CN113837952A - Three-dimensional point cloud noise reduction method and device based on normal vector, computer readable storage medium and electronic equipment - Google Patents
Three-dimensional point cloud noise reduction method and device based on normal vector, computer readable storage medium and electronic equipment Download PDFInfo
- Publication number
- CN113837952A CN113837952A CN202010585667.8A CN202010585667A CN113837952A CN 113837952 A CN113837952 A CN 113837952A CN 202010585667 A CN202010585667 A CN 202010585667A CN 113837952 A CN113837952 A CN 113837952A
- Authority
- CN
- China
- Prior art keywords
- dimensional point
- point cloud
- dimensional
- depth image
- normal vector
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000013598 vector Substances 0.000 title claims abstract description 50
- 238000000034 method Methods 0.000 title claims abstract description 42
- 230000009467 reduction Effects 0.000 title claims abstract description 21
- 230000000007 visual effect Effects 0.000 claims abstract description 21
- 238000012545 processing Methods 0.000 claims abstract description 15
- 230000011218 segmentation Effects 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 12
- 238000000513 principal component analysis Methods 0.000 claims description 10
- 239000011159 matrix material Substances 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000003709 image segmentation Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 230000000875 corresponding effect Effects 0.000 description 19
- 238000001914 filtration Methods 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000002146 bilateral effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 239000004984 smart glass Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention is applicable to the field of image processing, and provides a three-dimensional point cloud noise reduction method and device based on normal vectors, a computer readable storage medium and electronic equipment. The method comprises the following steps: acquiring a depth image and a corresponding three-dimensional point cloud; obtaining a plurality of second three-dimensional point clouds according to the depth image; obtaining a normal vector of the second three-dimensional point cloud according to the second three-dimensional point cloud; calculating rays from the center of the visual camera to each three-dimensional point in the second three-dimensional point cloud; calculating an included angle between a normal vector of the second three-dimensional point cloud and a ray from the center of the visual camera to each three-dimensional point in the second three-dimensional point cloud; and judging whether the included angle is larger than a preset angle threshold value, and if so, deleting the three-dimensional points in the corresponding three-dimensional point cloud. According to the invention, the three-dimensional point cloud corresponding to the depth image is filtered by adopting a normal vector-based three-dimensional point cloud noise reduction method, so that radial noise in the three-dimensional point cloud can be effectively and rapidly eliminated, a cleaner three-dimensional point cloud is obtained, and the point cloud precision of three-dimensional reconstruction is improved.
Description
Technical Field
The invention belongs to the field of image processing, and particularly relates to a three-dimensional point cloud noise reduction method and device based on a normal vector, a computer readable storage medium and electronic equipment.
Background
Depth images (depth images), also known as range images, refer to images having as pixel values the distances (depth values) from an image collector to points in a scene, which directly reflect the geometry of the visible surface of the scene. The depth image can be calculated into point cloud data through coordinate conversion, and the point cloud data with regular and necessary information can also be inversely calculated into depth image data.
At present, the depth image acquisition method includes a laser radar depth imaging method, a computer stereoscopic vision imaging method, a coordinate measuring machine method, a moire fringe method, a structured light method, and the like, and no matter what method is adopted to acquire the depth image, the depth image contains much noise, a filtering algorithm is generally adopted to perform denoising processing, but the traditional depth filtering mainly includes a guided filter (guidedfilter) and a bilateral filter (bilatelter), and the two types of filtering use an RGB image as a guide to filter the depth image, so that the effect of eliminating radial noise (the radial noise is point cloud noise which is radially scattered on rays emitted by an optical center of a camera) in three-dimensional point cloud is poor, and the speed is slow.
Disclosure of Invention
The invention aims to provide a three-dimensional point cloud noise reduction method and device based on a normal vector, a computer readable storage medium and electronic equipment, and aims to solve the problems that a traditional depth filtering method is poor in effect and low in speed in removing radial noise in three-dimensional point cloud.
