CN112085773A - Plane fitting method and device for removing local outliers - Google Patents
Plane fitting method and device for removing local outliers Download PDFInfo
- Publication number
- CN112085773A CN112085773A CN202010930337.8A CN202010930337A CN112085773A CN 112085773 A CN112085773 A CN 112085773A CN 202010930337 A CN202010930337 A CN 202010930337A CN 112085773 A CN112085773 A CN 112085773A
- Authority
- CN
- China
- Prior art keywords
- plane
- fitting
- points
- data points
- depth data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000005457 optimization Methods 0.000 claims abstract description 20
- 238000001514 detection method Methods 0.000 claims abstract description 11
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000005259 measurement Methods 0.000 abstract description 6
- 238000007781 pre-processing Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000002452 interceptive effect Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The method comprises the steps of fitting effective depth data points in a depth image to obtain a plurality of candidate planes, calculating the distance between the effective depth data points and the candidate planes, and performing iterative circulation on the candidate planes within the maximum allowable iteration frequency range to obtain suboptimal planes; and then fitting the inner points in the suboptimal plane to obtain a plurality of optimal planes, performing iterative optimization on the optimal planes, and selecting the fitted plane with the minimum number of the local outer points from the optimal planes as the optimal plane. The method for plane fitting by removing the out-of-office points is a continuous iteration optimization searching process, different distance thresholds can be set according to an actual scene, different plane fitting results are obtained, preprocessing is not needed to be carried out on the depth image, the out-of-office points can be effectively removed, the obtained fitting plane is more accurate, and a guarantee is provided for a measurement and detection algorithm.
Description
Technical Field
The application relates to the technical field of visual images, in particular to a plane fitting method and device for removing local outliers.
Background
In the field of visual images, depth images may reflect depth information of a photographed object. The pixel value of each point in the depth image can be used for representing the distance between a certain point in the image scene and the camera, and the depth image directly reflects the three-dimensional geometrical shape of the visible surface of the object. By acquiring the reference plane in the depth image, height measurement, volume measurement and related detection operation of the object can be realized.
Due to the influence of the shooting environment or the existence of local points (interference defects) on the surface of the object itself, as shown in fig. 1, the obtained reference plane has errors, so that the measurement and detection results also have errors.
However, in the related art, the above plane fitting methods all have certain limitations, and therefore, no relevant operation step for removing the local points is provided. Therefore, an ideal fast and high-precision effective removing method cannot be achieved for the interference information of the out-of-office points in the three-dimensional plane.
Disclosure of Invention
The application provides a plane fitting method for removing local outliers, which aims to solve the problem that the local outliers in a depth image do not relate to an effective, ideal, rapid, high-precision and effective removing mode due to certain limitations in the existing plane fitting method.
The technical scheme adopted by the application for solving the technical problems is as follows:
a plane fitting method for removing local outliers comprises the following steps:
randomly selecting effective depth data points in the depth image, wherein the effective depth data points refer to data points with a mask value of true and data information of-32768-32767 in the depth image;
fitting the effective depth data points to obtain a plurality of candidate planes;
calculating a distance of the effective depth data point to the candidate plane;
performing iterative circulation on the candidate plane within the maximum allowable iteration frequency range to obtain a suboptimal plane, wherein the suboptimal plane refers to a plane with the minimum number of local outliers in the candidate plane, and the local outliers refer to effective depth data points with the distance greater than a preset distance threshold;
fitting the interior points in the suboptimal plane to obtain a plurality of optimal planes, wherein the interior points refer to effective depth data points of which the distance is less than or equal to a preset distance threshold;
and performing iterative optimization on the preferred plane, and selecting a fitting plane with the minimum number of the outlying points from the preferred planes to be the optimal plane.
Optionally, the method for plane fitting to remove local outliers, where the distance threshold is preset, includes:
and setting a distance threshold value meeting the removal requirement according to the actual application scene of the depth image.
Optionally, obtaining the maximum number of allowed iterations includes:
inputting the confidence coefficient and the proportion of the local outliers into an iterative optimization model, and calculating the maximum allowable iteration times by the iterative optimization model according to the following formula:
wherein, P is the confidence coefficient, t is the proportion of the local out-point, and K is the maximum allowable iteration number.
