Object mass measurement method, medium and system

Abstract

The invention discloses an object mass measurement method, medium and system, and the method comprises the steps: obtaining a to-be-measured object image, and carrying out the recognition of the to-be-measured object image, so as to obtain an object type corresponding to a to-be-measured object; obtaining a to-be-measured object surrounding video, and generating an initial three-dimensional model corresponding to the to-be-measured object based on the to-be-measured object surrounding video; obtaining a group photo image of the to-be-measured object and the reference object, and calculating a corresponding zoom factor based on the group photo image; scaling the initial three-dimensional model based on the scaling factor to obtain a real-scale three-dimensional model of the to-be-measured object; and obtaining the object density according to the object category, calculating the model volume corresponding to the real-scale three-dimensional model, and calculating the mass of the to-be-measured object according to the object density and the model volume. The object mass can be effectively measured, and the convenience of object mass measurement is improved.

Description

Technical Field

[0001] The present application relates to the field of three-dimensional reconstruction technology, and in particular to an object mass measurement method, medium and system. Background Art

[0002] In the existing digital twin world generation, when users upload a three-dimensional model of an object, if they want to measure the mass of the object, most of them use the following methods: 1. Directly use a weighing device to measure the mass of the object; 2. Use depth sensors such as the mobile phone's lidar to obtain the depth of the object to obtain a three-dimensional model of real scale in three-dimensional modeling.

[0003] It is understandable that it is inconvenient to use a weighing device to measure mass, as it requires a weighing device, which is often inconvenient to carry. Using a lidar to measure the depth of an object has high requirements for the terminal and low applicability. Summary of the invention

[0004] The present invention aims to solve one of the technical problems in the related art at least to a certain extent. To this end, one object of the present invention is to provide an object mass measurement method that can effectively measure the mass of an object and improve the convenience of object mass measurement.

[0005] In a first aspect, an embodiment of the present invention proposes a method for measuring object mass, comprising the following steps: obtaining an image of an object to be measured, and identifying the image of the object to be measured to obtain an object category corresponding to the object to be measured; obtaining a surround video of the object to be measured, and generating an initial three-dimensional model corresponding to the object to be measured based on the surround video of the object to be measured; obtaining a group image of the object to be measured and a reference object, and calculating a corresponding scaling factor based on the group image; scaling the initial three-dimensional model based on the scaling factor to obtain a true-scale three-dimensional model of the object to be measured; obtaining an object density according to the object category, and calculating a model volume corresponding to the true-scale three-dimensional model, and calculating the mass of the object to be measured based on the object density and the model volume.

[0006] According to the object mass measurement method of the embodiment of the present invention, first, an image of the object to be measured is obtained, and the image of the object to be measured is identified to obtain an object category corresponding to the object to be measured; then, a surround video of the object to be measured is obtained, and an initial three-dimensional model corresponding to the object to be measured is generated based on the surround video of the object to be measured; then, a group photo image of the object to be measured and a reference object is obtained, and a corresponding scaling factor is calculated based on the group photo image; then, the initial three-dimensional model is scaled based on the scaling factor to obtain a real-scale three-dimensional model of the object to be measured; then, the object density is obtained according to the object category, and the model volume corresponding to the real-scale three-dimensional model is calculated, and the mass of the object to be measured is calculated according to the object density and the model volume; thereby, effective measurement of the object mass is achieved and the convenience of object mass measurement is improved.

[0007] In some embodiments, an image of an object to be tested is obtained, and the image of the object to be tested is identified to obtain an object category corresponding to the object to be tested, including: photographing the object to be tested to obtain an image of the object to be tested; displaying the image of the object to be tested through a user terminal, and obtaining a selection instruction input by a user through the user terminal, and determining a target area corresponding to the object to be tested in the image of the object to be tested according to the selection instruction; and performing image recognition on the target area to obtain an object category corresponding to the object to be tested.

