CN113111757B - Accurate personnel positioning system based on image processing and intelligent Internet of things - Google Patents
Accurate personnel positioning system based on image processing and intelligent Internet of things Download PDFInfo
- Publication number
- CN113111757B CN113111757B CN202110365017.7A CN202110365017A CN113111757B CN 113111757 B CN113111757 B CN 113111757B CN 202110365017 A CN202110365017 A CN 202110365017A CN 113111757 B CN113111757 B CN 113111757B
- Authority
- CN
- China
- Prior art keywords
- personnel
- grid
- matrix
- node
- image
- 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.)
- Active
Links
- 238000012545 processing Methods 0.000 title claims abstract description 29
- 239000011159 matrix material Substances 0.000 claims abstract description 71
- 230000008859 change Effects 0.000 claims abstract description 33
- 238000001514 detection method Methods 0.000 claims abstract description 19
- 238000013528 artificial neural network Methods 0.000 claims abstract description 16
- 238000004891 communication Methods 0.000 claims abstract description 13
- 238000004364 calculation method Methods 0.000 claims abstract description 7
- 238000000034 method Methods 0.000 claims description 9
- 230000009466 transformation Effects 0.000 claims description 8
- 238000010191 image analysis Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 3
- 230000006855 networking Effects 0.000 claims 1
- 238000010586 diagram Methods 0.000 abstract description 16
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000012549 training Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 210000004205 output neuron Anatomy 0.000 description 2
- 238000012805 post-processing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the field of artificial intelligence and personnel positioning, in particular to a personnel accurate positioning system based on image processing and an intelligent Internet of things. The system comprises: the personnel detection module is used for acquiring personnel outlines; the weight matrix acquisition module is used for acquiring an energy change diagram according to the energy diagram and the initial energy diagram and distributing weight to each grid in the energy change diagram to acquire a weight matrix; the node reliability obtaining module is used for obtaining the reliability of each node according to the average energy change on a communication path from a bottom center point to each node in the energy change graph; the reliability matrix acquisition module is used for acquiring a reliability matrix according to the node reliability; and the personnel position acquisition module is used for inputting the feature matrix obtained according to the weight matrix and the credibility matrix and the signal intensity of each node into the key point detection neural network to obtain the position coordinates of the personnel. The system not only solves the technical problem of inaccurate RSSI fingerprint positioning, but also reduces the calculation amount.
Description
Technical Field
The invention relates to the technical field of artificial intelligence and personnel positioning, in particular to a personnel accurate positioning system based on image processing and an intelligent Internet of things.
Background
With the rapid development of wireless network technology and the wide application of various intelligent terminals, the application requirements of indoor positioning technology are more prominent and present an ever-increasing trend. In the field of daily life, the indoor positioning of a large airport waiting hall can enable passengers to quickly and accurately find a boarding gate; in the field of fire rescue, fire officers and soldiers can accurately position the current position of personnel according to the position information of users, strive for time for fire rescue, and reduce casualty probability of the personnel; in the commercial field, a merchant can push commodity information within a certain range around according to the current position of a user so as to stimulate the purchasing desire of the customer and improve the shopping experience of the customer.
In the prior art, an RSSI fingerprint positioning method is adopted for indoor positioning, the RSSI fingerprint positioning is influenced by the size of grid division, the smaller the grid division is, the more accurate the positioning is, but the positioning belongs to coarse positioning, only the grid serial number of the position of a person is known, and the specific position in the grid is not known; the smaller the grid division is, the larger the calculation amount of fingerprint positioning is; the fingerprint positioning is more easily influenced by shadow effect and multipath effect, and meanwhile, environmental change has great influence on the positioning and has the problem of insufficient precision.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide an accurate personnel positioning system based on image processing and an intelligent internet of things, and the adopted technical scheme is as follows:
the embodiment of the invention provides a personnel accurate positioning system based on image processing and intelligent Internet of things, which comprises:
the personnel detection module is used for analyzing the collected indoor image to obtain a personnel outline;
the weight matrix acquisition module is used for carrying out perspective transformation on a personnel image to obtain a planar grid map, carrying out difference on an energy map obtained according to the texture characteristics of the planar grid map and an initial energy map corresponding to the initial planar grid map to obtain an energy change map, and distributing weight to each grid in the energy change map by combining an entropy weight method to obtain a weight matrix;
the node reliability obtaining module is used for obtaining the bottom central point of the minimum circumscribed rectangle of the personnel outline, obtaining the average energy change of all pixels on a communication path from the bottom central point to each node from the energy change graph, and obtaining the reliability of each node according to the average energy change; the nodes are a plurality of wireless communication devices arranged indoors;
a reliability matrix obtaining module, configured to randomly select at least three nodes to obtain a node combination, input the signal strength of each node in the node combination into a fully-connected neural network to obtain a grid label, multiply the reliability of each node in the node combination to obtain a combined reliability, multiply the combined reliability corresponding to each grid to obtain a grid reliability, and obtain a reliability matrix according to the reliability of each grid;
and the personnel position acquisition module is used for inputting the feature matrix obtained according to the weight matrix and the credibility matrix and the signal intensity of each node into the key point detection neural network to obtain the position coordinates of personnel.
