CN113869390A - Information processing method and device for multi-view three-dimensional reconstruction - Google Patents
Information processing method and device for multi-view three-dimensional reconstruction Download PDFInfo
- Publication number
- CN113869390A CN113869390A CN202111121954.4A CN202111121954A CN113869390A CN 113869390 A CN113869390 A CN 113869390A CN 202111121954 A CN202111121954 A CN 202111121954A CN 113869390 A CN113869390 A CN 113869390A
- Authority
- CN
- China
- Prior art keywords
- pixel block
- pixel
- determining
- picture
- pixel point
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
Abstract
The disclosure discloses an information processing method and device for multi-view three-dimensional reconstruction, wherein the method comprises the following steps: after acquiring the semantically identified reference picture and the semantically identified picture associated with the reference picture, determining a pixel block corresponding to a target pixel point in the reference picture aiming at the target pixel point; determining an associated pixel block corresponding to the pixel block in the associated picture based on the semantic label corresponding to the pixel block and the semantic label of the associated picture; and determining the value of each pixel point in the associated pixel block. After the pixel block is determined, the associated pixel block is determined in the associated picture based on the semantic tag information, and then the value of the pixel point in the associated pixel block is determined, so that the accuracy of determining the pixel value is improved, the reconstruction effect based on MVS is improved, and the problem that the MVS reconstruction effect is not ideal due to low accuracy of determining the pixel value in the related technology is solved.
Description
Technical Field
The present disclosure relates to the field of image processing technologies, and in particular, to an information processing method and apparatus for multi-view three-dimensional reconstruction.
Background
MVS-Multi view system, MVS almost matches each pixel point in the picture, almost reconstructs the three-dimensional coordinate of each pixel point, and the density degree of the obtained points can be closer to the definition shown by the image.
In the related art, the pixel scoring accuracy in the MVS process is low, which results in poor effect after three-dimensional reconstruction based on MVS.
Disclosure of Invention
The main purpose of the present disclosure is to provide an information processing method and apparatus for multi-view three-dimensional reconstruction.
In order to achieve the above object, according to a first aspect of the present disclosure, there is provided an information processing method for multi-view three-dimensional reconstruction, comprising: after acquiring the semantically identified reference picture and the semantically identified picture associated with the reference picture, determining a pixel block corresponding to a target pixel point in the reference picture aiming at the target pixel point; determining an associated pixel block corresponding to the pixel block in the associated picture based on the semantic label corresponding to the pixel block and the semantic label of the associated picture; and determining the value of each pixel point in the associated pixel block.
Optionally, determining, in the associated picture, an associated pixel block corresponding to the pixel block based on the semantic tag corresponding to the pixel block and the semantic tag of the associated picture comprises: aiming at each pixel point in the pixel block, determining a related pixel point of the pixel point in the related picture; determining an initial associated pixel block corresponding to the pixel block based on the position of each associated pixel point; and determining an associated pixel block corresponding to the pixel block in the initial associated pixel block based on the semantic label corresponding to the pixel block in the pixel block and the semantic label corresponding to the initial associated pixel block.
Optionally, determining an initial associated pixel block corresponding to the pixel block based on the position of each associated pixel point includes: determining neighborhood pixels corresponding to each associated pixel point based on the position of each associated pixel point, wherein the neighborhood pixels comprise a preset number of neighborhood pixel points; and determining all neighborhood pixels corresponding to all the associated pixel points as initial associated pixel blocks.
Optionally, determining, based on the semantic tag corresponding to the pixel block and the semantic tag corresponding to the initial associated pixel block, an associated pixel block corresponding to the pixel block in the initial associated pixel block includes: and filtering neighborhood pixels with the semantic labels inconsistent with the semantic labels of the pixels in the neighborhood pixels to obtain target neighborhood pixels corresponding to each associated pixel point, wherein the target neighborhood pixels corresponding to all the associated pixel points form associated pixel blocks.
Optionally, determining a value of each pixel point in the associated pixel block includes: and calculating to obtain the pixel value of the corresponding associated pixel point by utilizing a preset calculation strategy based on the pixel values of the pixel points in the target neighborhood pixels.
