CN108537834A - A kind of volume measuring method, system and depth camera based on depth image - Google Patents

Abstract

The invention belongs to the technical field of logistics and volume measurement, and specifically relates to a volume measurement method, system and depth camera based on a depth image, comprising the following steps: S1, obtaining a scene depth map containing an object to be measured, and obtaining scene point cloud coordinates; S2 , to transform the coordinates of the scene point cloud to obtain the coordinates of the scene point cloud in the depth camera coordinate system; S3, to process the coordinates of the scene point cloud in the depth camera coordinate system to obtain the coordinate set of the object to be measured; S4, according to the The coordinate set of the object is used to calculate the length, width and height of the object to be measured, and the volume of the object to be measured is obtained by multiplying the length, width and height together. Compared with the existing logistics volume measurement scheme, the present invention can be realized by using a common depth camera on the market in terms of hardware, and the cost is low; when the camera is tilted, it can still accurately measure the volume of the object to be measured in real time.

Description

A volume measurement method, system and depth camera based on depth image

technical field

The invention belongs to the technical field of logistics and volume measurement, and in particular relates to a volume measurement method, system and depth camera based on a depth image.

Background technique

In recent years, with the rapid development of economic globalization, a large amount of materials need to flow frequently between regions, especially the rise of e-commerce accompanied by the revolution of information technology, which has made the logistics industry develop rapidly, and the logistics enterprises Competition is also becoming increasingly fierce. How to reduce labor costs and efficiently send express shipments to their destinations is the key to gaining a competitive advantage.

In logistics and warehousing management, the volume attribute of items is very important for the logistics center to optimize receipt, warehousing, picking, packaging and shipping management. Therefore, automatic and accurate measurement of the size and volume of items can greatly improve the efficiency of warehousing logistics. Efficiency and the level of intelligence and automation of logistics systems.

Existing volume measurement equipment is mostly based on light curtain or linear array laser scanning, which must cooperate with the conveyor belt encoder to calculate the volume. Although this technology is relatively mature, it is expensive and the system complexity is high.

Contents of the invention

Aiming at the defects in the prior art, the present invention provides a volume measurement method, system and depth camera based on depth image. Compared with the existing logistics volume measurement scheme, in terms of hardware, the ordinary depth camera on the market can be used Realization, the cost is low; in the tilted state of the camera, the volume of the object to be measured can still be accurately measured in real time.

In a first aspect, the present invention provides a method for volume measurement based on a depth image, comprising the following steps:

S1, obtain the scene depth map containing the object to be measured, and obtain the scene point cloud coordinates;

S2, transforming the coordinates of the scene point cloud to obtain the coordinates of the scene point cloud in the depth camera coordinate system;

S3, processing the scene point cloud coordinates in the depth camera coordinate system to obtain the coordinate set of the object to be measured;

S4. Calculate the length, width, and height of the object to be measured according to the coordinate set of the object to be measured, and multiply the length, width, and height to obtain the volume of the object to be measured.

Preferably, the step S2 is specifically:

S21, setting a reference plane in the scene depth map;

S22, calculating the tilt attitude data of the depth camera according to the reference plane;

S23. Transform the scene point cloud coordinates according to the tilt attitude data to obtain the depth camera coordinate system

The scene point cloud coordinates of .

Preferably, the S22 is specifically:

S221, setting the angle range between the X-axis and Y-axis of the depth camera and the reference plane normal, the angle range includes several X-axis angles θ _x and Y-axis angles θ _y ;

S222, traversing each X-axis included angle and each Y-axis included angle, using a coordinate transformation formula to transform the Z _CK coordinates in the reference plane to obtain several transformed Z _CK coordinates, the transformation formula is:

Z'＝Y ₀ *sinθ _x +Z ₀ cosθ _x ;

Z _ck =Z'*cosθ _y -X ₀ sinθ _y ;