[0008] In some embodiments, image recognition is performed on the target area to obtain an object category corresponding to the object to be tested, including: performing image recognition on the target area to obtain a pre-selected object category corresponding to the object to be tested; displaying the pre-selected object category and obtaining a user's click instruction for the pre-selected object category, and determining a final object category based on the click instruction.

[0009] In some embodiments, generating an initial three-dimensional model corresponding to the object to be tested based on the surround video of the object to be tested includes: extracting multi-perspective images of the object to be tested based on the surround video; and generating an initial three-dimensional model corresponding to the object to be tested based on the multi-perspective images using nerf technology.

[0010] In some embodiments, the reference object is a preset finger joint of the user, wherein calculating the corresponding scaling factor based on the group photo image includes: calculating a mapping length of the preset finger joint in the initial three-dimensional model based on the group photo image; obtaining a real length of the preset finger joint; and calculating the scaling factor according to the mapping length and the real length.

[0011] In some embodiments, the group photo image includes a first-perspective group photo image and a second-perspective group photo image, wherein calculating the mapping length of the preset finger joint in the initial three-dimensional model based on the group photo image includes: performing image recognition on the first-perspective group photo image and the second-perspective group photo image respectively to obtain two-dimensional feature points in the first-perspective group photo image and the second-perspective group photo image; performing feature point retrieval based on the two-dimensional feature points to determine the first camera pose corresponding to the first-perspective group photo image and the second camera pose corresponding to the second-perspective group photo image; obtaining the image coordinates of the preset finger joint key points in the first-perspective group photo image and the image coordinates of the preset finger joint key points in the second-perspective group photo image; calculating the three-dimensional coordinate values ​​of the preset finger joint key points in the initial three-dimensional model based on the least squares method, and calculating the mapping length of the preset finger joint in the initial three-dimensional model based on the three-dimensional coordinate values.

[0012] In some embodiments, the method further includes: displaying the mass of the object to be measured through a user terminal; and displaying the true-scale three-dimensional model through a user terminal.

[0013] In some embodiments, the method further includes: obtaining a user's adjustment instruction for the real-scale three-dimensional model, and adjusting the real-scale three-dimensional model according to the adjustment instruction; calculating the real-time volume of the adjusted real-scale three-dimensional model, and calculating the real-time mass corresponding to the adjusted real-scale three-dimensional model according to the real-time volume.

[0014] In a second aspect, an embodiment of the present invention provides a computer-readable storage medium on which an object mass measurement program is stored. When the object mass measurement program is executed by a processor, the object mass measurement method as described above is implemented.

[0015] In a third aspect, an embodiment of the present invention proposes an object mass measurement system, comprising: an acquisition module, the acquisition module is used to acquire an image of an object to be measured, and identify the image of the object to be measured to obtain an object category corresponding to the object to be measured; a modeling module, the modeling module is used to acquire a surround video of the object to be measured, and generate an initial three-dimensional model corresponding to the object to be measured based on the surround video of the object to be measured; a calculation module, the calculation module is used to acquire a group image of the object to be measured and a reference object, and calculate a corresponding scaling factor based on the group image; a scaling module, the scaling module is used to scale the initial three-dimensional model based on the scaling factor to obtain a real-scale three-dimensional model of the object to be measured; the calculation module is also used to acquire an object density according to the object category, calculate a model volume corresponding to the real-scale three-dimensional model, and calculate the mass of the object to be measured based on the object density and the model volume.

[0016] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a flow chart of an object mass measurement method according to an embodiment of the present invention; Figure 2 is a block diagram of an object mass measurement system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0018] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0019] The object mass measurement method according to an embodiment of the present invention will be described below with reference to the accompanying drawings.

[0020] See also Figure 1 , Figure 1 FIG. 1 is a flow chart of a method for measuring object mass according to an embodiment of the present invention. Figure 1 As shown, the object mass measurement method includes the following steps: S101, acquiring an image of an object to be tested, and identifying the image of the object to be tested to obtain an object category corresponding to the object to be tested.

