CN111182449A - Shopping cart tracking, positioning and monitoring method based on business surpasses - Google Patents
Shopping cart tracking, positioning and monitoring method based on business surpasses Download PDFInfo
- Publication number
- CN111182449A CN111182449A CN202010012969.6A CN202010012969A CN111182449A CN 111182449 A CN111182449 A CN 111182449A CN 202010012969 A CN202010012969 A CN 202010012969A CN 111182449 A CN111182449 A CN 111182449A
- Authority
- CN
- China
- Prior art keywords
- map
- wifi signal
- shopping cart
- super
- positioning
- 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
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000012544 monitoring process Methods 0.000 title claims abstract description 16
- 230000033001 locomotion Effects 0.000 claims abstract description 16
- 238000003066 decision tree Methods 0.000 claims abstract description 10
- 238000005070 sampling Methods 0.000 claims description 39
- 230000001133 acceleration Effects 0.000 claims description 5
- 238000010276 construction Methods 0.000 abstract description 2
- 239000006185 dispersion Substances 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 10
- 238000007726 management method Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000001228 spectrum Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000002238 attenuated effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000003651 drinking water Substances 0.000 description 1
- 235000020188 drinking water Nutrition 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 231100001261 hazardous Toxicity 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/029—Location-based management or tracking services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/021—Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/024—Guidance services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/025—Services making use of location information using location based information parameters
- H04W4/027—Services making use of location information using location based information parameters using movement velocity, acceleration information
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/33—Services specially adapted for particular environments, situations or purposes for indoor environments, e.g. buildings
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Navigation (AREA)
Abstract
The invention provides a tracking, positioning and monitoring method based on a shopping cart, which is used for constructing a priori dense WiFi signal fingerprint database construction, a priori micro inertial motion state database and priori map (vector map and topological map) information by adopting a vehicle-mounted WiFi positioning module and an inertial navigation module of the shopping cart aiming at the characteristics of large shopping carts, such as high mobility, distributed dispersion, complex management, correlation with pedestrian flow distribution and the like, and is used for generating a spatial map (WiFi signal fingerprint spatial map, micro inertial information spatial map) for mobile positioning of the shopping cart. Thus, the optimal two-dimensional spatial position/motion state estimation is solved in real time based on the ID3 decision tree algorithm to analyze customer behavior patterns and business over-the-counter management information.
Description
Technical Field
The invention relates to a tracking, positioning and monitoring method based on a commercial shopping cart, and belongs to the technical field of positioning and navigation.
Background
At present, the industry of large supermarkets develops rapidly. With the increasing scale of supermarkets, the demands of supermarket shopping cart management and safety monitoring are increasingly highlighted while the quantity of supermarket infrastructures is increased. The management and maintenance of large-scale commercial and super-infrastructure facilities, especially shopping carts, still requires a great deal of labor and cannot meet the requirements of efficient real-time management work. Most supermarkets usually pass experience on shelf design and goods arrangement, and have no clear standard and basis, so that the benefits of the supermarkets and the shopping experience of customers are influenced to a certain extent. For example, the exit position of the supermarket is unreasonable, so that potential safety hazards exist in the distribution, guidance and diversion of customers; two kinds of closely related goods are arranged on goods shelves which are separated for a long time, so that the time for a customer to search for the goods is long; the lack of observation and analysis of the behavior habits of customers leads to the occurrence of lost sales and disbursement of partial goods. In general, there is still a need to develop a shopping cart positioning method for efficient management of business over owners, convenient shopping for consumers, and safety monitoring analysis requirements.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a tracking, positioning and monitoring method based on a shopping cart for super shopping, which generates a spatial map (a WiFi signal fingerprint spatial map and a micro inertial information spatial map) for the mobile positioning of a shopping cart for super shopping by establishing a priori WiFi signal fingerprint database, establishing a priori micro inertial motion state database and information of a priori map (a business super vector map and a topological map). Therefore, the positioning of the WiFi signal strength and the micro-inertia information which are acquired by the shopping cart in real time and are most matched under the current map environment is solved in real time based on an ID3 decision tree algorithm, so that the behavior pattern of a customer and the business over-the-counter operation management information are analyzed.