Among them, X ₀ , Y ₀ , and Z ₀ are the original coordinate points of the reference plane, and Z _CK is the transformed Z _CK coordinate;

S223, calculate the average value Zmean and minimum variance Zsigma of all transformed Z _CK coordinates;

S224, taking the X-axis angle θ _x corresponding to the minimum variance Zsigma as the X-axis tilt angle α _x of the depth camera, and the corresponding Y-axis angle θ _y as the Y-axis tilt angle α _y of the depth camera, so as to obtain the tilt attitude Data: the mean Zmean of the Z _CK coordinates, the minimum variance Zsigma, the X-axis tilt angle α _x and the Y-axis tilt angle α _y .

Preferably, the S23 is specifically:

According to the X-axis tilt angle α _x and the Y-axis tilt angle α _y , use the transformation formula to transform the scene point cloud coordinates to obtain the scene point cloud coordinates in the depth camera coordinate system. The transformation formula is:

Z' _i =Y _io *sinα _x +Z _io cosα _x ;

X _i =Z' _i *sinα _y +X _io cosα _y ;

Y _i =Y _io *cosα _y -Z _io sinα _y ;

Z _i =Z' _i *cosα _y -X _io sinα _y ;

Among them, X _io , Y _io , Z _io are the original scene point cloud coordinates, and Xi _, Y _i , Z _i are the scene point cloud coordinates in the depth camera coordinate system.

Preferably, the S3 is specifically:

According to the screening formula, from the scene cloud coordinates under the depth camera coordinate system, filter out the X _i , Y _i , and _Zi coordinate point sets of the object to be measured that meet the conditions. The screening formula is:

|Zi-Zmean|＞N*Zsigma, where N is a positive number.

Preferably, said S4 is specifically:

S41, according to the preset grid accuracy, calculate the X _i , Y _i coordinate points of the object to be measured and project them to the corresponding grid area in the reference plane, calibrate the connected area of the grid area, and count the size of each connected area;

S42, select the X _i , Y _i coordinate point set corresponding to the connected region with the largest area, and calculate the minimum circumscribed rectangle corresponding to the selected X _i , Y _i coordinate point through the principal component analysis method, and obtain the projection of the object to be measured into the reference plane length and width;

S43. Calculate the maximum difference between _Zi and Zmean to obtain the height of the object to be measured, and multiply the length, width and height together to obtain the volume of the object to be measured.

In a second aspect, the present invention provides a depth image-based volume measurement system, which is suitable for the depth image-based volume measurement method described in the first aspect, including:

The scene acquisition unit is used to obtain the scene depth map containing the object to be measured, and obtain the scene point cloud coordinates;

The coordinate transformation unit is used to transform the coordinates of the scene point cloud to obtain the coordinates of the scene point cloud under the depth camera coordinate system;

The object to be measured extraction unit is used to process the scene point cloud coordinates under the depth camera coordinate system to obtain the coordinate set of the object to be measured;

The volume calculation unit is used to calculate the length, width and height of the test object according to the coordinate set of the test object, and multiply the length, width and height to obtain the volume of the test object.

In a third aspect, the present invention provides a depth camera, including a processor, an input device, an output device, and a memory, the processor, the input device, the output device, and the memory are connected to each other, and the memory is used to store computer programs, so The computer program includes program instructions, and the processor is configured to invoke the program instructions to execute the method as described in the first aspect.

The beneficial effects of the present invention are: compared with the existing logistics volume measurement scheme, in terms of hardware, it can be realized by using a common depth camera on the market, and the cost is low; when the camera is tilted, it can still accurately measure the object to be measured in real time volume of.

Description of drawings

In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings that need to be used in the description of the specific embodiments or the prior art. Throughout the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, elements or parts are not necessarily drawn in actual scale.

FIG. 1 is a flow chart of a volume measurement method based on a depth image in this embodiment;

FIG. 2 is a structural diagram of a volume measurement system based on a depth image in this embodiment.