[0021] In some embodiments, an image of an object to be tested is obtained, and the image of the object to be tested is identified to obtain an object category corresponding to the object to be tested, including: photographing the object to be tested to obtain an image of the object to be tested; displaying the image of the object to be tested through a user terminal, and obtaining a selection instruction input by a user through the user terminal, and determining a target area corresponding to the object to be tested in the image of the object to be tested according to the selection instruction; performing image recognition on the target area to obtain an object category corresponding to the object to be tested.

[0022] In some embodiments, image recognition is performed on the target area to obtain an object category corresponding to the object to be tested, including: performing image recognition on the target area to obtain a pre-selected object category corresponding to the object to be tested; displaying the pre-selected object category and obtaining a user's click instruction for the pre-selected object category, and determining a final object category based on the click instruction.

[0023] As an example, first, the object to be tested is photographed through a user terminal (for example, a mobile phone, a computer, a tablet computer, etc.) to obtain an image of the object to be tested; then, the image of the object to be tested is displayed through the display screen of the user terminal; and through the displayed image of the object to be tested, the user inputs a selection instruction according to his own needs (the selection instruction can be input in a variety of ways, for example, the user's circled range can be obtained as the selection instruction; or the user's click instruction can be obtained as the selection instruction, and the setting method of the selection instruction is not limited here); in this way, the target area corresponding to the object to be tested can be determined according to the user's selection instruction; then, the target area is image recognized to obtain the pre-selected object category corresponding to the object to be tested; preferably, when the target area is image recognized, multiple possible pre-selected object categories corresponding to the object to be tested can be output, and the names of the multiple possible pre-selected object categories and their corresponding probability percentages can be displayed (for example, orange 98%, grapefruit 30%, lemon 10%), so that the user can click according to the displayed multiple possible pre-selected object categories and their corresponding probabilities to determine the pre-selected object category corresponding to the object to be tested.

[0024] S102, obtaining a surround video of the object to be measured, and generating an initial three-dimensional model corresponding to the object to be measured based on the surround video of the object to be measured.

[0025] In some embodiments, generating an initial three-dimensional model corresponding to the object to be tested based on the surround video of the object to be tested includes: extracting multi-perspective images of the object to be tested based on the surround video; and generating an initial three-dimensional model corresponding to the object to be tested based on the multi-perspective images using nerf technology.

[0026] As an example, first, surround shooting of the object to be measured is performed through a user terminal to obtain a surround video of the object to be measured; then, the surround video of the object to be measured is frame extracted to obtain a multi-perspective image of the object to be measured; then, based on the extracted multi-perspective image, the nerf technology is used to generate a three-dimensional model of the object to be measured, and the three-dimensional model is the initial three-dimensional model; it should be noted that the initial three-dimensional model has no real scale.

[0027] S103, obtaining a combined image of the object to be measured and the reference object, and calculating a corresponding scaling factor based on the combined image.

[0028] In some embodiments, the reference object is a preset finger joint of the user, wherein the corresponding scaling factor is calculated based on the group photo image, including: calculating the mapping length of the preset finger joint in the initial three-dimensional model based on the group photo image; obtaining the actual length of the preset finger joint; and calculating the scaling factor based on the mapping length and the actual length.

[0029] In some embodiments, the group photo image includes a first-perspective group photo image and a second-perspective group photo image, wherein the mapping length of the preset finger joints in the initial three-dimensional model is calculated based on the group photo images, including: performing image recognition on the first-perspective group photo image and the second-perspective group photo image respectively to obtain two-dimensional feature points in the first-perspective group photo image and the second-perspective group photo image; performing feature point retrieval based on the two-dimensional feature points to determine a first camera pose corresponding to the first-perspective group photo image and a second camera pose corresponding to the second-perspective group photo image; obtaining the image coordinates of the preset finger joint key points in the first-perspective group photo image and the image coordinates of the preset finger joint key points in the second-perspective group photo image; calculating the three-dimensional coordinate values ​​of the preset finger joint key points in the initial three-dimensional model based on the least squares method, and calculating the mapping length of the preset finger joints in the initial three-dimensional model based on the three-dimensional coordinate values.

