CN111238470B - Intelligent glasses road planning method, medium and equipment under artificial intelligent big data - Google Patents
Intelligent glasses road planning method, medium and equipment under artificial intelligent big data Download PDFInfo
- Publication number
- CN111238470B CN111238470B CN202010023509.3A CN202010023509A CN111238470B CN 111238470 B CN111238470 B CN 111238470B CN 202010023509 A CN202010023509 A CN 202010023509A CN 111238470 B CN111238470 B CN 111238470B
- Authority
- CN
- China
- Prior art keywords
- intelligent glasses
- glasses
- intelligent
- matrix
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000011521 glass Substances 0.000 title claims abstract description 241
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000012544 monitoring process Methods 0.000 claims abstract description 8
- 239000011159 matrix material Substances 0.000 claims description 66
- 239000004984 smart glass Substances 0.000 claims description 56
- 238000004891 communication Methods 0.000 claims description 12
- 238000013519 translation Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000013473 artificial intelligence Methods 0.000 claims description 8
- 230000006978 adaptation Effects 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 7
- 238000005259 measurement Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 230000003993 interaction Effects 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 3
- 230000008602 contraction Effects 0.000 claims description 3
- 238000003708 edge detection Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 230000005251 gamma ray Effects 0.000 claims description 3
- 238000012804 iterative process Methods 0.000 claims description 3
- 238000005315 distribution function Methods 0.000 claims description 2
- 239000003814 drug Substances 0.000 claims description 2
- 238000002360 preparation method Methods 0.000 claims description 2
- 238000013179 statistical model Methods 0.000 claims description 2
- 230000003044 adaptive effect Effects 0.000 claims 1
- 238000004422 calculation algorithm Methods 0.000 abstract description 9
- 238000011160 research Methods 0.000 abstract description 7
- 238000013461 design Methods 0.000 abstract description 4
- 238000004458 analytical method Methods 0.000 abstract description 3
- 238000011217 control strategy Methods 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 5
- 230000033001 locomotion Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 230000004927 fusion Effects 0.000 description 2
- 206010034719 Personality change Diseases 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000003703 image analysis method Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/10—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
- G01C21/12—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning
- G01C21/16—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation
- G01C21/165—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation combined with non-inertial navigation instruments
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/10—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
- G01C21/12—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning
- G01C21/16—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation
- G01C21/18—Stabilised platforms, e.g. by gyroscope
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Navigation (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention belongs to the technical field of intelligent glasses algorithms, and particularly relates to a road planning method, medium and equipment for intelligent glasses under artificial intelligent big data based on a particlized fractional order. The invention comprises the following steps: (1) The image pickup system of the intelligent glasses collects images, performs denoising treatment on the collected images, and then performs optimal path planning through path edge points; (2) The intelligent glasses perform travel operation to guide the intelligent glasses user to travel in the planned path channel; (3) And carrying out gesture monitoring on the intelligent glasses in the journey. The invention expands research by using a fractional order intelligent glasses control strategy to realize the design and stability analysis of an intelligent glasses control system, optimizes parameters in a control law on the basis of the control law, and omits the problem of manually selecting the parameters. Therefore, the difficulty of road planning of the intelligent glasses group is simplified, and stable use of the intelligent glasses is realized.
Description
Technical Field
The invention belongs to the technical field of intelligent glasses algorithms, and particularly relates to a road planning method, medium and equipment for intelligent glasses under artificial intelligent big data based on a particlized fractional order.
Background
The intelligent glasses are one of the wearable intelligent devices which are proposed in recent years and are well-seen, and the intelligent glasses can liberate both hands and realize various life functions convenient for people. After the scientific technology is proposed, it is more important to apply it to reality or become a result. As a visual field representative wearable electronic device, intelligent glasses have great application market and potential in the field of artificial intelligence research. However, at present, no mature product is applied to the related technology in the artificial intelligence field in China, and no mature guiding article exists at the same time.
In daily life, a user can position the glasses through a mobile phone application, and can call the mobile phone through buttons on the glasses, so that the mobile phone is found. In summary, the design and research of the intelligent glasses meet the needs of people in actual life, and have a solid theoretical basis, so that the intelligent glasses have great research significance. Smart glasses have shown great application value and development potential in various fields. Along with the diversification of man-machine interaction technology, face recognition is an important embodiment of man-machine interaction, and has been widely applied to access control systems, monitoring systems and identity verification. The method is applied to wearable electronic equipment such as intelligent glasses and the like, so that a user can use the intelligent equipment more conveniently, but the hardware performance of the intelligent equipment is lower, and the traditional face recognition algorithm cannot be realized quickly or cannot realize preset functions at all when the hardware performance is limited. Therefore, it is important to research a path planning algorithm with low network complexity and high processing speed. The invention is suitable for the path recognition technology of the intelligent glasses, and can meet the requirements of various application occasions.
Disclosure of Invention
The invention aims to provide a road planning method for intelligent glasses under artificial intelligent big data, which has higher control precision and stronger obstacle avoidance performance.
The invention also aims to provide a road planning medium for the intelligent glasses under the artificial intelligent big data.
The invention also aims to provide road planning equipment for the intelligent glasses under the artificial intelligent big data.