In a first aspect, the present invention provides a method for denoising a three-dimensional point cloud based on a normal vector, the method comprising:
acquiring a depth image and a corresponding three-dimensional point cloud;
obtaining a plurality of second three-dimensional point clouds according to the depth image;
obtaining a normal vector of the second three-dimensional point cloud according to the second three-dimensional point cloud;
calculating rays from the center of the visual camera to each three-dimensional point in the second three-dimensional point cloud;
calculating an included angle between a normal vector of the second three-dimensional point cloud and a ray from the center of the visual camera to each three-dimensional point in the second three-dimensional point cloud;
judging whether the included angle is larger than a preset angle threshold value or not, and if so, deleting the three-dimensional points in the corresponding three-dimensional point cloud;
and each pixel point on the depth image and the three-dimensional point on the three-dimensional point cloud have a one-to-one correspondence relationship.
With reference to the first aspect, in a possible implementation manner, obtaining a plurality of second three-dimensional point clouds according to the depth image specifically includes:
performing superpixel segmentation on the depth image to obtain N superpixel blocks, wherein N is more than or equal to 2;
and sequentially obtaining three-dimensional points corresponding to each pixel point in each super pixel block to obtain a plurality of second three-dimensional point clouds.
With reference to the first aspect, in a possible implementation manner, obtaining a normal vector of the second three-dimensional point cloud according to the second three-dimensional point cloud specifically includes:
performing Principal Component Analysis (PCA) on the second three-dimensional point cloud, and taking a feature vector with the minimum feature value of the covariance matrix as a normal vector of the second three-dimensional point cloud;
with reference to the first aspect, in one possible implementation manner, the visual camera is located at the center of the second three-dimensional point cloud.
In a second aspect, the present invention provides a normal vector-based three-dimensional point cloud noise reduction apparatus, including:
an acquisition module: the system comprises a depth image acquisition module, a three-dimensional point cloud acquisition module and a three-dimensional point cloud acquisition module, wherein the depth image acquisition module is used for acquiring a depth image and a corresponding three-dimensional point cloud;
a first processing module: a plurality of second three-dimensional point clouds are obtained according to the depth image;
a second processing module: the normal vector used for obtaining the second three-dimensional point cloud according to the second three-dimensional point cloud;
a first calculation module: calculating a ray from the center of the visual camera to each three-dimensional point in the second three-dimensional point cloud;
a second calculation module: the included angle between the normal vector of the second three-dimensional point cloud and the ray from the center of the visual camera to each three-dimensional point in the second three-dimensional point cloud is calculated;
a third processing module: and the three-dimensional point detection device is used for judging whether the included angle is larger than a preset angle threshold value or not, and deleting the corresponding three-dimensional point in the three-dimensional point cloud if the included angle is larger than the preset angle threshold value.
With reference to the second aspect, in a possible implementation manner, the first processing module specifically includes:
a dividing unit: the depth image segmentation device is used for performing superpixel segmentation on the depth image to obtain N superpixel blocks, wherein N is more than or equal to 2;
a generation unit: and the system is used for sequentially obtaining the three-dimensional points corresponding to each pixel point in the super-pixel block to obtain a second three-dimensional point cloud.
In a third aspect, the present invention provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the steps of the normal vector based three-dimensional point cloud noise reduction method according to the first aspect.
In a fourth aspect, the present invention provides an electronic device, comprising: one or more processors; a memory; and one or more computer programs, the processor and the memory being connected by communication, wherein the one or more computer programs are stored in the memory and configured to be executed by the one or more processors, which when executed implement the steps of the normal vector based three-dimensional point cloud noise reduction method according to the first aspect.
In the invention, the three-dimensional point cloud noise reduction method based on the normal vector is adopted to filter the three-dimensional point cloud corresponding to the depth image, so that radial noise (namely point cloud noise which is radially distributed on rays emitted by a camera optical center) in the three-dimensional point cloud can be effectively and quickly eliminated, a cleaner three-dimensional point cloud is obtained, and the point cloud precision of three-dimensional reconstruction is improved.
