to obtain the imaging time of the first target image and the second target image; performing grayscale processing on the first target image and the second target image respectively to generate a first grayscale image and a second grayscale image; determining the coordinates of each pixel in the first grayscale image and the second grayscale image respectively to generate a first grayscale image pixel coordinate set and a second grayscale image pixel coordinate set; determining the grayscale value of the pixel corresponding to each first grayscale image pixel coordinate in the first grayscale image pixel coordinate set and the grayscale value of the pixel corresponding to each second grayscale image pixel coordinate in the second grayscale image pixel coordinate set respectively. The grayscale value of the pixel corresponding to the pixel coordinate is used to generate the first grayscale value and the second grayscale value to obtain the first grayscale value set and the second grayscale value set; the imaging time of the above-mentioned first target image, the above-mentioned first grayscale image pixel coordinate set and the above-mentioned first grayscale value set are subjected to data fusion processing to obtain the first grayscale image pixel information set; the imaging time of the above-mentioned second target image, the above-mentioned second grayscale image pixel coordinate set and the above-mentioned second grayscale value set are subjected to data fusion processing to obtain the second grayscale image pixel information set; based on the above-mentioned second grayscale image pixel information set, each first grayscale image pixel information in the above-mentioned first grayscale image pixel information set is subjected to instantaneous speed generation processing to generate an instantaneous speed to obtain an instantaneous speed field, wherein the above-mentioned instantaneous speed generation processing is performed in a digital signal processor; based on the above-mentioned instantaneous speed field, a region of interest is generated to obtain a region of interest set.

[0009] In a second aspect, some embodiments of the present disclosure provide a device for generating a region of interest, the device comprising: a selection unit, configured to randomly select two adjacent target images from a pre-acquired target image sequence as a first target image and a second target image respectively; a first determination unit, configured to respectively determine the imaging time of the first target image and the second target image to obtain the imaging time of the first target image and the second target image; a grayscale processing unit, configured to respectively perform grayscale processing on the first target image and the second target image to generate a first grayscale image and a second grayscale image; a second determination unit, configured to respectively determine the coordinates of each pixel in the first grayscale image and the second grayscale image to generate a first grayscale image pixel coordinate set and a second grayscale image pixel coordinate set; a third determination unit, configured to respectively determine the grayscale value of the pixel corresponding to each first grayscale image pixel coordinate in the first grayscale image pixel coordinate set and each second grayscale image pixel coordinate in the second grayscale image pixel coordinate set. The grayscale value of the pixel corresponding to the pixel coordinate is used to generate the first grayscale value and the second grayscale value to obtain the first grayscale value set and the second grayscale value set; the first data fusion processing unit is configured to perform data fusion processing on the imaging time of the first target image, the first grayscale image pixel coordinate set and the first grayscale value set to obtain the first grayscale image pixel information set; the second data fusion processing unit is configured to perform data fusion processing on the imaging time of the second target image, the second grayscale image pixel coordinate set and the second grayscale value set to obtain the second grayscale image pixel information set; the instantaneous speed generation processing unit is configured to perform instantaneous speed generation processing on each first grayscale image pixel information in the first grayscale image pixel information set based on the second grayscale image pixel information set to generate an instantaneous speed to obtain an instantaneous speed field, wherein the instantaneous speed generation processing is performed in a digital signal processor; the generation unit is configured to generate a region of interest based on the instantaneous speed field to obtain a region of interest set.

[0010] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner of the above-mentioned first aspect.

[0011] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner of the above-mentioned first aspect is implemented.

[0012] The above-mentioned embodiments of the present disclosure have the following beneficial effects: the region of interest obtained by the region of interest generation method of some embodiments of the present disclosure takes a short time, thereby improving the efficiency of the region of interest generation. Specifically, the reason for the long time and low efficiency of the region of interest generation is that the current region of interest generation method directly processes the target image to be processed, that is, the image will be first feature extracted and the feature points will be calculated. Then, the region of interest is generated according to the feature points. Therefore, it takes a long time. In turn, the efficiency of the region of interest generation is reduced. Based on this, the region of interest generation method of some embodiments of the present disclosure. In the process of generating the region of interest, first, two adjacent target images are randomly selected from the target image sequence as the first target image and the second target image respectively. In order to describe the motion state of the object in the target image, the current frame image and the next frame image are selected, and the motion state of the object is more easily obtained by processing the two adjacent frame images. Then, the imaging time of the first target image and the second target image is determined respectively, and the first target image and the second target image are grayed respectively. The imaging time and grayscale image of the two target images can be obtained, and the amount of calculation in the image processing process is reduced by graying the image. After that, the coordinates and grayscale values ​​of each pixel in the first grayscale image and the second grayscale image are determined respectively, and the imaging time, the grayscale image, the coordinates of each pixel and the grayscale value are fused respectively to obtain the first grayscale image pixel information set and the second grayscale image pixel information set. In this way, the information required for subsequent calculations can be obtained, and the necessary information data is provided for obtaining the instantaneous velocity field. Secondly, based on the second grayscale image pixel information set, each first grayscale image pixel information in the first grayscale image pixel information set is subjected to instantaneous velocity generation processing to obtain the instantaneous velocity field. By performing instantaneous velocity generation processing on each pixel in the image, the instantaneous velocity of each pixel can be obtained, and the instantaneous velocities of all pixels are combined into an instantaneous velocity field, and a region of interest can be generated from the obtained instantaneous velocity field. Finally, based on the instantaneous velocity field, a region of interest is generated to obtain a region of interest set. According to the instantaneous velocity field obtained, the instantaneous velocity of each pixel is compared to generate a region of interest and obtain a set of regions of interest. Optionally, the set of regions of interest is input into a preset neural network model to obtain recognition detection information. Since the region of interest is generated by the method of generating regions of interest before feature extraction of the image, and then feature extraction of the region of interest is performed, the time consumed is short, thereby improving the efficiency of generating the region of interest. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0014] Figure 1 is a schematic diagram of an application scenario of a method for generating a region of interest according to some embodiments of the present disclosure;

[0015] Figure 2 is a flow chart of some embodiments of the method for generating a region of interest according to the present disclosure;

[0016] Figure 3 is a schematic structural diagram of some embodiments of an apparatus for generating a region of interest according to the present disclosure;

[0017] Figure 4 It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0018] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0019] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.