Optionally, obtaining valid depth data points comprises:
and outputting data points with the mask value of true and the data information of-32768-32767 in the depth image data as effective depth data points.
Optionally, the confidence level has a value range of [0, 1 ].
Optionally, the method is also used for fitting depth data in a straight line, circle or sphere with local outliers.
A plane fitting apparatus for removing outliers, comprising:
the effective depth data point acquisition unit is used for randomly selecting effective depth data points in the depth data, wherein the effective depth data points refer to data points with a mask value of true and data information of-32768-32767 in the depth image;
the candidate plane acquisition unit is used for fitting the effective depth data points to obtain a plurality of candidate planes;
a calculation unit that calculates a distance of the effective depth data point to the candidate plane;
a suboptimal plane obtaining unit, configured to perform iterative loop on the candidate plane within a maximum allowable iteration number range to obtain a suboptimal plane, where the suboptimal plane is a plane with a smallest number of local outliers in the candidate plane, and the local outliers are effective depth data points whose distances are greater than a preset distance threshold;
the optimal plane obtaining unit is used for fitting the inner points in the suboptimal plane to obtain a plurality of optimal planes, wherein the inner points are effective depth data points of which the distance is less than or equal to a preset distance threshold;
and the optimal plane obtaining unit is used for carrying out iterative optimization on the optimal planes, and selecting the fitting plane with the minimum number of the local points from the optimal planes as the optimal plane.
Optionally, the plane fitting apparatus for removing the local outliers further includes:
and the distance threshold presetting unit is used for setting a distance threshold meeting the removal requirement according to the actual application scene of the depth image.
A detection apparatus, the detection apparatus comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the one processor to cause the at least one processor to perform the method of plane fitting to remove outliers.
The technical scheme provided by the application comprises the following beneficial technical effects:
the method comprises the steps of fitting effective depth data points in a depth image to obtain a plurality of candidate planes, calculating the distance between the effective depth data points and the candidate planes, and performing iterative circulation on the candidate planes within the maximum allowable iteration frequency range to obtain suboptimal planes; and then fitting the inner points in the suboptimal plane to obtain a plurality of optimal planes, performing iterative optimization on the optimal planes, and selecting the fitted plane with the minimum number of the local outer points from the optimal planes as the optimal plane. After the interfering local outer points in the depth image are removed, useful data capable of really expressing the information of the object is left, and a more accurate fitting result is obtained. The method for plane fitting by removing the local outliers is essentially a continuous iteration optimization searching process, different distance thresholds can be set according to an actual scene, different plane fitting results are obtained, namely corresponding results are obtained according to requirements, preprocessing is not needed for depth images, the local outliers can be effectively removed, the obtained fitting planes are more accurate, and a guarantee is provided for measurement and detection algorithms.
Drawings
In order to more clearly explain the technical solution of the present application, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious to those skilled in the art that other drawings can be obtained according to the drawings without any creative effort.
FIG. 1 is a schematic diagram of depth valid data including outliers;
fig. 2 is a flowchart of a plane fitting method for removing outliers according to an embodiment of the present disclosure;
FIG. 3 is a schematic diagram of a plane fitting process for removing outliers according to an embodiment of the present application;
FIG. 4 is a flowchart of an embodiment of a plane fitting method for removing outliers.
Detailed Description
In order to make the technical solutions in the present application better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application; it is to be understood that the embodiments described are only a few embodiments of the present application and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 2, a flowchart of a plane fitting method for removing outliers is provided according to an embodiment of the present application.
The application provides a plane fitting method for removing local outliers, which comprises the following steps:
randomly selecting effective depth data points in the depth image, wherein the effective depth data points refer to data points with a mask value of true and data information of-32768-32767 in the depth image; data points in the depth image are divided into data information and mask information, the mask value of an invalid pixel is false, and the data information is 0; and the mask of the effective pixel is true, the method selects the mask value in the depth image as true, and the data points with data information of-32768-32767 are used as effective data to be output.
Fitting the effective depth data points to obtain a plurality of candidate planes;
calculating a distance of the effective depth data point to the candidate plane;
performing iterative circulation on the candidate plane within the maximum allowable iteration frequency range to obtain a suboptimal plane, wherein the suboptimal plane refers to a plane with the minimum number of local outliers in the candidate plane, and the local outliers refer to effective depth data points with the distance greater than a preset distance threshold;
fitting the interior points in the suboptimal plane to obtain a plurality of optimal planes, wherein the interior points refer to effective depth data points of which the distance is less than or equal to a preset distance threshold;
and performing iterative optimization on the preferred plane, and selecting a fitting plane with the minimum number of the outlying points from the preferred planes to be the optimal plane.
Referring to fig. 3, a schematic diagram of a plane fitting process for removing outliers provided in the embodiment of the present application shows that as the fitting process continues, the number of outliers on the plane is less and less, and the number of inls fitted on the plane is more and more.
In the method provided by the application, iterative optimization is carried out on the candidate planes by adopting an iterative update algorithm, effective data in depth data are randomly selected to be fitted at the moment of each iteration to obtain a plurality of candidate planes, and the distance from the effective depth data points to the candidate planes is calculated; assuming that the iteration number of the initial input parameter calculation is n, the number of the out-of-office points is calculated for each randomly generated plane, then the number of the out-of-office points is substituted into the formula (1) to obtain a new iteration number, if the current iteration number is greater than the newly calculated iteration number, the iteration is stopped, and the plane with the least out-of-office points is output as a suboptimal plane (so that the loop can be exited without iterating to the initial n times). The optimal plane is obtained by re-fitting according to data points within a distance threshold range from the suboptimal plane, a plane, namely the optimal plane, can be obtained by fitting each time, and the optimal plane is output as the optimal plane by calculating the number of the local outer points on the optimal plane and proving that the obtained fitted plane is optimal when the number of the local outer points is not increased any more. After the interfering local outer points in the depth image are removed, useful data capable of really expressing the information of the object is left, and a more accurate fitting result is obtained.
In the implementation process of the method, the process from the suboptimal plane to the optimal plane exits the loop as long as the number of the out-of-local points is not increased any more, because the suboptimal plane is acquired, a fitting plane which is not the best (i.e. the plane with the largest number of the interior points) may be obtained, the optimal plane is increased on the basis, and it is also possible that after the suboptimal plane is obtained, the number of interior points which are not obtained by the suboptimal plane on the optimal plane obtained through the first loop is large, in this case, the continuous search for the optimal plane may be stopped, and the output suboptimal plane is the final optimal plane.
As a real-time approach, obtaining the maximum number of allowed iterations includes:
inputting the confidence coefficient and the proportion of the local outliers into an iterative optimization model, and calculating the maximum allowable iteration times by the iterative optimization model according to the following formula:
wherein, P is the confidence coefficient, t is the proportion of the local out-point, and K is the maximum allowable iteration number.
In the above formula (1), the smaller t is, the more the calculated iteration times are, the more reliable the fitting result is, and meanwhile, the larger confidence P is, the more the calculated iteration times are, the more reliable the fitting result is, that is, the method provided in the embodiment of the present application can obtain a more reliable result by increasing the iteration times, thereby achieving an effect of truly removing outliers.
In the formula (1), the value range of the confidence coefficient is [0, 1], and preferably, the value of the confidence coefficient is set to 0.8, so that the actual requirement of removing the outlier in most application scenes can be met.
An important parameter in the method is the setting of a distance threshold parameter, and the larger the distance threshold is set, the more effective data points of the inner points on the fitting plane are proved to be, the less the local outer points are removed, so that the distance threshold needs to be determined according to actual image data, the distance threshold can also be set according to actual needs, if a large number of data points are needed in an application scene to represent the plane, the more effective data points need to be reserved, and the larger the distance threshold is set when the distance threshold is set. According to the technical scheme, different removal threshold values can be set according to an actual scene, different plane fitting results are obtained, and corresponding results are obtained according to requirements. As a real-time method, for example, 30 valid depth data points in the depth image are fitted, where the plane fitted with 20 valid data points makes the distances from the 20 data points to the plane smaller than the distance threshold, and the plane fitted with the remaining 10 valid data points makes the distances from the 10 valid data points to the plane smaller than the distance threshold, the distance threshold is set well, and the number of the obtained inner points is greater than that of the outer points.
As a real-time mode, the method provided by the technical scheme of the application is also used for fitting depth data on the surface with the shape of a central symmetry structure, such as a straight line, a circle or a spherical surface with local outer points, and the like, and the iterative optimization mode in the application is adopted for fitting by calculating the minimum distance from the effective data points to the straight line, the circle or the spherical surface, so that the corresponding local outer points are removed according to the practical application scene. The method in the application is a continuously iterative calculation process for the depth image, data points are large during fitting, an obtained result is a plane expression, and the fitting process is shown in fig. 3. The ball, circle, etc. can be seen as the plane in fig. 3, and the principle adopted and the technical problem solved are the same.
The technical solution in the present application is further described below with a specific embodiment.
The plane fitting process for removing the out-of-office points according to this embodiment is shown in fig. 4, and is described in detail as follows:
randomly selecting effective depth data points in the depth image;
fitting the valid depth data points;
s1: in the maximum allowable iteration number range, the number of local points is calculated in the formula (1) to obtain the iteration number each time the fit plane is obtained, if the current iteration number reaches the calculated iteration number or is larger than the maximum allowable iteration number, the loop execution is stopped S3, and if not, the loop execution is executed S2;
s2: in the current iteration times, recording the plane with the minimum number of the out-office points as a suboptimal plane, and then executing S1;
s3: outputting a suboptimal plane, and then executing a fourth step;
s4: judging whether the number of the out-of-office points is reduced, if so, executing S5, otherwise, executing S6;
s5: iteratively updating the optimal plane, namely taking the plane with the minimum number of the out-of-office points as the optimal plane;
s6: and outputting the optimal plane.
A plane fitting apparatus for removing outliers, comprising:
the effective depth data point acquisition unit is used for randomly selecting effective depth data points in the depth data, wherein the effective depth data points refer to data points with a mask value of true and data information of-32768-32767 in the depth image;
the candidate plane acquisition unit is used for fitting the effective depth data points to obtain a plurality of candidate planes;
a calculation unit that calculates a distance of the effective depth data point to the candidate plane;
a suboptimal plane obtaining unit, configured to perform iterative loop on the candidate plane within a maximum allowable iteration number range to obtain a suboptimal plane, where the suboptimal plane is a plane with a smallest number of local outliers in the candidate plane, and the local outliers are effective depth data points whose distances are greater than a preset distance threshold;
the optimal plane obtaining unit is used for fitting the inner points in the suboptimal plane to obtain a plurality of optimal planes, wherein the inner points are effective depth data points of which the distance is less than or equal to a preset distance threshold;
and the optimal plane obtaining unit is used for carrying out iterative optimization on the optimal planes, and selecting the fitting plane with the minimum number of the local points from the optimal planes as the optimal plane.
Optionally, the plane fitting apparatus for removing the local outliers further includes:
and the effective depth data point output unit is used for outputting data points with the mask value of true and the data information of-32768-32767 in the depth image data as effective depth data points.
A computer readable storage medium having stored thereon computer instructions which, when executed by a processor, implement the steps of the plane fitting method for removing outliers.
A detection apparatus, the detection apparatus comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the one processor to cause the at least one processor to perform the method of plane fitting to remove outliers.
The technical scheme of the application has the advantages that: the method comprises the steps of fitting effective depth data points in a depth image to obtain a plurality of candidate planes, calculating the distance between the effective depth data points and the candidate planes, and performing iterative circulation on the candidate planes within the maximum allowable iteration frequency range to obtain suboptimal planes; and then fitting the inner points in the suboptimal plane to obtain a plurality of optimal planes, performing iterative optimization on the optimal planes, and selecting the fitted plane with the minimum number of the local outer points from the optimal planes as the optimal plane. After the interfering local outer points in the depth image are removed, useful data capable of really expressing the information of the object is left, and a more accurate fitting result is obtained. The method for plane fitting by removing the local outliers is essentially a continuous iteration optimization searching process, different distance thresholds can be set according to an actual scene, different plane fitting results are obtained, namely corresponding results are obtained according to requirements, preprocessing is not needed for depth images, the local outliers can be effectively removed, the obtained fitting planes are more accurate, and a guarantee is provided for measurement and detection algorithms.
It is noted that relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that an article or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above description is merely exemplary of the present application and is presented to enable those skilled in the art to understand and practice the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
It will be understood that the present application is not limited to what has been described above and shown in the accompanying drawings, and that various modifications and changes can be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (9)
1. A plane fitting method for removing local outliers is characterized by comprising the following steps:
randomly selecting effective depth data points in the depth image, wherein the effective depth data points refer to data points with a mask value of true and data information of-32768-32767 in the depth image;
fitting the effective depth data points to obtain a plurality of candidate planes;
calculating a distance of the effective depth data point to the candidate plane;
performing iterative circulation on the candidate plane within the maximum allowable iteration frequency range to obtain a suboptimal plane, wherein the suboptimal plane refers to a plane with the minimum number of local outliers in the candidate plane, and the local outliers refer to effective depth data points with the distance greater than a preset distance threshold;
fitting the interior points in the suboptimal plane to obtain a plurality of optimal planes, wherein the interior points refer to effective depth data points of which the distance is less than or equal to a preset distance threshold;
and performing iterative optimization on the preferred plane, and selecting a fitting plane with the minimum number of the outlying points from the preferred planes to be the optimal plane.
2. The method of claim 1, further comprising a distance threshold pre-setting, comprising:
and setting a distance threshold value meeting the removal requirement according to the actual application scene of the depth image.
3. The method of claim 2, wherein obtaining a maximum number of iterations allowed comprises:
inputting the confidence coefficient and the proportion of the local outliers into an iterative optimization model, and calculating the maximum allowable iteration times by the iterative optimization model according to the following formula:
wherein, P is the confidence coefficient, t is the proportion of the local out-point, and K is the maximum allowable iteration number.
4. The method of claim 3, wherein obtaining valid depth data points comprises:
and outputting data points with the mask value of true and the data information of-32768-32767 in the depth image data as effective depth data points.
5. The method of claim 1, wherein the confidence level is in the range of [0, 1 ].
6. The method of any one of claims 1-5, wherein the method is further applied to fit depth data in a straight line, circle or sphere with the local outliers.
7. A plane fitting apparatus for removing outliers, comprising:
the effective depth data point acquisition unit is used for randomly selecting effective depth data points in the depth data, wherein the effective depth data points refer to data points with a mask value of true and data information of-32768-32767 in the depth image;
the candidate plane acquisition unit is used for fitting the effective depth data points to obtain a plurality of candidate planes;
a calculation unit that calculates a distance of the effective depth data point to the candidate plane;
a suboptimal plane obtaining unit, configured to perform iterative loop on the candidate plane within a maximum allowable iteration number range to obtain a suboptimal plane, where the suboptimal plane is a plane with a smallest number of local outliers in the candidate plane, and the local outliers are effective depth data points whose distances are greater than a preset distance threshold;
the optimal plane obtaining unit is used for fitting the inner points in the suboptimal plane to obtain a plurality of optimal planes, wherein the inner points are effective depth data points of which the distance is less than or equal to a preset distance threshold;
and the optimal plane obtaining unit is used for carrying out iterative optimization on the optimal planes, and selecting the fitting plane with the minimum number of the local points from the optimal planes as the optimal plane.
8. The outlier plane fitting removing device of claim 7 further comprising:
and the distance threshold presetting unit is used for setting a distance threshold meeting the removal requirement according to the actual application scene of the depth image.
9. A detection device, characterized in that the detection device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the one processor to cause the at least one processor to perform the method of removing outlier plane fitting of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010930337.8A CN112085773A (en) | 2020-09-07 | 2020-09-07 | Plane fitting method and device for removing local outliers |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010930337.8A CN112085773A (en) | 2020-09-07 | 2020-09-07 | Plane fitting method and device for removing local outliers |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112085773A true CN112085773A (en) | 2020-12-15 |
Family
ID=73733116
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010930337.8A Pending CN112085773A (en) | 2020-09-07 | 2020-09-07 | Plane fitting method and device for removing local outliers |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112085773A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113654461A (en) * | 2021-08-24 | 2021-11-16 | 凌云光技术股份有限公司 | Cone fitting method and device for removing local outliers in depth image |
| CN113658156A (en) * | 2021-08-24 | 2021-11-16 | 凌云光技术股份有限公司 | Sphere fitting method and device for removing local outliers in depth image |
| CN113706505A (en) * | 2021-08-24 | 2021-11-26 | 凌云光技术股份有限公司 | Cylinder fitting method and device for removing local outliers in depth image |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108037514A (en) * | 2017-11-07 | 2018-05-15 | 国网甘肃省电力公司电力科学研究院 | One kind carries out screen of trees safety detection method using laser point cloud |
| CN110070570A (en) * | 2019-03-20 | 2019-07-30 | 重庆邮电大学 | A kind of obstacle detection system and method based on depth information |
| CN110533726A (en) * | 2019-08-28 | 2019-12-03 | 哈尔滨工业大学 | A kind of laser radar scene 3 d pose point normal estimation modification method |
| CN110910454A (en) * | 2019-10-11 | 2020-03-24 | 华南农业大学 | Automatic calibration registration method of mobile livestock three-dimensional reconstruction equipment |
| CN113706505A (en) * | 2021-08-24 | 2021-11-26 | 凌云光技术股份有限公司 | Cylinder fitting method and device for removing local outliers in depth image |
-
2020
- 2020-09-07 CN CN202010930337.8A patent/CN112085773A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108037514A (en) * | 2017-11-07 | 2018-05-15 | 国网甘肃省电力公司电力科学研究院 | One kind carries out screen of trees safety detection method using laser point cloud |
| CN110070570A (en) * | 2019-03-20 | 2019-07-30 | 重庆邮电大学 | A kind of obstacle detection system and method based on depth information |
| CN110533726A (en) * | 2019-08-28 | 2019-12-03 | 哈尔滨工业大学 | A kind of laser radar scene 3 d pose point normal estimation modification method |
| CN110910454A (en) * | 2019-10-11 | 2020-03-24 | 华南农业大学 | Automatic calibration registration method of mobile livestock three-dimensional reconstruction equipment |
| CN113706505A (en) * | 2021-08-24 | 2021-11-26 | 凌云光技术股份有限公司 | Cylinder fitting method and device for removing local outliers in depth image |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113654461A (en) * | 2021-08-24 | 2021-11-16 | 凌云光技术股份有限公司 | Cone fitting method and device for removing local outliers in depth image |
| CN113658156A (en) * | 2021-08-24 | 2021-11-16 | 凌云光技术股份有限公司 | Sphere fitting method and device for removing local outliers in depth image |
| CN113706505A (en) * | 2021-08-24 | 2021-11-26 | 凌云光技术股份有限公司 | Cylinder fitting method and device for removing local outliers in depth image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109493375B (en) | Data matching and merging method and device for three-dimensional point cloud and readable medium | |
| CN112085773A (en) | Plane fitting method and device for removing local outliers | |
| US10255480B2 (en) | Monitoring object shape and deviation from design | |
| EP3698275B1 (en) | Data processing method, apparatus, system and storage media | |
| JP5487298B2 (en) | 3D image generation | |
| CN106570867B (en) | Movable contour model image fast segmentation method based on gray scale morphology energy method | |
| US8755630B2 (en) | Object pose recognition apparatus and object pose recognition method using the same | |
| CN111275633B (en) | Point cloud denoising method, system, device and storage medium based on image segmentation | |
| JP6571225B2 (en) | Camera posture estimation method and system | |
| US20100232709A1 (en) | Estimation of image relations from point correspondences between images | |
| CN112489140B (en) | Attitude measurement method | |
| CN111476814B (en) | Target tracking method, device, equipment and storage medium | |
| CN111144213A (en) | Object detection method and related equipment | |
| CN112541950A (en) | Method and device for calibrating external parameter of depth camera | |
| CN109902641B (en) | Semantic alignment-based face key point detection method, system and device | |
| CN109035363B (en) | Line-circle optimal fitting method for rapid iteration | |
| CN115527050A (en) | Image feature matching method, computer device and readable storage medium | |
| CN114842213A (en) | Obstacle contour detection method and device, terminal equipment and storage medium | |
| US20210287049A1 (en) | Method and system for processing an image and performing instance segmentation using affinity graphs | |
| CN113706505A (en) | Cylinder fitting method and device for removing local outliers in depth image | |
| CN113658156A (en) | Sphere fitting method and device for removing local outliers in depth image | |
| CN110807818A (en) | RGB-DSLAM method and device based on key frame | |
| CN113344988A (en) | Stereo matching method, terminal and storage medium | |
| CN114266816B (en) | Dense depth map construction method, device, equipment and medium | |
| CN104751434A (en) | Method and apparatus for dividing object from image |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201215 |