The purpose of the invention is realized in the following way:
the road planning method of the intelligent glasses under the artificial intelligent big data comprises a glasses assembly and a frame, wherein the glasses assembly comprises two lenses, and the frame comprises a glasses frame and two intelligent glasses legs respectively connected to two ends of the glasses frame; the intelligent glasses leg comprises a glasses leg body provided with a containing cavity, a power module in the containing cavity, a camera system, a distance sensor, a height sensor, a processor, a voice recognition module, a voice playing module and a wireless communication module, wherein the camera system, the distance sensor, the height sensor, the processor, the voice recognition module, the voice playing module and the wireless communication module are electrically connected with the power module and are arranged in any containing cavity; the intelligent glasses group path planning and travel control method comprises the following steps that a camera shooting system, a distance sensor, a height sensor, a voice recognition module and a voice playing module are connected to a processor through signals, and can be connected with artificial intelligent interaction equipment through wireless communication modules and/or cloud control system information, a power module is a rechargeable battery, the voice recognition module is a receiver, the voice playing module is a microphone, and the intelligent glasses group path planning and travel control are carried out by an intelligent glasses cloud control system and a control module on intelligent glasses, and the planning method comprises the following steps:
(1) The image pickup system of the intelligent glasses collects images, performs denoising treatment on the collected images, and then performs optimal path planning through path edge points;
(2) The intelligent glasses perform travel operation to guide the intelligent glasses user to travel in the planned path channel;
(3) Performing gesture monitoring on the intelligent glasses in the journey;
(4) Repeating steps (2) - (3) until the smart glasses user stops using;
the step (1) comprises the following steps:
(1.1) image acquisition denoising:
the intelligent glasses acquire three-dimensional images of the environment where the path is located through the camera system, and Gaussian filtering processing is carried out on the acquired images;
(1.2) edge detection of a road in an image:
sobel operator calculation is carried out on the gray values of adjacent points around each pixel point in the image, and a threshold value tau is selected by the brightness acquired by the acquired image when
f x ＝(f(a-1,b-1)+2f(a-1,b)+f(a-1,b+1))-(f(a+1,b+1)+2f(a-1,b)+f(a+1,b+1))，
f y ＝(f(a-1,b-1)+2f(a,b-1)+f(a+1,b-1))-(f(a-1,b-1)+2f(a,b-1)+f(a+1,b-1))，
When So (a, b) > tau, the points (a, b) in the image are edge points, a, b are coordinates of the edge points, and f is a gray value;
(1.3) path planning according to edge points:
the cloud control system of the intelligent glasses collects edge point information, a path channel is constructed through the edge points, and an included angle between the imaging system of the intelligent glasses and the distance sensor and the horizontal direction is theta a The data returned by the distance sensor is l a The measurement value of the height sensor of the intelligent glasses is z', and the coordinate under the horizontal reference system is D n0 ＝(x a ,y b ,z′)＝(l a ×cosθ a ,l a ×sinθ a ,z′)；
Determining a planned path according to the iteration evaluation value of the nodes in the path channel, wherein the distance between two adjacent nodes is l n0 ，l n0 ＝D n0 -D n0-1 N0 is the index of the current node, the starting point I 0 To the current node I n0 The cost function of (2) is:
and scanning two neighbor nodes with maximum G (n 0) near each node to connect, so as to form a planned path channel.
The step (2) comprises:
(2.1) initializing an intelligent glasses group with the number of N, wherein the intelligent glasses group comprises the random speed of the area of the intelligent glasses and the position of the area of the intelligent glasses, and determining the gesture matrix, the angular rate of the gesture matrix and the gesture angle of each intelligent glasses;
(2.2) evaluating the fitness value of the smart glasses in each group;
(2.3) evaluating the best position in the current search space of the smart glasses in each group;
(2.4) updating the inertial weight of the intelligent glasses, and updating the speed and the position of each intelligent glasses;
(2.5) re-executing the step (2.2) under the working state of the intelligent glasses, and ending the method when the working of the intelligent glasses is finished;
the determining step of the gesture matrix of the intelligent glasses comprises the following steps:
(2.1.1) assuming the Earth coordinate System as the earth System, the geographic coordinate SystemThe carrier coordinate system is carrier system, the navigation coordinate system is pilot system, and the axes of the coordinate systems are respectively X in turn g 、Y g 、Z g ；X c 、Y c 、Z c ；X p 、Y p 、Z p ；
(2.1.2) calculating a directional cosine matrix of a geographic coordinate system of the intelligent glasses;
wherein the longitude of the intelligent glasses is alpha e And a latitude of delta e ；α e The range of the values of (a) is (-180 DEG, 180 DEG); delta e The range of the values of (a) is (-90 DEG, 90 DEG);
(2.1.3) calculating a direction cosine matrix of a carrier coordinate system of the intelligent glasses;
wherein gamma is c For roll angle of the carrier coordinate system relative to the geographical coordinate system, i.e. X c Relative to X g Is included in the plane of the first part;
wherein θ is c For pitch angle of the carrier coordinate system relative to the geographical coordinate system, i.e. Y c With respect to Y g Is included in the plane of the first part;
wherein the method comprises the steps of
For heading angle of the carrier coordinate system relative to the geographical coordinate system, i.e. Z c Relative to Z g Is included in the plane of the first part;
(2.1.4) calculating an attitude matrix of a navigation coordinate system of the intelligent glasses;
(2.1.5) calculating the attitude matrix angular rate of the navigation coordinate system of the intelligent glasses;
ω e omega is the projection of the earth angular velocity in the navigation coordinate system a Is a measured value of the intelligent glasses gyroscope.
The adaptation value of the intelligent glasses in each group is evaluated as follows:
f j (x) Representing a branching function on a j-th branch on a target path of the intelligent glasses; alpha j The weight corresponding to the jth branch is represented, m is the total number of branches of the target path, and x represents the estimated intelligent glasses label;
f j (x)＝(β j ∩γ j )(β j ∪γ j ) -2 ；
β j a set of smart glasses for executing a target path through a j-th branch; gamma ray j The intelligent glasses set is used for inputting the j-th branch which is passed by the tested program after being executed.
The step of evaluating the optimal position in the current search space of the intelligent glasses in each group comprises the following steps of;
(2.3.1) matching the fitness value of each smart glasses with the estimated current local best known position pbest of the smart glasses i,n Comparing, if the adaptation value of the intelligent glasses is small, replacing the adaptation value of the intelligent glasses with the current local best known position pbest i,n ；
(2.3.2) comparing the current locally-best known position pbest of each smart glasses with the best position gbest in the current search space of the smart glasses, and if the current locally-best known position pbest of the smart glasses is small, replacing the current locally-best known position pbest of the smart glasses with the best position gbest in the current search space.
The estimated current local best known position of the intelligent glassesPut the pbest i,n Comprising:
n intelligent glasses, wherein each intelligent glasses is positioned in a search space of S dimension, S is less than or equal to 3, and the position of the ith intelligent glasses in the nth iteration process of the method is as follows:
the corresponding speed of the intelligent glasses is as follows:
the updating of the speed and the position of each intelligent glasses comprises;
(2.4.1) update G n The inertial weight is:
G nmax g is the maximum value of the inertial weight of the intelligent glasses nmin As a minimum value of the inertial weight,
N max is the maximum value of the iteration times;
(2.4.2) update the speed of the smart glasses:
v i,n ＝p s [v i,n-1 +G n ·(pbest-x i,n-1 )+G n ·(gbest-x i,n-1 )]；
p s in order for the contraction factor to be a factor,
k is the upper limit speed of network searching;
(2.4.3) updating the position of the smart glasses;
x i,n ＝x i,n-1 +v i,n 。
said alpha j Indicating the weight corresponding to the jth branch,
γ n representing a value of the number of path consecutive matches greater than 1 in the iterative process.