[0020] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0021] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0022] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0023] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0024] Figure 1 It is a schematic diagram of an application scenario of the method for generating a region of interest in some embodiments of the present disclosure.

[0025] exist Figure 1 In the application scenario, first, the computing device 101 can randomly select two adjacent target images from the pre-acquired target image sequence 102 as the first target image 103 and the second target image 104. Then, the computing device 101 can respectively determine the imaging time of the first target image 103 and the second target image 104 to obtain the first target image imaging time 105 and the second target image imaging time 106. After that, the computing device 101 can respectively perform grayscale processing on the first target image and the second target image to generate a first grayscale image 107 and a second grayscale image 108. Secondly, the computing device 101 can respectively determine the coordinates of each pixel in the first grayscale image 107 and the second grayscale image 108 to generate a first grayscale image pixel coordinate set 109 and a second grayscale image pixel coordinate set 110. Then, the computing device 101 may respectively determine the grayscale value of each first grayscale image pixel coordinate in the first grayscale image pixel coordinate set 109 and the grayscale value of each second grayscale image pixel coordinate in the second grayscale image pixel coordinate set 110 to generate a first grayscale value and a second grayscale value, and obtain a first grayscale value set 111 and a second grayscale value set 112. Next, the computing device 101 may perform data fusion processing on the first target image imaging time 105, the first grayscale image pixel coordinate set 109, and the first grayscale value set 111 to obtain a first grayscale image pixel information set 113. Further, the computing device 101 may also perform data fusion processing on the second target image imaging time 106, the second grayscale image pixel coordinate set 110, and the second grayscale value set 112 to obtain a second grayscale image pixel information set 114. Subsequently, the computing device 101 may perform instantaneous speed generation processing on each first grayscale image pixel information in the first grayscale image pixel information set 113 based on the second grayscale image pixel information set 114 to generate an instantaneous speed, and obtain an instantaneous speed field 115, wherein the instantaneous speed generation processing is performed in the digital signal processor 116. Finally, the digital signal processor 116 may generate a region of interest based on the instantaneous speed field 115, and obtain a region of interest set 117. Optionally, the computing device 101 may also input the region of interest set 117 into a preset neural network model 118 to obtain recognition detection information 119, wherein the recognition detection information 119 may be any one of the following: target detection results and behavior recognition results.

[0026] It should be noted that the computing device 101 can be hardware or software. When the computing device is hardware, it can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or as a single server or a single terminal device. When the computing device is embodied as software, it can be installed in the hardware devices listed above. It can be implemented as multiple software or software modules for providing distributed services, or as a single software or software module. No specific limitation is made here.

[0027] It should be understood that Figure 1 The number of computing devices in the embodiment is only illustrative. Any number of computing devices may be provided according to implementation requirements.

[0028] Continue to refer Figure 2 , shows a process 200 of some embodiments of the method for generating a region of interest according to the present disclosure. The method for generating a region of interest comprises the following steps:

[0029] Step 201 : randomly selecting two adjacent target images from a pre-acquired target image sequence as a first target image and a second target image respectively.

[0030] In some embodiments, the execution subject of the method for generating a region of interest (eg Figure 1 The computing device 101 shown in the figure can randomly select two adjacent target images from the pre-acquired target image sequence as the first target image and the second target image respectively. The target image sequence can be an image sequence consisting of continuous frames (for example, a video). The first target image can be a frame image in the target image sequence. The second target image can be the next frame image of the first target image.

[0031] As an example, the target image sequence may be an image sequence corresponding to a video of a car driving on a road. The first target image may be an image of the first frame in the image sequence corresponding to the video of a car driving on a road. The second target image may be an image of the second frame in the image sequence corresponding to the video of a car driving on a road.

[0032] Step 202 : respectively determine the imaging time of the first target image and the second target image to obtain the imaging time of the first target image and the imaging time of the second target image.

[0033] In some embodiments, the execution subject may respectively determine the imaging time of the first target image and the second target image to obtain the imaging time of the first target image and the imaging time of the second target image. The imaging time of the first target image may be the shooting time corresponding to the first target image. The imaging time of the second target image may be the shooting time corresponding to the second target image. The execution subject may read the imaging time through video software.

[0034] Step 203 , grayscale processing is performed on the first target image and the second target image respectively to generate a first grayscale image and a second grayscale image.

[0035] In some embodiments, the execution subject may perform grayscale processing on the first target image and the second target image to generate a first grayscale image and a second grayscale image, respectively. The grayscale processing may be performed on the image by a mathematical algorithm (eg, average method).

[0036] Step 204 : determining the coordinates of each pixel in the first grayscale image and the second grayscale image respectively to generate a first grayscale image pixel coordinate set and a second grayscale image pixel coordinate set.