According to a second aspect of the present disclosure, there is provided an information processing apparatus for multi-view three-dimensional reconstruction, comprising: the pixel block determining unit is configured to determine a corresponding pixel block for a target pixel point in a reference picture after the semantically identified reference picture and the semantically identified picture associated with the reference picture are acquired; an associated pixel block determination unit configured to determine an associated pixel block corresponding to the pixel block in the associated picture based on the semantic tag corresponding to the pixel block and the semantic tag of the associated picture; a pixel value determination unit configured to determine a value of each pixel point in the associated pixel block.
Optionally, based on the semantic label corresponding to the pixel block and the semantic label of the associated picture, determining, in the associated picture, the associated pixel block corresponding to the pixel block is further configured to: aiming at each pixel point in the pixel block, determining a related pixel point of the pixel point in the related picture; determining an initial associated pixel block corresponding to the pixel block based on the position of each associated pixel point; and determining an associated pixel block corresponding to the pixel block in the initial associated pixel block based on the semantic label corresponding to the pixel block in the pixel block and the semantic label corresponding to the initial associated pixel block.
Optionally, determining, based on the position of each associated pixel point, that an initial associated pixel block corresponding to the pixel block is configured to: determining neighborhood pixels corresponding to each associated pixel point based on the position of each associated pixel point, wherein the neighborhood pixels comprise a preset number of neighborhood pixel points; and determining all neighborhood pixels corresponding to all the associated pixel points as initial associated pixel blocks.
According to a third aspect of the present disclosure, there is provided a computer-readable storage medium storing computer instructions for causing the information processing method for multi-view three-dimensional reconstruction according to any one of the first aspects of the computer.
According to a fourth aspect of the present disclosure, there is provided an electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to cause the at least one processor to perform the information processing method for multi-view three-dimensional reconstruction of any one of the first aspect.
In the embodiment of the disclosure, after acquiring the semantically identified reference picture and the semantically identified picture associated with the reference picture, determining a pixel block corresponding to a target pixel point in the reference picture for the target pixel point; determining an associated pixel block corresponding to the pixel block in the associated picture based on the semantic label corresponding to the pixel block and the semantic label of the associated picture; and determining the value of each pixel point in the associated pixel block. After the pixel block is determined, the associated pixel block is determined in the associated picture based on the semantic tag information, and then the value of the pixel point in the associated pixel block is determined, so that the accuracy of determining the pixel value is improved, the reconstruction effect based on MVS is improved, and the problem that the MVS reconstruction effect is not ideal due to low accuracy of determining the pixel value in the related technology is solved.
Drawings
In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of an information processing method for multi-view three-dimensional reconstruction according to an embodiment of the present disclosure;
fig. 2 is an application scenario diagram of an information processing method for multi-view three-dimensional reconstruction according to an embodiment of the present disclosure;
FIG. 3 is a schematic structural diagram of an information processing apparatus for multi-view three-dimensional reconstruction according to an embodiment of the present disclosure;
fig. 4 is a schematic diagram of an electronic device according to an embodiment of the disclosure.
Detailed Description
In order to make the technical solutions of the present disclosure better understood by those skilled in the art, the technical solutions of the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are only some embodiments of the present disclosure, not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure.
It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the present disclosure may be described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be noted that, in the present disclosure, the embodiments and features of the embodiments may be combined with each other without conflict. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
According to an embodiment of the present disclosure, there is provided an information processing method for multi-view three-dimensional reconstruction, as shown in fig. 1, the method including steps 101 to 103 as follows:
step 101: after the semantically identified reference picture and the semantically identified picture associated with the reference picture are obtained, a pixel block corresponding to a target pixel point in the reference picture is determined according to the target pixel point in the reference picture.
In this embodiment, semantic segmentation and recognition may be performed on each picture in advance, so that pixels on each picture correspond to semantic tags. For the reference picture, a target pixel point X may be selected, a patch tile of the target pixel point X is generated for the target pixel point X, the patch tile is used as a pixel block of this embodiment, and each pixel point in the pixel block corresponds to a corresponding semantic tag.
