CN110765918A - MFANet-based vSLAM rapid loop detection method and device - Google Patents
MFANet-based vSLAM rapid loop detection method and device Download PDFInfo
- Publication number
- CN110765918A CN110765918A CN201910988994.5A CN201910988994A CN110765918A CN 110765918 A CN110765918 A CN 110765918A CN 201910988994 A CN201910988994 A CN 201910988994A CN 110765918 A CN110765918 A CN 110765918A
- Authority
- CN
- China
- Prior art keywords
- image
- images
- current position
- similarity
- compared
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The application discloses a method and a device for rapidly detecting a vSLAM loop based on MFANet, and relates to the field of vSLAM. The method comprises the following steps: acquiring an image at the current position, calculating a covariance matrix after carrying out zero-mean on the image by using PCA, and carrying out SVD (singular value decomposition) to eliminate correlation between white noise and pixels of the image; inputting the image of the current position with the correlation eliminated into a trained MFANet, determining M images to be compared, calculating the similarity between the M images to be compared and the input image of the current position, and determining that loop returning occurs when the images meet the similarity condition according to the similarity calculation result. The device includes: the device comprises a processing module and a detection module. The method and the device meet the requirement of real-time performance of the vSLAM, and improve the performance of loop detection by using the excellent judgment capability of the MFANet.
Description
Technical Field
The application relates to the field of vSLAM (Visual Simultaneous Localization And Mapping based on vision), in particular to a method And a device for rapidly detecting vSLAM loop based on MFANet.
Background
The key to loop detection is how to effectively detect the fact that the camera passes through the same place. If this is detected successfully, more valid data can be provided to the back-end, which can lead to better estimation results, especially a globally consistent estimation result. Such loop detection is broadly divided into two concepts: one is based on the geometric relationship of the visual odometer and the other is based on appearance.
The geometric relation based on the visual odometer judges whether the robot returns to the explored area or not by means of the pose, and if the distance between the poses is small enough, a loop is considered to be generated. Early Olson et al considered the range of measurement accuracy of the sensor and judged whether a loop was created by comparing the mahalanobis distance between the current point and all previous point poses.
The appearance-based method usually adopts a Bag-of-Word (BoW-of-Word) model, the dictionary generation problem is similar to a clustering problem, namely unsupervised machine learning, the Bag-of-words model clusters visual feature descriptors in an image, each Word can be regarded as a set of local adjacent feature points, a dictionary is established, and then a corresponding Word is found in the Bag-of-words. Typical appearance-based methods are compared as follows: loop detection based on AlexNet, PCANet (Principal component analysis net), loop detection based on supervised LDANet (Linear Discriminant analysis net), and the like.
In the traditional geometric relationship method based on the visual odometer, due to the existence of the accumulated error of the visual odometer, the accuracy is poor, and the fact that the visual odometer returns to the vicinity of a certain previous position cannot be judged. In the appearance-based method, the robustness of feature extraction of the bag-of-words model is low when the scene changes continuously, and misjudgment is easy to occur on the condition that the environment and the decoration are very similar. AlexNet loop detection cannot meet requirements of SLAM real-time performance generally, LDANet loop detection leads distance change of clusters far away from a central point, real data rules cannot be expressed, and training effects are not ideal.
Disclosure of Invention
It is an object of the present application to overcome the above problems or to at least partially solve or mitigate the above problems.
According to one aspect of the application, a vSLAM fast loop detection method based on MFANet (local finite analysis net) is provided, which includes:
acquiring an image of a current position, calculating a covariance matrix after carrying out zero-mean on the image by PCA principal component analysis, and carrying out SVD (Singular Value Decomposition) to eliminate correlation between white noise and pixels of the image;
inputting the image of the current position with the correlation eliminated into a trained MFANet Fisher marginal analysis network, determining M images to be compared, calculating the similarity between the M images to be compared and the input image of the current position, and determining that loop returning occurs when the image is determined to meet the similarity condition according to the similarity calculation result.
Optionally, determining M images to be compared includes:
and selecting L images closest to the image at the current position from N images in the data set, and determining the rest M-N-L images except the L images as images to be compared.