Further, the personnel detection module comprises an image analysis unit, and the image analysis unit is used for carrying out background difference on every two adjacent frames of indoor images shot by the camera to obtain a difference image, and carrying out connected domain analysis on the difference image to obtain the personnel outline.
Further, the weight matrix acquisition module comprises a planar grid map acquisition unit, which is used for performing perspective transformation on the personnel image according to the corresponding relationship between the four corner points of the personnel image and the four corner points of the indoor planar grid map to obtain a planar grid map; the indoor plane grid graph is an image obtained by uniformly meshing plane images which are equal to the indoor area and have all pixels of 1.
Further, the weight matrix acquisition module further includes an initial planar grid map acquisition unit, configured to perform perspective transformation on an initial image of the moving object, which is captured by the camera, to obtain an initial planar grid map.
Further, the texture features are obtained according to the gray level co-occurrence matrix of the planar grid map.
Further, the planar mesh image and the initial planar mesh image are both normalized.
Further, the weight matrix obtaining module further includes a weight distribution unit, and the weight distribution unit includes:
the data processing subunit is used for carrying out standardization processing on the data in each grid in the energy change map;
the information entropy calculation subunit is used for acquiring the information entropy of each grid according to the energy value corresponding to the pixel in each grid;
the weight obtaining subunit is used for distributing weight to each grid according to the information entropy; the larger the energy variation within the grid, the higher the weight.
Further, the key point detection neural network comprises a feature fitting encoder, a first fully connected network, a heat map regression encoder and a heat map regression decoder;
the input of the feature fitting encoder is the feature matrix;
the input of the first fully connected network is the signal strength of each node;
the input of the heat map regression encoder is a feature map obtained by multiplying the output of the feature fitting encoder and the output of the first fully-connected network;
the heat map regression decoder inputs the image output by the heat map regression encoder and outputs the image as a heat map.
Further, the feature matrix is a matrix obtained by multiplying the weight matrix and the reliability matrix.
Further, the node reliability is inversely related to the average energy variation.
The embodiment of the invention at least has the following beneficial effects:
according to the embodiment of the invention, an energy change diagram is obtained through a planar grid diagram and an initial planar grid diagram, and a weight matrix is obtained by distributing weights for each grid in combination with an entropy weight method; obtaining a combined credibility according to the credibility of each node in the node combination, and obtaining a grid credibility by multiplying the combined credibility corresponding to each grid, thereby further obtaining a credibility matrix; inputting a feature matrix obtained according to the weight matrix and the credibility matrix and the signal intensity of each node into a key point detection neural network to obtain position coordinates of personnel; not only solved among the prior art technical problem that RSSI fingerprint positioning is inaccurate, still reduced the calculated amount.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts;
fig. 1 is a block diagram of a precise positioning system for people based on image processing and an intelligent internet of things according to an embodiment of the present invention.
Detailed Description
To further illustrate the technical means and effects of the present invention for achieving the predetermined objects, the following detailed description of the precise positioning system for people based on image processing and intelligent internet of things, which is provided by the present invention, with reference to the accompanying drawings and preferred embodiments, describes specific embodiments, structures, features and effects thereof. In the following description, different "one embodiment" or "another embodiment" refers to not necessarily the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following describes a specific scheme of the accurate personnel positioning system based on image processing and intelligent internet of things in detail with reference to the accompanying drawings.