The invention adopts the following technical scheme for solving the technical problems:
the shopping cart tracking, positioning and monitoring method based on the business supermarket specifically comprises the following steps:
step 1, constructing a WiFi signal fingerprint space map of the movement of the shopping cart with the business exceeding according to a WiFi hotspot AP distribution map in the business exceeding, a priori WiFi signal strength fingerprint database and a business exceeding vector map;
step 2, constructing a micro-inertia information space map of the movement of the shopping cart according to a priori acceleration observation database, a priori gyro angular velocity observation database, observation position information and a shopping super-topology map;
and 3, solving the positioning which is most matched with the WiFi signal strength and the micro inertia information acquired in real time under the current map environment by using an ID3 decision tree algorithm based on the WiFi signal fingerprint space map, the micro inertia information space map and the quotient super vector map of the movement of the commercial super shopping cart.
Further, the method for establishing the prior WiFi signal strength fingerprint database in step 1 is as follows:
firstly, setting a plurality of sampling points in the quotient super, respectively collecting the WiFi signal intensity sent by each AP, and establishing a sparse WiFi signal intensity fingerprint database, wherein the WiFi signal intensity fingerprint of the mth sampling point is expressed as
m∈{1,2,…M}，
N is equal to {1,2, … N }, M represents the number of sampling points, (x)m,ym) Indicating the position coordinates of the m-th sampling point,
for the set of acquired WiFi signal strengths for the mth sampling point,
the signal strength of the nth AP received by the mth sampling point is represented, and N represents the number of the APs;
secondly, a Newton interpolation method is adopted to perform uniform interpolation on the sparse WiFi signal intensity fingerprint database to obtain a WiFi signal intensity fingerprint database based on Newton interpolation:
based on the WiFi signal strength collected by the M sampling points, the WiFi signal strength of the interpolation point with the distance of l from the nth AP is obtained as follows:
wherein,
in the formula Im,nRepresenting the distance between the mth sampling point and the nth AP;
finally, based on a wireless signal attenuation model as shown in the formula (3), correcting the WiFi signal intensity in the WiFi signal intensity fingerprint database based on Newton interpolation to obtain a priori WiFi signal intensity fingerprint database;
wherein,
the received signal strength is the distance between the nth AP and the sampling point/interpolation point; s (l)0,n) The signal strength received by a position point with the distance of 1m from the nth AP is obtained; c is a path attenuation exponent;
further, the moving micro-inertia information space map of the commercial hypershopping cart in the step 2 is as follows: recording the position coordinates and all possible angles and speeds of each node of the quotient super-topology map based on the micro inertial element, wherein the inertial information of the p-th node of the quotient super-topology map is Yp＝{(xp,yp),Tp}，Tp＝{(θp1,vp1),(θp2,vp2),…,(θpQ,vpQ)}，(xp,yp) Is the position coordinate of the p-th node, TpIs as followsSet of all possible angles and velocities at p nodes, θpqAnd vpqThe q-th possible angle and speed at the p-th node.
The method for planning the path based on the commercial and super-commercial vehicles adopts an improved A path planning algorithm to plan the traveling path of the commercial and super-commercial vehicles, wherein the improved A path planning algorithm improves the valuation function of the A path planning algorithm, and the improved valuation function is as follows:
f(p)＝g(p)+h(p)*r+C
wherein g (p) is the distance required by the current position of the shopping cart to the routing node p, h (p) is the distance required by the routing node p to the target node, r is the risk coefficient of the distance from the routing node p to the target node, and C is the path complexity.
Compared with the prior art, the invention adopting the technical scheme has the following technical effects:
1. the invention provides a novel WIFI/inertia combined positioning method based on a space map, which can improve positioning accuracy and is suitable for indoor public occasions with known business super-equal structural layouts and relatively fixed advancing routes;
2. the invention provides a global path navigation planning algorithm, which realizes the reasonable planning function of the path in the business surpassing room;
3. according to the novel combined positioning algorithm based on the spatial map, the algorithm combines the information of the WiFi fingerprint map, the inertial information map and the map information by using an ID3 decision tree algorithm, and the optimal positioning result is calculated.