[0030] As an example, first, a photo of the object to be tested and the user's palm (i.e., a photo image) is obtained through the user terminal, and then, a two-perspective photo image (i.e., a first-perspective photo image and a second-perspective photo image) is obtained; then, image recognition is performed on the first-perspective photo image and the second-perspective photo image to obtain two-dimensional feature points in the first-perspective photo image and the second-perspective photo image; then, the three-dimensional coordinates in the initial three-dimensional model can be obtained through feature point retrieval and matching; then, the camera pose R1 and t1 corresponding to the first-perspective photo image can be obtained through the pnp algorithm; and the camera pose R2 and t2 corresponding to the second-perspective photo image can be obtained. Then, image detection is performed on the first-perspective photo image to obtain the image coordinates L of the first key point on the first-perspective photo image. 10 The image coordinates R of the first key point in the second perspective photo 10 Then, the least squares method can be used based on the camera pose R1 and t1, R2 and t2, and the image coordinate L 10 and image coordinates R 10 Calculate the three-dimensional coordinates of the first key point in the initial three-dimensional model; then, calculate the three-dimensional coordinates of the second key point in the same way as the first key point; then, the mapping length of the preset finger joint in the initial three-dimensional model can be calculated based on the three-dimensional coordinates of the first key point and the second key point. Specifically, the mapping length can be calculated using the following formula: ; ; ; in, Indicates the length of the mapping, Represents the three-dimensional coordinate value of the first key point, Indicates the 3D coordinate value of the second key point.

[0031] The scaling factor can then be calculated according to the following formula: ; in, Indicates the length of the mapping, represents the scaling factor, Indicates the true length.

[0032] It should be noted that the real length may be preset in the system by the user; or it may be obtained by obtaining user input during use, and the method for obtaining the real length is not limited here.

[0033] S104, scaling the initial three-dimensional model based on the scaling factor to obtain a true-scale three-dimensional model of the object to be measured.

[0034] S105, obtaining the object density according to the object category, calculating the model volume corresponding to the real-scale three-dimensional model, and calculating the mass of the object to be measured according to the object density and the model volume.

[0035] As an example, first, determine the bounding box, that is, calculate the axis-aligned bounding box of the real-scale three-dimensional model. This bounding box is the smallest cuboid that can completely contain the real-scale three-dimensional model; then, generate random points, that is, generate a large number of random points in this bounding box, and these random points should be evenly distributed in the volume of the bounding box; then, determine whether the random point is in the model, and for each random point, determine whether it is located inside the real-scale three-dimensional model; this is achieved by the ray intersection method, that is, emit a ray from the point, and then check the number of intersections between the ray and the model surface. If the number of intersections is an odd number, the point is inside the model; if the number of intersections is an even number, it is outside the model. Next, calculate the volume, calculate the proportion of the points inside the model, and then multiply it by the volume of the bounding box to obtain the volume of the real-scale three-dimensional model. Then, the mass of the object to be measured can be calculated based on the model volume and the object density.

[0036] It should be noted that a database of common object densities can be preset in the system. When calculation is required, the database can be queried according to the object category obtained by image recognition to obtain the object density corresponding to the object to be measured. In addition, if the object density corresponding to the object category cannot be found in the database, the corresponding object density can be queried by calling the large language model.

[0037] In some embodiments, the method further includes: displaying the mass of the object to be measured through a user terminal; and displaying the real-scale three-dimensional model through the user terminal.

[0038] In some embodiments, the method further includes: obtaining a user's adjustment instruction for the real-scale three-dimensional model, and adjusting the real-scale three-dimensional model according to the adjustment instruction; calculating the real-time volume of the adjusted real-scale three-dimensional model, and calculating the real-time mass corresponding to the adjusted real-scale three-dimensional model according to the real-time volume.