Referring to fig. 1, a block diagram of a precise positioning system for people based on image processing and intelligent internet of things according to an embodiment of the present invention is shown, where the system includes:
the personnel detection module 10 is used for analyzing the collected indoor images to obtain personnel outlines;
the weight matrix acquisition module 20 is configured to perform perspective transformation on the person image to obtain a planar grid map, perform a difference between an energy map obtained according to texture features of the planar grid map and an initial energy map corresponding to the initial planar grid map to obtain an energy change map, and assign a weight to each grid in the energy change map by combining an entropy weight method to obtain a weight matrix;
the node credibility obtaining module 30 is configured to obtain a bottom center point of a minimum circumscribed rectangle of the staff outline, obtain average energy changes of all pixels on a communication path from the bottom center point to each node from the energy change graph, and obtain a credibility of each node according to the average energy changes; the nodes are a plurality of wireless communication devices arranged indoors;
a reliability matrix obtaining module 40, configured to randomly select at least three nodes to obtain a node combination, input the signal strength of each node in the node combination into a fully-connected neural network to obtain a grid label, multiply the reliability of each node in the node combination to obtain a combined reliability, multiply the combined reliability corresponding to each grid to obtain a grid reliability, and obtain a reliability matrix according to the reliability of each grid;
and the personnel position acquisition module 50 is used for inputting the feature matrix obtained according to the weight matrix and the credibility matrix and the signal strength of each node into the key point detection neural network to obtain the position coordinates of the personnel.
In summary, the embodiment provides a precise positioning system for people based on image processing and an intelligent internet of things, the system obtains an energy change diagram through a planar grid diagram and an initial planar grid diagram, and a weight matrix is obtained by distributing weights to each grid in combination with an entropy weight method; obtaining a combined credibility according to the credibility of each node in the node combination, and obtaining a grid credibility by multiplying the combined credibility corresponding to each grid, thereby further obtaining a credibility matrix; inputting a feature matrix obtained according to the weight matrix and the credibility matrix and the signal intensity of each node into a key point detection neural network to obtain position coordinates of personnel; not only solved among the prior art technical problem that RSSI fingerprint positioning is inaccurate, still reduced the calculated amount.
Preferably, the person detection module 10 in this embodiment includes an image analysis unit 101.
The image analysis unit 101 is configured to perform background difference on every two adjacent frames of indoor images captured by the camera to obtain a difference image, perform connected domain analysis on the difference image to obtain a plurality of connected domains, and perform template matching on each connected domain to obtain a person profile.
According to the embodiment, the plane grid graph of the personnel image is acquired after the personnel outline is detected, and the wireless communication equipment is called to carry out signal detection, so that the calculated amount is effectively reduced.
Preferably, the weight matrix acquiring module 20 in this embodiment includes a planar grid map acquiring unit 201, an energy change map acquiring unit 202, and a weight allocating unit 203.
The planar grid pattern obtaining unit 201 is configured to calculate a homography matrix according to a correspondence between four corner points of the person image and four corner points of the indoor planar grid pattern, and perform perspective transformation on the person image captured by the camera according to the homography matrix to obtain a planar grid pattern.
The indoor plane grid graph is an image obtained by uniformly meshing a plane image which is equal to the indoor area and has all pixels of 1.
The planar image in this embodiment is divided into 32 × 32 grids, and the resolution size is 128 × 128. In other embodiments, the implementer may grid the planar image as appropriate.
The energy change map obtaining unit 202 is configured to obtain an energy map according to texture features of the gray level co-occurrence matrix of the person image, and obtain a normalized energy change map by subtracting the normalized energy map from the initial energy map.
The gray level co-occurrence matrix is used for describing the uniformity degree of the gray level distribution of the image and the thickness degree of the texture. When all the values of the gray level co-occurrence matrix are very close, the energy value is small, and the texture is fine; when all the values of the gray level co-occurrence matrix are different greatly, the energy value is large, and the texture is coarse. When the energy change is large, it indicates that someone is present here.
The weight assignment unit 203 includes a data processing subunit, an information entropy calculation subunit, and a weight acquisition subunit.
The data processing subunit is used for carrying out standardization processing on the data in each grid in the energy change diagram;
the information entropy calculation subunit is used for acquiring the information entropy of each grid according to the energy value corresponding to the pixel in each grid;
and the weight obtaining subunit is used for distributing a weight to each grid according to the information entropy, wherein the larger the energy change in the grid is, the smaller the information entropy is, and the higher the weight is.
Preferably, the formula of the average energy change in the node reliability obtaining module 30 in this embodiment is as follows:
where T' is the average energy change, n is the total number of pixels on the communication path, TiThe energy corresponding to the ith pixel on the communication path.
The calculation formula of the node credibility U is as follows:
U＝1-T′
the reliability of a node is in a negative correlation relation with the average energy change, and the smaller the average energy change on a communication path of a certain node is, the higher the reliability of the node is.
