CN113112393A - Marginalizing device in visual navigation system - Google Patents
Marginalizing device in visual navigation system Download PDFInfo
- Publication number
- CN113112393A CN113112393A CN202110237941.7A CN202110237941A CN113112393A CN 113112393 A CN113112393 A CN 113112393A CN 202110237941 A CN202110237941 A CN 202110237941A CN 113112393 A CN113112393 A CN 113112393A
- Authority
- CN
- China
- Prior art keywords
- parameter
- parameter block
- jacobian
- information
- block
- 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
- 230000000007 visual effect Effects 0.000 title claims abstract description 23
- 238000004364 calculation method Methods 0.000 claims description 39
- 239000011159 matrix material Substances 0.000 claims description 37
- 238000012545 processing Methods 0.000 claims description 14
- 238000003860 storage Methods 0.000 claims description 12
- 230000000295 complement effect Effects 0.000 claims description 10
- 238000001914 filtration Methods 0.000 claims description 6
- 238000009826 distribution Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 5
- 230000010354 integration Effects 0.000 claims description 5
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 238000011084 recovery Methods 0.000 claims description 2
- 238000000034 method Methods 0.000 abstract description 15
- 230000008569 process Effects 0.000 abstract description 8
- 238000010586 diagram Methods 0.000 description 12
- 238000004590 computer program Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 238000013461 design Methods 0.000 description 6
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000000717 retained effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
- G06T1/20—Processor architectures; Processor configuration, e.g. pipelining
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/30—Arrangements for executing machine instructions, e.g. instruction decode
- G06F9/38—Concurrent instruction execution, e.g. pipeline or look ahead
- G06F9/3867—Concurrent instruction execution, e.g. pipeline or look ahead using instruction pipelines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
- G06T1/60—Memory management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the application provides an edge device in a visual navigation system, which is used for solving the problem of low speed in the edge process and relates to the technical field of integrated circuits. In the embodiment of the application, marginalization is realized by adopting a hardware mode, the jacobian is calculated by utilizing the irrelevance of data and a parallel mode, and the operation performance is improved.
Description
Technical Field
The present application relates to the field of integrated circuit technology, and more particularly, to a marginalization apparatus in a visual navigation system.
Background
In a visual navigation (VSLAM) system, in order to simplify the design, the number of optimized state variables such as the position and orientation of a camera, the position and orientation of the camera relative to an IMU, and image characteristics is kept stable, so that the system does not increase the number of optimized state variables all the time due to the advancement of time, and a sliding window design mode is adopted. The sliding window method inevitably has new image frames coming in and old image frames leaving in the sliding process. Directly discarding the old image frame will lose some useful information, which will have some impact on the system performance. The marginalization can preserve the information of the old image frame, so that the old image frame is well utilized.
In the design of the related art, marginalization is mostly realized by software, but the software is converted into a machine instruction after being processed by a compiler, and the execution speed on a Central Processing Unit (CPU) is slow.
Disclosure of Invention
The application aims to provide a marginalization device in a visual navigation system, which is used for solving the problem of low speed in the marginalization process.
In a first aspect, an embodiment of the present application provides a marginalization apparatus in a visual navigation system, including:
the device comprises a marking and storage unit, a parameter block distribution unit and a parameter calculation circuit, wherein the parameter calculation circuit comprises a plurality of Jacobian calculation units and a parameter calculation unit, and the parameter calculation circuit comprises:
the marking and storing unit is used for acquiring at least one parameter block to be processed in the batch, marking the type of each acquired parameter block according to a preset marking rule and storing each parameter block; each parameter block comprises related parameters for visual navigation;
the parameter distribution unit is used for sending each parameter block to a Jacobian calculation unit corresponding to the type of the parameter block in the marginalized calculation circuit according to the type of the parameter block;
the parameter calculation circuit is used for processing each received parameter block based on a Jacobian calculation unit corresponding to the type of the parameter block to obtain a first Jacobian and a first residual error of the parameter block, wherein the first residual error is a residual error between the parameter block and preset information;
the parameter calculation circuit is further configured to perform a filtering operation on each of the parameter blocks by using the parameter calculation unit based on the first jacobian and the first residual of each of the parameter blocks, and calculate, for each of the remaining parameter blocks, the second jacobian and the second residual of the remaining parameter block by using the first jacobian and the first residual of the remaining parameter block.
In one embodiment, the parameter block carries an marginalization flag, the marginalization flag is used to indicate whether marginalization is to be performed, and the parameter calculation unit is specifically configured to:
and filtering the parameter blocks with the marginalized marks as second appointed values, and reserving the parameter blocks with the marginalized marks as first appointed values.