[0037] In some embodiments, the execution subject may respectively determine the coordinates of each pixel in the first grayscale image and the second grayscale image to generate a first grayscale image pixel coordinate set and a second grayscale image pixel coordinate set, wherein the image pixel coordinates may be coordinates in a pixel coordinate system.

[0038] As an example, the execution subject may obtain a first grayscale image pixel coordinate set and a second grayscale image pixel coordinate set by determining the coordinates of each pixel in the first grayscale image and the second grayscale image.

[0039] Step 205, respectively determine the grayscale value of the pixel corresponding to each first grayscale image pixel coordinate in the first grayscale image pixel coordinate set and the grayscale value of the pixel corresponding to each second grayscale image pixel coordinate in the second grayscale image pixel coordinate set to generate a first grayscale value and a second grayscale value, and obtain a first grayscale value set and a second grayscale value set.

[0040] In some embodiments, the execution entity may determine the grayscale value of each first grayscale image pixel coordinate in the first grayscale image pixel coordinate set and the grayscale value of each second grayscale image pixel coordinate in the second grayscale image pixel coordinate set in various ways to generate a first grayscale value and a second grayscale value, and obtain a first grayscale value set and a second grayscale value set.

[0041] As an example, the above-mentioned execution entity can determine the grayscale value of each first grayscale image pixel coordinate in the above-mentioned first grayscale image pixel coordinate set, and the grayscale value of each second grayscale image pixel coordinate in the above-mentioned second grayscale image pixel coordinate set through a mathematical algorithm (for example: weighted average method) to obtain the above-mentioned first grayscale value set and the above-mentioned second grayscale value set.

[0042] Step 206 , performing data fusion processing on the imaging time of the first target image, the first grayscale image pixel coordinate set, and the first grayscale value set to obtain a first grayscale image pixel information set.

[0043] In some embodiments, the execution subject may perform data fusion processing on the imaging time of the first target image, the first grayscale image pixel coordinate set, and the first grayscale value set to obtain the first grayscale image pixel information set. The data fusion processing may be to sequentially add the imaging time of the first target image, the first grayscale image pixel coordinate set, and the first grayscale value set to the empty set.

[0044] As an example, the first target image imaging time, the first grayscale image pixel coordinate set and the first grayscale value set are sequentially added to the empty set to obtain [first target image imaging time, first grayscale image pixel coordinate set, first grayscale value set]. Thus, the first grayscale image pixel information set is obtained.

[0045] Step 207 , performing data fusion processing on the imaging time of the second target image, the second grayscale image pixel coordinate set, and the second grayscale value set to obtain a second grayscale image pixel information set.

[0046] In some embodiments, the execution subject may perform data fusion processing on the imaging time of the second target image, the second grayscale image pixel coordinate set and the second grayscale value set to obtain the second grayscale image pixel information set. The data fusion processing may be to sequentially add the imaging time of the second target image, the second grayscale image pixel coordinate set and the second grayscale value set to the empty set.

[0047] As an example, the second target image imaging time, the second grayscale image pixel coordinate set and the second grayscale value set are sequentially added to the empty set to obtain [second target image imaging time, second grayscale image pixel coordinate set, second grayscale value set]. Thus, the second grayscale image pixel information set is obtained.

[0048] Step 208: Based on the second grayscale image pixel information set, perform instantaneous velocity generation processing on each first grayscale image pixel information in the first grayscale image pixel information set to generate an instantaneous velocity, and obtain an instantaneous velocity field.

[0049] In some embodiments, the execution entity may perform instantaneous velocity generation processing on each first grayscale image pixel information in the first grayscale image pixel information set based on the second grayscale image pixel information set to generate an instantaneous velocity and obtain an instantaneous velocity field, wherein the instantaneous velocity generation processing is performed in a digital signal processor.

[0050] As an example, the instantaneous speed generation process may be a process of determining the ratio of the distance between the pixel position at the current moment and the pixel position at the next moment to the difference between the preset time period to generate the instantaneous speed. The preset time period may be the time difference between the imaging time of the first target image and the imaging time of the second target image. For example: the position of the pixel at 1 second is (1 pixel, 2 pixels), and the position at 2 seconds is (2 pixels, 3 pixels), then the instantaneous speed of the pixel is (1 pixel / second, 1 pixel / second). The instantaneous speed field may be a set of the instantaneous speeds, for example: [(1 pixel / second, 1 pixel / second), (1 pixel / second, 2 pixels / second), (0 pixel / second, 0 pixel / second)]. The digital signal processor may be a processor for completing digital signal processing tasks (for example: DSP (Digital Signal Processor)). The execution subject may perform instantaneous speed generation processing on each first grayscale image pixel information in the first grayscale image pixel information set in the digital information processor to generate the instantaneous speed and obtain the instantaneous speed field.

[0051] In some optional implementations of some embodiments, the execution subject may perform instantaneous speed generation processing on each first grayscale image pixel information in the first grayscale image pixel information set based on the second grayscale image pixel information set to generate the instantaneous speed. The following steps may be included:

[0052] The first step is to determine the second grayscale image pixel information corresponding to the first grayscale image pixel information in the second grayscale image pixel information set.

[0053] As an example, the execution subject may take the pixel with the first grayscale value of 100 in the first grayscale image pixel information, and find the second grayscale image pixel information corresponding to the first grayscale image pixel information in the second grayscale image pixel information set. For example, the first grayscale image pixel information may be [1 second, (1 pixel, 2 pixels), 100], and the second grayscale image pixel information found in the second grayscale image pixel information set may be [2 seconds, (2 pixels, 3 pixels), 100].