Detailed ways

The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

It should be understood that when used in this specification and the appended claims, the terms "comprising" and "comprises" indicate the presence of described features, integers, operations, elements and/or components, but do not exclude one or more The presence or addition of other features, integers, operations, elements, components and/or collections thereof.

It should also be understood that the terminology used in the description of the present invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the present invention. As used in this specification and the appended claims, the singular forms "a", "an" and "the" are intended to include plural referents unless the context clearly dictates otherwise.

It should also be further understood that the term "and/or" used in the description of the present invention and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations .

Embodiment one:

This embodiment provides a volume measurement method based on a depth image, as shown in FIG. 1 , including the following four steps of S1, S2, S3, and S4:

S1, obtain the depth map of the scene containing the object to be measured, and obtain the point cloud coordinates of the scene. In this embodiment, the principle of time-of-flight of light, the principle of structured light, and the principle of binocular ranging can be used to obtain the scene depth map. The depth map is the coordinate set of the depth Z axis. The depth map is also called the distance image, which refers to the image with the distance (depth) from the image collector to each point in the scene as the pixel value, which directly reflects the objects in the scene. The geometry of the visible surface. The depth map can be calculated as scene point cloud data after coordinate conversion. The image collector in this embodiment is a depth camera. The depth map collected by the depth camera can apply the principle of time-of-flight, structured light, and binocular distance measurement.

S2. Transform the coordinates of the scene point cloud to obtain the coordinates of the scene point cloud in the depth camera coordinate system.

The step S2 specifically includes three steps of S21, S22, and S23:

S21, setting a reference plane in the scene depth map.

S22. Calculate the tilt attitude data of the depth camera according to the reference plane. The S22 specifically includes four steps of S221, S222, S223, and S224:

S221, setting the angle range between the X-axis and Y-axis of the depth camera and the reference plane normal, the angle range includes several X-axis angles θ _x and Y-axis angles θ _y ;

S222, traversing each X-axis included angle and each Y-axis included angle, using a coordinate transformation formula to transform the Z _CK coordinates in the reference plane to obtain several transformed Z _CK coordinates, the transformation formula is:

Z'＝Y ₀ *sinθ _x +Z ₀ cosθ _x ;

Z _ck =Z'*cosθ _y -X ₀ sinθ _y ;

Among them, X ₀ , Y ₀ , and Z ₀ are the original coordinate points of the reference plane, and Z _CK is the transformed Z _CK coordinate;

S223, calculate the average value Zmean and minimum variance Zsigma of all transformed Z _CK coordinates;

S224, taking the X-axis angle θ _x corresponding to the minimum variance Zsigma as the X-axis tilt angle α _x of the depth camera, and the corresponding Y-axis angle θ _y as the Y-axis tilt angle α _y of the depth camera, so as to obtain the tilt attitude Data: the mean Zmean of the Z _CK coordinates, the minimum variance Zsigma, the X-axis tilt angle α _x and the Y-axis tilt angle α _y .

In this embodiment, the X-axis angle, the Y-axis angle, and the distance from the reference plane between the depth camera and the reference plane are obtained according to step S22.

S23. Transform the scene point cloud coordinates according to the tilt attitude data to obtain the scene point cloud coordinates in the depth camera coordinate system. This step is specifically:

According to the X-axis tilt angle α _x and the Y-axis tilt angle α _y , use the transformation formula to transform the scene point cloud coordinates to obtain the scene point cloud coordinates in the depth camera coordinate system. The transformation formula is:

Z' _i =Y _io *sinα _x +Z _io cosα _x ;

X _i =Z' _i *sinα _y +X _io cosα _y ;

Y _i =Y _io *cosα _y -Z _io sinα _y ;

Z _i =Z' _i *cosα _y -X _io sinα _y ;

Among them, X _io , Y _io , Z _io are the original scene point cloud coordinates, and Xi _, Y _i , Z _i are the scene point cloud coordinates in the depth camera coordinate system.