In one embodiment, the parameter block further carries length information, the length information is used for indicating the information length of the parameter block and is in one-to-one correspondence with the parameter block type, and the mark and storage unit is continuously stored according to the length information when the parameter block is stored.
In one embodiment, the preset information includes:
inertial sensor IMU pre-integration information, visual re-projection information, previous batch marginalization information.
In one embodiment, the parameter calculation unit includes: constructing an information matrix and residual error subunit, a parameter extraction subunit, a schur complement subunit and a recovery jacobian and residual error subunit; wherein:
the construction information matrix and residual error subunit is used for constructing a first information matrix according to the first Jacobian of each parameter block and constructing a residual error vector according to the first residual error of each parameter block;
the parameter extraction subunit is configured to extract the parameter block with the marginalization flag being the first specified value from the first information matrix, and use the parameter block as the previous batch of marginalization information for the next batch of marginalization processing;
the schur complement subunit is configured to perform schur complement operation on the first information matrix to obtain a second information matrix;
and the sub-unit for recovering the Jacobian and the residual error is used for calculating a second Jacobian and a second residual error of the reserved parameter block according to the first Jacobian and the first residual error of the reserved parameter block by adopting a preset algorithm.
In an embodiment, when the marking and storing unit performs type marking on each obtained parameter block according to a preset marking rule, the marking and storing unit is specifically configured to:
and determining the type of the parameter block according to the parameter block type indication information.
In an embodiment, the constructing the information matrix and the residual unit, when performing the constructing the first information matrix according to the jacobian of the parameter block, is specifically configured to:
determining the placement position of the first Jacobian in the first information matrix according to the marginalized mark;
constructing the first information matrix according to the placement position; wherein the jacobian of the parameter block is placed at the upper half triangle or the lower half triangle of the first information matrix.
The method adopts a hardware mode, so that the marginalized operation capability in the visual navigation system is greatly improved, the irrelevance of data is utilized, the Jacobian is calculated in a parallel mode, the processing performance is improved, the whole process adopts a pipeline mode, the preceding-stage module and the subsequent-stage module calculate simultaneously, and the performance of the system is further improved.
Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the application. The objectives and other advantages of the application may be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments of the present application will be briefly described below, and it is obvious that the drawings described below are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic device diagram of a marginalization device in a visual navigation system according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of a parameter calculation circuit of a marginalization device in the visual navigation system according to an embodiment of the present disclosure;
fig. 3 is a schematic diagram of a parameter calculation unit of a marginalization apparatus in the visual navigation system according to an embodiment of the present disclosure.
Detailed Description
In order to make the technical solutions of the present application better understood by those of ordinary skill in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.
It is noted that the terms first, second and the like in the description and in the claims of the present application are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
The inventor researches and discovers that in order to simplify the design in a visual navigation (VSLAM) system, the number of the optimized state variables is kept stable, so that the system does not adopt a sliding window design mode because the number of the optimized states is increased all the time due to the advancement of time. The sliding window method inevitably has new image frames coming in and old image frames leaving in the sliding process. Directly discarding the old image frame will lose some useful information, which will have some impact on the system performance. The marginalization can preserve the information of the old image frame, so that the old image frame is well utilized.
In the design of the related art, marginalization is mostly realized by software, but the software is converted into a machine instruction after being processed by a compiler, and can only be sequentially executed on a Central Processing Unit (CPU), and the execution speed is slow. At the same time, the execution of the current instruction may be interrupted by a higher priority instruction or program, which further results in a reduction in execution speed.
In view of the above, the present application provides a marginalization apparatus in a visual navigation system, which is used to solve the above problem. The inventive concept of the present application can be summarized as follows: the marginalization is realized by adopting a hardware mode, the jacobian is calculated by utilizing the irrelevance of data and a parallel mode, and the operation performance is improved.
Fig. 1 is a schematic diagram of an edge device in a visual navigation system according to an embodiment of the present disclosure. The figure includes: a marking and storing unit 101, a parameter block distributing unit 102, a parameter calculating circuit 103; wherein:
the marking and storing unit 101 is used for acquiring at least one parameter block, respectively marking the type of each acquired parameter block according to a preset marking rule, and storing each parameter block; each parameter block comprises related parameters for visual navigation;
in the embodiment of the present application, in order to save resources of a memory, a parameter block carries an marginalization flag and length information of the parameter block, where:
the marginalization mark is used for indicating whether the parameter block is marginalized or not, and when the marginalization mark of the parameter block is a first designated value, the parameter block is represented as a reserved parameter block; when the marginalized flag of the parameter block is a second specified value, the parameter block is represented as a filtered parameter block.