The step (3) comprises the following steps:
(3.1) extracting point cloud data M of the intelligent glasses environment reference target at the previous time point through a cloud data system W At point cloud data M W Set m of medium fetch points i ∈M W The method comprises the steps of carrying out a first treatment on the surface of the Simultaneous extraction of m i Corresponding real set
(3.2) extracting point cloud data Q of the intelligent glasses environment reference target at the current time point by the camera system W At point cloud data Q W Set q of medium fetch points i ∈Q W Let |q i -m i Obtaining a minimum value;
(3.3) calculating the rotation matrix R in the image capturing System W And a translation matrix T W ；
(3.4) by rotating the matrix R W And a translation matrix T W The obtained real set
Set m' after changing position and posture i ；
(3.5) calculating m' i And q i Average distance of (2)
(3.6) if the average distance
Less than or equal to the pose early warning threshold value +.>
The target pose is normal, otherwise the communication target is adjusted.
The rotation matrix R in the calculation camera system W And a translation matrix T W Comprising the following steps:
(3.3.1) calculating centroids of the two sets:
(3.3.2) calculating covariance matrices of the two rendezvous points;
t is a transposed symbol;
(3.3.3) calculating an antisymmetric matrix;
(3.3.4) construction of a 4×4 matrix
I 3×3 Is a 3 x 3 matrix of units,
is the trace of matrix +.>
Is a column vector of components of an antisymmetric matrix, a->
Feature vector r= [ r ] corresponding to the maximum feature value of (a) 0 ,r 1 ,r 2 ,r 3 ]；
(3.3.5) rotating matrix R W The method comprises the following steps:
(3.3.6) translation matrix T W The method comprises the following steps:
the medium adopts the road planning method of the intelligent glasses under the artificial intelligent big data to carry out road planning.
The road planning equipment of the intelligent glasses under the artificial intelligent big data adopts the road planning medium of the intelligent glasses under the artificial intelligent big data to carry out intelligent glasses road planning.
The invention has the beneficial effects that:
the invention expands research by using a fractional order intelligent glasses control strategy to realize the design and stability analysis of an intelligent glasses control system, optimizes parameters in a control law on the basis of the control law, and omits the problem of manually selecting the parameters. Therefore, the difficulty of road planning of the intelligent glasses group is simplified, and stable use of the intelligent glasses is realized.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
FIG. 2 is a flow chart of a method of stroke control according to the present invention.
Fig. 3 is a schematic diagram of a preset obstacle image.
Fig. 4 is a feature extraction schematic.
Fig. 5 is an edge extraction schematic.
Fig. 6 is a schematic diagram of a path channel.
Fig. 7 is the smart glasses stroke test fig. 1.
Fig. 8 is the smart glasses stroke test fig. 2.
Fig. 9 is a schematic diagram of a simulation of the gesture monitoring method.
Detailed Description
The invention is further described below with reference to the accompanying drawings.
The invention relates to a road planning method of intelligent glasses under artificial intelligent big data, which comprises a glasses assembly and a frame, wherein the glasses assembly comprises two lenses, and the frame comprises a glasses frame and two intelligent glasses legs respectively connected to two ends of the glasses frame; the intelligent glasses leg comprises a glasses leg body provided with a containing cavity, a power module in the containing cavity, a camera system, a distance sensor, a height sensor, a processor, a voice recognition module, a voice playing module and a wireless communication module, wherein the camera system, the distance sensor, the height sensor, the processor, the voice recognition module, the voice playing module and the wireless communication module are electrically connected with the power module and are arranged in any containing cavity; the camera system, the distance sensor, the height sensor, the voice recognition module and the voice playing module are all in signal connection with the processor and can be in wireless connection with the artificial intelligent interaction device and/or in information connection with the cloud control system through the wireless communication module, the power module is a rechargeable battery, the voice recognition module is a receiver, and the voice playing module is a microphone. The invention carries on route planning and travel control to the intelligent glasses by the intelligent glasses cloud control system and the control module on the intelligent glasses, the signal is collected by the sensor of the intelligent glasses, and is transmitted to the cloud control system and the control module for processing, the cloud control system transmits the processed signal to the control module, finally the control module executes the control method uniformly, the cloud control system in the invention, namely the cloud (control) system which can be used in the market at present, can inquire and use through the network, the invention mainly aims to improve the operation speed, and simultaneously lighten the calculation amount of the control module, the intelligent glasses cloud control system and the control module on the intelligent glasses carry on route planning and travel control to the intelligent glasses group, as shown in figure 1, the method comprises the following steps:
(1) The image pickup system of the intelligent glasses collects images, performs denoising treatment on the collected images, and then performs optimal path planning through path edge points;
(2) The intelligent glasses perform travel operation to guide the intelligent glasses user to travel in the planned path channel;
(3) Performing gesture monitoring on the intelligent glasses in the journey;
(4) Repeating steps (2) - (3) until the smart glasses user stops using;
the step (1) comprises the following steps:
(1.1) image acquisition denoising:
the intelligent glasses acquire three-dimensional images of the environment where the path is located through the camera system, and Gaussian filtering processing is carried out on the acquired images;
(1.2) edge detection of a road in an image:
sobel operator calculation is carried out on the gray values of adjacent points around each pixel point in the image, and a threshold value tau is selected by the brightness acquired by the acquired image when
f x ＝(f(a-1,b-1)+2f(a-1,b)+f(a-1,b+1))-(f(a+1,b+1)+2f(a-1,b)+f(a+1,b+1))，
f y ＝(f(a-1,b-1)+2f(a,b-1)+f(a+1,b-1))-(f(a-1,b-1)+2f(a,b-1)+f(a+1,b-1))，
When So (a, b) > tau, the points (a, b) in the image are edge points, a, b are coordinates of the edge points, and f is a gray value;
(1.3) path planning according to edge points:
the cloud control system of the intelligent glasses collects edge point information, a path channel is constructed through the edge points, and an included angle between the imaging system of the intelligent glasses and the distance sensor and the horizontal direction is theta a The data returned by the distance sensor is l a The measurement value of the height sensor of the intelligent glasses is z', and the coordinate under the horizontal reference system is D n0 ＝(x a ,y b ,z′)＝(l a ×cosθ a ,l a ×sinθ a ,z′)；
Determining a planned path according to the iteration evaluation value of the nodes in the path channel, wherein the distance between two adjacent nodes is l n0 ，l n0 ＝D n0 -D n0-1 N0 is the index of the current node, the starting point I 0 To the current node I n0 The cost function of (2) is:
and scanning two neighbor nodes with maximum G (n 0) near each node to connect, so as to form a planned path channel.