[0039] As an example, the mass of the object to be measured can be displayed through the user terminal, and at the same time, the real-scale three-dimensional model can be displayed through the user terminal; in addition, the user's adjustment instruction for the real-scale three-dimensional model can be obtained (for example, the user's sliding operation on the real-scale three-dimensional model is obtained to adjust the volume of the real-scale three-dimensional model through the sliding operation); after the user completes the adjustment instruction, the real-time volume corresponding to the adjusted real-scale three-dimensional model is calculated, and the real-time mass corresponding to the real-scale three-dimensional model under the real-time volume is calculated, and the real-time mass is displayed.

[0040] In summary, according to the object mass measurement method of the embodiment of the present invention, first, an image of the object to be measured is obtained, and the image of the object to be measured is identified to obtain the object category corresponding to the object to be measured; then, a surround video of the object to be measured is obtained, and an initial three-dimensional model corresponding to the object to be measured is generated based on the surround video of the object to be measured; then, a group photo image of the object to be measured and a reference object is obtained, and a corresponding scaling factor is calculated based on the group photo image; then, the initial three-dimensional model is scaled based on the scaling factor to obtain a real-scale three-dimensional model of the object to be measured; then, the object density is obtained according to the object category, and the model volume corresponding to the real-scale three-dimensional model is calculated, and the mass of the object to be measured is calculated according to the object density and the model volume; thereby, effective measurement of the object mass is achieved and the convenience of object mass measurement is improved.

[0041] In a second aspect, an embodiment of the present invention provides a computer-readable storage medium on which an object mass measurement program is stored. When the object mass measurement program is executed by a processor, the object mass measurement method as described above is implemented.

[0042] In a third aspect, an embodiment of the present invention provides an object mass measurement system, such as Figure 2 As shown, the object quality measurement system includes: an acquisition module 10 , a modeling module 20 , a calculation module 30 and a scaling module 40 .

[0043] The acquisition module 10 is used to acquire an image of the object to be tested and identify the image of the object to be tested to obtain an object category corresponding to the object to be tested; The modeling module 20 is used to obtain a surround video of the object to be measured, and generate an initial three-dimensional model corresponding to the object to be measured based on the surround video of the object to be measured; The calculation module 30 is used to obtain a combined image of the object to be measured and the reference object, and calculate a corresponding scaling factor based on the combined image; The scaling module 40 is used to scale the initial three-dimensional model based on the scaling factor to obtain a true-scale three-dimensional model of the object to be measured; The calculation module 30 is further used to obtain the object density according to the object category, calculate the model volume corresponding to the real-scale three-dimensional model, and calculate the mass of the object to be measured according to the object density and the model volume.

[0044] It should be noted that the above description of the object mass measurement method is also applicable to the object mass measurement system and will not be elaborated here.

[0045] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0046] It should be understood that the various parts of the present invention 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.

[0047] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", 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 invention. 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.

[0048] In the description of the present invention, it is to be understood that the terms “center”, “longitudinal”, “lateral”, “length”, “width”, “thickness”, “up”, “down”, “front”, “back”, “left”, “right”, “vertical”, “horizontal”, “top”, “bottom”, “inside”, “outside”, “clockwise”, “counterclockwise”, “axial”, “radial”, “circumferential”, etc., indicating orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0049] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0050] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0051] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, a first feature being "above", "above" or "above" a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" or "below" a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0052] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A method for measuring the mass of an object, characterized in that: The following steps are involved: Acquire an image of the object to be tested, and identify the image of the object to be tested to obtain an object category corresponding to the object to be tested; Acquire a surround video of the object to be measured, and generate an initial three-dimensional model corresponding to the object to be measured based on the surround video of the object to be measured; Acquire a combined image of the object to be measured and the reference object, and calculate a corresponding scaling factor based on the combined image; Scaling the initial three-dimensional model based on the scaling factor to obtain a true-scale three-dimensional model of the object to be measured; The object density is acquired according to the object category, and the model volume corresponding to the real-scale three-dimensional model is calculated, and the mass of the object to be measured is calculated according to the object density and the model volume.