In one embodiment, a parameter block may be denoted by 0 to be retained and a parameter block may be denoted by 1 to be marginalized.
For example, the first Jacobian of the parameter block 1 is a, the Jacobian of the parameter block 2 is b, the Jacobian of the parameter block 3 is c, the Jacobian of the parameter block 4 is d, the Jacobian of the parameter block 5 is e, and the Jacobian of the parameter block 6 is f. Wherein the marginalization flag of the parameter blocks 1, 2, 3 is 1, i.e. the parameter blocks 1, 2, 3 are to be marginalized; the marginalized flag of the parameter block 4, 5, 6 is 0 and the first specified value, i.e., the parameter block 4, 5, 6, is to be reserved.
The length information is used for indicating the information length of the parameter block, and when the mark and storage unit stores the parameter block, the parameter block is stored in sequence according to the length information of the parameter block. For example: after the parameter block 1 arrives, the parameter block 1 is stored in the memory, and after the parameter block 2 arrives, the parameter block 2 is stored continuously.
In the embodiment of the application, all the parameter blocks are continuously stored in the memory, so that the storage resource is saved; for example: parameter block 1 occupies bits 0-8 in memory, and parameter block 2 begins to be stored at bit 9 of memory.
In order to save storage resources, the margining apparatus in the visual navigation system provided in the embodiment of the present application does not have a register for indicating the length of the parameter block, but associates the length information with the type of the parameter block, that is, determining the type of the parameter block is equivalent to determining the length information of the parameter block.
In one embodiment, the marking and storing unit determines the type of the parameter block according to the type indication information of the parameter block when respectively performing type marking on each acquired parameter block. For example: if the type indication information is 1, the type indication information corresponds to type 1, and if the type indication information is 2, the type indication information corresponds to type 2.
In one embodiment, the type of the parameter block is specially numbered according to the parameter information of the parameter block, for example, the type of the parameter block can be divided into: 0-10 are Pose (window position Pose) 0-Pose 10; 11-21 are SpeedBias (window speed and IMU bias) [0] -SpeedBias [10 ]; 22-23 are respectively Ex _ Pose (the poses of the left eye camera and the right eye camera relative to the IMU) [0] -Ex _ Pose [1 ]; td (time offset of IMU frame relative to image frame) [0] is 24; starting at 25 is Feature (inverse depth of Feature point).
Therefore, the window pose of the parameter block, the speed and IMU bias of the window, the poses of the left eye camera and the right eye camera relative to the IMU, the time offset of an IMU frame relative to an image frame, the inverse depth of the feature point and other information can be determined according to the type of the parameter block.
In the embodiment of the application, in order to improve the marginalized computation speed, a parallel mode is adopted to compute the jacobian of each parameter block, the jacobian computation units are in one-to-one correspondence with the types of the parameter blocks, and the parameter block distribution unit 102 sends the parameter blocks to the jacobian computation unit corresponding to the types of the parameter blocks in the marginalized computation circuit according to the types of the parameter blocks for each parameter block.
The parameter calculation circuit 103, as shown in fig. 2, includes: jacobian calculation section 104 and parameter calculation section 105.
For each received parameter block, processing the parameter block by a jacobian calculation unit 104 corresponding to the type of the parameter block to obtain a first jacobian and a first residual error of the parameter block, wherein the first residual error is a residual error between the parameter block and preset information; and the parameter calculation unit 105 is adopted to perform filtering operation on each parameter block based on the first Jacobian and the first residual error of each parameter block, and for each reserved parameter block, the first Jacobian and the first residual error of the reserved parameter block are adopted to calculate to obtain a second Jacobian and a second residual error of the reserved parameter block.
And the Jacobi calculation unit 104 is used for calculating a first Jacobi and a first residual error of the parameter block according to the IMU pre-integration information, the visual reprojection information and the last marginalization information of the inertial sensor. The inertial sensor IMU pre-integration information refers to the fact that the inertial sensor IMU obtains change information of the relative position and the posture of the inertial sensor IMU by using the acceleration and the linear velocity measured by the inertial sensor IMU. The visual re-projection information is change information of the relative position and orientation of the camera calculated by the functions of image acquisition, image processing, and the like of the camera.
For the sake of easy understanding, the parameter calculation unit is described in detail below, and as shown in fig. 3, the parameter calculation unit includes: an information matrix and residual error constructing subunit 301, a parameter extracting subunit 302, a schur complement subunit 303 and a Jacobian and residual error recovering subunit 304; wherein:
a construction information matrix and residual error subunit 301, configured to construct a first information matrix according to the first jacobian of each parameter block, and construct a residual error vector according to the first residual error of each parameter block;
in one embodiment, to conserve storage resources, only the upper half triangular matrix or the lower half triangular matrix is stored in the first information matrix. When the first information matrix is constructed, the position of the Jacobian of the parameter block in the first information matrix is determined according to the marginalized mark.