As shown in fig. 3-6, in the simulation process of forming the path channel according to the present invention, by using the above method, the shape of the obstacle in fig. 3 is fitted through the image, and the feature extraction is performed on the obstacle in fig. 4-5, so as to perform edge extraction, and finally, a layer of the path channel in fig. 6 is formed, the white area is a representation of the path channel, and finally, each layer of channels is overlapped, so that a three-dimensional path channel is formed. The image recognition and planning of the invention is based on local recognition between two targets, and the recognition of the images is the result of image discrimination and matching. The invention distinguishes and matches images, namely, the areas are divided according to the gray value of the acquired images, and the areas with the same characteristics are connected to form a collection of connected areas to form the path channel of the invention. The invention adopts the image analysis method based on cost function to divide the path channel from the background. The static path is subjected to image acquisition, and the cost function is continuously updated according to the segmentation effect by an iterative method, so that the accuracy of image processing is improved to a great extent by adopting an online cost function determination method, and the real-time effect of the invention is improved. Compared with the prior art, the method and the device have the advantages that the path channel is given through the operation of the gray value, and meanwhile, the optimal planning value of the path is given through the cost function method, so that the advancing efficiency of the intelligent glasses is effectively improved.
As shown in fig. 2, the step (2) includes:
(2.1) initializing an intelligent glasses group with the number of N, wherein the intelligent glasses group comprises the random speed of the area of the intelligent glasses and the position of the area of the intelligent glasses, and determining the gesture matrix, the angular rate of the gesture matrix and the gesture angle of each intelligent glasses;
(2.2) evaluating the fitness value of the smart glasses in each group;
(2.3) evaluating the best position in the current search space of the smart glasses in each group;
(2.4) updating the inertial weight of the intelligent glasses, and updating the speed and the position of each intelligent glasses;
(2.5) re-executing the step (2.2) under the working state of the intelligent glasses, and ending the method when the working of the intelligent glasses is finished;
the determining step of the gesture matrix of the intelligent glasses comprises the following steps:
(2.1.1) assuming that the earth coordinate system is the earth system, the geographic coordinate system is the geo system, the carrier coordinate system is the carrier system, the navigation coordinate system is the pilot system, and the axes of the coordinate systems are respectively X in turn g 、Y g 、Z g ；X c 、Y c 、Z c ；X p 、Y p 、Z p ；
(2.1.2) calculating a directional cosine matrix of a geographic coordinate system of the intelligent glasses;
wherein the longitude of the intelligent glasses is alpha e And a latitude of delta e ；α e The range of the values of (a) is (-180 DEG, 180 DEG); delta e The range of the values of (a) is (-90 DEG, 90 DEG);
(2.1.3) calculating a direction cosine matrix of a carrier coordinate system of the intelligent glasses;
wherein gamma is c For roll angle of the carrier coordinate system relative to the geographical coordinate system, i.e. X c Relative to X g Is included in the plane of the first part;
wherein θ is c For pitch angle of the carrier coordinate system relative to the geographical coordinate system, i.e. Y c With respect to Y g Is included in the plane of the first part;
wherein the method comprises the steps of
For heading angle of the carrier coordinate system relative to the geographical coordinate system, i.e. Z c Relative to Z g Is included in the plane of the first part;
(2.1.4) calculating an attitude matrix of a navigation coordinate system of the intelligent glasses;
(2.1.5) calculating the attitude matrix angular rate of the navigation coordinate system of the intelligent glasses;
ω e omega is the projection of the earth angular velocity in the navigation coordinate system a Is a measured value of the intelligent glasses gyroscope.
The intelligent glasses coordinate calculation is to calculate the real-time matrix through the angular velocity of the intelligent glasses measured by the gyroscope, and the attitude change angular velocity of the intelligent glasses is very fast, so that the time for calculating the attitude matrix needs a period of millisecond order, the real-time requirement cannot be met for the intelligent glasses group, and certain error is necessarily generated for the calculation of the matrix by the non-real-time calculation data. Therefore, the key technology is to calculate the posture of the intelligent glasses in real time, and is one of important factors influencing the accuracy of the intelligent glasses posture calculation algorithm, and the invention calculates a plurality of simultaneous equations, has no singularity, is convenient to calculate, and can be stably executed in a closed-loop switching control system. Compared with the prior art, the invention can give the accurate angular rate of the intelligent glasses through the conversion of the coordinate system, and is mainly superior to the accuracy of the gesture control of the intelligent glasses.
Therefore, the real-time value of the smart glasses attitude angle is:
the gesture matrix and the gesture matrix angular rate are key parameters of the intelligent glasses, and the position of the target point can be calculated more simply in the subsequent adjustment process through the two parameters.
Aiming at the inherent characteristics of the micro inertial device, the invention obtains the optimal attitude angle estimation through a cloud data fusion algorithm. The attitude angle can be obtained by angular velocity integration, but random drift errors exist in the gyroscope of the micro inertial device, the random drift errors can be gradually accumulated along with the increase of time, the carrier can introduce errors caused by linear acceleration on information such as pitch angle and the like in a dynamic environment, and the triaxial magnetometer can generate errors in yaw angle data due to electromagnetic interference. Therefore, the data fusion algorithm provided by the invention takes the measured data as the measured value, and obtains the optimal attitude angle estimation through matrix operation.