Step 102: and determining an associated pixel block corresponding to the pixel block in the associated picture based on the semantic label corresponding to the pixel block and the semantic label of the associated picture.
As an optional implementation manner of this embodiment, determining, based on the semantic tag corresponding to the pixel block and the semantic tag of the associated picture, an associated pixel block corresponding to the pixel block in the associated picture includes: aiming at each pixel point in the pixel block, determining a related pixel point of the pixel point in the related picture; determining an initial associated pixel block corresponding to the pixel block based on the position of each associated pixel point; and determining an associated pixel block corresponding to the pixel block in the initial associated pixel block based on the semantic label corresponding to the pixel block in the pixel block and the semantic label corresponding to the initial associated pixel block.
In this embodiment, referring to fig. 2, for any pixel point ps in a reference picture ref _ image pixel block, an associated pixel point pt associated with the pixel point ps is determined in a picture src _ image associated with the pixel point ps by using homography, after pt is determined, a preset number of pixel points at a preset position (for example, around the pixel point) are determined based on the position of the pixel point pt, and a pixel formed by the pixel points is hereinafter referred to as an "effective calculation region"; by the method, effective calculation areas of all the associated pixel points can be determined, and all the effective calculation areas serve as initial associated pixel blocks. And finally, determining an associated pixel block corresponding to the pixel block in the initial associated pixel block based on the semantic label corresponding to the pixel block in the pixel block and the semantic label corresponding to the initial associated pixel block. The contents of the semantic tags can be compared, and pixel points corresponding to different semantic tags are filtered.
As an optional implementation manner of this embodiment, determining, based on the position of each associated pixel point, an initial associated pixel block corresponding to a pixel block includes: determining neighborhood pixels corresponding to each associated pixel point based on the position of each associated pixel point, wherein the neighborhood pixels comprise a preset number of neighborhood pixel points; and determining all neighborhood pixels corresponding to all the associated pixel points as initial associated pixel blocks.
In this optional implementation manner, referring to fig. 2, an "effective calculation region" may be determined as a domain pixel by taking the associated pixel point as a center, for example, pt as a center, and a neighborhood pixel is a neighboring pixel point around the "effective calculation region" with a preset number (for example, 8) of neighboring pixels. By the method, the domain pixels determined by all the associated pixel points can be determined, and all the domain pixels can be used as initial associated pixel blocks.
As an optional implementation manner of this embodiment, based on the semantic tag corresponding to the pixel block and the semantic tag corresponding to the initial associated pixel block, determining, in the initial associated pixel block, an associated pixel block corresponding to the pixel block includes: and filtering neighborhood pixels with the semantic labels inconsistent with the semantic labels of the pixels in the neighborhood pixels to obtain target neighborhood pixels corresponding to each associated pixel point, wherein the target neighborhood pixels corresponding to all the associated pixel points form associated pixel blocks.
In this optional implementation, after determining the neighborhood pixels, pt and semantic labels of all pixel points in the neighborhood pixels may be determined first, and pixel points in the neighborhood pixels with different semantic labels from ps semantic labels may be filtered. By the method, all the pixel points with semantic labels different from those of all the pixel points in the pixel block can be filtered out from the initial associated pixel block.
By filtering the neighborhood pixels and determining the pixel values of the pixel points by using the filtered pixels, the accuracy of the pixel values can be improved, and the quality of MVS results is greatly improved.
Step 103: and determining the value of each pixel point in the associated pixel block.
In this embodiment, after the target neighborhood pixel of each associated pixel is determined, the pixel value of the associated pixel may be determined by using a calculation method such as an interpolation strategy, a random sampling strategy, or an average value. Taking linear interpolation as an example, if the pixel value of the (1,1) point in the target domain pixel is 40 and the pixel value of the (3,3) point is 140, for example, the pixel value of the estimated pt (2,2) point may be 100.