Drawings
Fig. 1 is a flowchart of a normal vector-based three-dimensional point cloud noise reduction method according to an embodiment of the present invention.
Fig. 2 is a specific structural diagram of a normal vector-based three-dimensional point cloud noise reduction device according to a second embodiment of the present invention.
Fig. 3 is a block diagram of a detailed structure of an electronic device according to a fourth embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more clearly apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
In order to better understand the present solution, the following description is given with respect to terms and concepts.
(1) Super-pixel segmentation: the super-pixel concept is an image segmentation technology proposed and developed by Xiaofeng Ren in 2003, and refers to an irregular pixel block which is composed of adjacent pixels with similar texture, color, brightness and other characteristics and has a certain visual significance. The method uses the similarity of the features between pixels to group the pixels, uses a small amount of super pixels to replace a large amount of pixels to express the picture features, and greatly reduces the complexity of image post-processing, so the method is usually used as a preprocessing step of a segmentation algorithm. Have been widely used in computer vision applications such as image segmentation, pose estimation, target tracking, target recognition, etc.
(2) Principal Component Analysis (PCA), a statistical method. A group of variables which are possibly correlated are converted into a group of linearly uncorrelated variables through orthogonal transformation, and the group of converted variables are called principal components.
(3) Depth image: the difference between the depth image and the gray image lies in that the information contained in the pixel points is different, the pixel points in the depth image contain three-dimensional information of each point on the surface of an object or in a scene, namely the real distance between the position of the point in reality and a vertical plane where a camera scanner is located, and in addition, the pixel points in the depth image and each pixel point in an RGB image shot by the camera have a one-to-one correspondence relationship;
(4) three-dimensional point cloud: a data set containing three-dimensional information and color information for each point in the surface or scene of an object captured by the camera;
in order to explain the technical means of the present invention, the following description will be given by way of specific examples.
The first embodiment is as follows:
referring to fig. 1, a normal vector-based three-dimensional point cloud noise reduction method according to an embodiment of the present invention includes the following steps:
s101, acquiring a depth image and a corresponding three-dimensional point cloud;
in the first embodiment of the present invention, the method for obtaining the depth image may include one or more of the following common methods: laser radar depth imaging method, computer stereoscopic vision imaging, coordinate measuring machine method, moire fringe method, structured light method, etc.; of course, the depth image may also be stored in a memory, and the processor may obtain the depth image data from the memory; of course, the depth image here can also be directly acquired by the depth camera.
In the first embodiment of the present invention, the three-dimensional point cloud corresponding to the depth image may be directly acquired by the laser radar, and may also be obtained by converting the acquired depth image, where the specific conversion idea is as follows: the two-dimensional coordinates, the depth values and the camera internal parameters of the pixel points in the depth image are combined to generate three-dimensional coordinates of the pixel points in a camera coordinate system, and then the three-dimensional coordinates of the pixel points in a world coordinate system are generated by combining the external parameters of the camera. Specific references may be made to the following:
knowing the two-dimensional coordinates (u, v), the depth value d and the camera parameter K of a certain pixel point in the depth image, the three-dimensional coordinates P of the pixel point in the camera coordinate system for shooting the depth image can be generated through a correlation formulan；
And then, obtaining a three-dimensional coordinate P of the pixel point under a world coordinate system through a correlation formula by combining external parameters of the camera (generally, a rotation matrix and a translation matrix of the camera).
In the first embodiment of the present invention, a one-to-one correspondence exists between each pixel point on the depth image and a three-dimensional point on the three-dimensional point cloud.
Obtaining a plurality of second three-dimensional point clouds according to the depth images;
in the first embodiment of the present invention, S102 may specifically be:
s1021, performing superpixel segmentation on the depth image to obtain N superpixel blocks, wherein N is more than or equal to 2;
and S1022, sequentially obtaining three-dimensional points corresponding to each pixel point in the super-pixel block to obtain a second three-dimensional point cloud.