[0054] The second step is to perform curve fitting on the first grayscale image pixel information based on the second grayscale image pixel information to generate a basic constraint equation.

[0055] Optionally, based on the second grayscale image pixel information, the first grayscale image pixel information is input into the following formula, and curve fitting is performed on the first grayscale image pixel information to generate a basic constraint equation:

[0056] F(x,y,t)=F(x+dx,y+dy,t+dt).

[0057] Wherein, F(x, y, t) represents the first grayscale value in the above-mentioned first grayscale image pixel information. F(x+dx, y+dy, t+dt) represents the second grayscale value in the above-mentioned second grayscale image pixel information. x represents the horizontal coordinate of the first grayscale image pixel coordinate in the above-mentioned first grayscale image pixel information. y represents the vertical coordinate of the first grayscale image pixel coordinate in the above-mentioned first grayscale image pixel information. t represents the imaging time of the above-mentioned first target image. dx represents the difference between the first grayscale image pixel coordinate and the second grayscale image pixel coordinate in the above-mentioned second grayscale image pixel information in the horizontal axis direction. dy represents the difference between the first grayscale image pixel coordinate and the second grayscale image pixel coordinate in the above-mentioned second grayscale image pixel information in the vertical axis direction. dt represents the difference between the imaging time of the above-mentioned first target image and the imaging time of the above-mentioned second target image.

[0058] Specifically, the execution subject can select a pixel and determine the pixel coordinates of the pixel at the current moment. Assuming that the pixel reaches the next moment after the moment dt, the moving distances of the pixel on the x-axis and y-axis are dx and dy respectively, and the basic constraint equation is established.

[0059] As an example, the first grayscale value may be 100. F(x, y, t) may be F(1, 2, 1). It can be obtained that F(1, 2, 1)=F(1+dx, 2+dy, 1+dt)=100.

[0060] The third step is to perform first constraint equation generation processing on the above basic constraint equation to generate the first constraint equation.

[0061] Specifically, the first constraint equation generation process may be a curve fitting process. Curve fitting is performed on the basic constraint equation to obtain the first constraint equation. The first constraint equation may be a polynomial equation.

[0062] Optionally, the first constraint equation generation process is performed on the above basic constraint equation to generate the first constraint equation. The following sub-steps may be included:

[0063] The first sub-step is to obtain the partial derivatives of the first gray value along the first preset direction, the second preset direction and the third preset direction respectively, to obtain the first partial derivative, the second partial derivative and the third partial derivative.

[0064] Specifically, the first preset direction may be along the x-axis direction. The second preset direction may be along the y-axis direction. The third preset direction may be along the t-time direction. The partial derivatives of the first gray value are calculated along the x-axis direction, the y-axis direction and the t-time direction to obtain the first partial derivative, the second partial derivative and the third partial derivative.

[0065] In the second sub-step, the first constraint equation is generated using the following formula:

[0066]

[0067] Wherein, F represents the first grayscale value. x represents the horizontal coordinate of the pixel coordinate of the first grayscale image. y represents the vertical coordinate of the pixel coordinate of the first grayscale image. t represents the imaging time of the first target image. F′ x represents the first partial derivative mentioned above. F′ y represents the second partial derivative mentioned above. F′ t represents the third partial derivative. m represents the velocity component of the instantaneous velocity corresponding to the first grayscale image pixel coordinate in the first grayscale image pixel information along the first preset direction. n represents the velocity component of the instantaneous velocity corresponding to the first grayscale image pixel coordinate in the first grayscale image pixel information along the second preset direction.

[0068] Specifically, the first partial derivative, the second partial derivative and the third partial derivative are input into the above formula to generate a first constraint equation.

[0069] As an example, the first partial derivative may be 10. The second partial derivative may be 10. The third partial derivative may be 10. Inputting the first partial derivative, the second partial derivative and the third partial derivative into the above formula, we obtain:

[0070] m 2 +n 2 +2×n×n+2×m+2×n+1=0.

[0071] The fourth step is to generate a second constraint equation based on the first grayscale image pixel information and the first constraint equation.

[0072] Specifically, the first grayscale image pixel information and the first constraint equation are analyzed. For example, the distribution of the first grayscale image pixel information is analyzed, and the parameters of the first constraint equation are analyzed. The constraint condition of the second constraint equation is determined, and the constraint condition can be that all adjacent pixels have the same instantaneous speed. For example, in a 3×3 area around the target pixel, each pixel has the same instantaneous speed.

[0073] For example, the constraint condition may be within a 3×3 region around the target pixel. The first constraint equation may be:

[0074]

[0075] The second constraint equation obtained above can be:

[0076]

[0077] The fifth step is to generate the instantaneous speed based on the second constraint equation.

[0078] Specifically, the second constraint equation may be:

[0079]

[0080] Evaluating the matrix, we get the instantaneous speed (0 pixels / second, -2 pixels / second). That is, the instantaneous speed of the pixel in the x-axis direction is 0 pixels / second, and the instantaneous speed in the y-axis direction is -2 pixels / second.

[0081] Step 209: Generate a region of interest based on the instantaneous velocity field to obtain a set of regions of interest.

[0082] In some optional implementations of some embodiments, the execution subject may generate a region of interest based on the instantaneous velocity field to obtain a set of regions of interest. The following steps may be included:

[0083] The first step is to perform threshold segmentation on the instantaneous velocity field to obtain a set of segmented regions. The threshold segmentation can be a region-based image segmentation technique (eg, maximum inter-class variance method).