Referring to fig. 2, in the present embodiment, a given reference picture (i.e., ref _ image) is subjected to depth estimation with respect to a target pixel (x); firstly, forming a patch small block of x aiming at a target pixel point x, and then searching a related pixel (pt) in a related image (src _ image) through homography transformation aiming at each pixel in the patch small block; the semantic labels of each pixel in the src _ image _ i image are obtained through semantic segmentation, when the corresponding value of pt is calculated, an "effective calculation range" is locked by taking pt as the center, for example, pt is taken as the center in the legend, the "effective calculation range" is 8 adjacent pixel points around the "effective calculation range", after the "effective calculation range" is determined, the semantic labels of all pixel points in pt and the "effective calculation range" are firstly judged, pixel points with different semantic labels from ps are filtered, a semantic label set identical to pt is formed, and the corresponding value of pt is obtained through strategies such as interpolation in the set.
According to the method, the accuracy of pixel scoring can be improved, and the quality of MVS results can be improved.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
According to an embodiment of the present disclosure, there is also provided an apparatus for implementing the information processing method for multi-view three-dimensional reconstruction, as shown in fig. 3, the apparatus includes: the pixel block determining unit 301 is configured to determine a pixel block corresponding to a target pixel point in a reference picture after acquiring the semantically identified reference picture and the semantically identified picture associated with the reference picture; an associated pixel block determination unit 302 configured to determine an associated pixel block corresponding to the pixel block in the associated picture based on the semantic tag corresponding to the pixel block and the semantic tag of the associated picture; a pixel value determining unit 303 configured to determine a value of each pixel point in the associated pixel block.
As an optional implementation manner of this embodiment, based on the semantic tag corresponding to the pixel block and the semantic tag of the associated picture, determining, in the associated picture, an associated pixel block corresponding to the pixel block is further configured to: aiming at each pixel point in the pixel block, determining a related pixel point of the pixel point in the related picture; determining an initial associated pixel block corresponding to the pixel block based on the position of each associated pixel point; and determining an associated pixel block corresponding to the pixel block in the initial associated pixel block based on the semantic label corresponding to the pixel block in the pixel block and the semantic label corresponding to the initial associated pixel block.
As an optional implementation manner of this embodiment, based on the position of each associated pixel point, determining that an initial associated pixel block corresponding to a pixel block is configured to: determining neighborhood pixels corresponding to each associated pixel point based on the position of each associated pixel point, wherein the neighborhood pixels comprise a preset number of neighborhood pixel points; and determining all neighborhood pixels corresponding to all the associated pixel points as initial associated pixel blocks.
After the pixel block is determined, the associated pixel block is determined in the associated picture based on the semantic tag information, and then the value of the pixel point in the associated pixel block is determined, so that the accuracy of determining the pixel value is improved, the reconstruction effect based on MVS is improved, and the problem that the MVS reconstruction effect is not ideal due to low accuracy of determining the pixel value in the related technology is solved.
The embodiment of the present disclosure provides an electronic device, as shown in fig. 4, the electronic device includes one or more processors 41 and a memory 42, where one processor 41 is taken as an example in fig. 4.
The controller may further include: an input device 43 and an output device 44.
The processor 41, the memory 42, the input device 43 and the output device 44 may be connected by a bus or other means, and fig. 4 illustrates the connection by a bus as an example.
The processor 41 may be a Central Processing Unit (CPU). The processor 41 may also be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or combinations thereof. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 42, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to the control methods in the embodiments of the present disclosure. The processor 41 executes various functional applications of the server and data processing, namely, implements the information processing method for multi-view three-dimensional reconstruction of the above-described method embodiment, by running the non-transitory software program, instructions and modules stored in the memory 42.
The memory 42 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of a processing device operated by the server, and the like. Further, the memory 42 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, memory 42 may optionally include memory located remotely from processor 41, which may be connected to a network connection device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 43 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the processing device of the server. The output device 44 may include a display device such as a display screen.
One or more modules are stored in the memory 42, which when executed by the one or more processors 41, perform the method as shown in fig. 1.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program to instruct related hardware, and the program can be stored in a computer readable storage medium, and when executed, the program can include the processes of the embodiments of the motor control methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-only memory (ROM), a Random Access Memory (RAM), a flash memory (FlashMemory), a hard disk (hard disk drive, abbreviated as HDD) or a Solid State Drive (SSD), etc.; the storage medium may also comprise a combination of memories of the kind described above.