S3. Process the scene point cloud coordinates in the depth camera coordinate system to obtain a coordinate set of the object to be measured. This step is specifically:

According to the screening formula, from the scene cloud coordinates under the depth camera coordinate system, filter out the X _i , Y _i , and _Zi coordinate point sets of the object to be measured that meet the conditions. The screening formula is:

|Zi-Zmean|＞N*Zsigma, where N is a positive number.

Step S3 of this embodiment is to remove the relevant information of other objects in the scene, and extract the coordinate data of the object to be measured.

S4. Calculate the length, width, and height of the object to be measured according to the coordinate set of the object to be measured, and multiply the length, width, and height to obtain the volume of the object to be measured. Said S4 specifically includes two steps of S41 and S42:

S41, according to the preset grid accuracy, calculate the X _i , Y _i coordinate points of the object to be measured and project them to the corresponding grid area in the reference plane, calibrate the connected area of the grid area, and count the size of each connected area;

S42, select the X _i , Y _i coordinate point set corresponding to the connected region with the largest area, calculate the minimum circumscribed rectangle corresponding to the selected X _i , Y _i coordinate point through the principal component analysis method, and obtain the projection of the object to be measured into the reference plane length and width;

S43. Calculate the maximum difference between _Zi and Zmean to obtain the height of the object to be measured, and multiply the length, width and height together to obtain the volume of the object to be measured.

To sum up, compared with the existing logistics volume measurement scheme, this embodiment can be realized by using a common depth camera on the market in terms of hardware, and the cost is relatively low; when the camera is tilted, it can still accurately measure the volume to be measured in real time. volume of the object. In this embodiment, the tilt attitude of the camera is calibrated in advance. During the operation, only key steps such as multiplication, connected area calibration and principal component analysis are needed to calculate the length, width and height of the object to be measured, and then calculate the volume of the object to be measured, which can achieve very good results. real-time measurement. This embodiment supports the tilting of the camera during installation, which is easy to install and expands the measurement range. The point clouds output by many high-precision depth cameras in the existing market are unstructured. This embodiment does not require the structured point cloud data (point cloud coordinates), so it is easier to select the measurement equipment.

Embodiment two:

This embodiment provides a volume measurement system based on depth images, as shown in Figure 2, including:

The scene acquisition unit is used to obtain the scene depth map containing the object to be measured, and obtain the scene point cloud coordinates;

The coordinate transformation unit is used to transform the coordinates of the scene point cloud to obtain the coordinates of the scene point cloud under the depth camera coordinate system;

The object to be measured extraction unit is used to process the scene point cloud coordinates under the depth camera coordinate system to obtain the coordinate set of the object to be measured;

The volume calculation unit is used to calculate the length, width and height of the test object according to the coordinate set of the test object, and multiply the length, width and height to obtain the volume of the test object.

This system is applicable to the volume measurement method based on the depth image described in Embodiment 1, as shown in Figure 1, including the following four steps of S1, S2, S3, and S4:

S1, obtain the depth map of the scene containing the object to be measured, and obtain the point cloud coordinates of the scene. In this embodiment, the principle of time-of-flight of light, the principle of structured light, and the principle of binocular ranging can be used to obtain the scene depth map. The depth map is the coordinate set of the depth Z axis. The depth map is also called the distance image, which refers to the image with the distance (depth) from the image collector to each point in the scene as the pixel value, which directly reflects the objects in the scene. The geometry of the visible surface. The depth map can be calculated as scene point cloud data after coordinate conversion. The image collector in this embodiment is a depth camera. The depth map collected by the depth camera can apply the principle of time-of-flight, structured light, and binocular distance measurement.

S2. Transform the coordinates of the scene point cloud to obtain the coordinates of the scene point cloud in the depth camera coordinate system.

The step S2 specifically includes three steps of S21, S22, and S23:

S21, setting a reference plane in the scene depth map.