2. The object mass measurement method according to claim 1, characterized in that: Acquiring an image of the object to be tested and identifying the image of the object to be tested to obtain an object category corresponding to the object to be tested, including: Photographing the object to be measured to obtain an image of the object to be measured; The image of the object to be tested is displayed through a user terminal, and a selection instruction input by a user through the user terminal is obtained, and a target area corresponding to the object to be tested in the image of the object to be tested is determined according to the selection instruction; Perform image recognition on the target area to obtain the object category corresponding to the object to be detected.

3. The object mass measurement method according to claim 2, characterized in that: Performing image recognition on the target area to obtain the object category corresponding to the object to be detected includes: Performing image recognition on the target area to obtain a preselected object category corresponding to the object to be detected; The pre-selected object category is displayed, and a user's click instruction for the pre-selected object category is obtained, and a final object category is determined according to the click instruction.

4. The object mass measurement method according to claim 1, characterized in that: Generating an initial three-dimensional model corresponding to the object to be measured based on the surround video of the object to be measured, including: Extracting multi-view images of the object to be measured based on the surround video; The nerf technology is used to generate an initial three-dimensional model corresponding to the object to be measured based on the multi-view images.

5. The object mass measurement method according to claim 1, characterized in that: The reference object is a preset finger joint of the user, wherein the corresponding scaling factor is calculated based on the group photo image, including: Calculating the mapping length of the preset finger joint in the initial three-dimensional model based on the group photo image; Obtaining the actual length of the preset finger joint; The scaling factor is calculated based on the mapped length and the real length.

6. The object mass measurement method according to claim 5, characterized in that: The group photo image includes a first-view group photo image and a second-view group photo image, wherein calculating the mapping length of the preset finger joint in the initial three-dimensional model based on the group photo image includes: Performing image recognition on the first-viewing angle group photo image and the second-viewing angle group photo image respectively to obtain two-dimensional feature points in the first-viewing angle group photo image and the second-viewing angle group photo image; Performing feature point retrieval according to the two-dimensional feature points to determine a first camera pose corresponding to the first-view group photo image and a second camera pose corresponding to the second-view group photo image; Obtaining image coordinates of preset finger joint key points in the first-view group photo image and image coordinates of the preset finger joint key points in the second-view group photo image; The three-dimensional coordinate values ​​of the preset finger joint key points in the initial three-dimensional model are calculated based on the least squares method, and the mapping length of the preset finger joints in the initial three-dimensional model is calculated according to the three-dimensional coordinate values.

7. The object mass measurement method according to claim 1, characterized in that: Also includes: Displaying the mass of the object to be measured through a user terminal; The true-scale three-dimensional model is displayed through a user terminal.

8. The object mass measurement method according to claim 7, characterized in that: Also includes: Acquiring a user's adjustment instruction for the real-scale three-dimensional model, and adjusting the real-scale three-dimensional model according to the adjustment instruction; The real-time volume of the adjusted true-scale three-dimensional model is calculated, and the real-time mass corresponding to the adjusted true-scale three-dimensional model is calculated according to the real-time volume.

9. A computer-readable storage medium, characterized in that: An object mass measurement program is stored thereon, and when the object mass measurement program is executed by a processor, the object mass measurement method according to any one of claims 1 to 8 is implemented.

10. An object mass measurement system, characterized in that: include: An acquisition module, the acquisition module is used to acquire an image of the object to be tested, and identify the image of the object to be tested to obtain an object category corresponding to the object to be tested; A modeling module, the modeling module is used to obtain a surround video of the object to be measured, and generate an initial three-dimensional model corresponding to the object to be measured based on the surround video of the object to be measured; A calculation module, the calculation module is used to obtain a combined image of the object to be measured and the reference object, and calculate a corresponding scaling factor based on the combined image; A scaling module, the scaling module is used to scale the initial three-dimensional model based on the scaling factor to obtain a true-scale three-dimensional model of the object to be measured; The calculation module is further used to obtain the object density according to the object category, calculate the model volume corresponding to the real-scale three-dimensional model, and calculate the mass of the object to be measured according to the object density and the model volume.

Images