In the first embodiment of the present invention, the super-pixel segmentation method in S1021 may adopt a commonly used super-pixel segmentation method, for example: SLIC, Ncut, etc.
It should be understood that, in the first embodiment of the present invention, the super-pixel segmentation method in S1021 may also be replaced by other segmentation methods, and it is only necessary to ensure that the size of each sub-region in the segmentation result is as uniform as possible, and the boundary of the sub-region respects the boundary information of the original image.
Obtaining a normal vector of the second three-dimensional point cloud according to the second three-dimensional point cloud;
in the first embodiment of the present invention, the obtaining the normal vector of the second three-dimensional point cloud according to the second three-dimensional point cloud in S103 specifically includes:
performing Principal Component Analysis (PCA) on the second three-dimensional point cloud, and taking a feature vector with the minimum feature value of a covariance matrix as a normal vector of the second three-dimensional point cloud;
performing Principal Component Analysis (PCA) on the second three-dimensional point cloud, and taking a feature vector with the minimum feature value of a covariance matrix as a normal vector of the second three-dimensional point cloud, wherein the method can be specifically realized by adopting the following steps:
1) Centralizing the second three-dimensional point cloud data;
2) Calculating a covariance matrix of the second three-dimensional point cloud data;
3) Carrying out eigenvalue decomposition on the covariance matrix;
4) And taking out the eigenvector corresponding to the minimum eigenvalue as the normal vector of the superpixel block.
Calculating rays from the center of the visual camera to each three-dimensional point in the second three-dimensional point cloud;
in the first embodiment of the present invention, the visual camera in S104 specifically includes:
the visual camera is located at the center of the second three-dimensional point cloud.
And calculating the included angle between the normal vector of the second three-dimensional point cloud and the ray from the center of the visual camera to each three-dimensional point in the second three-dimensional point cloud.
In the first embodiment of the present invention, in S105, calculating an included angle between a normal vector of the second three-dimensional point cloud and a ray from the center of the visual camera to each three-dimensional point in the second three-dimensional point cloud may specifically be:
the second three-dimensional point cloud comprises M (M is more than or equal to 2) three-dimensional points, the normal vector of the second three-dimensional point cloud is P, and the ray from the center of the visual camera to each three-dimensional point is M1、M2、M3......MmSeparately calculate M1、M2、M3......MmAngle theta with P1、θ2、θ3......θmThe included angle can be any angle value.
Judging whether the included angle is larger than a preset angle threshold value, and if so, deleting the three-dimensional points in the corresponding three-dimensional point cloud;
in the first embodiment of the present invention, the preset angle threshold in S106 may be any angle, generally speaking, the smaller the preset angle threshold is, the more point clouds are filtered out, but in view of effect, it is recommended that the preset angle threshold is greater than 85 °;
in the first embodiment of the present invention, in S106, it is determined whether the included angle is greater than a preset angle threshold, and if so, the three-dimensional point in the corresponding three-dimensional point cloud is deleted, specifically:
if angle thetaiAnd (i =1, 2, 3.. eta.. m) is greater than a preset threshold, removing the corresponding three-dimensional point i in the second three-dimensional point cloud from the original three-dimensional point cloud to obtain a new three-dimensional point cloud.
In the first embodiment of the invention, after the three-dimensional points which do not meet the condition are deleted, a new three-dimensional point cloud can be obtained, and the point cloud precision of three-dimensional reconstruction can be improved by the new three-dimensional point cloud.