Drawings
FIG. 1 is a schematic diagram of a WiFi fingerprint spatial map of the present invention;
FIG. 2 is a schematic diagram of an inertial information space map of the present invention;
fig. 3 is a schematic diagram of the WIFI/inertial integrated navigation position estimation algorithm of the present invention.
Detailed Description
The technical scheme of the invention is further explained in detail by combining the attached drawings:
the WiFi signal fingerprint space map of the movement of the super-purchased commodity vehicle is constructed by a method of combining a distribution map of WiFi hotspots (AP) in the super-purchased commodity vehicle, a priori signal intensity fingerprint database collected by a WiFi module on the super-purchased commodity vehicle and a priori quotient super-vector map.
Typical WiFi fingerprinting uses quotient super-internal signal strength database matching for positioning, but building a dense and large sample WiFi fingerprint database requires a lot of manpower and time. In order to improve the construction efficiency, sample diversity and data effectiveness of the position fingerprint database, the WiFi fingerprint space spectrum of the commercial ultrahigh-density large sample is constructed by adopting a radio transmission distance loss interpolation method. Firstly, a plurality of sampling points are set in the business surpassing process, the signal intensity sent by each AP is collected, and a sparse WiFi signal intensity fingerprint database (actual WiFi sampling points) obtained through actual measurement is established. Due to the fact that actual WiFi sampling point data are lost or invalid, the number and the density of WiFi actual sampling points are limited, the discretization degree of WiFi fingerprint matching is large, and positioning accuracy is affected. The signal intensity of the interpolation point is estimated by carrying out Newton interpolation on the WiFi sampling point, and the signal intensity of the sampling point and the interpolation point is corrected based on the wireless signal attenuation model, so that the WiFi signal fingerprint space spectrum with dense space, large space sample and high efficiency is constructed.
In the sparse WiFi signal strength fingerprint database, sequence arrangement is performed on M sampling points, the position information of each sampling point corresponds to the RSSI values of N APs acquired by the sampling point, that is, the WiFi signal strength fingerprint of the mth sampling point is expressed as:
wherein M represents the number of sampling points, (x)m，ym) Indicating the position coordinates of the m-th sampling point,
for the set of acquired WiFi signal strengths for the mth sampling point,
the signal strength of the nth AP received by the mth sampling point is shown, and N represents the number of the APs.
therefore, the schematic diagram of the WiFi signal fingerprint consists of sampling points and interpolation points, as shown in FIG. 1, wherein '●' represents the sampling points and 'solidup' represents the interpolation points.
According to the invention, a Newton interpolation method is adopted to perform uniform interpolation on the sparse WiFi signal intensity fingerprint database to obtain the WiFi signal intensity fingerprint database based on Newton interpolation.
Based on the WiFi signal strength collected by the M sampling points, the WiFi signal strength of the interpolation point with the distance of l from the nth AP is obtained as follows:
wherein,
in the formula Im,nIndicating the distance of the mth sampling point from the nth AP,
the RSSI value of the nth AP measured at the mth actual sampling point is shown.
By the above formula, the RSSI/l relation curve corresponding to N APs in the map can be obtained. Interpolation points are uniformly set in the WiFi fingerprint, the distance between each interpolation point and N APs is determined, then the RSSI value corresponding to each interpolation point is calculated according to the Newton interpolation formula of the formula 1, and the WiFi signal intensity fingerprint data of the interpolation points are classified into the WiFi fingerprint, so that the WiFi fingerprint contains more accurate interpolation values in time and space.
In addition, in order to eliminate multipath and non-line-of-sight errors of the real collected fingerprint data in the wireless signal propagation process, a wireless signal attenuation model is introduced to correct the RSSI value. The WiFi energy is gradually attenuated as the propagation distance increases, and the distance between the AP and the sampling/interpolation point is obtained by constructing a functional relationship between the RSSI and the distance.