S22. Calculate the tilt attitude data of the depth camera according to the reference plane. The S22 specifically includes four steps of S221, S222, S223, and S224:

S221, setting the angle range between the X-axis and Y-axis of the depth camera and the reference plane normal, the angle range includes several X-axis angles θ _x and Y-axis angles θ _y ;

S222, traversing each X-axis included angle and each Y-axis included angle, using a coordinate transformation formula to transform the Z _CK coordinates in the reference plane to obtain several transformed Z _CK coordinates, the transformation formula is:

Z'＝Y ₀ *sinθ _x +Z ₀ cosθ _x ;

Z _ck =Z'*cosθ _y -X ₀ sinθ _y ;

Among them, X ₀ , Y ₀ , and Z ₀ are the original coordinate points of the reference plane, and Z _CK is the transformed Z _CK coordinate;

S223, calculate the average value Zmean and minimum variance Zsigma of all transformed Z _CK coordinates;

S224, taking the X-axis angle θ _x corresponding to the minimum variance Zsigma as the X-axis tilt angle α _x of the depth camera, and the corresponding Y-axis angle θ _y as the Y-axis tilt angle α _y of the depth camera, so as to obtain the tilt attitude Data: the mean Zmean of the Z _CK coordinates, the minimum variance Zsigma, the X-axis tilt angle α _x and the Y-axis tilt angle α _y .

In this embodiment, the X-axis angle, the Y-axis angle, and the distance from the reference plane between the depth camera and the reference plane are obtained according to step S22.

S23. Transform the scene point cloud coordinates according to the tilt attitude data to obtain the scene point cloud coordinates in the depth camera coordinate system. This step is specifically:

According to the X-axis tilt angle α _x and the Y-axis tilt angle α _y , use the transformation formula to transform the scene point cloud coordinates to obtain the scene point cloud coordinates in the depth camera coordinate system. The transformation formula is:

Z' _i =Y _io *sinα _x +Z _io cosα _x ;

X _i =Z' _i *sinα _y +X _io cosα _y ;

Y _i =Y _io *cosα _y -Z _io sinα _y ;

Z _i =Z' _i *cosα _y -X _io sinα _y ;

Among them, X _io , Y _io , Z _io are the original scene point cloud coordinates, and Xi _, Y _i , Z _i are the scene point cloud coordinates in the depth camera coordinate system.

S3. Process the scene point cloud coordinates in the depth camera coordinate system to obtain a coordinate set of the object to be measured. This step is specifically:

According to the screening formula, from the scene cloud coordinates under the depth camera coordinate system, filter out the X _i , Y _i , and _Zi coordinate point sets of the object to be measured that meet the conditions. The screening formula is:

|Zi-Zmean|＞N*Zsigma, where N is a positive number.

Step S3 of this embodiment is to remove the relevant information of other objects in the scene, and extract the coordinate data of the object to be measured.

S4. Calculate the length, width, and height of the object to be measured according to the coordinate set of the object to be measured, and multiply the length, width, and height to obtain the volume of the object to be measured. Said S4 specifically includes two steps of S41 and S42:

S41, according to the preset grid accuracy, calculate the X _i , Y _i coordinate points of the object to be measured and project them to the corresponding grid area in the reference plane, calibrate the connected area of the grid area, and count the size of each connected area;

S42, select the X _i , Y _i coordinate point set corresponding to the connected region with the largest area, and calculate the minimum circumscribed rectangle corresponding to the selected X _i , Y _i coordinate point through the principal component analysis method, and obtain the projection of the object to be measured into the reference plane length and width;

S43. Calculate the maximum difference between _Zi and Zmean to obtain the height of the object to be measured, and multiply the length, width and height together to obtain the volume of the object to be measured.