A parameter extraction subunit 302, configured to extract, from the first information matrix, a parameter block whose marginalization flag is a first specified value as previous marginalization information of a next marginalization process;
namely, when the marginalization processing is carried out next time and the residual error of the parameter block is calculated, the residual error is calculated according to IMU pre-integration information, reprojection information and the marginalization information of the time of the inertial sensor.
A schur complement subunit 303, configured to perform schur complement operation on the first information matrix to obtain a second information matrix. The schur complement operation refers to a process of performing an operation such as elementary transformation of gaussian elimination on the first information matrix to convert the first information matrix into an upper triangular matrix or a lower triangular matrix.
And a recover jacobian and residual sub-unit 304, configured to calculate, by using a preset algorithm, a second jacobian and a second residual of the retained parameter block according to the first jacobian and the first residual of the retained parameter block.
In the embodiment of the present application, the operation mode of each unit is in a pipeline manner, that is, the preceding unit and the subsequent unit perform calculation simultaneously, which greatly increases the calculation amount and reduces the requirement on storage resources.
It should be noted that although several units or sub-units of the apparatus are mentioned in the above detailed description, such division is merely exemplary and not mandatory. Indeed, the features and functions of two or more units described above may be embodied in one unit, according to embodiments of the application. Conversely, the features and functions of one unit described above may be further divided into embodiments by a plurality of units.
Further, while the operations of the methods of the present application are depicted in the drawings in a particular order, this does not require or imply that these operations must be performed in this particular order, or that all of the illustrated operations must be performed, to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.
Claims (7)
1. A rimming device in a visual navigation system, the device comprising:
the device comprises a marking and storage unit, a parameter block distribution unit and a parameter calculation circuit, wherein the parameter calculation circuit comprises a plurality of Jacobian calculation units and a parameter calculation unit, and the parameter calculation circuit comprises:
the marking and storing unit is used for acquiring at least one parameter block to be processed in the batch, marking the type of each acquired parameter block according to a preset marking rule and storing each parameter block; each parameter block comprises related parameters for visual navigation;
the parameter distribution unit is used for sending each parameter block to a Jacobian calculation unit corresponding to the type of the parameter block in the marginalized calculation circuit according to the type of the parameter block;
the parameter calculation circuit is used for processing each received parameter block based on a Jacobian calculation unit corresponding to the type of the parameter block to obtain a first Jacobian and a first residual error of the parameter block, wherein the first residual error is a residual error between the parameter block and preset information;
the parameter calculation circuit is further configured to perform a filtering operation on each of the parameter blocks by using the parameter calculation unit based on the first jacobian and the first residual of each of the parameter blocks, and calculate, for each of the remaining parameter blocks, the second jacobian and the second residual of the remaining parameter block by using the first jacobian and the first residual of the remaining parameter block.
2. The apparatus of claim 1, wherein the parameter block carries a marginalization flag, the marginalization flag is used to indicate whether to be marginalized, and when the parameter calculation unit performs the filtering operation on the parameter block, the parameter calculation unit is specifically configured to:
and filtering the parameter blocks with the marginalized marks as second appointed values, and reserving the parameter blocks with the marginalized marks as first appointed values.
3. The apparatus of claim 1, wherein the parameter block further carries length information, the length information is used for indicating the information length of the parameter block and corresponds to the parameter block type one to one, and the flag and the storage unit are stored continuously according to the length information when storing the parameter block.
4. The apparatus of claim 1, wherein the preset information comprises:
inertial sensor IMU pre-integration information, visual re-projection information, previous batch marginalization information.
5. The apparatus according to claim 1, wherein the parameter calculation unit comprises: constructing an information matrix and residual error subunit, a parameter extraction subunit, a schur complement subunit and a recovery jacobian and residual error subunit; wherein:
the construction information matrix and residual error subunit is used for constructing a first information matrix according to the first Jacobian of each parameter block and constructing a residual error vector according to the first residual error of each parameter block;
the parameter extraction subunit is configured to extract the parameter block with the marginalization flag being the first specified value from the first information matrix, and use the parameter block as the previous batch of marginalization information for the next batch of marginalization processing;
the schur complement subunit is configured to perform schur complement operation on the first information matrix to obtain a second information matrix;
and the sub-unit for recovering the Jacobian and the residual error is used for calculating a second Jacobian and a second residual error of the reserved parameter block according to the first Jacobian and the first residual error of the reserved parameter block by adopting a preset algorithm.
6. The apparatus of claim 1, wherein the marking and storing unit, when performing type marking on each obtained parameter block according to a preset marking rule, is specifically configured to:
and determining the type of the parameter block according to the parameter block type indication information.
7. The apparatus of claim 5, wherein the constructing the information matrix and the residual unit, when performing the constructing the first information matrix according to the jacobian of the parameter block, is specifically configured to:
determining the placement position of the Jacobian of the parameter block in the first information matrix according to the marginalized mark;
constructing the first information matrix according to the placement position; wherein the jacobian of the parameter block is placed at the upper half triangle or the lower half triangle of the first information matrix.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110237941.7A CN113112393B (en) | 2021-03-04 | 2021-03-04 | Marginalizing device in visual navigation system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110237941.7A CN113112393B (en) | 2021-03-04 | 2021-03-04 | Marginalizing device in visual navigation system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113112393A true CN113112393A (en) | 2021-07-13 |
| CN113112393B CN113112393B (en) | 2022-05-31 |
Family
ID=76709953
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110237941.7A Active CN113112393B (en) | 2021-03-04 | 2021-03-04 | Marginalizing device in visual navigation system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113112393B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012068494A2 (en) * | 2010-11-18 | 2012-05-24 | Texas Instruments Incorporated | Context switch method and apparatus |
| WO2020034500A1 (en) * | 2018-08-14 | 2020-02-20 | 珠海市一微半导体有限公司 | Acceleration control system chip based on thresholding method, and robot |
| US20200103231A1 (en) * | 2018-09-30 | 2020-04-02 | Huazhong University Of Science And Technology | Intelligent device navigation method and navigation system |
-
2021
- 2021-03-04 CN CN202110237941.7A patent/CN113112393B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012068494A2 (en) * | 2010-11-18 | 2012-05-24 | Texas Instruments Incorporated | Context switch method and apparatus |
| WO2020034500A1 (en) * | 2018-08-14 | 2020-02-20 | 珠海市一微半导体有限公司 | Acceleration control system chip based on thresholding method, and robot |
| US20200103231A1 (en) * | 2018-09-30 | 2020-04-02 | Huazhong University Of Science And Technology | Intelligent device navigation method and navigation system |
Non-Patent Citations (1)
| Title |
|---|
| 郑少华等: "视觉导航AGV多路径快速检测算法研究", 《电子设计工程》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113112393B (en) | 2022-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107807625B (en) | End-to-end-based automatic driving system comfort evaluation method and device | |
| CN107909107A (en) | Fiber check and measure method, apparatus and electronic equipment | |
| CN111260726A (en) | Visual positioning method and device | |
| CN108880915B (en) | Electric power information network safety alarm information false alarm determination method and system | |
| CN109816639B (en) | Real-time straight line segment detection system and method based on LSD algorithm | |
| CN108716916B (en) | Distributed parallel star point centroid extraction method based on superblock and FPGA implementation device | |
| Wei et al. | Unsupervised monocular visual-inertial odometry network | |
| CN101908214B (en) | Moving object detection method with background reconstruction based on neighborhood correlation | |
| CN108829996B (en) | Method and device for obtaining vehicle positioning information | |
| CN112712018A (en) | Identification map establishing method, visual positioning method and device | |
| CN113112393B (en) | Marginalizing device in visual navigation system | |
| CN115049731A (en) | Visual mapping and positioning method based on binocular camera | |
| CN113298692B (en) | Augmented reality method for realizing real-time equipment pose calculation based on mobile terminal browser | |
| CN106355247B (en) | Data processing method and device, chip and electronic equipment | |
| CN112533060B (en) | Video processing method and device | |
| CN106802958A (en) | Conversion method and system of the CAD data to GIS data | |
| CN104346380A (en) | Data sequencing method and system on basis of MapReduce model | |
| CN112347896A (en) | Head data processing method and device based on multitask neural network | |
| CN108053751B (en) | Method and device for drawing direction arrow on electronic map navigation route | |
| CN103377031B (en) | A kind of multiple-data processing and device | |
| CN110378352B (en) | High-precision anti-interference two-dimensional filtering navigation data denoising method in complex underwater environment | |
| CN110705479A (en) | Model training method, target recognition method, device, equipment and medium | |
| CN103593285B (en) | A kind of image class software unit testing method based on judging to identify | |
| CN106557430A (en) | A kind of data cached brush method and device | |
| US9887904B2 (en) | Information processing apparatus, control method, and program |
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 |