The traditional wireless signal attenuation model is
Wherein,
the received RSSI value is the distance between the nth AP and the sampling point/interpolation point, wherein the distance is l, and the unit dBm is the received RSSI value; s (l)0,n) RSSI values received for location points 1m away from the nth AP in dBm, l0As the distance of the reference point, 1m is usually taken; and c is a path attenuation index, and a specific numerical value is related to the environment.
Therefore, based on the wireless signal attenuation model of the formula (3), the WiFi signal strength in the WiFi signal strength fingerprint database based on Newton interpolation is corrected to obtain a priori WiFi signal strength fingerprint database.
The method comprises the steps of corresponding a priori acceleration observation database, a priori gyro angular velocity observation database, observation position information and a priori quotient super-topology map of a micro inertial element on the commercial super-shopping vehicle, and constructing a moving micro inertial information space map of the commercial super-shopping vehicle, so that the WiFi fingerprint position is restrained from being estimated and the positioning effect is optimized.
Based on a topological map of the quotient super, all possible motion modes of the current position are measured on each node, namely angle and speed information are opposite to the current node position, and an inertia information map of the quotient super is constructed.
The inertial information map takes inertial elements such as an accelerometer and a gyroscope as a core, when a carrier moves, the accelerometer continuously outputs the acceleration a (initial value 0) of the carrier, and after a coordinate system is converted and the gravity acceleration is removed, the velocity v (initial value v) of the carrier is obtained through one-time integration0) Then, the moving distance s (initial value s) of the carrier is obtained by twice integration0) (ii) a Meanwhile, the gyroscope outputs the angular velocity omega of the carrier, and the motion direction and the attitude theta (initial value theta) of the carrier are obtained through integration0) Thereby realizing the positioning and orientation of the shopping cart. the calculation formula of the motion model at the time t is as follows:
wherein v istSpeed at time t of the carrier, stFor the path of the carrier at time t, thetatThe direction of travel of the carrier at time t.
Since the placement of the shelves in the business overload environment is known, the travel route of the customer is also fixed accordingly. Therefore, the invention provides a method for constructing an inertial information map by combining inertial information and original map information to judge the current traveling road section of the shopping cart and correct the inertial navigation positioning result. On the map of the quotient super topology, each node records the position of the node and all possible angles and velocities. At each node can be represented as:
Yp＝{(xp,yp),Tp} (5)
Tp＝{(θp1,vp1),(θp2,vp2),…,(θpq,vpq)} (6)
wherein, YpRepresenting the p-th topological map node on the topological map, (x)p,yp) Representing the true position, T, of the p-th node on the quotient super mappIs the set of all possible angles and velocities at the p-th node, θpqAnd vpqThe q-th possible angle and speed at the p-th node.
Fig. 2 is a schematic diagram of a quotient super-inertia information map.
The method uses an ID3 decision tree algorithm to combine a WiFi signal fingerprint space map, a micro-inertia information space map, a prior quotient super-vector map and WiFi signal strength and micro-inertia information which are acquired in real time of a commercial super-shopping vehicle, and then calculates the optimal two-dimensional space position/motion state estimation.
And matching the WiFi signal strength and micro-inertia information measured by the shopping cart in real time with the established WiFi signal fingerprint space map and micro-inertia information space map of the movement of the shopping cart by using an ID3 decision tree algorithm based on a combined positioning algorithm of the space maps to find the best matched positioning point.
The ID3 decision tree algorithm inputs WiFi fingerprint and inertial information map information simultaneously, and the most matched positioning position coordinate in the current map environment is solved by taking the falling speed of the information entropy as the standard for selecting the test attribute.
The input to the ID3 decision tree algorithm is Wt＝{Mt,Nt}, (7)
Mt＝[s1,s2,…,sn,…,sN],
Nt＝{(θt,vt)},
Wherein, WtSet of WiFi information and inertial information measured for the shopping cart at time t, snThe received signal strength (theta) of the nth AP measured by the shopping cartt,vt) Representing the real-time travel angle and speed measured by the shopping cart. Matching the current WiFi space map with the inertial space map, and using a decision tree algorithm:
wherein A isrtDenotes the r-th condition at time t, p (A)rt) Indicating the probability of occurrence of the condition of meeting the r-th condition at time t, Encopy (U)t) The information entropy of the event at the time t is represented.
The general algorithm schematic diagram of the combined positioning algorithm based on the spatial map is shown in fig. 3, and the best matching position is found, so that the effect of accurate positioning is achieved.
Since the alternative travel directions of each intersection are known in the quotient and super environment, a path planning algorithm can be established by combining a quotient and super map and an inertial information map. And traversing all the selectable traveling directions at each corresponding intersection position in the inertial information map in a traversing mode, and calculating the distance required to be consumed by each selection according to the map information. And finally, calculating the total distance of each traversal scheme from the path planning starting point to the end point, and further selecting the optimal path.
The method combines the position/heading estimated in real time, the prior quotient super vector map and the application requirement of the quotient super navigation to form a cost field based on distance, establishes an improved A-path planning algorithm, and calculates the optimal object-searching route and the evacuation route. Estimating action costs of surrounding adjacent positions by taking the current position as a starting point through cost estimation taking the distance between the nodes as a function, selecting the optimal cost, namely the nearest distance, and searching surrounding nodes by taking the position as the starting point until the current position is a target end point.
The principles of business exceeding early warning, guiding and emergency path planning are as follows: (1) the path must avoid the hazardous area; (2) the complexity of the escape path cannot be too high; when disaster early warning occurs, the position server sends the dangerous case range to the shopping cart early warning module and the customer mobile terminal, the escape path is customized for each user, and the customer is guided to leave the scene quickly and safely through voice.
When the path cost of the emergency escape navigation path is calculated, high-density pedestrian flow and risk factors need to be considered, so that the evaluation function f (p) in the traditional A route planning algorithm is modified into f (p) ═ g (p) + h (p) × r + C (9)
G (p) is the distance required by the current position of the shopping cart to the routing node p, and h (p) is the distance required by the routing node p to the target node; r is a danger coefficient of the distance from the route node p to the target node, and the r value is larger if the r value is closer to a position with high pedestrian flow density or high danger; c is the path complexity.
Example 1:
the positioning tracking and path planning method based on the shopping cart can set a business superman flow safety monitoring and early warning system, and comprises the following steps:
the early warning module, the shopping cart position and posture estimation monitoring module, the people flow distribution estimation module based on the shopping cart pose and the sudden disaster real-time early warning decision module are arranged; the position and posture module is connected to the vehicle-mounted terminal; the distribution situation map display module, the personnel distribution situation calculation display module and the sudden disaster real-time decision module are connected to the server terminal.
And the people flow monitoring and early warning module is provided with an alarm system for reminding the customer of keeping away from a dangerous area at the first time and sending out a danger warning. And the position and attitude module is used for acquiring accurate position information of the shopping cart by combining the WiFi positioning and inertial navigation system and uploading the position information to the server.
The personnel distribution and people flow direction speed condition calculation and display module is used for acquiring the position and posture information of each device, mapping each personnel information in a quotient hyperplane graph and acquiring a real-time display graph of the personnel distribution condition; and the people flow density/speed danger estimation module is used for carrying out decision judgment on disaster information and implementing an early warning function.
The super-internal security alarm function sequence of the provider of the present embodiment is as follows:
step one, the server accesses the business super-internal fire-proof structure diagram, the internal plane diagram and the shelf and goods visiting position data, and stores the internal structure diagram, the internal plane diagram and the shelf and goods placing position data in a database.
And secondly, the server accesses the position information and the pose information of each device, calculates the position information and the pose information into coordinates on a map inside the shopping mall, and displays the coordinates on the personnel distribution condition calculation display module.
And step three, the position server acquires the track, density and speed analysis of all the devices, compares the distribution situation of monitoring estimation with a preset threshold value, intelligently judges whether a safety risk exists in the monitoring area, and simultaneously triggers an early warning system.
And step four, the server calculates the reasonable escape route planning of the personnel in different areas by combining the personnel distribution condition and the emergency safety event area information and combining a set algorithm, so that the safety and effectiveness of emergency evacuation are realized.
Example 2:
according to another aspect of the application, the object-searching and person-searching system based on the positioning information and the path planning method can improve the shopping experience of customers;
the system comprises part of the modules in the embodiment 1;
the system further comprises: a business super map module and a position sharing module.
The business super map module comprises safety channel position information, goods shelf position information, infrastructure position information such as toilets, drinking water points, customer service centers and the like.
And the position sharing module is used for sharing the position information of the customer with the specific passers-by.
The customer finding function sequence provided by the embodiment is as follows:
step one, a customer inputs goods information to be inquired, such as name, number and the like, at a customer mobile terminal.
And step two, comparing the goods information input by the customer with the goods shelf-on position information in the shopping mall map module, determining the position information of the corresponding goods, resolving the position information into coordinates on a map inside the shopping mall, displaying the coordinates on a visual map interface of a customer mobile terminal, and planning a path to guide the customer to go.
And step three, leading the customer to reach the goods shelf according to the map, and finishing the object searching function.
The order of the customer seeking function provided by this embodiment is as follows:
step one, a customer adds a peer at a customer mobile terminal.
And step two, the server communicates with the customer and the members in the same row, and the position information of the customer and the added members in the same row is shared to the other side.
And thirdly, resolving the position information of the fellow staff into coordinates on the business super interior map, and displaying the coordinates on a visual map interface of the customer mobile terminal. The customer can know the position of the peer in the business supermarket in real time.
The above description is only an embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can understand that the modifications or substitutions within the technical scope of the present invention are included in the scope of the present invention, and therefore, the scope of the present invention should be subject to the protection scope of the claims.
Claims (4)
1. The shopping cart tracking, positioning and monitoring method based on the business supermarket is characterized by comprising the following steps:
step 1, constructing a WiFi signal fingerprint space map of the movement of the shopping cart with the business exceeding according to a WiFi hotspot AP distribution map in the business exceeding, a priori WiFi signal strength fingerprint database and a business exceeding vector map;
step 2, constructing a micro-inertia information space map of the movement of the shopping cart according to a priori acceleration observation database, a priori gyro angular velocity observation database, observation position information and a shopping super-topology map;
and 3, solving the positioning which is most matched with the WiFi signal strength and the micro inertia information acquired in real time under the current map environment by using an ID3 decision tree algorithm based on the WiFi signal fingerprint space map, the micro inertia information space map and the quotient super vector map of the movement of the commercial super shopping cart.
2. The shopping cart tracking, positioning and monitoring method based on shopping cart passing through the merchant according to claim 1, wherein the method for establishing the prior WiFi signal strength fingerprint database in the step 1 comprises the following steps:
firstly, setting a plurality of sampling points in the quotient super, respectively collecting the WiFi signal intensity sent by each AP, and establishing a sparse WiFi signal intensity fingerprint database, wherein the WiFi signal intensity fingerprint of the mth sampling point representsIs composed of
M represents the number of sampling points, (x)m，ym) Indicating the position coordinates of the m-th sampling point,
for the set of acquired WiFi signal strengths for the mth sampling point,
the signal strength of the nth AP received by the mth sampling point is represented, and N represents the number of the APs;
secondly, a Newton interpolation method is adopted to perform uniform interpolation on the sparse WiFi signal intensity fingerprint database to obtain a WiFi signal intensity fingerprint database based on Newton interpolation:
based on the WiFi signal strength collected by the M sampling points, the WiFi signal strength of the interpolation point with the distance of l from the nth AP is obtained as follows:
wherein,
in the formula Im，nRepresenting the distance between the mth sampling point and the nth AP;
finally, based on a wireless signal attenuation model as shown in the formula (3), correcting the WiFi signal intensity in the WiFi signal intensity fingerprint database based on Newton interpolation to obtain a priori WiFi signal intensity fingerprint database;
wherein,
the received signal strength is the distance between the nth AP and the sampling point/interpolation point; s (l)0，n) The signal strength received by a position point with the distance of 1m from the nth AP is obtained; c is the path attenuation exponent.
3. The shopping cart tracking, positioning and monitoring method based on the shopping cart of claim 1, wherein the micro-inertia information space map of the movement of the shopping cart in the step 2 is as follows: recording the position coordinates and all possible angles and speeds of each node of the quotient super-topology map based on the micro inertial element, wherein the inertial information of the p-th node of the quotient super-topology map is Yp＝{(xp，yp)，Tp}，Tp＝{(θp1，vp1)，(θp2，vp2)，...，(θpQ，vpQ)}，(xp，yp) Is the position coordinate of the p-th node, TpIs the set of all possible angles and velocities at the p-th node, θpqAnd vpqThe q-th possible angle and speed at the p-th node.
4. The path planning method based on the commercial and super-purchased vehicles is characterized in that the travel path of the commercial and super-purchased vehicles is planned by adopting an improved A path planning algorithm, the improved A path planning algorithm improves the valuation function of the A path planning algorithm, and the improved valuation function is as follows:
f(p)＝g(p)+h(p)*r+C
wherein g (p) is the distance required by the current position of the shopping cart to the routing node p, h (p) is the distance required by the routing node p to the target node, r is the risk coefficient of the distance from the routing node p to the target node, and C is the path complexity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010012969.6A CN111182449B (en) | 2020-01-07 | 2020-01-07 | Shopping cart tracking, positioning and monitoring method based on business surpasses |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010012969.6A CN111182449B (en) | 2020-01-07 | 2020-01-07 | Shopping cart tracking, positioning and monitoring method based on business surpasses |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111182449A true CN111182449A (en) | 2020-05-19 |
| CN111182449B CN111182449B (en) | 2020-12-29 |
Family
ID=70652521
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010012969.6A Active CN111182449B (en) | 2020-01-07 | 2020-01-07 | Shopping cart tracking, positioning and monitoring method based on business surpasses |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111182449B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117250583A (en) * | 2023-11-13 | 2023-12-19 | 汉朔科技股份有限公司 | Positioning method, system, computer equipment and storage medium of intelligent shopping cart |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104535064A (en) * | 2014-12-29 | 2015-04-22 | 北京工业大学 | Wi-Fi fingerprint-assisted indoor mobile terminal inertial navigation method |
| CN104596508A (en) * | 2015-02-15 | 2015-05-06 | 杭州酷班科技有限公司 | Indoor navigation method based on combination of region location, inertial navigation and map path |
| CN106525031A (en) * | 2015-09-11 | 2017-03-22 | 王庆文 | Combined indoor positioning method |
| CN107094319A (en) * | 2016-02-17 | 2017-08-25 | 王庆文 | A kind of high-precision indoor and outdoor fusion alignment system and method |
| CN107979810A (en) * | 2017-11-03 | 2018-05-01 | 上海斐讯数据通信技术有限公司 | Indoor orientation method, server and system |
| CN109298389A (en) * | 2018-08-29 | 2019-02-01 | 东南大学 | Indoor pedestrian based on multiparticle group optimization combines position and orientation estimation method |
| CN109764886A (en) * | 2019-01-15 | 2019-05-17 | 成都信息工程大学 | A kind of paths planning method |
-
2020
- 2020-01-07 CN CN202010012969.6A patent/CN111182449B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104535064A (en) * | 2014-12-29 | 2015-04-22 | 北京工业大学 | Wi-Fi fingerprint-assisted indoor mobile terminal inertial navigation method |
| CN104596508A (en) * | 2015-02-15 | 2015-05-06 | 杭州酷班科技有限公司 | Indoor navigation method based on combination of region location, inertial navigation and map path |
| CN106525031A (en) * | 2015-09-11 | 2017-03-22 | 王庆文 | Combined indoor positioning method |
| CN107094319A (en) * | 2016-02-17 | 2017-08-25 | 王庆文 | A kind of high-precision indoor and outdoor fusion alignment system and method |
| CN107979810A (en) * | 2017-11-03 | 2018-05-01 | 上海斐讯数据通信技术有限公司 | Indoor orientation method, server and system |
| CN109298389A (en) * | 2018-08-29 | 2019-02-01 | 东南大学 | Indoor pedestrian based on multiparticle group optimization combines position and orientation estimation method |
| CN109764886A (en) * | 2019-01-15 | 2019-05-17 | 成都信息工程大学 | A kind of paths planning method |
Non-Patent Citations (2)
| Title |
|---|
| LIN MA ET.AL: "Radio Map Efficient Building Method Using Tensor Completion for WLAN Indoor Positioning System", 《2018 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC)》 * |
| 冷泽富: "大型物流配送中心人员定位系统的设计与实现", 《中国优秀硕士学位论文全文数据库 基础科学辑》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117250583A (en) * | 2023-11-13 | 2023-12-19 | 汉朔科技股份有限公司 | Positioning method, system, computer equipment and storage medium of intelligent shopping cart |
| CN117250583B (en) * | 2023-11-13 | 2024-04-09 | 汉朔科技股份有限公司 | Positioning method, system, computer equipment and storage medium of intelligent shopping cart |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111182449B (en) | 2020-12-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Li et al. | Real-time locating systems applications in construction | |
| EP3197217B1 (en) | System for determining location of entrance and area of interest | |
| Woo et al. | Application of WiFi-based indoor positioning system for labor tracking at construction sites: A case study in Guangzhou MTR | |
| EP3271748B1 (en) | Guided geometry extraction for localization of a device | |
| Rahmani et al. | Path inference from sparse floating car data for urban networks | |
| US8180104B2 (en) | Tracking method and tracking apparatus | |
| CN101526601B (en) | Self-adaptive localization method, equipment and system adopting TOA and RSS fusion mode | |
| US10415978B2 (en) | Landmark location determination | |
| Razavi et al. | GPS-less indoor construction location sensing | |
| CN105466421A (en) | Mobile robot autonomous cruise method for reliable WIFI connection | |
| CN104736968A (en) | Crowd-sourcing indoor locations | |
| US9515752B2 (en) | Method for mapping wi-fi fingerprints by means of blind collection of RSS measurements | |
| CN104236556A (en) | Trajectory information processing device and method | |
| CN111182449B (en) | Shopping cart tracking, positioning and monitoring method based on business surpasses | |
| CN114636422A (en) | Positioning and navigation method for information machine room scene | |
| Gikas et al. | A low-cost wireless sensors positioning solution for indoor parking facilities management | |
| Ramaneti et al. | IoT based 2D indoor navigation system using BLE beacons and Dijkstra's algorithm | |
| JP5979352B2 (en) | Information processing apparatus, movement prediction system, and movement prediction method | |
| JP6367771B2 (en) | POSITION ESTIMATION DEVICE, POSITION ESTIMATION METHOD, AND POSITION ESTIMATION PROGRAM | |
| KR20170064280A (en) | System for transportation search and location-logging using public transport information, and operating method of the system | |
| JP2005316739A (en) | Method and device for associating vehicle detection position with link, jam spot determination method, jam spot display method, and program | |
| Lee et al. | Beacon-based Indoor Fire Evacuation System using Augmented Reality and Machine Learning | |
| Lam et al. | A business model for personalized promotion systems on using wlan localization and nfc techniques | |
| KR101567769B1 (en) | Method for reducing acquisition time for searching a moving target through multi node cooperation based on network | |
| JP2020085783A (en) | Pedestrian-purpose positioning device, pedestrian-purpose positioning system, and pedestrian-purpose positioning method |
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 |