The fitness value of the intelligent glasses in each group is evaluated as follows:
f j (x) Representing a branching function on a j-th branch on a target path of the intelligent glasses; alpha j The weight corresponding to the jth branch is represented, m is the total number of branches of the target path, and x represents the estimated intelligent glasses label;
f j (x)＝(β j ∩γ j )(β j ∪γ j ) -2 ；
β j a set of smart glasses for executing a target path through a j-th branch; gamma ray j The intelligent glasses set is used for inputting the j-th branch which is passed by the tested program after being executed.
The step of evaluating the optimal position in the current search space of the intelligent glasses in each group comprises the following steps of;
(2.3.1) matching the fitness value of each smart glasses with the estimated current local best known position pbest of the smart glasses i,n Comparing, if the adaptation value of the intelligent glasses is small, replacing the adaptation value of the intelligent glasses with the current local best known position pbest i,n ；
(2.3.2) comparing the current locally-best known position pbest of each smart glasses with the best position gbest in the current search space of the smart glasses, and if the current locally-best known position pbest of the smart glasses is small, replacing the current locally-best known position pbest of the smart glasses with the best position gbest in the current search space.
The estimated current local best known position pbest of the intelligent glasses i,n Comprising:
n intelligent glasses, wherein each intelligent glasses is positioned in a search space of S dimension, S is less than or equal to 3, and the position of the ith intelligent glasses in the nth iteration process of the method is as follows:
the corresponding speed of the intelligent glasses is as follows:
the updating of the speed and the position of each intelligent glasses comprises;
(2.4.1) update G n The inertial weight is:
G nmax g is the maximum value of the inertial weight of the intelligent glasses nmin As a minimum value of the inertial weight,
N max is the maximum value of the iteration times;
(2.4.2) update the speed of the smart glasses:
v i,n ＝p s [v i,n-1 +G n ·(pbest-x i,n-1 )+G n ·(gbest-x i,n-1 )]；
p s in order for the contraction factor to be a factor,
k is the upper limit speed of network searching;
(2.4.3) updating the position of the smart glasses;
x i,n ＝x i,n-1 +v i,n 。
said alpha j Indicating the weight corresponding to the jth branch,
γ n representing a value of the number of path consecutive matches greater than 1 in the iterative process.
In order to further accurately control the position of the intelligent glasses, the speed of the intelligent glasses is optimized, and the specific steps comprise:
(2.4.2.1) inputting the Intelligent glasses speed function v i,n Probability utility function
Mean function->
Step function->
Testing duration;
(2.4.2.2) initializing a directivity statistical model;
(2.4.2.3) calculating the current step function value
(2.4.2.4) evaluating the smart glasses utility value by a probability utility function;
z is an intermediate variable which is used for the preparation of the medicine,
φ 1 (Z)、φ 2 (Z) is a standard normal distribution function and a probability density function;
(2.4.2.5) if the smart glasses utility value is below the threshold P, selecting the smart glasses and recording the speed value of the smart glasses;
(2.4.2.6) calculating an corrected effective amount;
as a utility metering function of the global search of the intelligent glasses, the expected effective amount of a certain intelligent glasses possibly brought by the global search strategy is measured,
(2.4.2.7) updating (2.4.2.5) the speed of the smart glasses to
(2.4.2.8) re-executing step (2.4.2.1) until all smart glasses utility values remain above the threshold P.
(2.5) re-executing the step 2.2 under the working state of the intelligent glasses group, and ending the method when the working of the intelligent glasses group is finished.
As shown in fig. 7 and 8, after route presetting, the intelligent glasses implement a test chart for forming control. In the figure, the ordinate represents the position of one axis (manually set) in the planar coordinate system, and the abscissa represents time in seconds. In fig. 7, it can be seen that in the linear movement, as time increases, the error increases, so that the smart glasses can form more accurate route control in real-time by setting enough iteration conditions (such as time or threshold value). As shown in fig. 8, the error of the present invention is small if it is a curve type motion, because the iteration of the threshold value is continuously adjusted, and because the motion of the smart glasses is mainly a curve type motion, the present invention is most suitable for practical use. For the above data, the invention extracts 1 number of values per 100 time points as shown in the following table:
| Time | preset | Measurement value | |
| 0 | 0 | 0 | |
| 5 | 0.1275 | 0.1303 | |
| 10 | 0.255 | 0.2602 | |
| 15 | 0.3825 | 0.3806 | |
| 20 | 0.51 | 0.5005 | |
| 25 | 0.6375 | 0.6404 | |
| 30 | 0.765 | 0.7703 | |
| 35 | 0.8925 | 0.8903 | |
| 40 | 1.02 | 0.986 | |
| 45 | 1.1475 | 1.1504 | |
| 50 | 1.275 | 1.303 | |
| 55 | 1.4025 | 1.4035 | |
| 60 | 1.53 | 1.5026 |
Table 1 shows the linear trace measurement data
Table 2 shows the curve trace measurement data
The invention expands research by using a fractional order intelligent glasses control strategy to realize the design and stability analysis of an intelligent glasses control system, optimizes parameters in a control law on the basis of the control law, and omits the problem of manually selecting the parameters. Therefore, the difficulty of controlling the intelligent glasses is simplified, and the stable control of the intelligent glasses is realized. Compared with the prior art, the accurate route is obtained through the particlized fractional order algorithm, and compared with the traditional particlized fractional order algorithm, the accuracy of intelligent glasses control is further improved through introducing the correction effective amount.
Further, the step (3) includes the following steps:
(3.1) extracting the point cloud data M of the outline of the intelligent glasses at the previous time point through the camera system W At point cloud data M W Set m of medium fetch points i ∈M W The method comprises the steps of carrying out a first treatment on the surface of the Simultaneous extraction of m i Corresponding real set
(3.2) extracting point cloud data Q of the outline of the intelligent glasses at the current time point by the camera system W At point cloud data Q W Set q of medium fetch points i ∈Q W Let |q i -m i Obtaining a minimum value;
(3.3) calculating a rotation matrix R in a rotation imaging System W And a translation matrix T W ；
(3.4) by rotating the matrix R W And a translation matrix T W The obtained real set
Set m' after changing position and posture i ；
(3.5) calculating m' i And q i Average distance of (2)
(3.6) if the average distance
Less than or equal to the pose early warning threshold value +.>
The target pose is normal, otherwise the communication target is adjusted.
The rotation matrix R in the rotary image pick-up system is calculated W And a translation matrix T W Comprising the following steps:
(3.3.1) calculating centroids of the two sets:
(3.3.2) calculating covariance matrices of the two rendezvous points;
t is a transposed symbol;
(3.3.3) calculating an antisymmetric matrix;
(3.3.4) construction of a 4×4 matrix
I 3×3 Is a 3 x 3 matrix of units,
is the trace of matrix +.>
Is a column vector of components of an antisymmetric matrix, a->
Feature vector r= [ r ] corresponding to the maximum feature value of (a) 0 ,r 1 ,r 2 ,r 3 ]；
(3.3.5) rotating matrix R W The method comprises the following steps:
(3.3.6) translation matrix T W The method comprises the following steps:
as shown in FIG. 9, the target tracking and gesture monitoring effect graph is obtained through the experiment of the invention, the average error of the method of the invention is 3.25, the times of calculation are 1350 times, and the success rate is 100 percent according to the test simulation
In the step (3), the video images of the intelligent glasses are used for monitoring the pose state of the intelligent glasses, once the threshold value is exceeded, the intelligent glasses can be alerted directly, the stability of the intelligent glasses is effectively improved, the intelligent glasses and the method in the step (2) are mutually coordinated and matched, so that the path planning, advancing and obstacle avoidance of the intelligent glasses can be effectively ensured, and the pose influence caused by the change of the external environment can be effectively avoided.
The medium adopts the road planning method of the intelligent glasses under the artificial intelligent big data to carry out road planning. The road planning equipment of the intelligent glasses under the artificial intelligent big data adopts the road planning medium of the intelligent glasses under the artificial intelligent big data to carry out road planning.
It should be noted that all symbols and special definitions have been explained in the present invention, and other technical features such as simple hardware and some simple parameters are common general knowledge in the art.
Claims (7)
1. The road planning method of the intelligent glasses under the artificial intelligent big data comprises a glasses assembly and a frame, wherein the glasses assembly comprises two lenses, and the frame comprises a glasses frame and two intelligent glasses legs respectively connected to two ends of the glasses frame; the intelligent glasses leg comprises a glasses leg body provided with a containing cavity, a power module in the containing cavity, a camera system, a distance sensor, a height sensor, a processor, a voice recognition module, a voice playing module and a wireless communication module, wherein the camera system, the distance sensor, the height sensor, the processor, the voice recognition module, the voice playing module and the wireless communication module are electrically connected with the power module and are arranged in any containing cavity; the intelligent glasses system comprises a camera system, a distance sensor, a height sensor, a voice recognition module and a voice playing module, wherein the camera system, the distance sensor, the height sensor, the voice recognition module and the voice playing module are all in signal connection with a processor and can be in wireless connection with artificial intelligent interaction equipment and/or in information connection with a cloud control system through a wireless communication module, a power module is a rechargeable battery, the voice recognition module is a receiver, the voice playing module is a microphone, and a path planning and a travel control are carried out on an intelligent glasses set through the intelligent glasses cloud control system and a control module on the intelligent glasses.
(1) The image pickup system of the intelligent glasses collects images, performs denoising treatment on the collected images, and then performs optimal path planning through path edge points;
(2) The intelligent glasses perform travel operation to guide the intelligent glasses user to travel in the planned path channel;
(3) Performing gesture monitoring on the intelligent glasses in the journey;
(4) Repeating steps (2) - (3) until the smart glasses user stops using;
the step (1) comprises the following steps:
(1.1) image acquisition denoising:
the intelligent glasses acquire three-dimensional images of the environment where the path is located through the camera system, and Gaussian filtering processing is carried out on the acquired images;
(1.2) edge detection of a road in an image:
performing Sobel operator calculation on the gray values of adjacent points around each pixel point in the image, selecting a threshold value tau by collecting the brightness taken by the image,
f x ＝(f(a-1,b-1)+2f(a-1,b)+f(a-1,b+1))-(f(a+1,b+1)+2f(a-1,b)+f(a+1,b+1))，
f y ＝(f(a-1,b-1)+2f(a,b-1)+f(a+1,b-1))-(f(a-1,b-1)+2f(a,b-1)+f(a+1,b-1))，
when So (a, b) > tau, the points (a, b) in the image are edge points, a, b are coordinates of the edge points, and f is a gray value;
(1.3) path planning according to edge points:
the cloud control system of the intelligent glasses collects edge point information, a path channel is constructed through the edge points, and an included angle theta between the camera system of the intelligent glasses and the horizontal direction of the distance sensor is set a The data returned by the distance sensor is l a The measurement value of the height sensor of the intelligent glasses is z', and the coordinate under the horizontal reference system is D n0 ＝(x a ,y b ,z′)＝(l a ×cosθ a ,l a ×sinθ a ,z′)；
Determining a planned path according to the iteration evaluation value of the nodes in the path channel, wherein the distance between two adjacent nodes is l n0 ，l n0 ＝D n0 -D n0-1 N0 is the index of the current node, the starting point I 0 To the current node I n0 The cost function of (2) is:
scanning two neighbor nodes with maximum G (n 0) near each node to connect to form a planned path channel;
the step (2) comprises:
(2.1) initializing an intelligent glasses group with the number of N, wherein the intelligent glasses group comprises the random speed of the area of the intelligent glasses and the position of the area of the intelligent glasses, and determining the gesture matrix, the angular rate of the gesture matrix and the gesture angle of each intelligent glasses;
(2.2) evaluating the fitness value of the smart glasses in each group;
(2.3) evaluating the best position in the current search space of the smart glasses in each group;
(2.4) updating the inertial weight of the intelligent glasses, and updating the speed and the position of each intelligent glasses;
(2.5) re-executing the step (2.2) under the working state of the intelligent glasses, and ending the method when the working of the intelligent glasses is finished;
the determining step of the gesture matrix of the intelligent glasses comprises the following steps:
(2.1.1) assuming that the earth coordinate system is the earth system, the geographic coordinate system is the geo system, the carrier coordinate system is the carrier system, the navigation coordinate system is the pilot system, and the axes of the coordinate systems are respectively X in turn g 、Y g 、Z g ；X c 、Y c 、Z c ；X p 、Y p 、Z p ；
(2.1.2) calculating a directional cosine matrix of a geographic coordinate system of the intelligent glasses;
wherein the longitude of the intelligent glasses is alpha e And a latitude of delta e ；α e The range of the values of (a) is (-180 DEG, 180 DEG); delta e The range of the values of (a) is (-90 DEG, 90 DEG);
(2.1.3) calculating a direction cosine matrix of a carrier coordinate system of the intelligent glasses;
wherein gamma is c For roll angle of the carrier coordinate system relative to the geographical coordinate system, i.e. X c Relative to X g Is included in the plane of the first part;
wherein θ is c For pitch angle of the carrier coordinate system relative to the geographical coordinate system, i.e. Y c With respect to Y g Is included in the plane of the first part;
wherein the method comprises the steps of
Is the coordinates of the carrierHeading angle relative to the geographic coordinate system, i.e. Z c Relative to Z g Is included in the plane of the first part;
(2.1.4) calculating an attitude matrix of a navigation coordinate system of the intelligent glasses;
(2.1.5) calculating the attitude matrix angular rate of the navigation coordinate system of the intelligent glasses;
ω e omega is the projection of the earth angular velocity in the navigation coordinate system a Is a measured value of an intelligent glasses gyroscope;
the real-time value of intelligent glasses attitude angle is:
2. The method for road planning for intelligent glasses under artificial intelligence big data according to claim 1, wherein the adaptive values of the intelligent glasses in each group are estimated as follows:
f j (x) Representing a branching function on a j-th branch on a target path of the intelligent glasses; alpha j The weight corresponding to the jth branch is represented, m is the total number of branches of the target path, and x represents the estimated intelligent glasses label;
f j (x)＝(β j ∩γ j )(β j ∪γ j ) -2 ；
β j a set of smart glasses for executing a target path through a j-th branch; gamma ray j The intelligent glasses set is used for inputting the j-th branch which is passed by the tested program after being executed.
3. The method for road planning for intelligent glasses under artificial intelligence big data according to claim 2, wherein the evaluating the best position in the current search space of the intelligent glasses in each group comprises;
(2.3.1) matching the fitness value of each smart glasses with the estimated current local best known position pbest of the smart glasses i,n Comparing, if the adaptation value of the intelligent glasses is small, replacing the adaptation value of the intelligent glasses with the current local best known position pbest i,n ；
(2.3.2) comparing the current locally-best known position pbest of each smart glasses with the best position gbest in the current search space of the smart glasses, and if the current locally-best known position pbest of the smart glasses is small, replacing the current locally-best known position pbest of the smart glasses with the best position gbest in the current search space.
4. A method for road planning for intelligent glasses under artificial intelligence big data according to claim 3, characterized in that the estimated current local best known position pbest of intelligent glasses i,n Comprising:
n intelligent glasses, wherein each intelligent glasses is positioned in a search space of S dimension, S is less than or equal to 3, and the position of the ith intelligent glasses in the nth iteration process of the method is as follows:
the corresponding speed of the intelligent glasses is as follows: />
5. The method for road planning for intelligent glasses under artificial intelligence big data according to claim 4, wherein updating the speed and position of each intelligent glasses comprises;
(2.4.1) update G n The inertial weight is:
G nmax g is the maximum value of the inertial weight of the intelligent glasses nmin As a minimum value of the inertial weight,
N max is the maximum value of the iteration times;
(2.4.2) update the speed of the smart glasses:
v i,n ＝p s [v i,n-1 +G n ·(pbest-x i,n-1 )+G n ·(gbest-x i,n-1 )]；
p s in order for the contraction factor to be a factor,
k is the upper limit speed of network searching;
optimizing the speed of the intelligent glasses, wherein the method comprises the following specific steps of:
(2.4.2.1) inputting the Intelligent glasses speed function v i,n Probability utility function
Mean function->
Step function
Testing duration;
(2.4.2.2) initializing a directivity statistical model;
(2.4.2.3) calculating the current step function value
(2.4.2.4) evaluating the smart glasses utility value by a probability utility function;
z is an intermediate variable which is used for the preparation of the medicine,
φ 1 (Z)、φ 2 (Z) is a standard normal distribution function and a probability density function;
(2.4.2.5) if the smart glasses utility value is below the threshold P, selecting the smart glasses and recording the speed value of the smart glasses;
(2.4.2.6) calculating an corrected effective amount;
as a utility metering function of the global search of the intelligent glasses, the expected effective amount of a certain intelligent glasses possibly brought by the global search strategy is measured,
(2.4.2.7) updating (2.4.2.5) the speed of the smart glasses to
(2.4.2.8) re-executing step (2.4.2.1) until all smart glasses utility values remain above the threshold P;
(2.4.3) updating the position of the smart glasses;
x i,n ＝x i,n-1 +v i,n ；
said alpha j Indicating the weight corresponding to the jth branch,
γ n representing a value of the number of path consecutive matches greater than 1 in the iterative process.
6. The method for road planning for intelligent glasses under artificial intelligence big data according to claim 5, wherein the step (3) comprises the steps of:
(3.1) extracting point cloud data M of the intelligent glasses environment reference target at the previous time point through a cloud data system W At point cloud data M W Set m of medium fetch points i ∈M W The method comprises the steps of carrying out a first treatment on the surface of the Simultaneous extraction of m i Corresponding real set
/>
(3.2) extracting point cloud data Q of the intelligent glasses environment reference target at the current time point by the camera system W At point cloud data Q W Set q of medium fetch points i ∈Q W Let |q i -m i Obtaining a minimum value;
(3.3) calculating the rotation matrix R in the image capturing System W And a translation matrix T W ；
(3.4) by rotating the matrix R W And a translation matrix T W The obtained real set
Set m 'after changing position and posture' i ；
(3.5) calculation of m' i And q i Average distance of (2)
(3.6) if the average distance
Less than or equal to the pose early warning threshold value +.>
The target pose is normal, otherwise the communication target is adjusted.
7. The method for planning a road for intelligent glasses under artificial intelligence big data according to claim 6, wherein the rotation matrix R in the calculation camera system is W And a translation matrix T W Comprising the following steps:
(3.3.1) calculating centroids of the two sets:
(3.3.2) calculating covariance matrices of the two rendezvous points;
t is a transposed symbol;
(3.3.3) calculating an antisymmetric matrix;
(3.3.4) construction of a 4×4 matrix
I 3×3 Is a 3 x 3 matrix of units,
is the trace of matrix +.>
Is a column vector of components of an antisymmetric matrix, a->
Feature vector r= [ r ] corresponding to the maximum feature value of (a) 0 ,r 1 ,r 2 ,r 3 ]；
(3.3.5) rotating matrix R W The method comprises the following steps:
(3.3.6) translation matrix T W The method comprises the following steps:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010023509.3A CN111238470B (en) | 2020-01-09 | 2020-01-09 | Intelligent glasses road planning method, medium and equipment under artificial intelligent big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010023509.3A CN111238470B (en) | 2020-01-09 | 2020-01-09 | Intelligent glasses road planning method, medium and equipment under artificial intelligent big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111238470A CN111238470A (en) | 2020-06-05 |
| CN111238470B true CN111238470B (en) | 2023-05-02 |
Family
ID=70872506
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010023509.3A Active CN111238470B (en) | 2020-01-09 | 2020-01-09 | Intelligent glasses road planning method, medium and equipment under artificial intelligent big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111238470B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108645413A (en) * | 2018-06-06 | 2018-10-12 | 江苏海事职业技术学院 | The dynamic correcting method of positioning and map building while a kind of mobile robot |
| CN110084825A (en) * | 2019-04-16 | 2019-08-02 | 上海岚豹智能科技有限公司 | A kind of method and system based on image edge information navigation |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5658963B2 (en) * | 2010-09-29 | 2015-01-28 | オリンパス株式会社 | Image processing apparatus, image processing method, and image processing program |
| CN102175251A (en) * | 2011-03-25 | 2011-09-07 | 江南大学 | Binocular intelligent navigation system |
| CN105760813A (en) * | 2016-01-19 | 2016-07-13 | 北京航空航天大学 | Unmanned aerial vehicle target detection method based on plant branch and root evolution behaviors |
| CN106214437B (en) * | 2016-07-22 | 2018-05-29 | 杭州视氪科技有限公司 | A kind of intelligent blind auxiliary eyeglasses |
| TW201833701A (en) * | 2017-03-14 | 2018-09-16 | 聯潤科技股份有限公司 | Self-propelling cleansing device and method thereof for establishing indoor map comprising a device body driving by wheels at a bottom thereof, a distance detection unit, an along-edge detector, a cleansing unit, a dust collection unit, a dynamic detection unit, a map establishing unit, and a control unit |
| CN107450576B (en) * | 2017-07-24 | 2020-06-16 | 哈尔滨工程大学 | Method for planning paths of bridge detection unmanned aerial vehicle |
| US20180150081A1 (en) * | 2018-01-24 | 2018-05-31 | GM Global Technology Operations LLC | Systems and methods for path planning in autonomous vehicles |
-
2020
- 2020-01-09 CN CN202010023509.3A patent/CN111238470B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108645413A (en) * | 2018-06-06 | 2018-10-12 | 江苏海事职业技术学院 | The dynamic correcting method of positioning and map building while a kind of mobile robot |
| CN110084825A (en) * | 2019-04-16 | 2019-08-02 | 上海岚豹智能科技有限公司 | A kind of method and system based on image edge information navigation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111238470A (en) | 2020-06-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107635204B (en) | Indoor fusion positioning method and device assisted by exercise behaviors and storage medium | |
| CN107451593B (en) | High-precision GPS positioning method based on image feature points | |
| CN106295512B (en) | Vision data base construction method and indoor orientation method in more correction lines room based on mark | |
| CN106125087A (en) | Dancing Robot indoor based on laser radar pedestrian tracting method | |
| CN104881029B (en) | Mobile Robotics Navigation method based on a point RANSAC and FAST algorithms | |
| CN109186606A (en) | A kind of robot composition and air navigation aid based on SLAM and image information | |
| CN106767828A (en) | A kind of mobile phone indoor positioning solution | |
| CN106767791A (en) | A kind of inertia/visual combination air navigation aid using the CKF based on particle group optimizing | |
| CN109029429B (en) | WiFi and geomagnetic fingerprint based multi-classifier global dynamic fusion positioning method | |
| CN111277946A (en) | Fingerprint database self-adaptive updating method in Bluetooth indoor positioning system | |
| CN110536245A (en) | A kind of indoor wireless positioning method and system based on deep learning | |
| CN111698774B (en) | Indoor positioning method and device based on multi-source information fusion | |
| CN103994765A (en) | Positioning method of inertial sensor | |
| CN112325883A (en) | Indoor positioning method for mobile robot with WiFi and visual multi-source integration | |
| CN111123953A (en) | Particle-based mobile robot group under artificial intelligence big data and control method thereof | |
| Deng et al. | Long-range binocular vision target geolocation using handheld electronic devices in outdoor environment | |
| CN108152812B (en) | Improved AGIMM tracking method for adjusting grid spacing | |
| CN113566820A (en) | Fusion pedestrian positioning method based on position fingerprint and PDR algorithm | |
| WO2022242018A1 (en) | Indoor target positioning method based on improved cnn model | |
| CN112365592B (en) | Local environment feature description method based on bidirectional elevation model | |
| CN111208820B (en) | Particle unmanned vehicle set under artificial intelligence big data, control method and medium | |
| CN110927765B (en) | Laser radar and satellite navigation fused target online positioning method | |
| CN111238470B (en) | Intelligent glasses road planning method, medium and equipment under artificial intelligent big data | |
| Wang et al. | Indoor position algorithm based on the fusion of wifi and image | |
| CN109803234A (en) | Unsupervised fusion and positioning method based on the constraint of weight different degree |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230331 Address after: 510000 Building 1, No. 106 Fengze East Road, Nansha District, Guangzhou City, Guangdong Province X1301-B8630 (Cluster Registration) (JM) Applicant after: Zhongyun (Guangdong) Information Technology Co.,Ltd. Address before: 150001 No. 145-1, Nantong Avenue, Nangang District, Heilongjiang, Harbin Applicant before: HARBIN ENGINEERING University |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |