Volume measurement method and device and electronic equipment

Abstract

The invention discloses a volume measurement method and device and electronic equipment, and relates to the field of data processing. The method comprises the following steps: acquiring depth images of a cabinet freezer at a plurality of visual angles; constructing a three-dimensional space model corresponding to the cabinet freezer according to the depth image; controlling a laser sensor to project laser structured light with a preset pattern to the inner wall of the cabinet freezer; laser reflected light is obtained, and a laser reflection pattern of the laser reflected light is determined; determining the thickness of a frosting layer on the inner wall of the cabinet freezer according to the laser reflection pattern; according to the thickness of the frosting layer, correcting the three-dimensional space model to obtain a target three-dimensional space model; extracting the target three-dimensional space model to obtain an unoccupied space; and the volume of the unoccupied space is used as the available volume of the cabinet freezer. By implementing the technical scheme provided by the invention, the problem of volume measurement error caused by a frosting layer is effectively solved, and more accurate available volume data of the cabinet freezer is provided.

Description

Technical Field

[0001] The present application relates to the field of data processing, and in particular to a volume measurement method, device and electronic equipment. Background Art

[0002] With the rapid development of the food industry and the change in household consumption patterns, freezers have become essential equipment for commercial and household food storage. Accurately measuring the volume of freezers is essential for optimizing storage space, improving energy efficiency, and maintaining food safety. Commercial users rely on this data to plan inventory and operational strategies, while household users need to understand the available space to arrange food storage reasonably. Therefore, accurate and real-time measurement of the available volume of freezers has become particularly important.

[0003] At present, the freezer volume measurement technology in the related art mainly relies on traditional physical size measurement or uses basic electronic sensors to estimate the internal volume. These methods fail to take into account the possible frost inside the freezer, which will form an uneven ice layer on the inner wall, which has a significant impact on the actual available volume of the freezer. Therefore, the freezer volume measurement method in the related art has the problem of low accuracy.

[0004] Therefore, there is an urgent need for a volume measurement method, device and electronic equipment. Summary of the invention

[0005] The present application provides a volume measurement method, device and electronic equipment, which effectively solve the problem of volume measurement error caused by frost layer and provide more accurate available volume data of freezer.

[0006] In a first aspect of the present application, a volume measurement method is provided, the method comprising: obtaining depth images of a freezer at multiple viewing angles, the depth images being obtained by scanning different sides of the freezer with multiple infrared sensors; constructing a three-dimensional space model corresponding to the freezer based on the depth images; controlling a laser sensor to project a laser structured light of a preset pattern onto an inner wall of the freezer; obtaining laser reflected light, and determining a laser reflection pattern of the laser reflected light, the laser reflected light being reflected light corresponding to the laser structured light received by the laser sensor; determining a frost layer thickness on the inner wall of the freezer based on the laser reflection pattern; correcting the three-dimensional space model based on the frost layer thickness to obtain a target three-dimensional space model; extracting the target three-dimensional space model to obtain free space; and using the volume of the free space as the available volume of the freezer.

[0007] By adopting the above technical solution, through multi-view depth image acquisition and three-dimensional space reconstruction technology, a three-dimensional space model inside the freezer is accurately constructed, which comprehensively depicts the internal space structure and layout characteristics of the freezer, and provides a digital model basis for subsequent frost layer thickness measurement and spatial analysis. By using laser structured light projection and reflection pattern analysis technology, the rapid, non-destructive, and full-domain measurement of the frost layer thickness on the inner wall of the freezer is achieved. The thickness of the frost layer will occupy a certain internal space and affect the actual available volume of the freezer. By accurately measuring the thickness of the frost layer, the impact of frost on the volume can be quantified, and more real and effective available volume data can be obtained. This method effectively solves the problem of volume measurement error caused by the frost layer, provides more accurate freezer available volume data, and improves the accuracy of freezer volume measurement.

[0008] Optionally, constructing a three-dimensional space model corresponding to the freezer based on the depth image specifically includes: extracting feature points in the depth image; matching the feature points to obtain matching feature points; establishing a correspondence between the depth images based on the matching feature points; determining the relative posture between the depth images based on the corresponding relationship, and establishing a posture transformation matrix of each depth image based on the relative posture; using the posture transformation matrix to transform the depth image to a preset coordinate system, and performing triangular meshing processing to obtain the three-dimensional space model.

[0009] By adopting the above technical solution, by extracting the feature points of the depth image and matching them, the correspondence between the depth images of different perspectives is established, and then the relative posture between the depth images is determined according to the correspondence, and the posture transformation matrix is ​​established. The depth image is unified to the preset coordinate system using the posture transformation matrix, and then triangulated meshing is performed to finally obtain the three-dimensional space model of the freezer. This method makes full use of the three-dimensional information contained in the depth image, and realizes the effective registration and fusion of multi-perspective depth images through feature matching and posture estimation technology. The triangulated meshing processing further optimizes the geometric shape of the surface of the three-dimensional space model, making it more consistent with the topological structure of the real object. This method provides a geometric basis for the subsequent frosting layer thickness correction and free space extraction. The constructed three-dimensional space model has high accuracy and detail expression, providing users with more realistic and three-dimensional internal space information of the freezer.

[0010] Optionally, determining the thickness of the frost layer on the inner wall of the freezer based on the laser reflection pattern specifically includes: performing a preprocessing operation on the laser reflection pattern to obtain a target laser reflection pattern, the preprocessing operation including filtering and enhancement; extracting laser stripe features from the target laser reflection pattern; calculating the laser layer stripe deformation amount of the laser stripe features; matching the laser layer stripe deformation amount with a preset frost layer thickness calibration curve to obtain the frost layer thickness, the preset frost layer thickness calibration curve including a corresponding relationship between the frost layer thickness and the laser stripe deformation amount.

[0011] By adopting the above technical scheme, the laser reflection pattern is first filtered and enhanced to improve the image quality; then the laser stripe features are extracted and the laser layer stripe deformation is calculated; finally, the laser layer stripe deformation is matched with the preset frosting layer thickness calibration curve to obtain the corresponding frosting layer thickness. This method utilizes the principle of structured light three-dimensional imaging, and infers the thickness distribution of the frosting layer by analyzing the deformation degree of the projected laser stripes. The preprocessing operation effectively removes image noise, enhances the distinguishability of the laser stripes, and improves the accuracy of feature extraction. The calculation of the laser layer stripe deformation fully quantifies the changing characteristics of the stripe shape. The larger the deformation, the thicker the frosting layer. The preset frosting layer thickness calibration curve is used for matching, which simplifies the measurement process and improves the calculation efficiency. This method realizes fast, accurate and full-domain measurement of frosting layer thickness through non-contact optical measurement, and can obtain the spatial distribution information of the frosting layer. The thickness data of the frosting layer provides an important basis for the correction of the three-dimensional space model, which helps to improve the accuracy and authenticity of the three-dimensional space model.

[0012] Optionally, the calculation of the laser layer stripe deformation amount of the laser stripe feature specifically includes: determining the center line of the laser stripe feature, and extracting the coordinates of each pixel point on the center line; performing curve fitting on the center line according to the coordinates of each pixel point to obtain a fitting curve; sampling the fitting curve at each sampling point to obtain a target sampling point; calculating the curvature of the target sampling point on the fitting curve, and using the curvature as the laser layer stripe deformation amount corresponding to the target sampling point.

[0013] By adopting the above technical solution, the center line of the laser stripe feature is first determined, and the coordinates of the pixel points on the center line are extracted; then the center line is curve fitted to obtain a fitting curve; uniform sampling is performed on the fitting curve to obtain the target sampling points; finally, the curvature of the fitting curve at each sampling point is calculated and used as the laser layer stripe deformation variable of the sampling point. This method makes full use of the geometric characteristics of the laser stripe. Through center line extraction and curve fitting, the analytical expression of the stripe shape is obtained, making the calculation of the laser layer stripe deformation variable more accurate and efficient. The center line reflects the main trend of the stripe shape. By fitting the curve, noise interference can be filtered out and a smooth curve representation can be obtained. The curvature calculation of the sampling point further quantifies the curvature of the curve. The larger the curvature, the more serious the deformation of the laser stripe and the thicker the frosting layer. Characterizing the overall deformation characteristics of the stripe by the curvature of discrete sampling points can reduce the amount of calculation and improve the real-time performance of the extraction of the laser layer stripe deformation variable.

[0014] Optionally, the three-dimensional space model is corrected according to the frosting layer thickness to obtain a target three-dimensional space model, which specifically includes: mapping the frosting layer thickness to the three-dimensional space model to obtain a frosting layer thickness distribution model; and performing offset correction on the inner wall of the three-dimensional space model according to the frosting layer thickness distribution model to obtain the target three-dimensional space model.

[0015] By adopting the above technical solution, the measured frost layer thickness is first mapped to the three-dimensional space model to obtain the frost layer thickness distribution model; then the frost layer thickness distribution model is used to perform offset correction on the inner wall of the original three-dimensional model, and finally the target three-dimensional space model is obtained. This method realizes the effective fusion of frost layer thickness information and three-dimensional space model, fully utilizes the complementarity of multi-source data, and improves the accuracy and authenticity of three-dimensional space model correction. Through thickness mapping, a digital representation of the spatial distribution of the frost layer is established on the three-dimensional space model, which intuitively reflects the law of the thickness change of the frost layer. Through the fusion correction of the frost layer thickness distribution model and the three-dimensional space model, the real and effective internal space representation of the freezer is obtained, which effectively improves the accuracy and comprehensiveness of the volume information.

[0016] Optionally, the extracting of the target three-dimensional space model to obtain the free space specifically includes: performing plane cutting on the target three-dimensional space model to obtain multiple two-dimensional cross-sectional views; performing edge detection on each of the two-dimensional cross-sectional views to extract edge contours of the two-dimensional cross-sectional views; calculating the degree of closure of the edge contours, and determining an area with a degree of closure greater than a preset closure threshold as an area for placing items; determining an area in the two-dimensional cross-sectional view other than the area for placing items as an area where no items are placed; and obtaining the free space based on the area where no items are placed.

[0017] By adopting the above technical scheme, the target three-dimensional space model is firstly plane-cut to obtain a series of two-dimensional cross-sectional images; then the two-dimensional cross-sectional images are edge-detected to extract edge contours; by calculating the closure of the edge contours, the area with a closure greater than a preset closure threshold is determined as the area where items are placed, and the remaining area is the area where items are not placed, that is, the projection of the free space on the two-dimensional cross-sectional image. Finally, according to the free area projection of each two-dimensional cross-sectional image, the complete free space is reconstructed. This method makes full use of the hierarchical characteristics of the target three-dimensional space model, and converts the complex three-dimensional structure into a simple two-dimensional figure through plane slicing, which reduces the computational difficulty of space extraction. The two-dimensional edge detection technology is mature and can accurately obtain the contour information of each object. The introduction of closure further quantifies the shape characteristics of the edge contour. The greater the closure, the higher the filling rate of the content of the area, and the more likely it is to be an item placement area. By setting a preset closure threshold, the area where items are placed and the area where items are not placed can be automatically distinguished, and the preliminary extraction of the two-dimensional space distribution is realized. The free space reconstruction based on the layered cross-section can obtain the complete free space, which fully reflects the actual space utilization status inside the freezer. The extracted free space accurately reflects the actual usage of the freezer space, providing users with intuitive and quantitative space utilization information feedback, which helps users optimize storage solutions and improve space utilization.

[0018] Optionally, obtaining the free space based on the area where no items are placed specifically includes: spatially dividing the area where no items are placed to obtain a plurality of three-dimensional subspaces; calculating the volume of each of the three-dimensional subspaces, and determining the three-dimensional subspace whose volume is greater than a preset volume threshold as a target subspace; and integrating each of the target subspaces to obtain the free space.

[0019] By adopting the above technical scheme, the initially extracted free space is first spatially divided to obtain multiple three-dimensional subspaces; then the volume of each three-dimensional subspace is calculated, and the three-dimensional subspace larger than the preset volume threshold is determined as the target subspace; finally, the target subspaces are integrated to obtain the final free space. This method obtains a more refined free space through spatial division, which is convenient for quantitative analysis of the volume contribution of each region. The introduction of the preset volume threshold can automatically screen out the target subspaces with practical value, filter out the invalid free areas that are too narrow or fragmented, and improve the effectiveness of space utilization. The integration of the target subspace makes full use of the connectivity of adjacent subspaces, and obtains a complete and practical large free space through spatial merging, avoiding excessive discretization of space. While realizing refined local spatial analysis, this method takes into account the integrity and practicality of the macroscopic spatial layout, making the representation of the free space more comprehensive, reasonable, and close to actual needs. The combination of quantified target subspace information and integrated free space provides users with a multi-level and multi-scale basis for spatial utilization decision-making. Users can flexibly select and match different free spaces according to the size, quantity, placement requirements, etc. of the items, and formulate scientific and reasonable storage planning plans.

[0020] In a second aspect of the present application, a volume measurement device is provided, which includes: an acquisition module and a processing module, wherein: the acquisition module is used to acquire depth images of a freezer at multiple viewing angles, wherein the depth images are obtained by scanning the freezer from different sides by multiple infrared sensors; the processing module is used to construct a three-dimensional space model corresponding to the freezer according to the depth images; the processing module is also used to control the laser sensor to project a laser structured light of a preset pattern onto the inner wall of the freezer; the acquisition module is also used to acquire laser reflected light and determine a laser reflection pattern of the laser reflected light, wherein the laser reflected light is the reflected light corresponding to the laser structured light received by the laser sensor; the processing module is also used to determine the thickness of the frost layer on the inner wall of the freezer according to the laser reflection pattern; the processing module is also used to correct the three-dimensional space model according to the thickness of the frost layer to obtain a target three-dimensional space model; the processing module is also used to extract the target three-dimensional space model to obtain the free space; the processing module is also used to use the volume of the free space as the available volume of the freezer.

[0021] In the third aspect of the present application, an electronic device is provided, including a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes any one of the methods described above.

[0022] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores instructions, and when the instructions are executed, any of the methods described above is executed.

[0023] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. Through multi-view depth image acquisition and three-dimensional space reconstruction technology, the three-dimensional space model inside the freezer is accurately constructed, and the internal space structure and layout characteristics of the freezer are fully characterized, providing a solid digital model foundation for the subsequent frost layer thickness measurement and spatial analysis. Using laser structured light projection and reflection pattern analysis technology, the rapid, non-destructive, and full-domain measurement of the frost layer thickness on the inner wall of the freezer is achieved. The thickness of the frost layer will occupy a certain internal space and affect the actual available volume of the freezer. By accurately measuring the thickness of the frost layer, the impact of frost on the volume can be quantified, and more real and effective available volume data can be obtained. This method effectively solves the problem of volume measurement error caused by the frost layer, provides more accurate freezer available volume data, and improves the accuracy of freezer volume measurement.

[0024] 2. By extracting the feature points of the depth image and matching them, the correspondence between the depth images of different perspectives is established, and then the relative posture between the depth images is determined based on the correspondence, and the posture transformation matrix is ​​established. The depth image is unified to the preset coordinate system using the posture transformation matrix, and then triangulated meshing is performed to finally obtain the three-dimensional space model of the freezer. This method makes full use of the three-dimensional information contained in the depth image, and realizes the effective registration and fusion of multi-perspective depth images through feature matching and posture estimation technology. The triangulated meshing processing further optimizes the geometric shape of the surface of the three-dimensional space model, making it more consistent with the topological structure of the real object. This method provides a geometric basis for the subsequent frosting layer thickness correction and free space extraction. The constructed three-dimensional space model has high accuracy and detail expression, providing users with more realistic and three-dimensional internal space information of the freezer.

[0025] 3. First, filter and enhance the laser reflection pattern to improve the image quality; then extract the laser stripe features and calculate the laser layer stripe deformation; finally, match the laser layer stripe deformation with the preset frosting layer thickness calibration curve to obtain the corresponding frosting layer thickness. This method uses the principle of structured light three-dimensional imaging, and infers the thickness distribution of the frosting layer by analyzing the deformation degree of the projected laser stripes. The preprocessing operation effectively removes image noise, enhances the distinguishability of laser stripes, and improves the accuracy of feature extraction. The calculation of the laser layer stripe deformation fully quantifies the changing characteristics of the stripe shape. The larger the deformation, the thicker the frosting layer. The preset frosting layer thickness calibration curve is used for matching, which simplifies the measurement process and improves the calculation efficiency. This method realizes fast, accurate, and full-domain measurement of frosting layer thickness through non-contact optical measurement, and can obtain the spatial distribution information of the frosting layer. The thickness data of the frosting layer provides an important basis for the correction of the three-dimensional space model, which helps to improve the accuracy and authenticity of the three-dimensional space model. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a flow chart of a volume measurement method disclosed in an embodiment of the present application; Figure 2 It is a module schematic diagram of a volume measurement device disclosed in an embodiment of the present application; Figure 3 It is a structural schematic diagram of an electronic device disclosed in an embodiment of the present application.

[0027] Explanation of the reference numerals: 201, acquisition module; 202, processing module; 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0028] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0029] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0030] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0031] This application provides a volume measurement method, referring to Figure 1 , Figure 1 1 is a flow chart of a volume measurement method provided in an embodiment of the present application. The method is applied to a server and includes steps S101 and S108. The steps are as follows: Step S101: Acquire depth images of the freezer at multiple viewing angles, where the depth images are obtained by scanning the freezer from different sides using multiple infrared sensors.