Although the embodiments of the present disclosure have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present disclosure, and such modifications and variations fall within the scope defined by the appended claims.
Claims (10)
1. An information processing method for multi-view three-dimensional reconstruction, comprising:
after acquiring the semantically identified reference picture and the semantically identified picture associated with the reference picture, determining a pixel block corresponding to a target pixel point in the reference picture aiming at the target pixel point;
determining an associated pixel block corresponding to the pixel block in the associated picture based on the semantic label corresponding to the pixel block and the semantic label of the associated picture;
and determining the value of each pixel point in the associated pixel block.
2. The information processing method for multi-view three-dimensional reconstruction according to claim 1, wherein determining an associated pixel block corresponding to the pixel block among the associated pictures based on the semantic label corresponding to the pixel block and the semantic label of the associated pictures comprises:
aiming at each pixel point in the pixel block, determining a related pixel point of the pixel point in the related picture;
determining an initial associated pixel block corresponding to the pixel block based on the position of each associated pixel point;
and determining an associated pixel block corresponding to the pixel block in the initial associated pixel block based on the semantic label corresponding to the pixel block in the pixel block and the semantic label corresponding to the initial associated pixel block.
3. The information processing method for multi-view three-dimensional reconstruction according to claim 2, wherein determining an initial associated pixel block corresponding to the pixel block based on the position of each associated pixel point comprises:
determining neighborhood pixels corresponding to each associated pixel point based on the position of each associated pixel point, wherein the neighborhood pixels comprise a preset number of neighborhood pixel points;
and determining all neighborhood pixels corresponding to all the associated pixel points as initial associated pixel blocks.
4. The information processing method for multi-view three-dimensional reconstruction according to claim 3, wherein determining an associated pixel block corresponding to a pixel block among the initial associated pixel blocks based on the semantic label corresponding to the pixel block and the semantic label corresponding to the initial associated pixel block comprises:
and filtering neighborhood pixels with the semantic labels inconsistent with the semantic labels of the pixels in the neighborhood pixels to obtain target neighborhood pixels corresponding to each associated pixel point, wherein the target neighborhood pixels corresponding to all the associated pixel points form associated pixel blocks.
5. The information processing method for multi-view three-dimensional reconstruction according to claim 4, wherein determining the value of each pixel point in the associated pixel block comprises:
and calculating to obtain the pixel value of the corresponding associated pixel point by utilizing a preset calculation strategy based on the pixel values of the pixel points in the target neighborhood pixels.
6. An information processing apparatus for multi-view three-dimensional reconstruction, comprising:
the pixel block determining unit is configured to determine a corresponding pixel block for a target pixel point in a reference picture after the semantically identified reference picture and the semantically identified picture associated with the reference picture are acquired;
an associated pixel block determination unit configured to determine an associated pixel block corresponding to the pixel block in the associated picture based on the semantic tag corresponding to the pixel block and the semantic tag of the associated picture;
a pixel value determination unit configured to determine a value of each pixel point in the associated pixel block.
7. The information processing apparatus for multi-view three-dimensional reconstruction according to claim 6, wherein determining, based on the semantic label corresponding to the pixel block and the semantic label of the associated picture, the associated pixel block corresponding to the pixel block in the associated picture is further configured to:
aiming at each pixel point in the pixel block, determining a related pixel point of the pixel point in the related picture;
determining an initial associated pixel block corresponding to the pixel block based on the position of each associated pixel point;
and determining an associated pixel block corresponding to the pixel block in the initial associated pixel block based on the semantic label corresponding to the pixel block in the pixel block and the semantic label corresponding to the initial associated pixel block.
8. The information processing apparatus for multi-view three-dimensional reconstruction according to claim 7, wherein determining, based on a position of each associated pixel point, an initial associated pixel block corresponding to a pixel block is configured to:
determining neighborhood pixels corresponding to each associated pixel point based on the position of each associated pixel point, wherein the neighborhood pixels comprise a preset number of neighborhood pixel points;
and determining all neighborhood pixels corresponding to all the associated pixel points as initial associated pixel blocks.
9. A computer-readable storage medium storing computer instructions for causing a computer to execute the information processing method for multi-view three-dimensional reconstruction according to any one of claims 1 to 5.
10. An electronic device, comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to cause the at least one processor to perform the information processing method for multi-view three-dimensional reconstruction as claimed in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111121954.4A CN113869390B (en) | 2021-09-24 | 2021-09-24 | Information processing method and device for multi-view three-dimensional reconstruction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111121954.4A CN113869390B (en) | 2021-09-24 | 2021-09-24 | Information processing method and device for multi-view three-dimensional reconstruction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113869390A true CN113869390A (en) | 2021-12-31 |
| CN113869390B CN113869390B (en) | 2023-03-24 |
Family
ID=78993797
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111121954.4A Active CN113869390B (en) | 2021-09-24 | 2021-09-24 | Information processing method and device for multi-view three-dimensional reconstruction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113869390B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050110610A1 (en) * | 2003-09-05 | 2005-05-26 | Bazakos Michael E. | System and method for gate access control |
| CN110097584A (en) * | 2019-03-18 | 2019-08-06 | 国网浙江省电力有限公司信息通信分公司 | The method for registering images of combining target detection and semantic segmentation |
| CN111126140A (en) * | 2019-11-19 | 2020-05-08 | 腾讯科技（深圳）有限公司 | Text recognition method and device, electronic equipment and storage medium |
-
2021
- 2021-09-24 CN CN202111121954.4A patent/CN113869390B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050110610A1 (en) * | 2003-09-05 | 2005-05-26 | Bazakos Michael E. | System and method for gate access control |
| CN110097584A (en) * | 2019-03-18 | 2019-08-06 | 国网浙江省电力有限公司信息通信分公司 | The method for registering images of combining target detection and semantic segmentation |
| CN111126140A (en) * | 2019-11-19 | 2020-05-08 | 腾讯科技（深圳）有限公司 | Text recognition method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113869390B (en) | 2023-03-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110795976B (en) | Method, device and equipment for training object detection model | |
| Cuisenaire | Locally adaptable mathematical morphology using distance transformations | |
| WO2022105608A1 (en) | Rapid face density prediction and face detection method and apparatus, electronic device, and storage medium | |
| CN110942071A (en) | License plate recognition method based on license plate classification and LSTM | |
| US20220270204A1 (en) | Image registration method, terminal, and computer storage medium | |
| CN112991349B (en) | Image processing method, device, equipment and storage medium | |
| CN113159026A (en) | Image processing method, image processing apparatus, electronic device, and medium | |
| CN113592720B (en) | Image scaling processing method, device, equipment and storage medium | |
| CN111260675A (en) | High-precision extraction method and system for image real boundary | |
| CN113869390B (en) | Information processing method and device for multi-view three-dimensional reconstruction | |
| JP2010257267A (en) | Device, method and program for detecting object area | |
| CN110046623B (en) | Image feature point extraction method and camera | |
| CN111178192A (en) | Position identification method and device for target object in image | |
| CN113436068B (en) | Image splicing method and device, electronic equipment and storage medium | |
| CN110874814A (en) | Image processing method, image processing device and terminal equipment | |
| CN113542847B (en) | Image display method, device, equipment and storage medium | |
| CN113763233A (en) | Image processing method, server and photographing device | |
| CN109657523B (en) | Driving region detection method and device | |
| US20210110202A1 (en) | 3d object detection from calibrated 2d images | |
| CN108345893B (en) | Straight line detection method and device, computer storage medium and terminal | |
| CN112465835A (en) | Method for jadeite image segmentation and model training method | |
| CN112580638B (en) | Text detection method and device, storage medium and electronic equipment | |
| CN117315406B (en) | Sample image processing method, device and equipment | |
| CN111160358A (en) | Image binarization method, device, equipment and medium | |
| CN110827377B (en) | Particle fuzzy processing method, device, computer equipment and storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |