CN113313967A - Parking stall level navigation based on indoor low-precision positioning - Google Patents
Parking stall level navigation based on indoor low-precision positioning Download PDFInfo
- Publication number
- CN113313967A CN113313967A CN202110448634.3A CN202110448634A CN113313967A CN 113313967 A CN113313967 A CN 113313967A CN 202110448634 A CN202110448634 A CN 202110448634A CN 113313967 A CN113313967 A CN 113313967A
- Authority
- CN
- China
- Prior art keywords
- image
- positioning
- module
- distance
- node
- 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
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
- G08G1/145—Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas
- G08G1/148—Management of a network of parking areas
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T19/00—Manipulating 3D models or images for computer graphics
- G06T19/003—Navigation within 3D models or images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
- G06T3/4038—Scaling the whole image or part thereof for image mosaicing, i.e. plane images composed of plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
- G08G1/145—Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas
- G08G1/146—Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas where the parking area is a limited parking space, e.g. parking garage, restricted space
-
- 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
- H04W4/30—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
-
- 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
- H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
Abstract
The invention belongs to the technical field of positioning, and discloses a parking space level navigation system based on indoor low-precision positioning, which comprises: the system comprises an information acquisition module, an image acquisition module, a sensing module, a central control module, a verification module, a positioning module, a distance calculation module, a parking space selection module, a three-dimensional map construction module and a navigation module. The parking space level navigation system can intuitively guide the car owner by constructing the three-dimensional map, and is favorable for the car owner to more accurately master the condition of the parking lot or the parking space; meanwhile, the invention can accurately position the parking space based on the indoor positioning method, and can acquire and process the information of the parking lot or the parking garage, thereby more accurately and intuitively navigating the user. According to the invention, the information provided by field monitoring is acquired, the map and satellite positioning function of a navigation system is not needed, the inherent defect of the map and satellite positioning function is avoided, and accurate navigation of the parking space is realized.
Description
Technical Field
The invention belongs to the technical field of positioning, and particularly relates to a parking space level navigation system based on indoor low-precision positioning.
Background
At present: in the driving and traveling process, the parking problem is one of the problems troubling the majority of car owners. In order to solve the parking problem, it has been proposed in the prior art to provide a parking guidance electronic screen on the road side, and put in the remaining parking spaces of the surrounding parking lot on the electronic screen in real time, so as to guide the vehicle to the parking lot with the remaining parking spaces. However, most of existing parking garages are arranged underground, the technology of utilizing a conventional positioning method to position parking spaces cannot be applied to underground parking garages, meanwhile, under the condition that the number of vacant parking spaces in a parking lot is small, the vacant parking spaces are difficult to find in the parking lot at once, the long time is often required to be found in the parking lot, meanwhile, the parking lot is large in area scale, the building structure is complex, and when the number of the parking spaces is large, a car owner can hardly find the parking spaces only through the simple parking space guide information, and inconvenience is brought to the process of parking the car owner in the place.
Through the above analysis, the problems and defects of the prior art are as follows: the existing parking space navigation system is inaccurate in positioning and navigation, wastes much time in navigation, is not visual, and cannot well perform parking space navigation.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a parking space level navigation system based on indoor low-precision positioning.
The invention is realized in this way, a parking space level navigation system based on indoor low-precision positioning, the parking space level navigation system based on indoor low-precision positioning includes:
the information acquisition module is connected with the central control module and is used for acquiring the position and the number of the current idle parking spaces, the entrances and exits near the idle parking spaces and other related information;
the image acquisition module is connected with the central control module and is used for acquiring image information of an idle parking space and image information of the whole garage by utilizing the camera equipment;
the sensing module is connected with the central control module and used for sensing the information of the current idle parking space by utilizing the infrared sensor;
the positioning module is connected with the central control module and is used for positioning the current position of the vehicle by utilizing an indoor positioning method;
the positioning of the current position of the vehicle by using the indoor positioning method comprises the following steps: let the anchor node coordinate in the communication range of the node O to be positioned be Ai(xi,yi) Wherein i is 0,1, …, n (n is more than or equal to 4);
(1) sampling a received signal r (t) by a node to be positioned to obtain a sampling signal r (N), wherein N is 0,1, …, N-1, N represents the number of subcarriers contained in an OFDM symbol, and simultaneously recording a sending node of the received signal as Ai(xi,yi);
(2) Calculating a cross-correlation value E according to the sampling signal r (n); according to the logarithmic distance path loss model, the node to be positioned and the anchor node A are calculated according to the following formulaiThe distance between:
Pr(d′i)=Pr(d0)-10·γlg(d′i)+Xσ;
wherein, Pr (d'i) Representing distance d 'from transmitting end'iTime-derived cross-correlation value, Pr (d)0) Indicating distance from sender d0The cross-correlation value obtained at 1 meter, γ represents the path loss factor, lg (·) represents a logarithmic operation with a base of 10, XσObeying a Gaussian distribution with a mean value of 0 and a standard deviation of sigma;
calculating the distances d 'between each anchor node and the node O to be positioned by utilizing the formula'iThe coordinates of the corresponding anchor nodes are respectively Ai(xi,yi) Where i is 0,1,2, …, n;
(3) estimating the coordinates O (x, y) of the node to be positioned according to a self-adaptive distance correction algorithm;
the three-dimensional map building module is connected with the central control module and used for building a three-dimensional map based on the acquired corresponding information and image data;
and the navigation module is connected with the central control module and used for calculating the closest distance based on the parking space matching selected by the user, and displaying the closest distance on the three-dimensional map for navigation.
Further, the parking space level navigation system based on indoor low-precision positioning further comprises:
the central control module is connected with the information acquisition module, the image acquisition module, the sensing module, the verification module, the positioning module, the distance calculation module, the parking place selection module, the three-dimensional map construction module and the navigation module and is used for controlling each module to normally work by utilizing a single chip microcomputer or a controller;
the verification module is connected with the central control module and is used for verifying whether the acquired information of the idle parking spaces is accurate or not by utilizing the sensed information of the idle parking spaces and the image information;
the distance calculation module is connected with the central control module and used for calculating the distance between each free parking space and the current vehicle based on the free parking space information and the current vehicle position;
and the parking place selection module is connected with the central control module and used for sequencing according to the distance between the idle parking places and the current vehicle and providing an interactive interface for selecting the parking places.
Further, the calculating the cross-correlation value E according to the sampling signal r (n) includes:
(2.1) constructing a correlation window consisting of a continuous sampling sequence with the length of l at the same sampling position in the continuous m OFDM symbols, and then expressing the log-likelihood function lambda (tau) corresponding to the correlation window as:
(2.2) sliding the correlation window by the length of N + L sampling points to obtain the maximum value of the log-likelihood function Lambda (tau), wherein the sampling time corresponding to the maximum value is the initial position of the OFDM symbol
Wherein the content of the first and second substances,representing the value of an independent variable tau when the function obtains the maximum value, representing a log-likelihood function by Λ (tau), representing the number of continuous OFDM symbols by m, representing the length of continuous sampling sequences at the same sampling position by L, representing a sampling signal by r (N), representing the number of subcarriers contained in the OFDM symbols by N, representing the number of sampling points of a cyclic prefix part in the OFDM symbols by L, and being a modulo operator by L;
wherein, (.)*Representing a conjugate operation.
Further, the estimating the coordinates of the node to be positioned according to the adaptive distance correction algorithm includes:
(3.1) selecting a differential correction point, determining the coordinates of the positioning intersection points and the plurality of positioning intersection points, and calculating the distance between the positioning intersection points;
from d'i(i-0, 1,2, …, n) selecting the anchor node A with the smallest distance value0For the differential correction point, 3 minimum distance values are taken from the remaining distance values, d 'being the respective 3 distance values'1、d′2And d'3The coordinates of the corresponding anchor nodes are respectively A1(x1,y1)、A2(x2,y2) And A3(x3,y3) Respectively with anchor nodes Ai(xi,yi) Is the center of a circle, d'iThree positioning circles i are made for the radius, wherein i is 1,2 and 3, 6 intersection conditions of the three positioning circles exist, two intersection points exist between the two circles, and the two intersection points are two equal real number intersection points or two unequal real number intersection points or two complex number intersection points; selecting one intersection point with a smaller distance from the center coordinates of the third positioning circle from two intersection points of the two positioning circles as a positioning intersection point to participate in positioning of the node to be positioned; the number m of three positioning intersections and the number m of plural positioning intersections are determined from 3 positioning circles, and the coordinates of the positioning intersections determined from the positioning circles 2 and 3 are A '(x'1,y′1) And the coordinates of the positioning intersection points determined from positioning circle 1 and positioning circle 3 are B '(x'2,y′2) The coordinates of the positioning intersection determined by the positioning circle 1 and the positioning circle 2 are C '(x'3,y′3) The distances between the positioning intersection points A 'and B', B 'and C', A 'and C' are d12、d23、d13:
(3.2) setting a threshold value T, an individual difference coefficient correction coefficient omega and a parameter lambda (lambda is more than 0);
(3.3) locating the intersection points according to the distances d between the three locating points12、d23And d13Judging whether d 'is needed'1、d′2、d′3Make a correction if d12<T、d23<T、d13< T, then do not need to be to d'1、d′2、d′3Correction is made, execution is performed (3.5), otherwise, pair d 'is required'1、d′2、d′3Correcting and executing (3.4);
(3.4) adjusting the directional correction factor λ of the three measured distances1、λ2And λ3D 'is corrected according to the following adaptive distance correction formula'1、d′2、d′3Obtaining a corrected distance d1、d2、d3:
Wherein d isiRepresenting the node to be positioned and the anchor node AiCorrected distance between d0iRepresenting a differential correction point A0And anchor node AiActual distance between, d'0iRepresenting a differential correction point A0And anchor node AiA measured distance therebetween, ω represents an individual difference coefficient correction coefficient, λiRepresents the directional correction factor, exp (-) represents the exponential function;
according to the corrected distance d1、d2、d3Re-solving the distance d between the three corrected positioning intersections12、d23、d13Returning to (3.3);
(3.5) calculating the positioning coordinate O (x) of the node to be positioned according to the following formula0,y0):
Wherein alpha is1、α2、α3Respectively represent x'1、x′2、x′3Weight of (1), beta1、β2、β3Are respectively y'1、y′2、y′3The weight of (c).
Further, the constructing of the three-dimensional map based on the acquired corresponding information and the image data includes:
1) acquiring corresponding image data, and processing the acquired image data; determining a matching relation between any two scene images according to the feature point information of the processed scene images;
2) dividing the scene image according to the matching relation to obtain at least two image sets; determining a matching point pair between any two image sets, wherein two mutually matched feature points contained in the matching point pair between the two image sets are respectively located in a first scene image and a second scene image, and the first scene image and the second scene image are respectively located in the two image sets;
3) and acquiring a three-dimensional sub map, splicing the three-dimensional sub maps according to matching point pairs between at least two image sets to obtain a target three-dimensional map, wherein each image set is used for uniquely constructing one three-dimensional sub map.
Further, the processing the acquired image data includes:
firstly, acquiring acquired image data and a plurality of original image samples in various scenes; carrying out image enhancement on the image parameters of each original image sample to generate an enhanced image sample after image enhancement;
secondly, acquiring a pre-constructed image enhancement model; training the image enhancement model by using an enhanced image sample, and updating network parameters of the enhanced model in the training process;
and finally, inputting the acquired image data into a trained image enhancement model to obtain an enhanced target image.
Further, the training the image enhancement model by using the enhanced image sample, and updating the network parameters of the enhanced model in the training process includes:
performing image processing on the enhanced image samples to obtain original images with preset number of target sizes and corresponding enhanced images; inputting the original images with the preset number of target sizes into a pre-constructed image enhancement model to obtain output images corresponding to the original images; calculating a loss value between the output image and the enhanced image;
and training the enhancement model based on the loss value, and updating the network parameters of the image enhancement model in the training process.
Further, for any two image sets, determining a matching point pair between the two image sets includes:
for each image set, dividing scene images in the image set into internal images and external images, wherein the scene images matched with the internal images are in the image set, and at least one scene image in the scene images matched with the external images is located in other image sets;
determining matching point pairs associated with the image sets according to matching relations between external images in the image sets and scene images in other image sets; and traversing each image set to obtain a matching point pair between any two image sets.
By combining all the technical schemes, the invention has the advantages and positive effects that: the parking space level navigation system can intuitively guide the car owner by constructing the three-dimensional map, and is favorable for the car owner to more accurately master the condition of the parking lot or the parking space; meanwhile, the invention can accurately position the parking space based on the indoor positioning method, and can acquire and process the information of the parking lot or the parking garage, thereby more accurately and intuitively navigating the user. According to the invention, the information provided by field monitoring is acquired, the map and satellite positioning function of a navigation system is not needed, the inherent defect of the map and satellite positioning function is avoided, and accurate navigation of the parking space is realized.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments of the present application will be briefly described below, and it is obvious that the drawings described below are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained from the drawings without creative efforts.
Fig. 1 is a schematic structural diagram of a parking space-level navigation system based on indoor low-precision positioning according to an embodiment of the present invention;
in the figure: 1. an information acquisition module; 2. an image acquisition module; 3. a sensing module; 4. a central control module; 5. a verification module; 6. a positioning module; 7. a distance calculation module; 8. a parking place selection module; 9. a three-dimensional map construction module; 10. and a navigation module.
Fig. 2 is a flowchart of a method for constructing a three-dimensional map based on acquired corresponding information and image data according to an embodiment of the present invention.
Fig. 3 is a flowchart of a method for processing acquired image data according to an embodiment of the present invention.
Fig. 4 is a flowchart of a method for training an image enhancement model by using an enhanced image sample and updating network parameters of the enhanced model in a training process according to an embodiment of the present invention.
Fig. 5 is a flowchart of a method for determining a matching point pair between two image sets for any two image sets according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Aiming at the problems in the prior art, the invention provides a parking space level navigation system based on indoor low-precision positioning, and the invention is described in detail with reference to the attached drawings.
As shown in fig. 1, a parking space level navigation system based on indoor low-precision positioning provided by the embodiment of the present invention includes:
the information acquisition module 1 is connected with the central control module 4 and is used for acquiring the position and the number of the current idle parking spaces, the entrances and exits near the idle parking spaces and other related information;
the image acquisition module 2 is connected with the central control module 4 and is used for acquiring image information of an idle parking space and image information of the whole garage by utilizing camera equipment;
the sensing module 3 is connected with the central control module 4 and used for sensing the information of the current idle parking space by using an infrared sensor;
the central control module 4 is connected with the information acquisition module 1, the image acquisition module 2, the induction module 3, the verification module 5, the positioning module 6, the distance calculation module 7, the parking space selection module 8, the three-dimensional map construction module 9 and the navigation module 10, and is used for controlling each module to normally work by utilizing a single chip microcomputer or a controller;
the verification module 5 is connected with the central control module 4 and used for verifying whether the acquired information of the idle parking spaces is accurate or not by utilizing the sensed information of the idle parking spaces and the image information;
the positioning module 6 is connected with the central control module 4 and is used for positioning the current position of the vehicle by utilizing an indoor positioning method;
the distance calculation module 7 is connected with the central control module 4 and used for calculating the distance between each free parking space and the current vehicle based on the free parking space information and the current vehicle position;
the parking place selection module 8 is connected with the central control module 4 and used for sequencing according to the distance between the idle parking places and the current vehicle and providing an interactive interface for selecting the parking places;
the three-dimensional map building module 9 is connected with the central control module 4 and used for building a three-dimensional map based on the acquired corresponding information and image data;
and the navigation module 10 is connected with the central control module 4, is used for calculating the closest distance based on the parking space matching selected by the user, and is displayed on the three-dimensional map for navigation.
The positioning of the current position of the vehicle by utilizing the indoor positioning method provided by the embodiment of the invention comprises the following steps: let the anchor node coordinate in the communication range of the node O to be positioned be Ai(xi,yi) Wherein i is 0,1, …, n (n is more than or equal to 4);
(1) sampling a received signal r (t) by a node to be positioned to obtain a sampling signal r (N), wherein N is 0,1, …, N-1, N represents the number of subcarriers contained in an OFDM symbol, and simultaneously recording a sending node of the received signal as Ai(xi,yi);
(2) Calculating a cross-correlation value E according to the sampling signal r (n); according to the logarithmic distance path loss model, the node to be positioned and the anchor node A are calculated according to the following formulaiThe distance between:
Pr(d′i)=Pr(d0)-10·γlg(d′i)+Xσ;
wherein, Pr (d'i) Representing distance d 'from transmitting end'iTime-derived cross-correlation value, Pr (d)0) Indicating distance from sender d0The cross-correlation value obtained at 1 meter, γ represents the path loss factor, lg (·) represents a logarithmic operation with a base of 10, XσObeying a Gaussian distribution with a mean value of 0 and a standard deviation of sigma;
calculating the distances d 'between each anchor node and the node O to be positioned by utilizing the formula'iThe coordinates of the corresponding anchor nodes are respectively Ai(xi,yi) Where i is 0,1,2, …, n;
(3) and estimating the coordinates O (x, y) of the node to be positioned according to the self-adaptive distance correction algorithm.
According to the sampling signal r (n), the method for calculating the cross-correlation value E comprises the following steps:
(2.1) constructing a correlation window consisting of a continuous sampling sequence with the length of l at the same sampling position in the continuous m OFDM symbols, and then expressing the log-likelihood function lambda (tau) corresponding to the correlation window as:
(2.2) sliding the correlation window by the length of N + L sampling points to obtain the maximum value of the log-likelihood function Lambda (tau), wherein the sampling time corresponding to the maximum value is the initial position of the OFDM symbol
Wherein the content of the first and second substances,representing the value of an independent variable tau when the function obtains the maximum value, representing a log-likelihood function by Λ (tau), representing the number of continuous OFDM symbols by m, representing the length of continuous sampling sequences at the same sampling position by L, representing a sampling signal by r (N), representing the number of subcarriers contained in the OFDM symbols by N, representing the number of sampling points of a cyclic prefix part in the OFDM symbols by L, and being a modulo operator by L;
wherein, (.)*Representing a conjugate operation.
The method for estimating the coordinates of the node to be positioned according to the self-adaptive distance correction algorithm comprises the following steps:
(3.1) selecting a differential correction point, determining the coordinates of the positioning intersection points and the plurality of positioning intersection points, and calculating the distance between the positioning intersection points;
from d'i(i-0, 1,2, …, n) selecting the anchor node A with the smallest distance value0For the differential correction point, 3 minimum distance values are taken from the remaining distance values, d 'being the respective 3 distance values'1、d′2And d'3The coordinates of the corresponding anchor nodes are respectively A1(x1,y1)、A2(x2,y2) And A3(x3,y3) Respectively with anchor nodes Ai(xi,yi) Is the center of a circle, d'iThree positioning circles i are made for the radius, wherein i is 1,2 and 3, 6 intersection conditions of the three positioning circles exist, two intersection points exist between the two circles, and the two intersection points are two equal real number intersection points or two unequal real number intersection points or two complex number intersection points; selecting one intersection point with a smaller distance from the center coordinates of the third positioning circle from two intersection points of the two positioning circles as a positioning intersection point to participate in positioning of the node to be positioned; the number m of three positioning intersections and the number m of plural positioning intersections are determined from 3 positioning circles, and the coordinates of the positioning intersections determined from the positioning circles 2 and 3 are A '(x'1,y′1) And the coordinates of the positioning intersection points determined from positioning circle 1 and positioning circle 3 are B '(x'2,y′2) The coordinates of the positioning intersection determined by the positioning circle 1 and the positioning circle 2 are C '(x'3,y′3) The distances between the positioning intersection points A 'and B', B 'and C', A 'and C' are d12、d23、d13:
(3.2) setting a threshold value T, an individual difference coefficient correction coefficient omega and a parameter lambda (lambda is more than 0);
(3.3) locating the intersection points according to the distances d between the three locating points12、d23And d13Judging whether d 'is needed'1、d′2、d′3Make a correction if d12<T、d23<T、d13< T, then do not need to be to d'1、d′2、d′3Correction is made, execution is performed (3.5), otherwise, pair d 'is required'1、d′2、d′3Correcting and executing (3.4);
(3.4) adjusting the directional correction factor λ of the three measured distances1、λ2And λ3D 'is corrected according to the following adaptive distance correction formula'1、d′2、d′3Obtaining a corrected distance d1、d2、d3:
Wherein d isiRepresenting the node to be positioned and the anchor node AiCorrected distance between d0iRepresenting a differential correction point A0And anchor node AiActual distance between, d'0iRepresenting a differential correction point A0And anchor node AiA measured distance therebetween, ω represents an individual difference coefficient correction coefficient, λiRepresents the directional correction factor, exp (-) represents the exponential function;
according to the corrected distance d1、d2、d3Re-solving the distance d between the three corrected positioning intersections12、d23、d13Returning to (3.3);
(3.5) according to the following formula, meterCalculating the positioning coordinate O (x) of the node to be positioned0,y0):
Wherein alpha is1、α2、α3Respectively represent x'1、x′2、x′3Weight of (1), beta1、β2、β3Are respectively y'1、y′2、y′3The weight of (c).
As shown in fig. 2, the construction of the three-dimensional map based on the acquired corresponding information and image data according to the embodiment of the present invention includes:
s101, acquiring corresponding image data and processing the acquired image data; determining a matching relation between any two scene images according to the feature point information of the processed scene images;
s102, dividing the scene image according to the matching relation to obtain at least two image sets; determining a matching point pair between any two image sets, wherein two mutually matched feature points contained in the matching point pair between the two image sets are respectively located in a first scene image and a second scene image, and the first scene image and the second scene image are respectively located in the two image sets;
s103, acquiring a three-dimensional sub map, and splicing the three-dimensional sub maps according to matching point pairs between at least two image sets to obtain a target three-dimensional map, wherein each image set is used for uniquely constructing one three-dimensional sub map.
As shown in fig. 3, the processing of the acquired image data according to the embodiment of the present invention includes:
s201, acquiring acquired image data and a plurality of original image samples in various scenes; carrying out image enhancement on the image parameters of each original image sample to generate an enhanced image sample after image enhancement;
s202, acquiring a pre-constructed image enhancement model; training the image enhancement model by using an enhanced image sample, and updating network parameters of the enhanced model in the training process;
and S203, inputting the acquired image data into a trained image enhancement model to obtain an enhanced target image.
As shown in fig. 4, the training of the image enhancement model by using the enhanced image sample, and updating the network parameters of the enhanced model in the training process according to the embodiment of the present invention includes:
s301, performing image processing on the enhanced image samples to obtain original images with preset number of target sizes and corresponding enhanced images;
s302, inputting the original images with the preset number of target sizes into a pre-constructed image enhancement model to obtain output images corresponding to the original images; calculating a loss value between the output image and the enhanced image;
s303, training the enhancement model based on the loss value, and updating the network parameters of the image enhancement model in the training process.
As shown in fig. 5, the determining a matching point pair between two image sets for any two image sets according to the embodiment of the present invention includes:
s401, for each image set, dividing scene images in the image set into internal images and external images, wherein the scene images matched with the internal images are in the image set, and at least one scene image in the scene images matched with the external images is located in other image sets;
s402, determining matching point pairs associated with the image set according to the matching relation between the external image in the image set and the scene images in other image sets; and traversing each image set to obtain a matching point pair between any two image sets.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention, and the scope of the present invention is not limited thereto, and any modification, equivalent replacement, and improvement made by those skilled in the art within the technical scope of the present invention disclosed herein, which is within the spirit and principle of the present invention, should be covered by the present invention.
Claims (10)
1. The utility model provides a parking stall level navigation based on indoor low accuracy location which characterized in that, parking stall level navigation based on indoor low accuracy location includes:
the information acquisition module is connected with the central control module and is used for acquiring the position and the number of the current idle parking spaces, the entrances and exits near the idle parking spaces and other related information;
the image acquisition module is connected with the central control module and is used for acquiring image information of an idle parking space and image information of the whole garage by utilizing the camera equipment;
the sensing module is connected with the central control module and used for sensing the information of the current idle parking space by utilizing the infrared sensor;
the positioning module is connected with the central control module and is used for positioning the current position of the vehicle by utilizing an indoor positioning method;
the positioning of the current position of the vehicle by using the indoor positioning method comprises the following steps: let the anchor node coordinate in the communication range of the node O to be positioned be Ai(xi,yi) Wherein i is 0,1, …, n (n is more than or equal to 4);
(1) sampling a received signal r (t) by a node to be positioned to obtain a sampling signal r (N), wherein N is 0,1, …, N-1, N represents the number of subcarriers contained in an OFDM symbol, and simultaneously recording a sending node of the received signal as Ai(xi,yi);
(2) Calculating a cross-correlation value E according to the sampling signal r (n); according to the logarithmic distance path loss model, the node to be positioned and the anchor node A are calculated according to the following formulaiThe distance between:
Pr(d′i)=Pr(d0)-10·γlg(d′i)+Xσ;
wherein, Pr (d'i) Representing distance d 'from transmitting end'iObtained at the timeCross correlation value, Pr (d)0) Indicating distance from sender d0The cross-correlation value obtained at 1 meter, γ represents the path loss factor, lg (·) represents a logarithmic operation with a base of 10, XσObeying a Gaussian distribution with a mean value of 0 and a standard deviation of sigma;
calculating the distances d 'between each anchor node and the node O to be positioned by utilizing the formula'iThe coordinates of the corresponding anchor nodes are respectively Ai(xi,yi) Where i is 0,1,2, …, n;
(3) estimating the coordinates O (x, y) of the node to be positioned according to a self-adaptive distance correction algorithm;
the three-dimensional map building module is connected with the central control module and used for building a three-dimensional map based on the acquired corresponding information and image data;
and the navigation module is connected with the central control module and used for calculating the closest distance based on the parking space matching selected by the user, and displaying the closest distance on the three-dimensional map for navigation.
2. The indoor low-precision positioning-based space-level navigation system according to claim 1, wherein the indoor low-precision positioning-based space-level navigation system further comprises:
the central control module is connected with the information acquisition module, the image acquisition module, the sensing module, the verification module, the positioning module, the distance calculation module, the parking place selection module, the three-dimensional map construction module and the navigation module and is used for controlling each module to normally work by utilizing a single chip microcomputer or a controller;
the verification module is connected with the central control module and is used for verifying whether the acquired information of the idle parking spaces is accurate or not by utilizing the sensed information of the idle parking spaces and the image information;
the distance calculation module is connected with the central control module and used for calculating the distance between each free parking space and the current vehicle based on the free parking space information and the current vehicle position;
and the parking place selection module is connected with the central control module and used for sequencing according to the distance between the idle parking places and the current vehicle and providing an interactive interface for selecting the parking places.
3. The system according to claim 1, wherein the calculating the cross-correlation value E according to the sampling signal r (n) comprises:
(2.1) constructing a correlation window consisting of a continuous sampling sequence with the length of l at the same sampling position in the continuous m OFDM symbols, and then expressing the log-likelihood function lambda (tau) corresponding to the correlation window as:
(2.2) sliding the correlation window by the length of N + L sampling points to obtain the maximum value of the log-likelihood function Lambda (tau), wherein the sampling time corresponding to the maximum value is the initial position of the OFDM symbol
Wherein the content of the first and second substances,representing the value of an independent variable tau when the function obtains the maximum value, representing a log-likelihood function by Λ (tau), representing the number of continuous OFDM symbols by m, representing the length of continuous sampling sequences at the same sampling position by L, representing a sampling signal by r (N), representing the number of subcarriers contained in the OFDM symbols by N, representing the number of sampling points of a cyclic prefix part in the OFDM symbols by L, and being a modulo operator by L;
wherein, (.)*Representing a conjugate operation.
4. The system according to claim 1, wherein the estimating coordinates of the node to be located according to the adaptive distance correction algorithm comprises:
(3.1) selecting a differential correction point, determining the coordinates of the positioning intersection points and the plurality of positioning intersection points, and calculating the distance between the positioning intersection points;
from d'i(i-0, 1,2, …, n) selecting the anchor node A with the smallest distance value0For the differential correction point, 3 minimum distance values are taken from the remaining distance values, d 'being the respective 3 distance values'1、d′2And d'3The coordinates of the corresponding anchor nodes are respectively A1(x1,y1)、A2(x2,y2) And A3(x3,y3) Respectively with anchor nodes Ai(xi,yi) Is the center of a circle, d'iThree positioning circles i are made for the radius, wherein i is 1,2 and 3, 6 intersection conditions of the three positioning circles exist, two intersection points exist between the two circles, and the two intersection points are two equal real number intersection points or two unequal real number intersection points or two complex number intersection points; selecting one intersection point with a smaller distance from the center coordinates of the third positioning circle from two intersection points of the two positioning circles as a positioning intersection point to participate in positioning of the node to be positioned; the number m of three positioning intersections and the number m of plural positioning intersections are determined from 3 positioning circles, and the coordinates of the positioning intersections determined from the positioning circles 2 and 3 are A '(x'1,y′1) And the coordinates of the positioning intersection points determined from positioning circle 1 and positioning circle 3 are B '(x'2,y′2) The coordinates of the positioning intersection determined by the positioning circle 1 and the positioning circle 2 are C '(x'3,y′3) The distances between the positioning intersection points A 'and B', B 'and C', A 'and C' are d12、d23、d13:
(3.2) setting a threshold value T, an individual difference coefficient correction coefficient omega and a parameter lambda (lambda is more than 0);
(3.3) locating the intersection points according to the distances d between the three locating points12、d23And d13Judging whether d 'is needed'1、d′2、d′3Make a correction if d12<T、d23<T、d13< T, then do not need to be to d'1、d′2、d′3Correction is made, execution is performed (3.5), otherwise, pair d 'is required'1、d′2、d′3Correcting and executing (3.4);
(3.4) adjusting the directional correction factor λ of the three measured distances1、λ2And λ3D 'is corrected according to the following adaptive distance correction formula'1、d′2、d′3Obtaining a corrected distance d1、d2、d3:
Wherein d isiRepresenting the node to be positioned and the anchor node AiCorrected distance between d0iRepresenting a differential correction point A0And anchor node AiActual distance between, d'0iRepresenting a differential correction point A0And anchor node AiMeasured distance betweenWhere ω denotes an individual difference coefficient correction coefficient, λiRepresents the directional correction factor, exp (-) represents the exponential function;
according to the corrected distance d1、d2、d3Re-solving the distance d between the three corrected positioning intersections12、d23、d13Returning to (3.3);
(3.5) calculating the positioning coordinate O (x) of the node to be positioned according to the following formula0,y0):
Wherein alpha is1、α2、α3Respectively represent x'1、x′2、x′3Weight of (1), beta1、β2、β3Are respectively y'1、y′2、y′3The weight of (c).
5. The system according to claim 1, wherein the construction of the three-dimensional map based on the collected corresponding information and image data comprises:
1) acquiring corresponding image data, and processing the acquired image data; determining a matching relation between any two scene images according to the feature point information of the processed scene images;
2) dividing the scene image according to the matching relation to obtain at least two image sets; determining a matching point pair between any two image sets, wherein two mutually matched feature points contained in the matching point pair between the two image sets are respectively located in a first scene image and a second scene image, and the first scene image and the second scene image are respectively located in the two image sets;
3) and acquiring a three-dimensional sub map, splicing the three-dimensional sub maps according to matching point pairs between at least two image sets to obtain a target three-dimensional map, wherein each image set is used for uniquely constructing one three-dimensional sub map.
6. The indoor low-precision positioning-based parking space level navigation system according to claim 5, wherein the processing of the collected image data comprises:
firstly, acquiring acquired image data and a plurality of original image samples in various scenes; carrying out image enhancement on the image parameters of each original image sample to generate an enhanced image sample after image enhancement;
secondly, acquiring a pre-constructed image enhancement model; training the image enhancement model by using an enhanced image sample, and updating network parameters of the enhanced model in the training process;
and finally, inputting the acquired image data into a trained image enhancement model to obtain an enhanced target image.
7. The system according to claim 6, wherein the training of the image enhancement model by using the enhanced image samples and the updating of the network parameters of the enhanced model during the training process comprises:
performing image processing on the enhanced image samples to obtain original images with preset number of target sizes and corresponding enhanced images; inputting the original images with the preset number of target sizes into a pre-constructed image enhancement model to obtain output images corresponding to the original images; calculating a loss value between the output image and the enhanced image;
and training the enhancement model based on the loss value, and updating the network parameters of the image enhancement model in the training process.
8. The indoor low-precision positioning-based space-level navigation system according to claim 6, wherein the determining, for any two image sets, a matching point pair between the two image sets comprises:
for each image set, dividing scene images in the image set into internal images and external images, wherein the scene images matched with the internal images are in the image set, and at least one scene image in the scene images matched with the external images is located in other image sets;
determining matching point pairs associated with the image sets according to matching relations between external images in the image sets and scene images in other image sets; and traversing each image set to obtain a matching point pair between any two image sets.
9. A computer program product stored on a computer readable medium, comprising a computer readable program for providing a user input interface for implementing an indoor low-precision positioning-based space-level navigation system according to any one of claims 1 to 8 when executed on an electronic device.
10. A computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to execute the system for parking space level navigation based on indoor low-precision positioning according to any one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110448634.3A CN113313967A (en) | 2021-04-25 | 2021-04-25 | Parking stall level navigation based on indoor low-precision positioning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110448634.3A CN113313967A (en) | 2021-04-25 | 2021-04-25 | Parking stall level navigation based on indoor low-precision positioning |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113313967A true CN113313967A (en) | 2021-08-27 |
Family
ID=77371048
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110448634.3A Pending CN113313967A (en) | 2021-04-25 | 2021-04-25 | Parking stall level navigation based on indoor low-precision positioning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113313967A (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104236539A (en) * | 2013-06-21 | 2014-12-24 | 北京四维图新科技股份有限公司 | Navigation method, navigation terminal and navigation system |
CN104469941A (en) * | 2014-12-23 | 2015-03-25 | 西安电子科技大学 | Indoor wireless locating method based on wireless local area network WLAN OFDM signal cyclic prefix |
CN108830816A (en) * | 2018-06-27 | 2018-11-16 | 厦门美图之家科技有限公司 | Image enchancing method and device |
CN110264777A (en) * | 2019-06-26 | 2019-09-20 | 广州小鹏汽车科技有限公司 | Indoor vehicle air navigation aid, device, storage medium and vehicle control terminal |
CN111833447A (en) * | 2020-07-13 | 2020-10-27 | Oppo广东移动通信有限公司 | Three-dimensional map construction method, three-dimensional map construction device and terminal equipment |
WO2021017212A1 (en) * | 2019-07-26 | 2021-02-04 | 魔门塔(苏州)科技有限公司 | Multi-scene high-precision vehicle positioning method and apparatus, and vehicle-mounted terminal |
-
2021
- 2021-04-25 CN CN202110448634.3A patent/CN113313967A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104236539A (en) * | 2013-06-21 | 2014-12-24 | 北京四维图新科技股份有限公司 | Navigation method, navigation terminal and navigation system |
CN104469941A (en) * | 2014-12-23 | 2015-03-25 | 西安电子科技大学 | Indoor wireless locating method based on wireless local area network WLAN OFDM signal cyclic prefix |
CN108830816A (en) * | 2018-06-27 | 2018-11-16 | 厦门美图之家科技有限公司 | Image enchancing method and device |
CN110264777A (en) * | 2019-06-26 | 2019-09-20 | 广州小鹏汽车科技有限公司 | Indoor vehicle air navigation aid, device, storage medium and vehicle control terminal |
WO2021017212A1 (en) * | 2019-07-26 | 2021-02-04 | 魔门塔(苏州)科技有限公司 | Multi-scene high-precision vehicle positioning method and apparatus, and vehicle-mounted terminal |
CN111833447A (en) * | 2020-07-13 | 2020-10-27 | Oppo广东移动通信有限公司 | Three-dimensional map construction method, three-dimensional map construction device and terminal equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113538919B (en) | Lane departure recognition method, device, equipment and storage medium | |
US7383125B2 (en) | Navigation method and system for accurately estimating positions of street address numbers | |
CN108230725A (en) | Method and apparatus are recommended in parking | |
CN111457925B (en) | Community path navigation method and device, computer equipment and storage medium | |
EP1970670A1 (en) | Route-selection-supporting device and method | |
CN107745711B (en) | Method and device for determining route in automatic driving mode | |
CN113506457B (en) | Device and method for searching parking space based on large parking lot scene | |
CN111174778B (en) | Building entrance determining method and device based on pedestrian dead reckoning | |
CN110647886A (en) | Interest point marking method and device, computer equipment and storage medium | |
JP2015076077A (en) | Traffic volume estimation system,terminal device, traffic volume estimation method and traffic volume estimation program | |
CN111401255B (en) | Method and device for identifying bifurcation junctions | |
CN112629558A (en) | Vehicle inertial navigation matching correction method and device, equipment and storage medium | |
CN111145574B (en) | Method, device and equipment for determining position relation of vehicle in curve | |
US10247562B2 (en) | Method for displaying real range of electric vehicles on a map | |
CN111679304A (en) | Method and device for determining and updating entrance and exit positions | |
CN109544981A (en) | Image processing method, device, equipment and medium | |
CN111340880B (en) | Method and apparatus for generating predictive model | |
CN113313967A (en) | Parking stall level navigation based on indoor low-precision positioning | |
CN115019216B (en) | Real-time ground object detection and positioning counting method, system and computer | |
CN116086429A (en) | Map updating method, device, equipment and computer readable storage medium | |
CN109520495B (en) | Navigation positioning device and navigation positioning method using same | |
JP2019179324A (en) | System and program for setting target parking spot | |
CN114396956A (en) | Navigation method and apparatus, computing device, storage medium, and computer program product | |
JP2009115485A (en) | Navigation device, method, and program | |
CN114782516A (en) | Method and system for processing orthoimage of unmanned aerial vehicle |
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 |