Example two:
fig. 2 shows that the second embodiment of the present invention provides a normal vector-based three-dimensional point cloud noise reduction apparatus 100, which includes:
101, an acquisition module: the system comprises a depth image acquisition module, a three-dimensional point cloud acquisition module and a three-dimensional point cloud acquisition module, wherein the depth image acquisition module is used for acquiring a depth image and a corresponding three-dimensional point cloud;
102 first processing module: a plurality of second three-dimensional point clouds are obtained according to the depth image;
103 a second processing module: the normal vector used for obtaining the second three-dimensional point cloud according to the second three-dimensional point cloud;
104 first calculation module: calculating a ray from the center of the visual camera to each three-dimensional point in the second three-dimensional point cloud;
105 a second calculation module: the included angle between the normal vector of the second three-dimensional point cloud and the ray from the center of the visual camera to each three-dimensional point in the second three-dimensional point cloud is calculated;
106 third processing module: and the three-dimensional point detection device is used for judging whether the included angle is larger than a preset angle threshold value or not, and deleting the corresponding three-dimensional point in the three-dimensional point cloud if the included angle is larger than the preset angle threshold value.
In a second embodiment of the present invention, the first processing module specifically includes:
a dividing unit: the depth image segmentation device is used for performing superpixel segmentation on the depth image to obtain N superpixel blocks, wherein N is more than or equal to 2;
a generation unit: and the system is used for sequentially obtaining the three-dimensional points corresponding to each pixel point in the super-pixel block to obtain a second three-dimensional point cloud.
Those skilled in the art will appreciate that the modules of the above-mentioned normal vector-based three-dimensional point cloud noise reduction device can be implemented wholly or partially by software, hardware and their combination. The modules can be embedded in a processor or independent of any electronic device in a hardware form, and can also be stored in a memory of any electronic device in a software form, so that the processor can call and execute operations corresponding to the modules, and the electronic device can be a computer, a mobile phone, an IPAD, a server, a computer, an intelligent watch, intelligent glasses, a camera and the like.
Example three:
the third embodiment of the present invention provides a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the steps of the method for denoising a three-dimensional point cloud based on a normal vector according to the first embodiment of the present invention are implemented.
Example four:
fig. 3 shows a detailed block diagram of an electronic device according to a fourth embodiment of the present invention, where the electronic device may be a computer, a mobile phone, an IPAD, a server, a computer, a smart watch, smart glasses, a camera, and the like, and an electronic device 200 includes: one or more processors 201, a memory 202, and one or more computer programs, wherein the processors 201 and the memory 202 are connected by communication or a bus, the one or more computer programs are stored in the memory 202 and configured to be executed by the one or more processors 201, and the processor 201 when executing the computer programs implements the steps of the normal vector based three-dimensional point cloud noise reduction method according to an embodiment of the present invention.
In the invention, the three-dimensional point cloud noise reduction method based on the normal vector is adopted to filter the three-dimensional point cloud corresponding to the depth image, so that radial noise (namely point cloud noise which is radially distributed on rays emitted by a camera optical center) in the three-dimensional point cloud can be effectively and quickly eliminated, a cleaner three-dimensional point cloud is obtained, and the point cloud precision of three-dimensional reconstruction is improved.
Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by associated hardware instructed by a program, which may be stored in a computer-readable storage medium, and the storage medium may include: read Only Memory (ROM), Random Access Memory (RAM), magnetic or optical disks, and the like.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (8)
1. A three-dimensional point cloud noise reduction method based on normal vectors is characterized by comprising the following steps:
acquiring a depth image and a corresponding three-dimensional point cloud;
obtaining a plurality of second three-dimensional point clouds according to the depth image;
obtaining a normal vector of the second three-dimensional point cloud according to the second three-dimensional point cloud;
calculating rays from the center of the visual camera to each three-dimensional point in the second three-dimensional point cloud;
calculating an included angle between a normal vector of the second three-dimensional point cloud and a ray from the center of the visual camera to each three-dimensional point in the second three-dimensional point cloud;
judging whether the included angle is larger than a preset angle threshold value or not, and if so, deleting the three-dimensional points in the corresponding three-dimensional point cloud;
and each pixel point on the depth image and the three-dimensional point on the three-dimensional point cloud have a one-to-one correspondence relationship.
2. The method of claim 1, wherein obtaining a plurality of second three-dimensional point clouds from the depth image comprises:
performing superpixel segmentation on the depth image to obtain N superpixel blocks, wherein N is more than or equal to 2;
and sequentially obtaining three-dimensional points corresponding to each pixel point in each super pixel block to obtain a plurality of second three-dimensional point clouds.
3. The method according to claim 1 or 2, wherein obtaining the normal vector of the second three-dimensional point cloud from the second three-dimensional point cloud comprises:
and performing Principal Component Analysis (PCA) on the second three-dimensional point cloud, and taking the eigenvector with the minimum eigenvalue of the covariance matrix as the normal vector of the second three-dimensional point cloud.
4. The method of claim 1,
the visual camera is located at the center of the second three-dimensional point cloud.
5. A normal vector based three-dimensional point cloud noise reduction device, the device comprising:
an acquisition module: the system comprises a depth image acquisition module, a three-dimensional point cloud acquisition module and a three-dimensional point cloud acquisition module, wherein the depth image acquisition module is used for acquiring a depth image and a corresponding three-dimensional point cloud;
a first processing module: a plurality of second three-dimensional point clouds are obtained according to the depth image;
a second processing module: the normal vector used for obtaining the second three-dimensional point cloud according to the second three-dimensional point cloud;
a first calculation module: calculating a ray from the center of the visual camera to each three-dimensional point in the second three-dimensional point cloud;
a second calculation module: the included angle between the normal vector of the second three-dimensional point cloud and the ray from the center of the visual camera to each three-dimensional point in the second three-dimensional point cloud is calculated;
a third processing module: and the three-dimensional point detection device is used for judging whether the included angle is larger than a preset angle threshold value or not, and deleting the corresponding three-dimensional point in the three-dimensional point cloud if the included angle is larger than the preset angle threshold value.
6. The apparatus of claim 5, wherein the first processing module specifically comprises:
a dividing unit: the depth image segmentation device is used for performing superpixel segmentation on the depth image to obtain N superpixel blocks, wherein N is more than or equal to 2;
a generation unit: and the system is used for sequentially obtaining the three-dimensional points corresponding to each pixel point in the super-pixel block to obtain a second three-dimensional point cloud.
7. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the normal vector based three-dimensional point cloud noise reduction method according to any one of claims 1 to 4.
8. An electronic device, comprising: one or more processors; a memory; and one or more computer programs, the processor and the memory being connected by communication or a bus, wherein the one or more computer programs are stored in the memory and configured to be executed by the one or more processors, characterized in that the processor when executing the computer programs implements the steps of the normal vector based three-dimensional point cloud noise reduction method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010585667.8A CN113837952A (en) | 2020-06-24 | 2020-06-24 | Three-dimensional point cloud noise reduction method and device based on normal vector, computer readable storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010585667.8A CN113837952A (en) | 2020-06-24 | 2020-06-24 | Three-dimensional point cloud noise reduction method and device based on normal vector, computer readable storage medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113837952A true CN113837952A (en) | 2021-12-24 |
Family
ID=78964504
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010585667.8A Pending CN113837952A (en) | 2020-06-24 | 2020-06-24 | Three-dimensional point cloud noise reduction method and device based on normal vector, computer readable storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113837952A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114066779A (en) * | 2022-01-13 | 2022-02-18 | 杭州蓝芯科技有限公司 | Depth map filtering method and device, electronic equipment and storage medium |
| CN115408549A (en) * | 2022-08-31 | 2022-11-29 | 深圳前海瑞集科技有限公司 | Workpiece point cloud filtering method and device, computer readable medium and electronic equipment |
| CN116071495A (en) * | 2022-12-27 | 2023-05-05 | 中国人民解放军61363部队 | Three-dimensional point cloud data noise reduction processing method and system based on deep learning multi-statistics |
| CN117474795A (en) * | 2023-12-27 | 2024-01-30 | 深圳市信润富联数字科技有限公司 | Point cloud noise reduction method and device, electronic equipment and storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103542868A (en) * | 2013-11-05 | 2014-01-29 | 武汉海达数云技术有限公司 | Automatic removing method of vehicle-mounted laser point cloud noisy point based on angle and intensity |
| WO2016201671A1 (en) * | 2015-06-18 | 2016-12-22 | 北京大学深圳研究生院 | Method and device for extracting local features of three-dimensional point cloud |
| CN106504275A (en) * | 2016-10-12 | 2017-03-15 | 杭州深瞳科技有限公司 | A kind of inertial positioning and the real-time three-dimensional method for reconstructing of point cloud registering coupling and complementing |
| US20180096463A1 (en) * | 2016-09-30 | 2018-04-05 | Disney Enterprises, Inc. | Point cloud noise and outlier removal for image-based 3d reconstruction |
| CN108010002A (en) * | 2017-12-25 | 2018-05-08 | 浙江大学 | A kind of structuring point cloud denoising method based on adaptive implicit Moving Least Squares |
| CN108986048A (en) * | 2018-07-18 | 2018-12-11 | 大连理工大学 | Based on the quick compound filter processing method of line laser structured light three-dimensional point cloud |
| US10346998B1 (en) * | 2019-02-25 | 2019-07-09 | Nurulize, Inc. | Method of merging point clouds that identifies and retains preferred points |
| US20190219700A1 (en) * | 2017-11-17 | 2019-07-18 | DeepMap Inc. | Iterative closest point process based on lidar with integrated motion estimation for high definition maps |
| CN110147815A (en) * | 2019-04-10 | 2019-08-20 | 深圳市易尚展示股份有限公司 | Multiframe point cloud fusion method and device based on K mean cluster |
| CN110874864A (en) * | 2019-10-25 | 2020-03-10 | 深圳奥比中光科技有限公司 | Method, device, electronic equipment and system for obtaining three-dimensional model of object |
-
2020
- 2020-06-24 CN CN202010585667.8A patent/CN113837952A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103542868A (en) * | 2013-11-05 | 2014-01-29 | 武汉海达数云技术有限公司 | Automatic removing method of vehicle-mounted laser point cloud noisy point based on angle and intensity |
| WO2016201671A1 (en) * | 2015-06-18 | 2016-12-22 | 北京大学深圳研究生院 | Method and device for extracting local features of three-dimensional point cloud |
| US20180096463A1 (en) * | 2016-09-30 | 2018-04-05 | Disney Enterprises, Inc. | Point cloud noise and outlier removal for image-based 3d reconstruction |
| CN106504275A (en) * | 2016-10-12 | 2017-03-15 | 杭州深瞳科技有限公司 | A kind of inertial positioning and the real-time three-dimensional method for reconstructing of point cloud registering coupling and complementing |
| US20190219700A1 (en) * | 2017-11-17 | 2019-07-18 | DeepMap Inc. | Iterative closest point process based on lidar with integrated motion estimation for high definition maps |
| CN108010002A (en) * | 2017-12-25 | 2018-05-08 | 浙江大学 | A kind of structuring point cloud denoising method based on adaptive implicit Moving Least Squares |
| CN108986048A (en) * | 2018-07-18 | 2018-12-11 | 大连理工大学 | Based on the quick compound filter processing method of line laser structured light three-dimensional point cloud |
| US10346998B1 (en) * | 2019-02-25 | 2019-07-09 | Nurulize, Inc. | Method of merging point clouds that identifies and retains preferred points |
| CN110147815A (en) * | 2019-04-10 | 2019-08-20 | 深圳市易尚展示股份有限公司 | Multiframe point cloud fusion method and device based on K mean cluster |
| CN110874864A (en) * | 2019-10-25 | 2020-03-10 | 深圳奥比中光科技有限公司 | Method, device, electronic equipment and system for obtaining three-dimensional model of object |
Non-Patent Citations (3)
| Title |
|---|
| JULIA SANCHEZ等: "Robust normal vector estimation in 3D point clouds through iterative principal component analysis", 《ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING》, 31 May 2020 (2020-05-31), pages 18 - 35 * |
| 刘静静: "三维点云重建中的去噪算法研究", 《中国优秀硕士学位论文电子期刊》, 15 January 2020 (2020-01-15), pages 30 - 50 * |
| 闫利;陈长海;费亮;张奕戈;: "密集点云的数字表面模型自动生成方法", 遥感信息, no. 05, 15 October 2017 (2017-10-15), pages 5 - 11 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114066779A (en) * | 2022-01-13 | 2022-02-18 | 杭州蓝芯科技有限公司 | Depth map filtering method and device, electronic equipment and storage medium |
| CN115408549A (en) * | 2022-08-31 | 2022-11-29 | 深圳前海瑞集科技有限公司 | Workpiece point cloud filtering method and device, computer readable medium and electronic equipment |
| CN115408549B (en) * | 2022-08-31 | 2024-04-12 | 深圳前海瑞集科技有限公司 | Workpiece point cloud filtering method and device, computer readable medium and electronic equipment |
| CN116071495A (en) * | 2022-12-27 | 2023-05-05 | 中国人民解放军61363部队 | Three-dimensional point cloud data noise reduction processing method and system based on deep learning multi-statistics |
| CN116071495B (en) * | 2022-12-27 | 2024-02-02 | 中国人民解放军61363部队 | Point cloud data noise reduction processing method and system based on deep learning multi-statistics |
| CN117474795A (en) * | 2023-12-27 | 2024-01-30 | 深圳市信润富联数字科技有限公司 | Point cloud noise reduction method and device, electronic equipment and storage medium |
| CN117474795B (en) * | 2023-12-27 | 2024-05-24 | 深圳市信润富联数字科技有限公司 | Point cloud noise reduction method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102319177B1 (en) | Method and apparatus, equipment, and storage medium for determining object pose in an image | |
| CN113837952A (en) | Three-dimensional point cloud noise reduction method and device based on normal vector, computer readable storage medium and electronic equipment | |
| CN111066065B (en) | System and method for hybrid depth regularization | |
| CN107705333B (en) | Space positioning method and device based on binocular camera | |
| CN107025660B (en) | Method and device for determining image parallax of binocular dynamic vision sensor | |
| WO2017078847A1 (en) | Fusion of panoramic background images using color and depth data | |
| CN109086724B (en) | Accelerated human face detection method and storage medium | |
| CN110264573B (en) | Three-dimensional reconstruction method and device based on structured light, terminal equipment and storage medium | |
| CN110503620B (en) | Image fusion method based on Fourier spectrum extraction | |
| JP2013185905A (en) | Information processing apparatus, method, and program | |
| Huang et al. | Boosting point clouds rendering via radiance mapping | |
| JP6285686B2 (en) | Parallax image generation device | |
| CN112154479A (en) | Method for extracting feature points, movable platform and storage medium | |
| Shen et al. | Depth map enhancement method based on joint bilateral filter | |
| KR101526465B1 (en) | A Depth Image Enhancement Method based on GPGPU | |
| CN111630569B (en) | Binocular matching method, visual imaging device and device with storage function | |
| CN115409949A (en) | Model training method, visual angle image generation method, device, equipment and medium | |
| Yu et al. | Intensity guided depth upsampling using edge sparsity and super-weighted $ l_0 $ gradient minimization | |
| CN114638891A (en) | Target detection positioning method and system based on image and point cloud fusion | |
| Cao et al. | Depth image vibration filtering and shadow detection based on fusion and fractional differential | |
| Pan et al. | An automatic 2D to 3D video conversion approach based on RGB-D images | |
| Jäger et al. | A comparative Neural Radiance Field (NeRF) 3D analysis of camera poses from HoloLens trajectories and Structure from Motion | |
| CN111986246A (en) | Three-dimensional model reconstruction method and device based on image processing and storage medium | |
| Xue et al. | Multi-view image denoising based on graphical model of surface patch | |
| Tang et al. | Saliency detection integrated with depth information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |