Methods, apparatus, equipment and storage media for determining target point clouds
By projecting a sinusoidal fringe pattern onto the target object and acquiring deformation images using two cameras, high-key pixels are selected to generate the target point cloud, thus solving the problem of low accuracy of monocular cameras and achieving higher-precision point cloud determination.
Patent Information
- Application Number
- CN202211742095.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-12-29
- Publication Date
- 2025-10-28
- Estimated Expiration
- 2042-12-29
AI Technical Summary
In existing technologies, target point cloud determination based on monocular cameras suffers from low accuracy, especially when the target object is occluded or has a highly reflective surface, resulting in incomplete imaging.
Two cameras are used in conjunction with a projector to project a sinusoidal fringe pattern onto the target object to obtain the deformed image. The target point cloud is generated by selecting high-key pixels, and the three-dimensional coordinates are determined using a unified coordinate system.
It improves the accuracy of target point cloud determination, avoids the problem of incomplete imaging by monocular cameras, selects clearer pixels, and generates more accurate point clouds.
Smart Images
Figure CN116228946B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of computer vision, and more particularly to a method, apparatus, device, and storage medium for determining target point clouds. Background Technology
[0002] Currently, when determining the point cloud of a target object, images acquired by a monocular camera are used. A projector projects an coded pattern onto the target object, the monocular camera acquires the image of the target object encoded by the coded pattern, and the computing module decodes it to obtain its three-dimensional coordinates in the world coordinate system. However, when acquiring images with a monocular camera, there is a problem of incomplete imaging, such as when the target object is occluded or its surface is highly reflective. Therefore, existing technologies suffer from low accuracy in determining the point cloud of a target object based on a monocular camera.
[0003] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention
[0004] The main objective of this invention is to provide a method for determining target point clouds, aiming to solve the problem of low accuracy in the determination of target point clouds based on monocular cameras in the prior art.
[0005] To achieve the above objectives, this application provides a method for determining a target point cloud, the method comprising:
[0006] Control the preset projector to project a preset sine fringe pattern onto the target object;
[0007] A first image captured by a preset first camera is acquired, and a second image captured by a preset second camera is acquired, wherein the sinusoidal fringe pattern is deformed on the target object, the deformation amount corresponds to the size of the target object, and the first image and the second image are images of the target object covered with the deformed sinusoidal fringe pattern;
[0008] A target pixel is selected from the pixels of the first image and the pixels of the second image, wherein the camera corresponding to the target pixel is the target camera;
[0009] Based on the target pixels, a target point cloud of the target object is generated.
[0010] In one possible implementation of this application, the step of selecting the target pixel from the pixels of the first image and the pixels of the second image includes:
[0011] The first image is modulated to obtain a first modulation degree of the first image, and the second image is modulated to obtain a second modulation degree of the second image;
[0012] Based on the first modulation degree and the second modulation degree, the pixel corresponding to the high modulation degree is selected as the target pixel from the pixels of the first image and the pixels of the second image.
[0013] In one possible implementation of this application, the step of selecting the target pixel from the pixels of the first image and the pixels of the second image includes:
[0014] When it is determined that the sum of the number of the first image and the second image reaches a preset number, a target pixel is selected from the pixels of the first image and the pixels of the second image.
[0015] In one possible implementation of this application, the step of generating a target point cloud of the target object based on the target pixels includes:
[0016] Establish a unified coordinate system;
[0017] Based on the target camera and the projector, the three-dimensional coordinates of the target pixel in the unified coordinate system are determined and the target point cloud of the target object is generated.
[0018] In one possible implementation of this application, the step of determining a unified coordinate system includes:
[0019] Transform the coordinate systems of the first camera and the second camera into the coordinate system of the projector;
[0020] The coordinate system of the projector is determined to be the unified coordinate system.
[0021] In one possible implementation of this application, the step of selecting the pixel corresponding to the high modulation degree from the pixels of the first image and the pixels of the second image as the target pixel based on the first modulation degree and the second modulation degree includes:
[0022] When the target object cannot be fully imaged, based on the first modulation degree and the second modulation degree, the pixel corresponding to the high modulation degree is selected as the target pixel from the pixels of the first image and the pixels of the second image.
[0023] In one possible implementation of this application, the target point cloud determination device is an NX development board.
[0024] Furthermore, to achieve the above objectives, this application also provides a target point cloud determination device, the target point cloud determination device comprising:
[0025] The control module is used to control the preset projector to project a preset sine fringe pattern onto the target object;
[0026] The acquisition module is used to acquire a first image captured by a preset first camera and a second image captured by a preset second camera, wherein the sinusoidal fringe pattern is deformed on the target object, the deformation amount corresponds to the size of the target object, and the first image and the second image are images of the target object covered with the deformed sinusoidal fringe pattern;
[0027] The selection module is used to select a target pixel from the pixels of the first image and the pixels of the second image, wherein the camera corresponding to the target pixel is the target camera;
[0028] The generation module is used to generate a target point cloud of the target object based on the target pixels.
[0029] In addition, to achieve the above objectives, this application also provides a target point cloud determination device, which is a physical node device. The target point cloud determination device includes: a memory, a processor, and a target point cloud determination program stored in the memory and executable on the processor. The processor executes the target point cloud determination program to implement the steps of the target point cloud determination method.
[0030] In addition, to achieve the above objectives, this application also provides a storage medium storing a program for implementing a method for determining a target point cloud, wherein when the program for determining the target point cloud is executed by a processor, it implements the steps of the method for determining the target point cloud described above.
[0031] This application provides a method, apparatus, device and storage medium for determining target point clouds. Compared with the problem of low determination accuracy when determining target point clouds based on a monocular camera in the prior art, in this application, a preset projector is controlled to project a preset sine fringe pattern on the target object.
[0032] A first image captured by a preset first camera and a second image captured by a preset second camera are acquired. The sinusoidal fringe pattern deforms on the target object, with the deformation corresponding to the size of the target object. The first and second images are images of the target object overlaid with the deformed sinusoidal fringe pattern. Target pixels are selected from the pixels of the first and second images, where the camera corresponding to the target pixel is the target camera. A target point cloud of the target object is generated based on the target pixel. In this application, when two cameras are used to determine the target point cloud, the target pixel is selected based on the projected sinusoidal fringe pattern. This avoids the problem of incomplete imaging when using only a single monocular camera, allowing for the selection of clearer pixels, resulting in better target point cloud determination and improved accuracy. Attached Figure Description
[0033] Figure 1 This is a flowchart illustrating the first embodiment of the method for determining the target point cloud in this application.
[0034] Figure 2 This is a schematic diagram of the target point cloud determination device in the third embodiment of the target point cloud determination method of this application;
[0035] Figure 3 This is a schematic diagram of the device structure of the hardware operating environment involved in the fourth embodiment of the method for determining the target point cloud of this application. Detailed Implementation
[0036] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.
[0037] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, components, features, and elements with the same names in different embodiments of this application may have the same meaning or different meanings, the specific meaning of which must be determined by its interpretation in that specific embodiment or further in conjunction with the context of that specific embodiment.
[0038] It should be understood that although the terms first, second, third, etc., may be used herein to describe various information, such information should not be limited to these terms. These terms are used only to distinguish information of the same type from one another. For example, without departing from the scope of this document, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if," as used herein, may be interpreted as "when," "when," or "in response to determination." Furthermore, as used herein, the singular forms "a," "an," and "the" are intended to also include the plural forms unless the context indicates otherwise. It should be further understood that the terms "comprising," "including," indicate the presence of the stated feature, step, operation, element, component, item, kind, and / or group, but do not exclude the presence, occurrence, or addition of one or more other features, steps, operations, elements, components, items, kinds, and / or groups. The terms "or," "and / or," "including at least one of the following," etc., as used in this application, may be interpreted as inclusive, or mean any one or any combination thereof. For example, "including at least one of the following: A, B, C" means "any one of the following: A; B; C; A and B; A and C; B and C; A and B and C." Similarly, "A, B, or C" or "A, B, and / or C" means "any one of the following: A; B; C; A and B; A and C; B and C; A and B and C." Exceptions to this definition only occur when the combination of elements, functions, steps, or operations is inherently mutually exclusive in some way.
[0039] It should be understood that although the steps in the flowcharts of this application's embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.
[0040] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”
[0041] It should be noted that step designations such as S10 and S20 are used in this document for the purpose of more clearly and concisely describing the corresponding content, and do not constitute a substantial limitation on the order. In specific implementation, those skilled in the art may execute S20 first and then S10, etc., but these should all be within the protection scope of this application.
[0042] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.
[0043] In the following description, the use of suffixes such as "module," "part," or "unit" to denote elements is solely for the purpose of illustrative purposes and has no specific meaning in itself. Therefore, "module," "part," or "unit" may be used interchangeably.
[0044] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0045] Example 1
[0046] This application provides a method for determining a target point cloud. In the first embodiment of this method, referring to... Figure 1 A device for determining target point clouds, the method comprising:
[0047] Step S10: Control the preset projector to project a preset sine fringe pattern onto the target object;
[0048] Step S20: Obtain a first image captured by a preset first camera and a second image captured by a preset second camera, wherein the sinusoidal fringe pattern is deformed on the target object, the deformation amount corresponds to the size of the target object, and the first image and the second image are images of the target object covered with the deformed sinusoidal fringe pattern;
[0049] Step S30: Select a target pixel from the pixels of the first image and the pixels of the second image, wherein the camera corresponding to the target pixel is the target camera;
[0050] Step S40: Based on the target pixels, generate a target point cloud of the target object.
[0051] This embodiment aims to improve the accuracy of target point cloud determination.
[0052] As an example, the target object can be the goods to be transported by the AGV vehicle, and the target point cloud is determined for the goods to be transported.
[0053] As an example, the first camera and the second camera are respectively positioned on the left and right sides of the target object.
[0054] As an example, a projector projects a preset sine fringe pattern onto the goods to be transported. Due to the shape of the goods themselves, the sine fringe pattern is deformed on the surface of the goods, thereby obtaining the three-dimensional information of the goods to be transported.
[0055] As an example, the image captured by the first camera after the sinusoidal stripes are deformed is the first image, and the image captured by the second camera after the sinusoidal stripes are deformed is the second image. Pixels are selected from either the first or second image, and these selected pixels are used as target pixels. The target point cloud is then determined based on these target pixels.
[0056] As an example, the target point cloud is determined using the NX development board. Compared to a PC, the NX development board generates target point clouds from images much faster, and it avoids the latency issues associated with acquiring cached data. Using a PC, however, requires connecting the projector and both cameras to the PC, resulting in significant hardware inconvenience. Furthermore, during long-distance data transmission, bandwidth limitations can lead to data loss during camera-captured images. The NX development board avoids this data loss problem during long-distance transmission. Its simplified interface and ease of operation shorten the development cycle.
[0057] The specific steps are as follows:
[0058] Step S10: Control the preset projector to project a preset sine fringe pattern onto the target object;
[0059] As an example, the target point cloud determination device controls a preset industrial projector to project a preset sine fringe pattern onto the goods to be transported.
[0060] Step S20: Obtain a first image captured by a preset first camera and a second image captured by a preset second camera, wherein the sinusoidal fringe pattern is deformed on the target object, the deformation amount corresponds to the size of the target object, and the first image and the second image are images of the target object covered with the deformed sinusoidal fringe pattern;
[0061] As an example, a camera is set up on the left and right sides of the goods to be moved, which are called the left camera and the right camera respectively. The left camera is the first camera and the right camera is the second camera.
[0062] As an example, the target point cloud determination device acquires a first image captured by a first camera and a second image captured by a second camera, both of which are images of the target object covered with a deformed sinusoidal fringe pattern.
[0063] Step S30: Select a target pixel from the pixels of the first image and the pixels of the second image, wherein the camera corresponding to the target pixel is the target camera;
[0064] As an example, a target pixel is selected from the pixels of the first image and the pixels of the second image. The camera corresponding to the target pixel is the target camera. For example, if a pixel in the first image taken by the first camera is selected as the target pixel, then the target camera is the first camera. If a pixel in the second image taken by the second camera is selected as the target pixel, then the target camera is the second camera.
[0065] As an example, when the goods to be transported are partially obscured, or when the first camera takes a picture, there is high reflectivity at certain angles, the target object cannot be fully imaged. When the target object cannot be fully imaged, the pixel corresponding to the high-key ratio is selected from the pixels of the first image and the pixels of the second image as the target pixel, wherein the camera corresponding to the target pixel is the target camera.
[0066] Step S30, the step of selecting the target pixel from the pixels of the first image and the pixels of the second image, includes steps S31-S32:
[0067] Step S31: Modulate the first image to obtain a first modulation degree of the first image, and modulate the second image to obtain a second modulation degree of the second image;
[0068] As an example, the modulation depth corresponding to the first image acquired by the first camera is obtained by modulation, i.e., the first modulation depth, and the modulation depth corresponding to the second image acquired by the second camera is obtained by modulation, i.e., the second modulation depth. The projected sinusoidal fringe pattern produces deformation on the target object, and the modulation depth can reflect the amount of three-dimensional information of the target object obtained from the deformed sinusoidal fringes. The larger the modulation depth, the more three-dimensional information can be obtained. In this embodiment, the image pixel point corresponding to the larger modulation depth is selected as the target pixel point.
[0069] Step S32: Based on the first modulation degree and the second modulation degree, select the pixel corresponding to the high modulation degree from the pixels of the first image and the pixels of the second image as the target pixel.
[0070] As an example, based on a first modulation degree and a second modulation degree, the image pixel with the larger modulation degree is selected as the target pixel. If the first modulation degree is greater than the second modulation degree, the pixel of the first image is selected as the target pixel; if the second modulation degree is greater than the first modulation degree, the pixel of the second image is selected as the target pixel.
[0071] Step S40: Based on the target pixels, generate a target point cloud of the target object.
[0072] Step S40, the step of generating the target point cloud of the target object based on the target pixels, includes steps S41-S42:
[0073] Step S41: Determine a unified coordinate system;
[0074] Step S42: Based on the target camera and the projector, determine the three-dimensional coordinates of the target pixel in the unified coordinate system and generate the target point cloud of the target object.
[0075] As an example, the first camera, the second camera, and the projector all need to be in the same coordinate system. The first and second cameras are unified to the projector's coordinate system, and the coordinate systems of the first and second cameras are aligned with the projector's coordinate system, thus defining the projector's coordinate system as the unified coordinate system. Based on the target camera and the projector, the three-dimensional coordinates of the target pixel point in the unified coordinate system are determined, and the target point cloud determination device generates the target point cloud of the target object.
[0076] This application provides a method, apparatus, device and storage medium for determining target point clouds. Compared with the problem of low determination accuracy when determining target point clouds based on a monocular camera in the prior art, in this application, a preset projector is controlled to project a preset sine fringe pattern on the target object.
[0077] A first image captured by a preset first camera and a second image captured by a preset second camera are acquired. The sinusoidal fringe pattern deforms on the target object, with the deformation corresponding to the size of the target object. The first and second images are images of the target object overlaid with the deformed sinusoidal fringe pattern. Target pixels are selected from the pixels of the first and second images, where the camera corresponding to the target pixel is the target camera. A target point cloud of the target object is generated based on the target pixel. In this application, when two cameras are used to determine the target point cloud, the target pixel is selected based on the projected sinusoidal fringe pattern. This avoids the problem of incomplete imaging when using only a single monocular camera, allowing for the selection of clearer pixels, resulting in better target point cloud determination and improved accuracy.
[0078] Example 2
[0079] Furthermore, based on Embodiment 1 of this application, another embodiment of this application is provided. In this embodiment, step S30, based on the step of selecting the target pixel from the pixels of the first image and the pixels of the second image, includes:
[0080] When it is determined that the sum of the number of the first image and the second image reaches a preset number, a target pixel is selected from the pixels of the first image and the pixels of the second image.
[0081] As an example, the first and second images obtained are sample images. When only two samples are obtained (one first image and one second image), the target point cloud generated based on these two sample images has limited applicability.
[0082] As an example, the preset number is a manually set number used to determine whether to select and generate a point cloud based on the first and second images.
[0083] As an example, when the sum of the number of the first image and the second image reaches a preset number, a target pixel is selected from the pixels of the first image and the pixels of the second image. Images that reach the preset number correspond to a wider range of selectable pixels, making it easier to select a target pixel with a higher modulation intensity.
[0084] In this embodiment, target pixels are selected only when the sum of the number of the first image and the second image reaches a preset number, thus avoiding the problem of low applicability of the generated target point cloud. Target pixels with high modulation intensity can be selected, further improving the determination accuracy of the target point cloud.
[0085] Example 3
[0086] Furthermore, based on all the above embodiments, another embodiment of this application is provided, in which, as... Figure 2 A target point cloud determination device is provided, the device comprising:
[0087] The control module is used to control the preset projector to project a preset sine fringe pattern onto the target object;
[0088] The acquisition module is used to acquire a first image captured by a preset first camera and a second image captured by a preset second camera, wherein the sinusoidal fringe pattern is deformed on the target object, the deformation amount corresponds to the size of the target object, and the first image and the second image are images of the target object covered with the deformed sinusoidal fringe pattern;
[0089] The selection module is used to select a target pixel from the pixels of the first image and the pixels of the second image, wherein the camera corresponding to the target pixel is the target camera;
[0090] The generation module is used to generate a target point cloud of the target object based on the target pixels.
[0091] In one possible embodiment of this application, the apparatus for selecting the target pixel from the pixels of the first image and the pixels of the second image includes:
[0092] A modulation module is used to modulate the first image to obtain a first modulation degree of the first image, and to modulate the second image to obtain a second modulation degree of the second image;
[0093] The first selection module is used to select, based on the first modulation degree and the second modulation degree, the pixel corresponding to the high modulation degree as the target pixel from the pixels of the first image and the pixels of the second image.
[0094] In one possible implementation of this application, the step of selecting the target pixel from the pixels of the first image and the pixels of the second image includes:
[0095] The second selection module is used to select a target pixel from the pixels of the first image and the second image when the sum of the number of the first image and the second image reaches a preset number.
[0096] In one possible implementation of this application, the apparatus for generating a target point cloud of the target object based on the target pixels includes:
[0097] The first determining module is used to determine a unified coordinate system;
[0098] The second determining module is used to determine the three-dimensional coordinates of the target pixel in the unified coordinate system based on the target camera and the projector, and generate the target point cloud of the target object.
[0099] In one possible embodiment of this application, the apparatus for determining a unified coordinate system includes:
[0100] The conversion module is used to convert the coordinate system of the first camera and the coordinate system of the second camera to the coordinate system of the projector.
[0101] The third determining module is used to determine that the coordinate system of the projector is the unified coordinate system.
[0102] In one possible implementation of this application, the apparatus for selecting the pixel corresponding to the high modulation degree from the pixels of the first image and the pixels of the second image as the target pixel based on the first modulation degree and the second modulation degree includes:
[0103] The first selection module is used to select, based on the first modulation degree and the second modulation degree, the pixel corresponding to the high modulation degree from the pixels of the first image and the pixels of the second image as the target pixel when the target object cannot be fully imaged.
[0104] In one possible implementation of this application, the target point cloud determination device is an NX development board.
[0105] The specific implementation of the target point cloud determination device in this application is basically the same as the various embodiments of the target point cloud determination method described above, and will not be repeated here.
[0106] Example 4
[0107] Furthermore, based on all the above embodiments, another embodiment of this application is provided. In this embodiment, a target point cloud determination device is provided. The target point cloud determination device is a physical node device. The target point cloud determination device includes: a memory, a processor, and a program stored in the memory for implementing the target point cloud determination method. The memory is used to store the program for implementing the target point cloud determination method; the processor is used to execute the program for implementing the target point cloud determination method to implement the steps of the target point cloud determination method in the above embodiments.
[0108] Reference Figure 3 , Figure 3 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiments of this application.
[0109] like Figure 3 As shown, the device for determining the target point cloud may include: a processor 1001, such as a CPU, a memory 1005, and a communication bus 1002. The communication bus 1002 is used to establish communication between the processor 1001 and the memory 1005. The memory 1005 may be a high-speed RAM or a stable, non-volatile memory, such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.
[0110] In one possible implementation of this application, the device for determining the target point cloud may further include a network interface, audio circuitry, a display, connecting cables, sensors, input modules, etc. The network interface may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface or a Bluetooth interface), and the input module may optionally include a keyboard, a system soft keyboard, voice input, wireless receiver input, etc.
[0111] Those skilled in the art will understand that the structure of the device for determining the target point cloud does not constitute a limitation on the device for determining the target point cloud, and may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.
[0112] A memory, as a computer storage medium, may include an operating system, an information exchange module, and a target point cloud determination program. The operating system is a program that manages and controls the hardware and software resources of the target point cloud determination device, supporting the execution of the target point cloud determination program and other software and / or programs. The information exchange module is used to enable communication between various components within the memory, as well as communication with other hardware and software in the management system.
[0113] In the target point cloud determination device, the processor is used to execute the target point cloud determination program stored in the memory to implement the above-mentioned target point cloud determination steps.
[0114] The specific implementation method of the target point cloud determination device in this application is basically the same as the above-described target point cloud determination method embodiments, and will not be repeated here.
[0115] Example 5
[0116] This application provides a storage medium that stores one or more programs, which can be executed by one or more processors to implement the steps of the target point cloud determination method in the above embodiments.
[0117] The specific implementation of the storage medium in this application is basically the same as the embodiments of the above-described method for determining the target point cloud, and will not be repeated here.
[0118] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.
[0119] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.
[0120] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM or RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.
[0121] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.
Claims
1. A method for determining a target point cloud, characterized in that, An apparatus for determining a target point cloud, wherein the method for determining the target point cloud includes: Control the preset projector to project a preset sine fringe pattern onto the target object; A first image captured by a preset first camera is acquired, and a second image captured by a preset second camera is acquired, wherein the sinusoidal fringe pattern is deformed on the target object, the deformation amount corresponds to the size of the target object, and the first image and the second image are images of the target object covered with the deformed sinusoidal fringe pattern; The first image is modulated to obtain a first modulation degree of the first image, and the second image is modulated to obtain a second modulation degree of the second image; Based on the first modulation degree and the second modulation degree, the pixel corresponding to the high modulation degree is selected from the pixels of the first image and the pixels of the second image as the target pixel to obtain the target pixel. The modulation degree reflects the amount of three-dimensional information of the target object obtained from the deformed sinusoidal stripes. The camera corresponding to the target pixel is the target camera. Based on the target pixels, a target point cloud of the target object is generated.
2. The method for determining a target point cloud according to claim 1, characterized in that, The device for determining the target point cloud is an NX development board.
3. The method for determining a target point cloud according to claim 1, characterized in that, The step of selecting the target pixel from the pixels of the first image and the pixels of the second image includes: When it is determined that the sum of the number of the first image and the second image reaches a preset number, a target pixel is selected from the pixels of the first image and the pixels of the second image.
4. The method for determining a target point cloud according to claim 1, characterized in that, The step of generating a target point cloud of the target object based on the target pixels includes: Establish a unified coordinate system; Based on the target camera and the projector, the three-dimensional coordinates of the target pixel in the unified coordinate system are determined and the target point cloud of the target object is generated.
5. The method for determining a target point cloud according to claim 4, characterized in that, The step of determining a unified coordinate system includes: Transform the coordinate systems of the first camera and the second camera into the coordinate system of the projector; The coordinate system of the projector is determined to be the unified coordinate system.
6. The method for determining a target point cloud according to claim 1, characterized in that, The step of selecting the pixel corresponding to the high modulation degree from the pixels of the first image and the second image as the target pixel based on the first modulation degree and the second modulation degree includes: When the target object cannot be fully imaged, based on the first modulation degree and the second modulation degree, the pixel corresponding to the high modulation degree is selected as the target pixel from the pixels of the first image and the pixels of the second image.
7. A device for determining a target point cloud, characterized in that, The device for determining the target point cloud includes: The control module is used to control the preset projector to project a preset sine fringe pattern onto the target object; The acquisition module is used to acquire a first image captured by a preset first camera and a second image captured by a preset second camera, wherein the sinusoidal fringe pattern is deformed on the target object, the deformation amount corresponds to the size of the target object, and the first image and the second image are images of the target object covered with the deformed sinusoidal fringe pattern; A modulation module is used to modulate the first image to obtain a first modulation degree of the first image, and to modulate the second image to obtain a second modulation degree of the second image; The selection module is used to select a target pixel from the pixels of the first image and the pixels of the second image, wherein the camera corresponding to the target pixel is the target camera; The first selection module is used to select the pixel corresponding to the high modulation degree from the pixels of the first image and the pixels of the second image as the target pixel based on the first modulation degree and the second modulation degree, wherein the modulation degree reflects the amount of three-dimensional information of the target object obtained from the deformed sinusoidal stripes. The generation module is used to generate a target point cloud of the target object based on the target pixels.
8. A device for determining a target point cloud, characterized in that, The method includes a memory, a processor, and a target point cloud determination program stored in the memory and executable on the processor. The processor executes the target point cloud determination program to implement the steps of the target point cloud determination method according to any one of claims 1 to 6.
9. A storage medium, characterized in that, The storage medium stores a program for implementing a method for determining a target point cloud, which is executed by a processor to implement the steps of the method for determining a target point cloud as described in any one of claims 1 to 6.
Citation Information
Patent Citations
Digital speckle-based telecentric microscopic binocular stereoscopic vision measurement method
CN106595528A