[0084] As an example, since the instantaneous speed of the moving object is different from the instantaneous speed of the background image, the instantaneous speed of the entire image can be divided into two parts. For example: the instantaneous speed corresponding to the pixels included in the object during the movement can be [(1 pixel / second, 1 pixel / second), (1 pixel / second, 2 pixels / second)]. The instantaneous speed corresponding to the pixels included in the background image during the movement can be [(0 pixel / second, 0 pixel / second), (0 pixel / second, 0 pixel / second)]. The segmented area can be obtained. The above-mentioned background image can be the remaining image of the target image except the image of the moving object.

[0085] The second step is to perform a smoothing process on each segmented region in the segmented region set to generate a smoothed region, thereby obtaining a smoothed region set. The smoothing process may be an interpolation process for adding pixels to the image.

[0086] As an example, there may be some independent pixels or edge regions in the above segmented region set, which affect the generation of the region of interest. A morphological algorithm (e.g., opening operation) can be used to remove edge regions whose instantaneous velocity values ​​do not match the objects in the image, while retaining the edge regions that match. Then, a morphological algorithm (e.g., closing operation) is used again to fill the edge regions.

[0087] In the third step, a region of interest generation process is performed on each smooth region in the above smooth region set to generate a region of interest, thereby obtaining a region of interest set.

[0088] As an example, the above-mentioned smooth region can be a region that can be connected as a whole. Using the region connectivity merging and segmentation technology (eg, quadtree decomposition method), the region of interest is generated to obtain a set of regions of interest.

[0089] The formula in step 208 and its related contents are an inventive point of an embodiment of the present disclosure, which solves the second technical problem mentioned in the background technology, "it is necessary to process the region of interest in the image, and it is also necessary to process the background information in the image, which leads to a waste of computing resources". The factors that cause the waste of computing resources are often as follows: not only the region of interest in the image needs to be processed, but also the background information in the image needs to be processed. If the region of interest in the image is small, but the background area is large, directly processing the image will cause a waste of computing resources. If the above factors are solved, the waste of computing resources will be reduced. In order to achieve this effect, the above formula introduces information related to the generation of the region of interest: the instantaneous velocity field. Since the generation of the instantaneous velocity field requires different equations, the above formula introduces the basic constraint equation, the first constraint equation and the second constraint equation. In order to obtain the instantaneous velocity field, a set of regions of interest is obtained. First, the formula is obtained through the basic constraint equation, and the above first grayscale image pixel information is curve fitted to generate the basic constraint equation. Then, the partial derivatives of the first gray value along the first preset direction, the second preset direction and the third preset direction are obtained respectively to obtain the first partial derivative, the second partial derivative and the third partial derivative. After that, the basic constraint equation is expanded according to the Taylor formula and converted into a matrix to obtain the first constraint equation. The first constraint equation limits the evaluation range of the instantaneous velocity. Next, the pixel information of the first gray image and the first constraint equation are analyzed. The constraint conditions for solving the second constraint equation are determined to obtain the second constraint equation. The second constraint equation obtained according to the pixel information of the first gray image further limits the evaluation range of the instantaneous velocity. Secondly, the second constraint equation is solved to obtain the instantaneous velocity, multiple instantaneous velocities are combined into an instantaneous velocity field, and the instantaneous velocity field is threshold segmented to obtain a segmentation area set. Using the difference in instantaneous velocity between the moving object and the stationary object in the instantaneous velocity field, the moving object and the stationary object in the above image are segmented to obtain a segmentation area set. And each segmentation area in the above segmentation area set is smoothed to generate a smooth area to obtain a smooth area set. Each segmented region in the above segmented region set may have independent pixels or edge regions. Each segmented region is smoothed using a smoothing algorithm to obtain a smoothed region set. Finally, each smoothed region in the above smoothed region set is subjected to a region of interest generation process to generate a region of interest, thereby obtaining a region of interest set. This solves the problem of not only processing the region of interest in the image, but also processing the background information in the image, thereby reducing the waste of computing resources.

[0090] Optionally, the execution subject may input the set of regions of interest into a preset neural network model to obtain recognition detection information, wherein the recognition detection information may include any one of the following: target detection results, behavior recognition results, and target analysis results.

[0091] As an example, the preset neural network model may be a convolutional neural network model (eg, a CNN (Convolutional Neural Networks) model). The above-mentioned recognition detection information may include, but is not limited to, any of the following: target detection results, behavior recognition results, and target analysis results.

[0092] The above-mentioned embodiments of the present disclosure have the following beneficial effects: the region of interest obtained by the region of interest generation method of some embodiments of the present disclosure takes a short time, thereby improving the efficiency of the region of interest generation. Specifically, the reason for the long time and low efficiency of the region of interest generation is that the current region of interest generation method directly processes the target image to be processed, that is, the image will be first feature extracted and the feature points will be calculated. Then, the region of interest is generated according to the feature points. Therefore, it takes a long time. In turn, the efficiency of the region of interest generation is reduced. Based on this, the region of interest generation method of some embodiments of the present disclosure. In the process of generating the region of interest, first, two adjacent target images are randomly selected from the target image sequence as the first target image and the second target image respectively. In order to describe the motion state of the object in the target image, the current frame image and the next frame image are selected, and the motion state of the object is more easily obtained by processing the two adjacent frame images. Then, the imaging time of the first target image and the second target image is determined respectively, and the first target image and the second target image are grayed respectively. The imaging time and grayscale image of the two target images can be obtained, and the amount of calculation in the image processing process is reduced by graying the image. After that, the coordinates and grayscale values ​​of each pixel in the first grayscale image and the second grayscale image are determined respectively, and the imaging time, the grayscale image, the coordinates of each pixel and the grayscale value are fused respectively to obtain the first grayscale image pixel information set and the second grayscale image pixel information set. In this way, the information required for subsequent calculations can be obtained, and the necessary information data is provided for obtaining the instantaneous velocity field. Secondly, based on the second grayscale image pixel information set, each first grayscale image pixel information in the first grayscale image pixel information set is subjected to instantaneous velocity generation processing to obtain the instantaneous velocity field. By performing instantaneous velocity generation processing on each pixel in the image, the instantaneous velocity of each pixel can be obtained, and the instantaneous velocities of all pixels are combined into an instantaneous velocity field, and a region of interest can be generated from the obtained instantaneous velocity field. Finally, based on the instantaneous velocity field, a region of interest is generated to obtain a region of interest set. According to the instantaneous velocity field obtained, the instantaneous velocity of each pixel is compared to generate a region of interest and obtain a set of regions of interest. Optionally, the set of regions of interest is input into a preset neural network model to obtain recognition detection information. Since the region of interest is generated by the method of generating regions of interest before feature extraction of the image, and then feature extraction of the region of interest is performed, the time consumed is short, thereby improving the efficiency of generating the region of interest.

[0093] Further references Figure 3 As an implementation of the above methods in the above figures, the present disclosure provides some embodiments of an apparatus for generating a region of interest, and these apparatus embodiments are similar to Figure 2 Corresponding to the above method embodiments, the device can be specifically applied to various electronic devices.

[0094] like Figure 3 As shown, the region of interest generating device 300 of some embodiments includes: a selection unit 301, a first determination unit 302, a grayscale processing unit 303, a second determination unit 304, a third determination unit 305, a first data fusion processing unit 306, a second data fusion processing unit 307, an instantaneous speed generation processing unit 308 and a generation unit 309. Among them, the selection unit 301 is configured to randomly select two adjacent target images from a pre-acquired target image sequence as the first target image and the second target image respectively; the first determination unit 302 is configured to respectively determine the imaging time of the first target image and the second target image to obtain the first target image imaging time and the second target image imaging time; the grayscale processing unit 303 is configured to respectively perform grayscale processing on the first target image and the second target image to generate a first grayscale image and a second grayscale image; the second determination unit 304 is configured to respectively determine the coordinates of each pixel in the first grayscale image and the second grayscale image to generate a first grayscale image pixel coordinate set and a second grayscale image pixel coordinate set; the third determination unit 305 is configured to respectively determine the grayscale value of the pixel corresponding to each first grayscale image pixel coordinate in the first grayscale image pixel coordinate set and the grayscale value of the pixel corresponding to each second grayscale image pixel coordinate in the second grayscale image pixel coordinate set to obtain a first grayscale image pixel coordinate set and a second grayscale image pixel coordinate set. Generate a first grayscale value and a second grayscale value to obtain a first grayscale value set and a second grayscale value set; a first data fusion processing unit 306 is configured to perform data fusion processing on the imaging time of the first target image, the first grayscale image pixel coordinate set and the first grayscale value set to obtain a first grayscale image pixel information set; a second data fusion processing unit 307 is configured to perform data fusion processing on the imaging time of the second target image, the second grayscale image pixel coordinate set and the second grayscale value set to obtain a second grayscale image pixel information set; an instantaneous speed generation processing unit 308 is configured to perform instantaneous speed generation processing on each first grayscale image pixel information in the first grayscale image pixel information set based on the second grayscale image pixel information set to generate an instantaneous speed to obtain an instantaneous speed field, wherein the instantaneous speed generation processing is performed in a digital signal processor; a generation unit 309 is configured to generate a region of interest based on the instantaneous speed field to obtain a region of interest set.

[0095] It is understood that the units described in the device 300 are similar to those described in the reference Figure 2Therefore, the operations, features and beneficial effects described above for the method are also applicable to the device 300 and the units contained therein, and will not be described in detail here.

[0096] Reference below Figure 4 , which shows an electronic device (eg, Figure 1 Schematic diagram of the structure of the computing device 101)400. Figure 4 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0097] like Figure 4 As shown, the electronic device 400 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 401, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 402 or a program loaded from a storage device 408 into a random access memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the electronic device 400 are also stored. The processing device 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0098] Typically, the following devices may be connected to the I / O interface 405: an input device 406 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 407 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 408 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 409. The communication device 409 may allow the electronic device 400 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 4 The electronic device 400 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 4 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0099] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 409, or installed from the storage device 408, or installed from the ROM 402. When the computer program is executed by the processing device 401, the above-mentioned functions defined in the method of some embodiments of the present disclosure are executed.

[0100] It should be noted that the computer-readable medium in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In some embodiments of the present disclosure, the computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0101] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0102] The above-mentioned computer-readable medium may be included in the above-mentioned device; or it may exist independently and not be assembled into the electronic device. The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: randomly selects two adjacent target images from the pre-acquired target image sequence as the first target image and the second target image respectively; determines the imaging time of the above-mentioned first target image and the above-mentioned second target image respectively to obtain the first target image imaging time and the second target image imaging time; performs grayscale processing on the above-mentioned first target image and the above-mentioned second target image respectively to generate the first grayscale image and the second grayscale image; determines the coordinates of each pixel in the above-mentioned first grayscale image and the above-mentioned second grayscale image respectively to generate the first grayscale image pixel coordinate set and the second grayscale image pixel coordinate set; determines the grayscale value of the pixel corresponding to each first grayscale image pixel coordinate in the above-mentioned first grayscale image pixel coordinate set and the grayscale value of the pixel in the above-mentioned second grayscale image pixel coordinate set respectively. The grayscale value of the pixel corresponding to each second grayscale image pixel coordinate is used to generate the first grayscale value and the second grayscale value to obtain the first grayscale value set and the second grayscale value set; the imaging time of the first target image, the first grayscale image pixel coordinate set and the first grayscale value set are subjected to data fusion processing to obtain the first grayscale image pixel information set; the imaging time of the second target image, the second grayscale image pixel coordinate set and the second grayscale value set are subjected to data fusion processing to obtain the second grayscale image pixel information set; based on the second grayscale image pixel information set, each first grayscale image pixel information in the first grayscale image pixel information set is subjected to instantaneous speed generation processing to generate an instantaneous speed to obtain an instantaneous speed field, wherein the instantaneous speed generation processing is performed in a digital signal processor; based on the instantaneous speed field, a region of interest is generated to obtain a region of interest set.

[0103] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0104] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0105] The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The described units may also be provided in a processor, for example, may be described as: a processor including a selection unit, a first determination unit, a grayscale processing unit, a second determination unit, a third determination unit, a first data fusion processing unit, a second data fusion processing unit, an instantaneous speed generation processing unit, and a generation unit. Among them, the names of these units do not constitute a limitation on the units themselves in certain cases, for example, the selection unit may also be described as "a unit that randomly selects two adjacent target images from a pre-acquired target image sequence as the first target image and the second target image, respectively".

[0106] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), etc.

[0107] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above invention concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure to form a technical method.

Claims

1. A method for generating a region of interest, comprising: Randomly select two adjacent target images from a pre-acquired target image sequence as a first target image and a second target image respectively; Determining imaging times of the first target image and the second target image respectively, to obtain imaging times of the first target image and the second target image; Performing grayscale processing on the first target image and the second target image respectively to generate a first grayscale image and a second grayscale image; Determining coordinates of each pixel in the first grayscale image and the second grayscale image respectively to generate a first grayscale image pixel coordinate set and a second grayscale image pixel coordinate set; Respectively determining the grayscale value of a pixel corresponding to each first grayscale image pixel coordinate in the first grayscale image pixel coordinate set and the grayscale value of a pixel corresponding to each second grayscale image pixel coordinate in the second grayscale image pixel coordinate set to generate a first grayscale value and a second grayscale value, thereby obtaining a first grayscale value set and a second grayscale value set; Performing data fusion processing on the imaging time of the first target image, the first grayscale image pixel coordinate set, and the first grayscale value set to obtain a first grayscale image pixel information set; Performing data fusion processing on the imaging time of the second target image, the second grayscale image pixel coordinate set, and the second grayscale value set to obtain a second grayscale image pixel information set; Based on the second grayscale image pixel information set, performing instantaneous velocity generation processing on each first grayscale image pixel information in the first grayscale image pixel information set to generate an instantaneous velocity, thereby obtaining an instantaneous velocity field, wherein the instantaneous velocity generation processing is performed in a digital signal processor; Based on the instantaneous velocity field, a region of interest is generated to obtain a set of regions of interest; The step of performing instantaneous speed generation processing on each first grayscale image pixel information in the first grayscale image pixel information set based on the second grayscale image pixel information set to generate an instantaneous speed includes: Determine second grayscale image pixel information corresponding to the first grayscale image pixel information in the second grayscale image pixel information set; Based on the second grayscale image pixel information, performing curve fitting on the first grayscale image pixel information to generate a basic constraint equation; Performing a first constraint equation generation process on the basic constraint equation to generate a first constraint equation; Generate a second constraint equation based on the first grayscale image pixel information and the first constraint equation; generating the instantaneous velocity based on the second constraint equation; The step of performing curve fitting on the first grayscale image pixel information based on the second grayscale image pixel information to generate a basic constraint equation includes: Based on the second grayscale image pixel information, the first grayscale image pixel information is input into the following formula, and curve fitting is performed on the first grayscale image pixel information to generate a basic constraint equation: F(x,y,t)=F(x+dx,y+dy,t+dt), Wherein, F(x, y, t) represents the first grayscale value in the first grayscale image pixel information, F(x+dx, y+dy, t+dt) represents the second grayscale value in the second grayscale image pixel information, x represents the abscissa of the first grayscale image pixel coordinate in the first grayscale image pixel information, y represents the ordinate of the first grayscale image pixel coordinate in the first grayscale image pixel information, t represents the imaging time of the first target image, dx represents the difference between the first grayscale image pixel coordinate and the second grayscale image pixel coordinate in the second grayscale image pixel information in the abscissa direction, dy represents the difference between the first grayscale image pixel coordinate and the second grayscale image pixel coordinate in the second grayscale image pixel information in the ordinate direction, and dt represents the difference between the imaging time of the first target image and the imaging time of the second target image; The step of performing a first constraint equation generation process on the basic constraint equation to generate the first constraint equation includes: Respectively obtain partial derivatives of the first gray value along a first preset direction, a second preset direction, and a third preset direction to obtain a first partial derivative, a second partial derivative, and a third partial derivative; Generate the first constraint equation using the following formula: Wherein, F represents the first grayscale value, x represents the abscissa of the pixel coordinates of the first grayscale image, y represents the ordinate of the pixel coordinates of the first grayscale image, t represents the imaging time of the first target image, F′x represents the first partial derivative, F′y represents the second partial derivative, and F′ t represents the third partial derivative, m represents the velocity component of the instantaneous velocity corresponding to the first grayscale image pixel coordinates in the first grayscale image pixel information along the first preset direction, and n represents the velocity component of the instantaneous velocity corresponding to the first grayscale image pixel coordinates in the first grayscale image pixel information along the second preset direction.

2. The method according to claim 1, wherein: The generating of a region of interest based on the instantaneous velocity field to obtain a set of regions of interest includes: Performing threshold segmentation on the instantaneous velocity field to obtain a set of segmented regions; Performing a smoothing process on each segmented region in the segmented region set to generate a smoothed region, thereby obtaining a smoothed region set; Performing a region of interest generation process on each smooth region in the smooth region set to generate a region of interest, thereby obtaining a region of interest set.

3. The method according to claim 1, wherein: The method further comprises: The set of regions of interest is input into a preset neural network model to obtain recognition detection information, wherein the recognition detection information includes any one of the following: target detection results, behavior recognition results and target analysis results.

4. A device for generating a region of interest, comprising: A selection unit is configured to randomly select two adjacent target images from a pre-acquired target image sequence as a first target image and a second target image respectively; A first determining unit is configured to respectively determine the imaging time of the first target image and the second target image to obtain the imaging time of the first target image and the imaging time of the second target image; A grayscale processing unit, configured to perform grayscale processing on the first target image and the second target image respectively to generate a first grayscale image and a second grayscale image; a second determining unit, configured to respectively determine the coordinates of each pixel in the first grayscale image and the second grayscale image to generate a first grayscale image pixel coordinate set and a second grayscale image pixel coordinate set; a third determining unit, configured to respectively determine the grayscale value of a pixel corresponding to each first grayscale image pixel coordinate in the first grayscale image pixel coordinate set and the grayscale value of a pixel corresponding to each second grayscale image pixel coordinate in the second grayscale image pixel coordinate set to generate a first grayscale value and a second grayscale value, and obtain a first grayscale value set and a second grayscale value set; A first data fusion processing unit is configured to perform data fusion processing on the imaging time of the first target image, the first grayscale image pixel coordinate set and the first grayscale value set to obtain a first grayscale image pixel information set; A second data fusion processing unit is configured to perform data fusion processing on the imaging time of the second target image, the second grayscale image pixel coordinate set and the second grayscale value set to obtain a second grayscale image pixel information set; an instantaneous speed generation processing unit, configured to perform instantaneous speed generation processing on each first grayscale image pixel information in the first grayscale image pixel information set based on the second grayscale image pixel information set to generate an instantaneous speed, and obtain an instantaneous speed field, wherein the instantaneous speed generation processing is performed in a digital signal processor; A generating unit is configured to generate a region of interest based on the instantaneous velocity field to obtain a set of regions of interest; Wherein, the instantaneous speed generation processing unit is further configured to: Determine second grayscale image pixel information corresponding to the first grayscale image pixel information in the second grayscale image pixel information set; Based on the second grayscale image pixel information, performing curve fitting on the first grayscale image pixel information to generate a basic constraint equation; Performing a first constraint equation generation process on the basic constraint equation to generate a first constraint equation; Generate a second constraint equation based on the first grayscale image pixel information and the first constraint equation; generating the instantaneous velocity based on the second constraint equation; The step of performing curve fitting on the first grayscale image pixel information based on the second grayscale image pixel information to generate a basic constraint equation includes: Based on the second grayscale image pixel information, the first grayscale image pixel information is input into the following formula, and curve fitting is performed on the first grayscale image pixel information to generate a basic constraint equation: F(x,y,t)=F(x+dx,y+dy,t+dt), Wherein, F(x, y, t) represents the first grayscale value in the first grayscale image pixel information, F(x+dx, y+dy, t+dt) represents the second grayscale value in the second grayscale image pixel information, x represents the abscissa of the first grayscale image pixel coordinate in the first grayscale image pixel information, y represents the ordinate of the first grayscale image pixel coordinate in the first grayscale image pixel information, t represents the imaging time of the first target image, dx represents the difference between the first grayscale image pixel coordinate and the second grayscale image pixel coordinate in the second grayscale image pixel information in the abscissa direction, dy represents the difference between the first grayscale image pixel coordinate and the second grayscale image pixel coordinate in the second grayscale image pixel information in the ordinate direction, and dt represents the difference between the imaging time of the first target image and the imaging time of the second target image; The step of performing a first constraint equation generation process on the basic constraint equation to generate the first constraint equation includes: Respectively obtain partial derivatives of the first gray value along a first preset direction, a second preset direction, and a third preset direction to obtain a first partial derivative, a second partial derivative, and a third partial derivative; Generate the first constraint equation using the following formula: Wherein, F represents the first grayscale value, x represents the abscissa of the pixel coordinates of the first grayscale image, y represents the ordinate of the pixel coordinates of the first grayscale image, t represents the imaging time of the first target image, and F′ x Denotes the first partial derivative, F′ y Denotes the second partial derivative, F′ t represents the third partial derivative, m represents the velocity component of the instantaneous velocity corresponding to the first grayscale image pixel coordinates in the first grayscale image pixel information along the first preset direction, and n represents the velocity component of the instantaneous velocity corresponding to the first grayscale image pixel coordinates in the first grayscale image pixel information along the second preset direction.

5. An electronic device comprising: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 3.

6. A computer readable medium having a computer program stored thereon, wherein: When the program is executed by a processor, the method according to any one of claims 1 to 3 is implemented.

Images