The nodes are a plurality of wireless communication devices arranged indoors. The wireless communication equipment is used for acquiring the position of the person according to the signal strength. The signal strength can be obtained by adopting network positioning, self-positioning and mixed positioning.
In this embodiment, a network positioning manner is adopted to obtain the signal strength. In other embodiments, the implementer may select a suitable positioning manner according to the actual situation.
Preferably, the reliability matrix obtaining module 40 in this embodiment includes a node combination obtaining unit 401 and a fully-connected neural network 402.
A node combination obtaining unit 401, configured to randomly select at least three nodes from a plurality of nodes arranged indoors to obtain a plurality of node combinations.
A specific example of an acquisition node combination is given below: the number of node combinations is
N is the total number of nodes, N1The number of nodes in each node combination. Such as
Namely, three nodes are randomly selected from 8 nodes to be combined, and 56 node combinations are always available.
The fully-connected neural network 402 training process is as follows:
(1) and labeling the sample image training set to obtain grid label data. The sample image training set is the signal strength of each node in the node combination.
(2) And optimizing network parameters by adopting a cross entropy loss function.
Preferably, the key point detection neural network in this embodiment includes a feature fitting encoder 501, a first fully-connected network 502, a heatmap regression encoder 503, and a heatmap regression decoder 504.
The input to the feature fitting encoder 501 is a feature matrix; and the feature fitting encoder performs feature fitting operations such as two-dimensional convolution, BN layer and pooling layer on the feature matrix to output a plurality of sub-feature graphs.
The feature matrix is a matrix obtained by multiplying the weight matrix and the reliability matrix. The larger the value of the element in the feature matrix, the larger the image change in the corresponding grid is, and the higher the possibility that a person exists in the grid is.
Specifically, the number of the sub feature maps in the present embodiment is 32. In other embodiments, the implementer may select the number of sub-feature maps as appropriate.
The input to the first fully connected network 502 is the signal strength of each node; the first fully-connected network performs feature mapping on the signal strength to output a plurality of neurons.
The first fully-connected network outputs 32 neurons in this embodiment. In other embodiments, the implementer may select the number of output neurons as the case may be.
The number of output neurons corresponds to the number of sub-feature maps.
The input to the heat map regression encoder 503 is a feature map obtained by multiplying the output of the feature fitting encoder by the output of the first fully connected network.
The heat map regression decoder 504 inputs the image output by the heat map regression encoder, upsamples and feature fits the image, and outputs a human coordinate thermodynamic map.
The heatmap regression encoder 503 and heatmap regression decoder 504 may employ a network model such as Hourglass, HRNet, uet, etc.
Both the heatmap regression encoder 503 and the heatmap regression decoder 504 in this embodiment employ a Hourglass network model. In other embodiments, the implementer may select an appropriate network model based on the circumstances.
The training process of the key point detection neural network comprises the following steps:
(1) and marking the position coordinates of the personnel in the sample image training set to obtain a personnel coordinate scatter diagram, and performing Gaussian kernel convolution on the personnel coordinate scatter diagram to obtain a label image.
The sample image training set is a set of planar grid graphs corresponding to a plurality of collected personnel images.
(2) The loss function may be a regression-type loss function such as L2, SmoothL1, or the like.
In this example, the SmoothL1 loss function is used. In other embodiments, the implementer may select an appropriate loss function based on the circumstances.
Preferably, the staff position obtaining module 50 in this embodiment includes a post-processing unit, which is configured to perform post-processing on the staff coordinate thermodynamic diagram output by the key point detection neural network to obtain the position coordinates of the staff.
It should be noted that: the precedence order of the above embodiments of the present invention is only for description, and does not represent the merits of the embodiments. And specific embodiments thereof have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments.
The present invention is not limited to the above preferred embodiments, and any modifications, equivalent replacements, improvements, etc. within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. The utility model provides an accurate positioning system of personnel based on image processing and intelligent thing networking which characterized in that, this system includes:
the personnel detection module is used for analyzing the collected indoor image to obtain a personnel outline;
the weight matrix acquisition module is used for carrying out perspective transformation on a personnel image to obtain a planar grid map, carrying out difference on an energy map obtained according to the texture characteristics of the planar grid map and an initial energy map corresponding to the initial planar grid map to obtain an energy change map, and distributing weight to each grid in the energy change map by combining an entropy weight method to obtain a weight matrix;
the node reliability obtaining module is used for obtaining the bottom central point of the minimum circumscribed rectangle of the personnel outline, obtaining the average energy change of all pixels on a communication path from the bottom central point to each node from the energy change graph, and obtaining the reliability of each node according to the average energy change; the nodes are a plurality of wireless communication devices arranged indoors;
a reliability matrix obtaining module, configured to randomly select at least three nodes to obtain a node combination, input the signal strength of each node in the node combination into a fully-connected neural network to obtain a grid label, multiply the reliability of each node in the node combination to obtain a combined reliability, multiply the combined reliability corresponding to each grid to obtain a grid reliability, and obtain a reliability matrix according to the reliability of each grid;
and the personnel position acquisition module is used for inputting the feature matrix obtained according to the weight matrix and the credibility matrix and the signal intensity of each node into the key point detection neural network to obtain the position coordinates of personnel.