[0032] In step S101, the server establishes a communication connection with multiple infrared sensors to obtain depth images of the freezer from multiple perspectives of the freezer from these infrared sensors. These infrared sensors can be independent devices installed at different positions inside the freezer, or they can be sensor arrays fixed on the inner wall of the freezer. Specifically, the server first establishes a data communication channel with each infrared sensor, such as connecting through wired or wireless methods such as Wi-Fi, Bluetooth, USB, etc. Then, the server sends a control instruction to these infrared sensors to start them to scan the freezer. During the scanning process, each infrared sensor performs a depth scan of the internal space of the freezer and the items placed from its own perspective. The infrared sensor emits infrared light to the inner surface of the freezer and receives the reflected infrared light. By measuring the time difference between emitting and receiving infrared light, the infrared sensor can calculate the distance between each sampling point inside the freezer and the infrared sensor, thereby generating a depth image. The value of each pixel in the depth image represents the distance from the sampling point to the infrared sensor. Since the items are placed inside the freezer at the same time, the depth image contains not only the depth information of the inner wall surface, but also the depth information of the surface of the placed items. By analyzing the depth image, objects and inner walls can be distinguished.

[0033] For example, suppose an infrared sensor is installed on each of the six surfaces inside the freezer: top, bottom, left, right, front, and back, forming a 3D scanning array. The server sends a command to start scanning to the six infrared sensors via Wi-Fi. After receiving the command, the infrared sensors start scanning the inside of the freezer and generate depth images from six different perspectives. After the infrared sensor completes the scan, it sends the generated depth image to the server via Wi-Fi. After the server receives the depth image data from different infrared sensors, it decodes and synchronizes the data to obtain depth images from multiple perspectives inside the freezer. The depth image of each perspective reflects the three-dimensional shape and depth information of the internal space and items of the freezer observed from that perspective. By acquiring depth images from different internal perspectives, the server can obtain all-round three-dimensional information about the internal space and items placed in the freezer, providing a data basis for the subsequent construction of an internal three-dimensional space model.

[0034] Step S102: constructing a three-dimensional space model corresponding to the freezer according to the depth image.

[0035] In step S102, feature points in the depth image are extracted; the feature points are matched to obtain matching feature points; a correspondence between the depth images is established based on the matching feature points; the relative posture between the depth images is determined based on the corresponding relationship, and a posture transformation matrix of each depth image is established based on the relative posture; the depth image is transformed into a preset coordinate system using the posture transformation matrix, and triangulated meshing is performed to obtain a three-dimensional space model.

[0036] Specifically, the server uses the SIFT feature point extraction algorithm to analyze each depth image and extract some points with significant features, called feature points. Feature points are corner points, edge points or other points that are easy to identify and match in the depth image. The server matches the feature points in the depth images of different perspectives to find the corresponding relationship between them. The matching principle is to find feature points representing the same physical point in different depth images. Through feature point matching, the association between depth images of different perspectives can be established. Based on the matched feature points, the server can determine the corresponding relationship between pixels between different depth images. In other words, a pixel in one depth image corresponds to which pixel in another depth image, and they represent the same physical point. Based on the corresponding relationship between the depth images, the server can use the ICP algorithm to calculate the relative pose between different depth images, that is, their relative position and direction in three-dimensional space. The server establishes a pose transformation matrix for each depth image based on the calculated relative pose. The pose transformation matrix describes how to transform the depth image from its own coordinate system to the common world coordinate system. Through the pose transformation matrix, all depth images can be unified into the same coordinate system. The server uses the pose transformation matrix to transform the pixels in each depth image into a preset coordinate system to obtain a 3D point cloud. The server performs triangulation on the 3D point cloud to generate a mesh model composed of triangular facets, i.e., a 3D spatial model of the interior space of the freezer.

[0037] Step S103: Control the laser sensor to project a laser structured light of a preset pattern onto the inner wall of the freezer.

[0038] In step S103, the server establishes a communication connection with the laser sensor, which can be done by wired or wireless means, such as USB, Wi-Fi, and Bluetooth. After the communication connection is established, the server sends a control instruction to the laser sensor to specify the pattern, intensity, and projection duration parameters of the laser structured light. After receiving the instruction from the server, the laser sensor generates a laser structured light of a preset pattern according to the specified parameters. Laser structured light is a pattern of some regular points, lines, stripes, or grids. The selection of the preset pattern should take into account factors such as easy recognition and strong robustness. The preset pattern can be a single point, a crosshair, a stripe, a dot matrix, or a grid. After the laser structured light is generated, the laser sensor projects it onto the inner wall of the freezer. Due to a layer of frost on the inner wall, the pattern of the laser structured light will be distorted. The thicker the frost layer, the more serious the distortion of the preset pattern. By analyzing the laser layer deformation of the preset pattern, the server can calculate the thickness of the frost layer.

[0039] Step S104: acquiring laser reflected light and determining a laser reflection pattern of the laser reflected light, where the laser reflected light is the reflected light corresponding to the laser structured light received by the laser sensor.

[0040] In step S104, the server obtains the reflected light after the laser structured light is irradiated on the frosted layer on the inner wall of the freezer through the laser sensor, and determines the corresponding laser reflection pattern based on the reflected light. Specifically, after the laser sensor projects a preset pattern of laser structured light onto the inner wall of the freezer, these laser structured lights will irradiate the surface of the frosted layer and be reflected back to the sensor by the frosted surface. Due to the ups and downs on the surface of the frosted layer, the reflected laser pattern will be deformed and carry information about the surface morphology of the frosted layer. The laser sensor receives the reflected laser reflection pattern through a built-in photodetector array and converts it into an electrical signal. These electrical signals carry the intensity and phase information of the reflected light, reflecting the modulation effect of the surface of the frosted layer on the laser pattern. The sensor amplifies, filters, and digitizes the electrical signal to obtain a frame of laser reflection pattern data. The server receives the laser reflection pattern data from the laser sensor through a communication interface with the laser sensor, such as USB or Ethernet.

[0041] Step S105: Determine the thickness of the frost layer on the inner wall of the freezer according to the laser reflection pattern.

[0042] In step S105, a preprocessing operation is performed on the laser reflection pattern to obtain a target laser reflection pattern, the preprocessing operation includes filtering and enhancement; laser stripe features are extracted from the target laser reflection pattern; the laser layer stripe deformation amount of the laser stripe features is calculated; the laser layer stripe deformation amount is matched with a preset frosting layer thickness calibration curve to obtain the frosting layer thickness, and the preset frosting layer thickness calibration curve includes a corresponding relationship between the frosting layer thickness and the laser stripe deformation amount.

[0043] In a possible implementation, calculating the laser layer stripe deformation amount of the laser stripe feature specifically includes: determining the center line of the laser stripe feature and extracting the coordinates of each pixel point on the center line; performing curve fitting on the center line according to the coordinates of each pixel point to obtain a fitting curve; sampling the fitting curve at each sampling point to obtain a target sampling point; calculating the curvature of the target sampling point on the fitting curve, and using the curvature as the laser layer stripe deformation amount corresponding to the target sampling point.

[0044] Specifically, the server finally determines the thickness distribution of the frost layer on the inner wall of the freezer through a series of processing and calculation based on the acquired laser reflection pattern. This process can be divided into four main stages: pattern preprocessing, stripe feature extraction, deformation calculation and thickness estimation. First, the server performs preprocessing operations on the original laser reflection pattern to remove noise interference in the pattern and enhance the visibility of the stripe features. The server uses median filtering and Gaussian filtering methods to smooth the image and eliminate discrete noise points. At the same time, the server also uses histogram equalization and Gamma correction methods to adjust the contrast and brightness of the image to make the stripe outline clearer. After preprocessing, a higher quality target laser reflection pattern is obtained. The server extracts laser stripe feature information from the target laser reflection pattern. The server uses image segmentation algorithms such as threshold segmentation and edge detection to divide the target laser reflection pattern into two parts: the stripe area and the background area. For each extracted laser stripe, its morphological characteristics are further analyzed, including extracting the center line of the stripe, calculating the stripe width and length, and obtaining the corresponding laser stripe features. After obtaining the laser stripe features, the server calculates the deformation of each laser stripe, which is a quantitative indicator for evaluating the degree of stripe bending deformation. Specifically, the server extracts the coordinates of a series of pixel points along the center line of the laser stripe; then, a curve fitting algorithm, such as spline interpolation and polynomial fitting, is used to fit these discrete points into a smooth curve (fitting curve); then, uniform sampling is performed on the fitting curve to obtain a set of target sampling points; finally, the curvature of the fitting curve at each target sampling point is calculated as the deformation variable at the target sampling point. The curvature reflects the degree of curvature of the curve. The larger the curvature, the more serious the stripe deformation and the thicker the frosting layer at the corresponding position. After obtaining the laser layer stripe deformation variable, the server uses the pre-established preset frosting layer thickness calibration curve to convert the laser layer stripe deformation variable into the frosting layer thickness. The preset frosting layer thickness calibration curve describes the corresponding relationship between the frosting layer thickness and the laser stripe deformation variable, which is usually obtained through experimental measurement. Specifically, a series of frosting layer samples of known thickness are manufactured on the inner wall of the freezer, and then the stripe deformation variable generated by each sample in the laser reflection pattern is measured, and the average value is taken after multiple measurements. Finally, the curve fitting method is used to obtain the functional relationship between the stripe deformation variable and the preset frosting layer thickness, that is, the preset frosting layer thickness calibration curve. In actual estimation, the server substitutes the deformation of each laser stripe into the preset frosting layer thickness calibration curve to calculate the thickness of the frosting layer at the position of the stripe. The server calculates all laser stripes in turn to obtain the distribution map of the frosting layer thickness of the entire inner wall.

[0045] Ideally, if the inner wall of the freezer is flat, the laser stripe projected onto the inner wall should be a straight line. However, due to the presence of the frosting layer, the inner wall surface is no longer flat, causing the laser stripe to deform and present a certain curved shape. The degree of deformation of the laser stripe is related to the thickness of the frosting layer. The thicker the frosting layer, the greater the degree of surface unevenness, and the more obvious the deformation of the laser stripe. Therefore, the thickness of the frosting layer can be indirectly estimated by measuring the deformation of the laser stripe. In order to quantify the degree of deformation of the laser stripe, the center line of the laser stripe needs to be extracted first. The center line of the laser stripe represents the basic characteristics of the shape of the laser stripe, corresponding to the intersection of the laser plane and the surface of the frosting layer. Since the center line of the laser stripe actually extracted may have noise and scatter points, in order to more accurately describe the shape of the laser stripe, it is necessary to perform curve fitting on the center line to obtain a smooth fitting curve for subsequent deformation calculation. Curvature is an important geometric parameter that describes the degree of curvature of a curve. Generally speaking, the greater the curvature of a curve, the greater the degree of curvature of the curve, and the more obvious the deformation of the laser stripe. Therefore, the curvature at each sampling point on the fitting curve can be used as the laser layer stripe deformation corresponding to the point.

[0046] Step S106: Correct the three-dimensional space model according to the thickness of the frosting layer to obtain a target three-dimensional space model.

[0047] In step S106, the thickness of the frost layer is mapped to the three-dimensional space model to obtain a frost layer thickness distribution model; according to the frost layer thickness distribution model, the inner wall of the three-dimensional space model is offset corrected to obtain a target three-dimensional space model.

[0048] Specifically, the server maps the frost layer thickness distribution map to the three-dimensional space model to obtain the frost layer thickness distribution model. The server corresponds each pixel on the frost thickness distribution map to a certain point in the three-dimensional space model according to its coordinate position, and uses the pixel grayscale value as the frost thickness attribute value at the point. By traversing all pixels of the frost layer thickness distribution map, a thickness attribute field consistent with the frost distribution can be formed on the surface of the three-dimensional space model. The thickness attribute field defines the frost layer thickness value at each position inside the three-dimensional space model. After obtaining the frost layer thickness distribution model, the server performs offset correction on the original three-dimensional space model of the inner wall. The server offsets each vertex on the surface of the three-dimensional space model along the opposite direction of its normal vector according to the frost thickness value at the point, that is, moves the vertex coordinates along the normal vector direction by a corresponding distance to obtain the new vertex coordinates after frosting. By offsetting all vertices in turn, a corrected inner wall three-dimensional model can be obtained, and the shape and position of each facet on the inner wall three-dimensional model are consistent with the inner wall after actual frosting, that is, the target three-dimensional space model.

[0049] Step S107: extract the target three-dimensional space model to obtain the free space.

[0050] In step S107, the target three-dimensional space model is plane-cut to obtain multiple two-dimensional cross-sectional images; edge detection is performed on each two-dimensional cross-sectional image to extract the edge contour of the two-dimensional cross-sectional image; the degree of closure of the edge contour is calculated, and the area with a degree of closure greater than a preset closure threshold is determined as the area where items are placed; the area other than the area where items are placed in the two-dimensional cross-sectional image is determined as the area where no items are placed; and the free space is obtained based on the area where no items are placed.

[0051] In a possible implementation, the free space is obtained based on the area where no items are placed, specifically including: spatially dividing the area where no items are placed to obtain multiple three-dimensional subspaces; calculating the volume of each three-dimensional subspace, and determining the three-dimensional subspace with a volume greater than a preset volume threshold as a target subspace; and integrating each target subspace to obtain the free space.

[0052] Specifically, the server performs plane cutting on the target three-dimensional space model to obtain multiple two-dimensional cross-sectional images. The cutting plane selects a direction parallel to the inner wall of the freezer, such as the horizontal direction or the vertical direction. The spacing of the cutting plane can be set according to the required spatial resolution. The smaller the spacing, the more cross sections there are, the higher the analysis accuracy, but the greater the amount of calculation. The server implements cutting through the geometric algorithm of the target three-dimensional space model, such as intersecting the plane with the triangular facet to obtain the cross-sectional contour line. After cutting, the target three-dimensional space model is converted into a series of two-dimensional cross-sectional images, which facilitates subsequent analysis. The server performs edge detection on each two-dimensional cross-sectional image and extracts its edge contour. Edge detection can use various operators in image processing, such as Canny and Sobel, to find the pixels with the most drastic brightness changes in the cross-sectional image, that is, the edge points. By connecting these edge points, the edge contour line of the cross-sectional image can be obtained. The edge contour line reflects the plane distribution of the placement of items and space occupancy inside the freezer. In order to determine which areas in the cross-sectional image are placed items and which are not placed items, the server calculates the degree of closure of each closed contour area. The degree of closure is measured by the ratio of the length of the contour line to the area. The greater the degree of closure, the more regular and full the contour is, and the more likely it is that the object is located. A preset closure threshold is pre-set inside the server, and the closed area greater than the preset closure threshold is identified as the area where the object is placed, and the rest of the area is the area where the object is not placed, that is, the projection of the free space on the cross-sectional image. The preset closure threshold can be determined and set based on the research experience of industry experts on freezers and the experience of the characteristics of the placed objects. This application does not limit the specific value of the preset closure threshold.

[0053] After obtaining the free space of each cross-sectional view, the server further extracts the overall free space. Specifically, the server divides the area without items into multiple three-dimensional subspaces. Each three-dimensional subspace is composed of a group of free cross-sectional areas connected end to end. Then, the server calculates the volume of each three-dimensional subspace and sets a preset volume threshold. The subspace with a volume greater than the preset volume threshold is considered to be a free space that can be effectively utilized and is recorded as a target subspace; the three-dimensional subspace with a volume less than the preset volume threshold may be a narrow gap or an irregular area, which has little practical value and can be ignored. The preset volume threshold is used to determine which three-dimensional subspaces are large enough and should be considered as valid target subspaces. The specific value of the preset volume threshold can take into account the overall utilization efficiency of the freezer, set a practical volume threshold, and avoid too small space from being calculated. These spaces may not actually be effectively utilized. The specific value of the preset volume threshold is not limited in this application. Finally, the server integrates all target subspaces according to the connectivity of adjacent target subspaces. Connectivity means that two target subspaces are adjacent on a certain surface, and there is no space occupied by items in the middle. The server can determine the connectivity by analyzing the spatial coordinates of each target subspace. For example: the spatial range of target subspace A is (x1~x2, y1~y2, z1~z2); the spatial range of target subspace B is (x3~x4, y3~y4, z3~z4); if x2=x3, and y1<=y4<=y2, z1<=z4<=z2, then A and B are connected in the X-axis direction; if y2=y3, and x1<=x4<=x2, z1<=z4<=z2, then A and B are connected in the Y-axis direction; if z2=z3, and x1<=x4<=x2, y1<=y4<=y2, then A and B are connected in the Z-axis direction. If the two target subspaces are connected in any axis, they can be merged into a larger free space. The range of the merged free space takes the minimum and maximum values ​​of the two subspaces in each axis. The server compares all target subspaces in pairs, finds all connected target subspaces and merges them. The merged free space continues to compare connectivity with other target subspaces until no more merges are possible. In the end, multiple unconnected free spaces may be obtained, which represent all the space that can be effectively used inside the freezer.

[0054] For example, assume that the internal space size of a vertical freezer is 1000mm×600mm×1500mm. The server first cuts its target three-dimensional space model into 30 horizontal cross-sections at a spacing of 50mm along the vertical direction. Then, edge detection and closure calculation are performed on each cross-section, and the area where items are placed and the area where items are not placed are identified with a preset closure threshold of 0.8. The server divides the area where items are not placed according to the connectivity of the free area to obtain several three-dimensional subspaces. Assume that a total of 100 three-dimensional subspaces are obtained, of which 20 have a volume greater than 10 liters and are determined as target subspaces. Finally, these 20 target subspaces are integrated. If they are connected in the vertical direction and the overall space after the merger still has a regular shape, they are merged into a larger free space. After the merger, it is assumed that 5 free spaces are finally obtained, namely the space between 2 drawers, 1 bottom space, 1 top space, and 1 irregular space near the side wall.

[0055] Step S108: taking the volume of the free space as the available volume of the freezer.

[0056] In step S108, for each target subspace in the available volume, the server uses the corresponding volume formula to calculate according to its geometric shape and size information. For example, for a regular rectangular subspace, its volume is equal to the product of the length, width and height; for an irregular polyhedral subspace, a triangulation method can be used to decompose it into multiple tetrahedral units, and then the volume of each tetrahedron is summed. By traversing all target subspaces and accumulating their volumes, the server can obtain the volume of each free space. Then, by adding up the volumes of all free spaces, the total available volume inside the freezer is obtained. This available volume represents the maximum amount of space that can be used to store additional items in the freezer in its current placement state, and is a key indicator for measuring the efficiency of freezer space utilization. After obtaining the available volume, the server displays it to the user together with the target three-dimensional space model.

[0057] Reference Figure 2The present application also provides a volume measurement device, which is a server, and the server includes: an acquisition module 201 and a processing module 202, wherein: the acquisition module 201 is used to acquire depth images of the freezer at multiple perspectives, and the depth images are obtained by scanning multiple infrared sensors from different sides of the freezer; the processing module 202 is used to construct a three-dimensional space model corresponding to the freezer according to the depth images; the processing module 202 is also used to control the laser sensor to project a laser structured light of a preset pattern to the inner wall of the freezer; the acquisition module 201 is also used to acquire laser reflected light and determine a laser reflection pattern of the laser reflected light, and the laser reflected light is the reflected light corresponding to the laser structured light received by the laser sensor; the processing module 202 is also used to determine the thickness of the frost layer on the inner wall of the freezer according to the laser reflection pattern; the processing module 202 is also used to correct the three-dimensional space model according to the thickness of the frost layer to obtain a target three-dimensional space model; the processing module 202 is also used to extract the target three-dimensional space model to obtain the free space; the processing module 202 is also used to use the volume of the free space as the available volume of the freezer.

[0058] In one possible implementation, the processing module 202 constructs a three-dimensional space model corresponding to the freezer based on the depth image, specifically including: the processing module 202 extracts feature points in the depth image; matches the feature points to obtain matching feature points; the processing module 202 establishes a correspondence between the depth images based on the matching feature points; the processing module 202 determines the relative posture between the depth images based on the corresponding relationship, and establishes a posture transformation matrix of each depth image based on the relative posture; the processing module 202 uses the posture transformation matrix to transform the depth image to a preset coordinate system, and performs triangulated meshing to obtain a three-dimensional space model.

[0059] In one possible embodiment, the processing module 202 determines the thickness of the frost layer on the inner wall of the freezer based on the laser reflection pattern, specifically including: the processing module 202 performs a preprocessing operation on the laser reflection pattern to obtain a target laser reflection pattern, the preprocessing operation includes filtering and enhancement; the processing module 202 extracts the laser stripe feature from the target laser reflection pattern; the processing module 202 calculates the laser layer stripe deformation amount of the laser stripe feature; the processing module 202 matches the laser layer stripe deformation amount with a preset frost layer thickness calibration curve to obtain the frost layer thickness, the preset frost layer thickness calibration curve includes the correspondence between the frost layer thickness and the laser stripe deformation amount.

[0060] In a possible implementation, the processing module 202 calculates the laser layer stripe deformation amount of the laser stripe feature, specifically including: the processing module 202 determines the center line of the laser stripe feature and extracts the coordinates of each pixel point on the center line; the processing module 202 performs curve fitting on the center line according to the coordinates of each pixel point to obtain a fitting curve; the processing module 202 samples the fitting curve at each sampling point to obtain a target sampling point; the processing module 202 calculates the curvature of the target sampling point on the fitting curve, and uses the curvature as the laser layer stripe deformation amount corresponding to the target sampling point.

[0061] In a possible implementation, the processing module 202 corrects the three-dimensional space model according to the thickness of the frost layer to obtain a target three-dimensional space model, specifically including: the processing module 202 maps the thickness of the frost layer to the three-dimensional space model to obtain a frost layer thickness distribution model; the processing module 202 performs offset correction on the inner wall of the three-dimensional space model according to the frost layer thickness distribution model to obtain a target three-dimensional space model.

[0062] In a possible implementation, the processing module 202 extracts the target three-dimensional space model to obtain the free space, which specifically includes: the processing module 202 performs plane cutting on the target three-dimensional space model to obtain multiple two-dimensional cross-sectional views; the processing module 202 performs edge detection on each two-dimensional cross-sectional view to extract the edge contour of the two-dimensional cross-sectional view; the processing module 202 calculates the degree of closure of the edge contour, and determines the area with a degree of closure greater than a preset degree of closure threshold as the area for placing items; the processing module 202 determines the area in the two-dimensional cross-sectional view other than the area for placing items as the area where no items are placed; the processing module 202 obtains the free space based on the area where no items are placed.

[0063] In a possible implementation, the processing module 202 obtains the free space based on the area where no items are placed, specifically including: the processing module 202 spatially divides the area where no items are placed to obtain multiple three-dimensional subspaces; the processing module 202 calculates the volume of each three-dimensional subspace, and determines the three-dimensional subspace with a volume greater than a preset volume threshold as a target subspace; the processing module 202 integrates each target subspace to obtain the free space.

[0064] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0065] The present application also provides an electronic device. Figure 3 , Figure 3 The electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0066] The communication bus 302 is used to realize the connection and communication between these components.

[0067] The user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0068] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0069] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0070] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally also be at least one storage device located away from the aforementioned processor 301. Refer to Figure 3 , the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module and an application program of a volume measurement method.

[0071] exist Figure 3 In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call an application program storing a volume measurement method in the memory 305. When executed by one or more processors 301, the electronic device 300 executes one or more of the methods described in the above embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited to the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0072] The present application also provides a computer-readable storage medium, which stores instructions. When executed by one or more processors 301, the electronic device 300 executes one or more of the methods described in the above embodiments.

[0073] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0074] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0075] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0076] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0077] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0078] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, those skilled in the art will easily think of other embodiments of the present disclosure.

[0079] This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art not described in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A volume measurement method, characterized in that: The method comprises: Acquire depth images of the freezer at multiple viewing angles, where the depth images are obtained by scanning the freezer from different sides of the freezer using multiple infrared sensors; Constructing a three-dimensional spatial model corresponding to the freezer according to the depth image; Controlling the laser sensor to project a laser structured light of a preset pattern onto the inner wall of the freezer; Acquire laser reflected light, and determine a laser reflection pattern of the laser reflected light, wherein the laser reflected light is reflected light corresponding to the laser structured light received by the laser sensor; Determining the thickness of the frost layer on the inner wall of the freezer according to the laser reflection pattern; Correcting the three-dimensional space model according to the thickness of the frosting layer to obtain a target three-dimensional space model; Extracting the target three-dimensional space model to obtain free space; The volume of the empty space is used as the available volume of the freezer.

2. The method according to claim 1, characterized in that The constructing a three-dimensional space model corresponding to the freezer according to the depth image specifically includes: Extracting feature points in the depth image; Matching the feature points to obtain matching feature points; Establishing a corresponding relationship between the depth images according to the matching feature points; Determine the relative postures between the depth images according to the corresponding relationship, and establish a posture transformation matrix of each depth image according to the relative postures; The depth image is transformed into a preset coordinate system using the posture transformation matrix, and triangulated meshing is performed to obtain the three-dimensional space model.

3. The method according to claim 1, characterized in that Determining the thickness of the frost layer on the inner wall of the freezer according to the laser reflection pattern specifically includes: Performing a preprocessing operation on the laser reflection pattern to obtain a target laser reflection pattern, wherein the preprocessing operation includes filtering and enhancing; extracting laser stripe features from the target laser reflection pattern; Calculating the laser layer stripe deformation amount of the laser stripe feature; The laser stripe deformation amount is matched with a preset frosting layer thickness calibration curve to obtain the frosting layer thickness, wherein the preset frosting layer thickness calibration curve includes a corresponding relationship between the frosting layer thickness and the laser stripe deformation amount.

4. The method according to claim 3, characterized in that The step of calculating the laser layer stripe deformation amount of the laser stripe feature specifically includes: Determine the center line of the laser stripe feature, and extract the coordinates of each pixel point on the center line; Performing curve fitting on the center line according to the coordinates of each pixel point to obtain a fitting curve; Sampling the fitting curve at each sampling point to obtain a target sampling point; The curvature of the target sampling point on the fitting curve is calculated, and the curvature is used as the laser layer stripe deformation amount corresponding to the target sampling point.

5. The method according to claim 1, characterized in that The step of correcting the three-dimensional space model according to the thickness of the frosting layer to obtain a target three-dimensional space model specifically includes: Mapping the frosting layer thickness to the three-dimensional space model to obtain a frosting layer thickness distribution model; According to the frosting layer thickness distribution model, the inner wall of the three-dimensional space model is offset corrected to obtain the target three-dimensional space model.

6. The method according to claim 1, characterized in that The extracting of the target three-dimensional space model to obtain the free space specifically includes: Performing plane cutting on the target three-dimensional space model to obtain a plurality of two-dimensional cross-sectional images; Performing edge detection on each of the two-dimensional cross-sectional images to extract edge contours of the two-dimensional cross-sectional images; Calculating the degree of closure of the edge contour, and determining an area where the degree of closure is greater than a preset closure threshold as an area for placing items; Determine the area in the two-dimensional cross-sectional image other than the area where the objects are placed as an area where no objects are placed; The free space is obtained according to the area where no items are placed.

7. The method according to claim 6, characterized in that The obtaining of the free space according to the area where no items are placed specifically includes: Performing spatial division on the area where no items are placed to obtain a plurality of three-dimensional subspaces; Calculating the volume of each of the three-dimensional subspaces, and determining the three-dimensional subspace whose volume is greater than a preset volume threshold as a target subspace; The target subspaces are integrated to obtain the free space.

8. A volume measuring device, characterized in that: The device comprises an acquisition module (201) and a processing module (202), wherein: The acquisition module (201) is used to acquire depth images of the freezer at multiple viewing angles, wherein the depth images are obtained by scanning the freezer from different sides using multiple infrared sensors; The processing module (202) is used to construct a three-dimensional space model corresponding to the freezer according to the depth image; The processing module (202) is further used to control the laser sensor to project a laser structured light of a preset pattern onto the inner wall of the freezer; The acquisition module (201) is further used to acquire laser reflected light and determine a laser reflection pattern of the laser reflected light, wherein the laser reflected light is the reflected light corresponding to the laser structured light received by the laser sensor; The processing module (202) is further used to determine the thickness of the frost layer on the inner wall of the freezer according to the laser reflection pattern; The processing module (202) is further used to calibrate the three-dimensional space model according to the thickness of the frosting layer to obtain a target three-dimensional space model; The processing module (202) is further used to extract the target three-dimensional space model to obtain the free space; The processing module (202) is further configured to use the volume of the vacant space as the available volume of the freezer.

9. An electronic device, characterized in that: The electronic device (300) comprises a processor (301), a memory (305), a user interface (303) and a network interface (304), wherein the memory (305) is used to store instructions, the user interface (303) and the network interface (304) are used to communicate with other devices, and the processor (301) is used to execute the instructions stored in the memory (305) so that the electronic device (300) executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is executed.

Images