Optionally, calculating the similarity between the M images to be compared and the input image of the current location includes:
and calculating the cosine similarity between each image in the M images to be compared and the input image of the current position.
Optionally, when it is determined that an image meets the similarity condition according to the similarity calculation result, determining that a loop occurs includes:
and judging whether the similarity exceeds a specified threshold value in the obtained M cosine similarities, and if so, determining that loop returning occurs.
Optionally, the method further comprises:
and if the image of the current position determines that loop back does not occur, acquiring the image of the next current position to continue detection until the loop back is determined to occur.
According to another aspect of the present application, there is provided a MFANet-based vSLAM fast loopback detection apparatus, comprising:
the processing module is configured to acquire an image of a current position, calculate a covariance matrix after performing zero-averaging on the image by PCA principal component analysis, and perform SVD odd-art value decomposition to eliminate correlation between white noise and pixels of the image;
the detection module is configured to input the image of the current position with the correlation eliminated into a trained MFANet Fisher marginal analysis network, determine M images to be compared, calculate the similarity between the M images to be compared and the input image of the current position, and determine that loop returning occurs when the images meet the similarity condition according to the similarity calculation result.
Optionally, the detection module is specifically configured to:
and selecting L images closest to the image at the current position from N images in the data set, and determining the rest M-N-L images except the L images as images to be compared.
Optionally, the detection module is specifically configured to:
and calculating the cosine similarity between each image in the M images to be compared and the input image of the current position.
Optionally, the detection module is specifically configured to:
and judging whether the similarity exceeds a specified threshold value in the obtained M cosine similarities, and if so, determining that loop returning occurs.
Optionally, the detection module is further configured to:
and if the image of the current position determines that loop back does not occur, acquiring the image of the next current position to continue detection until the loop back is determined to occur.
According to yet another aspect of the application, there is provided a computing device comprising a memory, a processor and a computer program stored in the memory and executable by the processor, wherein the processor implements the method as described above when executing the computer program.
According to yet another aspect of the application, a computer-readable storage medium, preferably a non-volatile readable storage medium, is provided, having stored therein a computer program which, when executed by a processor, implements a method as described above.
According to yet another aspect of the application, there is provided a computer program product comprising computer readable code which, when executed by a computer device, causes the computer device to perform the method described above.
According to the technical scheme, an image of a current position is obtained, a PCA is used for carrying out zero mean value on the image, then a covariance matrix is calculated, and SVD is carried out to eliminate correlation between white noise and pixels of the image; inputting the image of the current position with the correlation eliminated into a trained MFANet, determining M images to be compared, calculating the similarity between the M images to be compared and the input image of the current position, determining that loop occurs when the image meets the similarity condition according to the similarity calculation result, meeting the requirement of vSLAM real-time performance, optimizing PCANet and LDANet schemes, using the MFANet without loss function on the premise of not influencing real-time performance, improving the loop detection performance by using the excellent judgment capability, obtaining higher accuracy on the basis of the PCANet, and better representing the real data compared with the LDANet.
The above and other objects, advantages and features of the present application will become more apparent to those skilled in the art from the following detailed description of specific embodiments thereof, taken in conjunction with the accompanying drawings.
Drawings
Some specific embodiments of the present application will be described in detail hereinafter by way of illustration and not limitation with reference to the accompanying drawings. The same reference numbers in the drawings identify the same or similar elements or components. Those skilled in the art will appreciate that the drawings are not necessarily drawn to scale. In the drawings:
fig. 1 is a flow diagram of a MFANet-based vSLAM fast loopback detection method according to one embodiment of the present application;
fig. 2 is a flow diagram of a MFANet-based vSLAM fast loopback detection method according to another embodiment of the present application;
fig. 3 is a block diagram of a MFANet-based vSLAM fast loop back detection apparatus according to another embodiment of the present application;
FIG. 4 is a block diagram of a computing device according to another embodiment of the present application;
fig. 5 is a diagram of a computer-readable storage medium structure according to another embodiment of the present application.
Detailed Description
Loop back detection is an important part of vSLAM. Along with the motion of the camera, the data of the sensor and the calculated camera pose are all in error, and even if optimization is carried out, accumulated errors still exist. The most effective method for eliminating errors is to find a closed loop, the loop detection needs the robot to judge whether the robot visits the position in real time during moving, and all results are optimized according to the closed loop. The embodiment of the application provides a method and a device for rapidly detecting vSLAM loop based on MFANet, which can be used for distinguishing whether the images pass through the same position or not through an environment image acquired by a camera.
Fig. 1 is a flow chart of a MFANet-based vSLAM fast loopback detection method according to an embodiment of the present application. Referring to fig. 1, the method includes:
101: acquiring an image at the current position, calculating a covariance matrix after carrying out zero-mean on the image by using PCA, and carrying out SVD (singular value decomposition) to eliminate correlation between white noise and pixels of the image;
102: inputting the image of the current position with the correlation eliminated into a trained MFANet, determining M images to be compared, calculating the similarity between the M images to be compared and the input image of the current position, and determining that loop returning occurs when the images meet the similarity condition according to the similarity calculation result.
In this embodiment, optionally, the determining M images to be compared includes:
among the N images in the data set, L images closest to the image at the current position are selected, and the remaining M-L images except the L images are determined as images to be compared.
In this embodiment, optionally, the calculating the similarity between the M images to be compared and the input image at the current position includes:
and calculating the cosine similarity between each image in the M images to be compared and the input image at the current position.
In this embodiment, optionally, when it is determined that an image meets the similarity condition according to the result of the similarity calculation, determining that a loop occurs includes:
and judging whether the similarity exceeds a specified threshold value in the obtained M cosine similarities, and if so, determining that loop returning occurs.
In this embodiment, optionally, the method further includes:
if the image of the current position determines that loop back does not occur, acquiring the image of the next current position and continuing detection until the loop back is determined to occur.
In the method provided by this embodiment, an image at a current position is obtained, a PCA is used to perform zero-averaging on the image, and then a covariance matrix is calculated, and SVD is performed to eliminate correlation between white noise and pixels of the image; inputting the image of the current position with the correlation eliminated into a trained MFANet, determining M images to be compared, calculating the similarity between the M images to be compared and the input image of the current position, determining that loop occurs when the image meets the similarity condition according to the similarity calculation result, meeting the requirement of vSLAM real-time performance, optimizing PCANet and LDANet schemes, using the MFANet without loss function on the premise of not influencing real-time performance, improving the loop detection performance by using the excellent judgment capability, obtaining higher accuracy on the basis of the PCANet, and better representing the real data compared with the LDANet.
Fig. 2 is a flow chart of a MFANet-based vSLAM fast loopback detection method according to another embodiment of the present application. Referring to fig. 2, the method includes:
201: acquiring an image at the current position, calculating a covariance matrix after carrying out zero-mean on the image by using PCA, and carrying out SVD (singular value decomposition) to eliminate correlation between white noise and pixels of the image;
202: inputting the image of the current position after the correlation is eliminated into a trained MFANet, selecting L images closest to the image of the current position from N images in the data set, and determining the rest M-N-L images except the L images as images to be compared;
the experimental data sets adopted in the embodiment are City Center and New College data sets, and the evaluation verification data set of the closed-loop detection algorithm specially used for the vSLAM is collected by the oxford university mobile robot team, so that the vSLAM loop detection experiment is performed. The data set comprises 1073 images, the images are collected by cameras respectively arranged on the left side and the right side of the mobile platform, the mobile platform collects the images every 1.5m, and the data collection is carried out outdoors under different light, permeability and background disorder degrees, so that the requirement of actual conditions on loopback detection is met. And (3) giving a real label forming a closed-loop area in the data set, wherein the label is given in a matrix form, if the image i and the image j form the closed-loop area, the corresponding numerical value of (i, j) is 1, and otherwise, the numerical value is 0. In this embodiment, optionally, a three-channel RGB color image with 640 × 480 pixels is obtained from the data set, and is divided into 32 × 24 formats, and then processed.
In the method, an MFA network structure is used, and MFA is a graph embedding model and is characterized in that two graphs are defined: the Intrinsic graph (Intrinsic graph) and the Penalty graph (Penalty graph) project image data into a feature space, nodes in the class can be pulled close to each other in the feature space, and nodes outside the class can be pushed far away.
203: calculating the cosine similarity between each image in the M images to be compared and the input image at the current position;
204: judging whether the similarity exceeds a specified threshold value in the obtained M cosine similarities, and if so, determining that loop returning occurs;
205: if the image of the current position determines that loop back does not occur, acquiring the image of the next current position and continuing detection until the loop back is determined to occur.
In this embodiment, optionally, the accuracy rate and the Recall rate may be used to determine whether the algorithm is good or bad, a Precision-Recall curve is made, and the success rate may be obtained by comparing the Precision-Recall curve with the real loopback data in the data set.
In the method provided by this embodiment, an image at a current position is obtained, a PCA is used to perform zero-averaging on the image, and then a covariance matrix is calculated, and SVD is performed to eliminate correlation between white noise and pixels of the image; inputting the image of the current position with the correlation eliminated into a trained MFANet, determining M images to be compared, calculating the similarity between the M images to be compared and the input image of the current position, determining that loop occurs when the image meets the similarity condition according to the similarity calculation result, meeting the requirement of vSLAM real-time performance, optimizing PCANet and LDANet schemes, using the MFANet without loss function on the premise of not influencing real-time performance, improving the loop detection performance by using the excellent judgment capability, obtaining higher accuracy on the basis of the PCANet, and better representing the real data compared with the LDANet.
Fig. 3 is a block diagram of a MFANet-based vSLAM fast loop back detection apparatus according to another embodiment of the present application. Referring to fig. 3, the apparatus includes:
a processing module 301 configured to acquire an image at a current position, calculate a covariance matrix after performing zero-averaging on the image using PCA, and perform SVD to eliminate correlation between white noise and pixels of the image;
the detection module 302 is configured to input the image at the current position from which the correlation is eliminated into the trained MFANet, determine M images to be compared, calculate similarities between the M images to be compared and the input image at the current position, and determine that a loop occurs when it is determined that an image meets a similarity condition according to a similarity calculation result.
In this embodiment, optionally, the detection module is specifically configured to:
among the N images in the data set, L images closest to the image at the current position are selected, and the remaining M-L images except the L images are determined as images to be compared.
In this embodiment, optionally, the detection module is specifically configured to:
and calculating the cosine similarity between each image in the M images to be compared and the input image at the current position.
In this embodiment, optionally, the detection module is specifically configured to:
and judging whether the similarity exceeds a specified threshold value in the obtained M cosine similarities, and if so, determining that loop returning occurs.
In this embodiment, optionally, the detection module is further configured to:
if the image of the current position determines that loop back does not occur, acquiring the image of the next current position and continuing detection until the loop back is determined to occur.
The apparatus provided in this embodiment may perform the method provided in any of the above method embodiments, and details of the process are described in the method embodiments and are not described herein again.
The device provided by the embodiment acquires an image at a current position, calculates a covariance matrix after performing zero-averaging on the image by using PCA, and performs SVD to eliminate correlation between white noise and pixels of the image; inputting the image of the current position with the correlation eliminated into a trained MFANet, determining M images to be compared, calculating the similarity between the M images to be compared and the input image of the current position, determining that loop occurs when the image meets the similarity condition according to the similarity calculation result, meeting the requirement of vSLAM real-time performance, optimizing PCANet and LDANet schemes, using the MFANet without loss function on the premise of not influencing real-time performance, improving the loop detection performance by using the excellent judgment capability, obtaining higher accuracy on the basis of the PCANet, and better representing the real data compared with the LDANet.
The above and other objects, advantages and features of the present application will become more apparent to those skilled in the art from the following detailed description of specific embodiments thereof, taken in conjunction with the accompanying drawings.
Embodiments also provide a computing device, referring to fig. 4, comprising a memory 1120, a processor 1110 and a computer program stored in said memory 1120 and executable by said processor 1110, the computer program being stored in a space 1130 for program code in the memory 1120, the computer program, when executed by the processor 1110, implementing the method steps 1131 for performing any of the methods according to the invention.
The embodiment of the application also provides a computer readable storage medium. Referring to fig. 5, the computer readable storage medium comprises a storage unit for program code provided with a program 1131' for performing the steps of the method according to the invention, which program is executed by a processor.
The embodiment of the application also provides a computer program product containing instructions. Which, when run on a computer, causes the computer to carry out the steps of the method according to the invention.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed by a computer, cause the computer to perform, in whole or in part, the procedures or functions described in accordance with the embodiments of the application. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
Those of skill would further appreciate that the various illustrative components and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It will be understood by those skilled in the art that all or part of the steps in the method for implementing the above embodiments may be implemented by a program, and the program may be stored in a computer-readable storage medium, where the storage medium is a non-transitory medium, such as a random access memory, a read only memory, a flash memory, a hard disk, a solid state disk, a magnetic tape (magnetic tape), a floppy disk (floppy disk), an optical disk (optical disk), and any combination thereof.
The above description is only for the preferred embodiment of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present application should be covered within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A method for rapidly detecting vSLAM loop based on MFANet comprises the following steps:
acquiring an image of a current position, calculating a covariance matrix after carrying out zero-averaging on the image by PCA principal component analysis, and carrying out SVD odd-art value decomposition to eliminate correlation between white noise and pixels of the image;
inputting the image of the current position with the correlation eliminated into a trained MFANet Fisher marginal analysis network, determining M images to be compared, calculating the similarity between the M images to be compared and the input image of the current position, and determining that loop returning occurs when the image is determined to meet the similarity condition according to the similarity calculation result.
2. The method of claim 1, wherein determining M images to be compared comprises:
and selecting L images closest to the image at the current position from N images in the data set, and determining the rest M-N-L images except the L images as images to be compared.
3. The method of claim 1, wherein calculating the similarity of the M images to be compared to the input image of the current location comprises:
and calculating the cosine similarity between each image in the M images to be compared and the input image of the current position.
4. The method of claim 3, wherein determining that a loop occurs when it is determined that the image meets the similarity condition according to the similarity calculation result comprises:
and judging whether the similarity exceeds a specified threshold value in the obtained M cosine similarities, and if so, determining that loop returning occurs.
5. The method according to any one of claims 1-4, further comprising:
and if the image of the current position determines that loop back does not occur, acquiring the image of the next current position to continue detection until the loop back is determined to occur.
6. A MFANet-based vSLAM fast loopback detection device, comprising:
the processing module is configured to acquire an image of a current position, calculate a covariance matrix after performing zero-averaging on the image by PCA principal component analysis, and perform SVD odd-art value decomposition to eliminate correlation between white noise and pixels of the image;
the detection module is configured to input the image of the current position with the correlation eliminated into a trained MFANet Fisher marginal analysis network, determine M images to be compared, calculate the similarity between the M images to be compared and the input image of the current position, and determine that loop returning occurs when the images meet the similarity condition according to the similarity calculation result.
7. The apparatus of claim 6, wherein the detection module is specifically configured to:
and selecting L images closest to the image at the current position from N images in the data set, and determining the rest M-N-L images except the L images as images to be compared.
8. The apparatus of claim 6, wherein the detection module is specifically configured to:
and calculating the cosine similarity between each image in the M images to be compared and the input image of the current position.
9. The apparatus of claim 8, wherein the detection module is specifically configured to:
and judging whether the similarity exceeds a specified threshold value in the obtained M cosine similarities, and if so, determining that loop returning occurs.
10. The apparatus of any one of claims 6-9, wherein the detection module is further configured to:
and if the image of the current position determines that loop back does not occur, acquiring the image of the next current position to continue detection until the loop back is determined to occur.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910988994.5A CN110765918A (en) | 2019-10-17 | 2019-10-17 | MFANet-based vSLAM rapid loop detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910988994.5A CN110765918A (en) | 2019-10-17 | 2019-10-17 | MFANet-based vSLAM rapid loop detection method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110765918A true CN110765918A (en) | 2020-02-07 |
Family
ID=69332371
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910988994.5A Pending CN110765918A (en) | 2019-10-17 | 2019-10-17 | MFANet-based vSLAM rapid loop detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110765918A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113377987A (en) * | 2021-05-11 | 2021-09-10 | 重庆邮电大学 | Multi-module closed-loop detection method based on ResNeSt-APW |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107330357A (en) * | 2017-05-18 | 2017-11-07 | 东北大学 | Vision SLAM closed loop detection methods based on deep neural network |
| CN109376631A (en) * | 2018-10-12 | 2019-02-22 | 中国人民公安大学 | A kind of winding detection method and device neural network based |
| CN110146099A (en) * | 2019-05-31 | 2019-08-20 | 西安工程大学 | A kind of synchronous superposition method based on deep learning |
-
2019
- 2019-10-17 CN CN201910988994.5A patent/CN110765918A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107330357A (en) * | 2017-05-18 | 2017-11-07 | 东北大学 | Vision SLAM closed loop detection methods based on deep neural network |
| CN109376631A (en) * | 2018-10-12 | 2019-02-22 | 中国人民公安大学 | A kind of winding detection method and device neural network based |
| CN110146099A (en) * | 2019-05-31 | 2019-08-20 | 西安工程大学 | A kind of synchronous superposition method based on deep learning |
Non-Patent Citations (2)
| Title |
|---|
| 王凯: ""基于深度学习的视觉SLAM闭环检测研究"", 《中国优秀博硕士学位论文全文数据库(硕士) 信息科技辑》 * |
| 薛潇宇: ""基于图嵌入流形学习的人脸识别算法研究"", 《中国优秀博硕士学位论文全文数据库(硕士) 信息科技辑》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113377987A (en) * | 2021-05-11 | 2021-09-10 | 重庆邮电大学 | Multi-module closed-loop detection method based on ResNeSt-APW |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109961009B (en) | Pedestrian detection method, system, device and storage medium based on deep learning | |
| CN108470332B (en) | Multi-target tracking method and device | |
| JP5554984B2 (en) | Pattern recognition method and pattern recognition apparatus | |
| CN108875533B (en) | Face recognition method, device, system and computer storage medium | |
| CN110135246A (en) | A kind of recognition methods and equipment of human action | |
| KR20150110697A (en) | Systems and methods for tracking and detecting a target object | |
| KR20220004009A (en) | Key point detection method, apparatus, electronic device and storage medium | |
| CN111209774A (en) | Target behavior recognition and display method, device, equipment and readable medium | |
| CN111383246B (en) | Scroll detection method, device and equipment | |
| CN110363790A (en) | Target tracking method, device and computer readable storage medium | |
| CN110533661A (en) | Adaptive real-time closed-loop detection method based on characteristics of image cascade | |
| CN111126268A (en) | Key point detection model training method and device, electronic equipment and storage medium | |
| CN110598771A (en) | Visual target identification method and device based on deep semantic segmentation network | |
| CN116777899A (en) | Regression model-based industrial image key point detection method, system and platform | |
| CN111597921A (en) | Scene recognition method and device, computer equipment and storage medium | |
| CN114676756A (en) | Image recognition method, image recognition device and computer storage medium | |
| CN114519401A (en) | Image classification method and device, electronic equipment and storage medium | |
| CN113781563A (en) | Mobile robot loop detection method based on deep learning | |
| CN110765918A (en) | MFANet-based vSLAM rapid loop detection method and device | |
| CN111027434B (en) | Training method and device of pedestrian recognition model and electronic equipment | |
| CN106406507B (en) | Image processing method and electronic device | |
| CN107665495B (en) | Object tracking method and object tracking device | |
| CN115527083B (en) | Image annotation method and device and electronic equipment | |
| CN111368624A (en) | Loop detection method and device based on generation of countermeasure network | |
| CN116433722A (en) | Target tracking method, electronic device, storage medium, and program product |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200207 |