2. The accurate personnel positioning system based on image processing and intelligent internet of things as claimed in claim 1, wherein the personnel detection module comprises an image analysis unit for performing background difference on every two adjacent frames of indoor images shot by a camera to obtain a difference image, and performing connected domain analysis on the difference image to obtain personnel outlines.
3. The accurate personnel positioning system based on image processing and intelligent internet of things as claimed in claim 1, wherein the weight matrix acquisition module comprises a planar grid map acquisition unit for performing perspective transformation on the personnel image according to the corresponding relationship between four corner points of the personnel image and four corner points of an indoor planar grid map to obtain a planar grid map; the indoor plane grid graph is an image obtained by uniformly meshing plane images which are equal to the indoor area and have all pixels of 1.
4. The accurate personnel positioning system based on image processing and intelligent internet of things as claimed in claim 1 or 3, wherein the weight matrix acquisition module further comprises an initial plane grid map acquisition unit for performing perspective transformation on an initial image of a moving object which is captured by the camera and does not exist to obtain an initial plane grid map.
5. The accurate personnel positioning system based on image processing and intelligent internet of things as claimed in claim 4, wherein the texture features are obtained according to a gray level co-occurrence matrix of the planar grid map.
6. The system for accurately positioning personnel based on image processing and intelligent internet of things as claimed in claim 1, wherein the planar mesh image and the initial planar mesh image are normalized.
7. The system for accurately positioning personnel based on image processing and intelligent internet of things according to claim 1, wherein the weight matrix acquisition module further comprises a weight distribution unit, and the weight distribution unit comprises:
the data processing subunit is used for carrying out standardization processing on the data in each grid in the energy change map;
the information entropy calculation subunit is used for acquiring the information entropy of each grid according to the energy value corresponding to the pixel in each grid;
the weight obtaining subunit is used for distributing weight to each grid according to the information entropy; the larger the energy variation within the grid, the higher the weight.
8. The system for accurately positioning people based on image processing and intelligent internet of things is characterized in that the key point detection neural network comprises a feature fitting encoder, a first full-connection network, a heat map regression encoder and a heat map regression decoder;
the input of the feature fitting encoder is the feature matrix;
the input of the first fully connected network is the signal strength of each node;
the input of the heat map regression encoder is a feature map obtained by multiplying the output of the feature fitting encoder and the output of the first fully-connected network;
the heat map regression decoder inputs the image output by the heat map regression encoder and outputs the image as a heat map.
9. The system for accurately positioning personnel based on image processing and intelligent internet of things as claimed in claim 1, wherein the feature matrix is a matrix obtained by multiplying the weight matrix and the credibility matrix.
10. The system for accurately positioning personnel based on image processing and intelligent internet of things as claimed in claim 1, wherein the node reliability is in negative correlation with the average energy variation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110365017.7A CN113111757B (en) | 2021-04-01 | 2021-04-01 | Accurate personnel positioning system based on image processing and intelligent Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110365017.7A CN113111757B (en) | 2021-04-01 | 2021-04-01 | Accurate personnel positioning system based on image processing and intelligent Internet of things |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113111757A CN113111757A (en) | 2021-07-13 |
| CN113111757B true CN113111757B (en) | 2022-04-05 |
Family
ID=76713674
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110365017.7A Active CN113111757B (en) | 2021-04-01 | 2021-04-01 | Accurate personnel positioning system based on image processing and intelligent Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113111757B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101695190A (en) * | 2009-10-20 | 2010-04-14 | 北京航空航天大学 | Three-dimensional wireless sensor network node self-locating method based on neural network |
| WO2019074315A1 (en) * | 2017-10-13 | 2019-04-18 | 네이버랩스 주식회사 | Method and system for providing user location information |
| CN109661030A (en) * | 2018-12-07 | 2019-04-19 | 南京工业大学 | Unknown object location algorithm in wireless sensor network based on dynamic grid |
| CN110516650A (en) * | 2019-09-02 | 2019-11-29 | 中北大学 | A kind of blind space seismic source location system of shallow-layer based on shock sensor array |
| CN111556431A (en) * | 2020-04-21 | 2020-08-18 | 西安交通大学 | Fingerprint indoor positioning method based on signal subspace |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11057118B2 (en) * | 2020-04-29 | 2021-07-06 | Intel Corporation | Indoor localization with beacon technology based on signal strength distribution and deep learning techniques |
-
2021
- 2021-04-01 CN CN202110365017.7A patent/CN113111757B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101695190A (en) * | 2009-10-20 | 2010-04-14 | 北京航空航天大学 | Three-dimensional wireless sensor network node self-locating method based on neural network |
| WO2019074315A1 (en) * | 2017-10-13 | 2019-04-18 | 네이버랩스 주식회사 | Method and system for providing user location information |
| CN109661030A (en) * | 2018-12-07 | 2019-04-19 | 南京工业大学 | Unknown object location algorithm in wireless sensor network based on dynamic grid |
| CN110516650A (en) * | 2019-09-02 | 2019-11-29 | 中北大学 | A kind of blind space seismic source location system of shallow-layer based on shock sensor array |
| CN111556431A (en) * | 2020-04-21 | 2020-08-18 | 西安交通大学 | Fingerprint indoor positioning method based on signal subspace |
Non-Patent Citations (2)
| Title |
|---|
| "Comparison of CNN Applications for RSSI-Based Fingerprint Indoor Localization";Rashmi Sharan Sinha等;《Electronics 2019》;20191204;第1-25页 * |
| "基于多分布密度位置指纹的高效室内定位算法研究";乐燕芬等;《通信学报》;20190131;第40卷(第1期);第1-8页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113111757A (en) | 2021-07-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109697435B (en) | People flow monitoring method and device, storage medium and equipment | |
| CN110084161B (en) | Method and system for rapidly detecting key points of human skeleton | |
| CN108549891B (en) | Multi-scale diffusion well-marked target detection method based on background Yu target priori | |
| CN106845487B (en) | End-to-end license plate identification method | |
| CN112990211B (en) | Training method, image processing method and device for neural network | |
| CN109410168B (en) | Modeling method of convolutional neural network for determining sub-tile classes in an image | |
| CN109145979A (en) | sensitive image identification method and terminal system | |
| CN108520216A (en) | A kind of personal identification method based on gait image | |
| CN109271895A (en) | Pedestrian's recognition methods again based on Analysis On Multi-scale Features study and Image Segmentation Methods Based on Features | |
| CN108960404A (en) | A kind of people counting method and equipment based on image | |
| CN111726765B (en) | WIFI indoor positioning method and system for large-scale complex scene | |
| CN109598220A (en) | A kind of demographic method based on the polynary multiple dimensioned convolution of input | |
| CN109583366B (en) | Sports building evacuation crowd trajectory generation method based on video images and WiFi positioning | |
| CN110827304B (en) | Traditional Chinese medicine tongue image positioning method and system based on deep convolution network and level set method | |
| CN111950406A (en) | Finger vein identification method, device and storage medium | |
| Arumugadevi et al. | Color image segmentation using feedforward neural networks with FCM | |
| CN111586605A (en) | KNN indoor target positioning method based on adjacent weighted self-adaptive k value | |
| CN110334584A (en) | A kind of gesture identification method based on the full convolutional network in region | |
| CN110426671B (en) | IMM target tracking method and device based on model probability real-time correction in WSN | |
| CN113111757B (en) | Accurate personnel positioning system based on image processing and intelligent Internet of things | |
| Jamil et al. | Can convolution neural network (CNN) triumph in ear recognition of uniform illumination invariant? | |
| Lin et al. | Posting techniques in indoor environments based on deep learning for intelligent building lighting system | |
| CN115849202B (en) | Intelligent crane operation target identification method based on digital twin technology | |
| CN102156879A (en) | Human target matching method based on weighted terrestrial motion distance | |
| CN109753934A (en) | A kind of method and identification device identifying image true-false |
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 | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A personnel precise positioning system based on image processing and intelligent Internet of Things Granted publication date: 20220405 Pledgee: Bank of China Limited Yixing branch Pledgor: Guoneng smart technology development (Jiangsu) Co.,Ltd. Registration number: Y2024980012078 |