To sum up, compared with the existing logistics volume measurement scheme, this embodiment can be realized by using a common depth camera on the market in terms of hardware, and the cost is relatively low; when the camera is tilted, it can still accurately measure the volume to be measured in real time. volume of the object. In this embodiment, the tilt attitude of the camera is calibrated in advance. During the operation, only key steps such as multiplication, connected area calibration and principal component analysis are needed to calculate the length, width and height of the object to be measured, and then calculate the volume of the object to be measured, which can achieve very good results. real-time measurement. This embodiment supports the tilting of the camera during installation, which is easy to install and expands the measurement range. The point clouds output by many high-precision depth cameras in the existing market are unstructured. This embodiment does not require the structured point cloud data (point cloud coordinates), so it is easier to select the measurement equipment.

Those of ordinary skill in the art can realize that the units and method steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the relationship between hardware and software Interchangeability. In the above description, the composition and steps of each example have been generally described according to their functions. Whether these functions are executed by hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may use different methods to implement the described functions for each specific application, but such implementation should not be regarded as exceeding the scope of the present invention.

In the several embodiments provided in this application, it should be understood that the disclosed method and system may be implemented in other ways. For example, the division of the above units is only a logical function division, and there may be other division methods in actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored, or not implemented . The above units may or may not be physically separated, and components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment of the present invention.

Embodiment three:

This embodiment provides a depth camera, including a processor, an input device, an output device and a memory, the processor, the input device, the output device and the memory are connected to each other, the memory is used to store a computer program, and the computer program It includes program instructions, and the processor is configured to invoke the program instructions to execute the method described in Embodiment 1.

Compared with the existing logistics volume measurement solution, this embodiment can be realized by using a common depth camera on the market in terms of hardware, and the cost is low; when the camera is tilted, it can still accurately measure the volume of the object to be measured in real time. In this embodiment, the tilt attitude of the camera is calibrated in advance. During the operation, only key steps such as multiplication, connected area calibration and principal component analysis are needed to calculate the length, width and height of the object to be measured, and then calculate the volume of the object to be measured, which can achieve very good results. real-time measurement. This embodiment supports the tilting of the camera during installation, which is easy to install and expands the measurement range. The point clouds output by many high-precision depth cameras in the existing market are unstructured. This embodiment does not require the structured point cloud data (point cloud coordinates), so it is easier to select the measurement equipment.

It should be understood that in this embodiment, the so-called processor may be a central processing unit (Central Processing Unit, CPU), and the processor may also be other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application-specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like.

Input devices may include image capture devices, and output devices may include displays (LCD, etc.), speakers, and the like.

The memory, which can include read only memory and random access memory, provides instructions and data to the processor. A portion of the memory may also include non-volatile random access memory. For example, the memory may also store device type information.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, rather than limiting them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: It is still possible to modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the technical solutions of the various embodiments of the present invention. All of them should be covered by the scope of the claims and description of the present invention.

Claims (8)

1. A volume measurement method based on depth image, is characterized in that, comprises the following steps: S1, obtain the scene depth map containing the object to be measured, and obtain the scene point cloud coordinates; S2, transforming the coordinates of the scene point cloud to obtain the coordinates of the scene point cloud in the depth camera coordinate system; S3, processing the scene point cloud coordinates in the depth camera coordinate system to obtain the coordinate set of the object to be measured; S4. Calculate the length, width, and height of the object to be measured according to the coordinate set of the object to be measured, and multiply the length, width, and height to obtain the volume of the object to be measured. 2. A method of volume measurement based on a depth image according to claim 1, wherein the step S2 is specifically: S21, setting a reference plane in the scene depth map; S22, calculating the tilt attitude data of the depth camera according to the reference plane; S23. Transform the scene point cloud coordinates according to the tilt attitude data to obtain the scene point cloud coordinates in the depth camera coordinate system. 3. A kind of volume measurement method based on depth image according to claim 2, is characterized in that, described S22 is specifically: S221, setting the angle range between the X-axis and Y-axis of the depth camera and the reference plane normal, the angle range includes several X-axis angles θ _x and Y-axis angles θ _y ; S222, traversing each X-axis included angle and each Y-axis included angle, using a coordinate transformation formula to transform the Z _CK coordinates in the reference plane to obtain several transformed Z _CK coordinates, the transformation formula is: Z'＝Y ₀ *sinθ _x +Z ₀ cosθ _x ; Z _ck =Z'*cosθ _y -X ₀ sinθ _y ; Among them, X ₀ , Y ₀ , and Z ₀ are the original coordinate points of the reference plane, and Z _CK is the transformed Z _CK coordinate; S223, calculate the average value Zmean and minimum variance Zsigma of all transformed Z _CK coordinates; S224, taking the X-axis angle θ _x corresponding to the minimum variance Zsigma as the X-axis tilt angle α _x of the depth camera, and the corresponding Y-axis angle θ _y as the Y-axis tilt angle α _y of the depth camera, so as to obtain the tilt attitude Data: the mean Zmean of the Z _CK coordinates, the minimum variance Zsigma, the X-axis tilt angle α _x and the Y-axis tilt angle α _y . 4. A kind of volume measurement method based on depth image according to claim 3, is characterized in that, described S23 is specifically: According to the X-axis tilt angle α _x and the Y-axis tilt angle α _y , use the transformation formula to transform the scene point cloud coordinates to obtain the scene point cloud coordinates in the depth camera coordinate system. The transformation formula is: Z' _i =Y _io *sinα _x +Z _io cosα _x ; X _i =Z' _i *sinα _y +X _io cosα _y ; Y _i =Y _io *cosα _y -Z _io sinα _y ; Z _i =Z' _i *cosα _y -X _io sinα _y ; Among them, X _io , Y _io , Z _io are the original scene point cloud coordinates, and Xi _, Y _i , Z _i are the scene point cloud coordinates in the depth camera coordinate system. 5. A kind of volume measurement method based on depth image according to claim 4, is characterized in that, described S3 is specifically: According to the screening formula, from the scene cloud coordinates under the depth camera coordinate system, filter out the X _i , Y _i , and _Zi coordinate point sets of the object to be measured that meet the conditions. The screening formula is: |Zi-Zmean|＞N*Zsigma, where N is a positive number. 6. A kind of volume measurement method based on depth image according to claim 5, is characterized in that, described S4 is specifically: S41, according to the preset grid accuracy, calculate the X _i , Y _i coordinate points of the object to be measured and project them to the corresponding grid area in the reference plane, calibrate the connected area of the grid area, and count the size of each connected area; S42, select the X _i , Y _i coordinate point set corresponding to the connected region with the largest area, and calculate the minimum circumscribed rectangle corresponding to the selected X _i , Y _i coordinate point through the principal component analysis method, and obtain the projection of the object to be measured into the reference plane length and width; S43. Calculate the maximum difference between _Zi and Zmean to obtain the height of the object to be measured, and multiply the length, width and height together to obtain the volume of the object to be measured. 7. A volume measurement system based on a depth image, suitable for the volume measurement method based on a depth image according to any one of claims 1-6, comprising: The scene acquisition unit is used to obtain the scene depth map containing the object to be measured, and obtain the scene point cloud coordinates; The coordinate transformation unit is used to transform the coordinates of the scene point cloud to obtain the coordinates of the scene point cloud under the depth camera coordinate system; The object to be measured extraction unit is used to process the scene point cloud coordinates under the depth camera coordinate system to obtain the coordinate set of the object to be measured; The volume calculation unit is used to calculate the length, width and height of the test object according to the coordinate set of the test object, and multiply the length, width and height to obtain the volume of the test object. 8. A depth camera, characterized in that it includes a processor, an input device, an output device and a memory, the processor, the input device, the output device and the memory are connected to each other, the memory is used to store a computer program, and the computer The program includes program instructions, wherein the processor is configured to call the program instructions to execute the method according to any one of claims 1-6.