CN109238286A

CN109238286A - Intelligent navigation method, device, computer equipment and storage medium

Info

Publication number: CN109238286A
Application number: CN201811008410.5A
Authority: CN
Inventors: 秦勇
Original assignee: Ping An Technology Shenzhen Co Ltd
Current assignee: Ping An Technology Shenzhen Co Ltd
Priority date: 2018-08-31
Filing date: 2018-08-31
Publication date: 2019-01-18
Anticipated expiration: 2038-08-31
Also published as: CN109238286B

Abstract

The invention discloses a kind of intelligent navigation method, device, computer equipment and storage mediums, wherein the intelligent navigation method includes: that follow shot end is arranged in the movable direction of current location；Based on movable direction, follow shot end is obtained in the real scene shooting that accessible direction is shot and pinpoints image；Library is inquired based on pre-set image, obtains and pinpoints at least one equidirectional presetting point image of image with real scene shooting；The pinpoint image most like with real scene shooting fixed point image is obtained from least one presetting point image, using the corresponding fixed point coordinate of pinpoint image as starting point coordinate；Terminal point coordinate is obtained, according to starting point coordinate and terminal point coordinate selection avoidance detection result is free of obstacles and the shortest recommendation navigation routine of distance is target navigation route.This method is not limited by hardware detection range, and positioning method is simple and fast, mode flexibility and reliability of navigating.

Description

Intelligent navigation method, device, computer equipment and storage medium

Technical field

The present invention relates to indoor positioning field more particularly to a kind of intelligent navigation method, device, computer equipment and storages Medium.

Background technique

Path planning is one of the important link of avoidance vehicle navigation research.When avoidance vehicle executes task, it is desirable that avoidance vehicle In the work environment the moment optimal path from current location to target location can be searched for according to current road conditions.Therefore to keeping away The current location of barrier vehicle position becoming in path planning and primarily solve the problems, such as.

Existing avoidance vehicle indoor positioning mainly uses bluetooth positioning, RFID (Radio Frequency Identification, radio frequency identification) modes such as positioning and infrared positioning, but bluetooth positioning system stability is bad, RFID positioning does not have ability to communicate, and penetrability is bad when infrared positioning encounters barrier.How to ensure that avoidance car room is default The stability and timely ability to communicate of position obtain optimal travel route as urgent need to resolve according to road conditions in real time to improve avoidance vehicle The problem of.

Summary of the invention

The embodiment of the present invention provides intelligent navigation method, device, computer equipment and the storage medium of a kind of intelligent navigation, To solve the problems, such as to ensure the stability and timely ability to communicate of avoidance vehicle indoor positioning.

A kind of intelligent navigation method, comprising:

Obtain at least one movable direction of follow shot end on pre-set navigational map；

Based at least one movable direction, follow shot end is obtained in the real scene shooting that accessible direction is shot and pinpoints image；

Library is inquired based on pre-set image, obtains and pinpoints at least one equidirectional presetting point image of image with real scene shooting；

Using feature extraction algorithm, the mesh most like with real scene shooting fixed point image is obtained from least one presetting point image Point image is demarcated, using the corresponding fixed point coordinate of pinpoint image as starting point coordinate；

Terminal point coordinate is obtained, at least two recommendation navigation routines are generated according to starting point coordinate and terminal point coordinate；

The avoidance detection result that navigation routine is recommended at least two at follow shot end is obtained, choosing avoidance detection result is Free of obstacles and the shortest recommendation navigation routine of distance are target navigation route, and target navigation route is sent to mobile bat End is taken the photograph, control follow shot end is mobile according to target navigation route.

A kind of intelligent navigation device, comprising:

Moving direction module is set, for obtaining the removable side of at least one of follow shot end on pre-set navigational map To；

Real scene shooting image module is obtained, for being based at least one movable direction, obtains follow shot end in accessible side Image is pinpointed to the real scene shooting of shooting；

Fixed point image module is obtained, for inquiring library based on pre-set image, is obtained equidirectional extremely with real scene shooting fixed point image A few presetting point image；

Obtain starting point coordinate module, for use feature extraction algorithm, from least one presetting point image obtain with Real scene shooting pinpoints the most like pinpoint image of image, using the corresponding fixed point coordinate of pinpoint image as starting point coordinate；

Recommended route module is generated, for obtaining terminal point coordinate, generates at least two according to starting point coordinate and terminal point coordinate Recommend navigation routine；

Mobile terminal mobile module is controlled, recommends the avoidance of navigation routine to detect at least two for obtaining follow shot end As a result, choosing, avoidance detection result is free of obstacles and the shortest recommendation navigation routine of distance is target navigation route, and will Target navigation route is sent to follow shot end, and control follow shot end is mobile according to target navigation route.

A kind of computer equipment, including memory, processor and storage are in the memory and can be in the processing The computer program run on device, the processor realize the step of above-mentioned intelligent navigation method when executing the computer program Suddenly.

A kind of computer readable storage medium, the computer-readable recording medium storage have computer program, the meter The step of calculation machine program realizes above-mentioned intelligent navigation method when being executed by processor.

Above-mentioned intelligent navigation method, device, computer equipment and storage medium are clapped by follow shot end in current location The real scene shooting fixed point image taken the photograph is compared with each presetting point image in pre-set image inquiry library, to obtain most like mesh Calibration point image is to confirm that follow shot end in the corresponding starting point coordinate in current location, is clapped using image comparison method mobile The current location for taking the photograph end is positioned, and is not limited by hardware detection range, positioning method is simple and fast.Meanwhile the intelligence is led Boat method, apparatus, computer equipment and storage medium can be cooked up according to the corresponding starting point coordinate in current location and terminal point coordinate It can be moved so that follow shot is short based on the target navigation route with the target navigation route of avoidance, it can be in real time according to road Condition adjusts target navigation route, influences its navigation procedure by hardware detection range equally, mode flexibility and reliability of navigating.

Detailed description of the invention

In order to illustrate the technical solution of the embodiments of the present invention more clearly, below by institute in the description to the embodiment of the present invention Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention Example, for those of ordinary skill in the art, without any creative labor, can also be according to these attached drawings Obtain other attached drawings.

Fig. 1 is the application environment schematic diagram of intelligent navigation method in one embodiment of the invention；

Fig. 2 is the flow chart of intelligent navigation method in one embodiment of the invention；

Fig. 3 is that the corresponding real scene shooting fixed point image schematic diagram of fixed point is preset in one embodiment of the invention；

Fig. 4 is the schematic diagram for two recommendation navigation routines that server generates in one embodiment of the invention；

Fig. 5 is another flow chart of intelligent navigation method in one embodiment of the invention；

Fig. 6 is another flow chart of intelligent navigation method in one embodiment of the invention；

Fig. 7 is that pre-set image inquires the corresponding presetting point image of a fixed point coordinate in library in one embodiment of the invention Data；

Fig. 8 is another flow chart of intelligent navigation method in one embodiment of the invention；

Fig. 9 is the neighboring pixel schematic diagram in one embodiment of the invention around candidate point；

It using characteristic point is four points in the circle in the center of circle to schematic diagram that Figure 10, which is in one embodiment of the invention,；

Figure 11 is another flow chart of intelligent navigation method in one embodiment of the invention；

Figure 12 is another flow chart of intelligent navigation method in one embodiment of the invention；

Figure 13 is the schematic diagram of intelligent navigation device in one embodiment of the invention；

Figure 14 is the schematic diagram of computer equipment in one embodiment of the invention.

Specific embodiment

Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete Site preparation description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts Example, shall fall within the protection scope of the present invention.

Intelligent navigation method provided in an embodiment of the present invention can be applicable in the application environment such as Fig. 1, the intelligent navigation side Method is applied in intelligent guidance system, which includes client and server, wherein client by network with Server is communicated.Wherein, client is also known as user terminal, refers to corresponding with server, provides local service for client Program.The client it is mountable but be not limited to various personal computers, laptop, smart phone, tablet computer and In the computer equipments such as portable wearable device.Server can use the either multiple server compositions of independent server Server cluster is realized.

In one embodiment, as shown in Fig. 2, providing a kind of intelligent navigation method, the service in Fig. 1 is applied in this way It is illustrated, includes the following steps: for device

S10. at least one movable direction of follow shot end on pre-set navigational map is obtained.

Wherein, follow shot end is equipped with camera, and the signal receiving end of WIFI signal is received when can move indoors.It should Follow shot end includes but is not limited to be equipped with intelligent robot or avoidance vehicle of camera etc..

Pre-set navigational map is preset in server, pinpoints with coordinate system with default to what indoor area of feasible solutions was established The grid map of (namely grid intersection point).Wherein, each default fixed point (namely grid intersection point) corresponds to one in a coordinate system and determines Point coordinate.In the present embodiment, pre-set navigational map is preset in server, for setting moving direction to follow shot end, The removable route at follow shot end can also be shown on pre-set navigational map.

Movable direction is server with reference to current location of the follow shot end in pre-set navigational map, with pre-set navigational Coordinate system on map is the transportable direction in follow shot end of object of reference setting, such as parallel with horizontal axis in coordinate system Move horizontally direction or the vertical shift direction parallel with the longitudinal axis in coordinate system.

In step S10, server can obtain follow shot end by position of the follow shot end on pre-set navigational map At least one corresponding movable direction of coordinate system on pre-set navigational map, to fixed in movable direction photographs real scene shooting Point image preparation techniques basis.

S20. it is based at least one movable direction, obtains the real scene shooting fixed point figure that follow shot end is shot in accessible direction Picture.

Wherein, accessible direction is that follow shot end is detected along each movable direction, one of them detected The direction of barrier is not present on movable direction.

Real scene shooting fixed point image is along the shooting of accessible direction including the ground between current location and next default fixed point Image, wherein default fixed point is each intersection point in the grid that pre-set navigational map is constituted based on coordinate system, is moved to guide Dynamic shooting end is moved along specified default fixed point direction, as shown in Figure 3.

In step S20, server is detected by infrared detector in each movable direction, because of infrared detector Limited generally 1 meter of detection range, and the distance between default fixed point of every two is set to infrared detector in the present embodiment Detectable distance be 1 meter, i.e., server may detect current location where follow shot end and adjacent default fixed point it Between whether there are obstacles.It is to be appreciated that in the pre-set navigational map the distance between default fixed point of any two be less than or Equal to the detection range of infrared detector so that between the detectable current location of the infrared detector and next default fixed point whether There are barriers.Server can pinpoint image in the real scene shooting that accessible direction obtains the shooting of follow shot end, convenient for passing through the reality It claps fixed point image and position positioning is carried out to follow shot end.

S30. library is inquired based on pre-set image, obtains and pinpoints at least one equidirectional presetting point diagram of image with real scene shooting Picture.

Wherein, pre-set image inquiry library be it is preset in the server will each preset fixed point and default fixed point is moving Presetting point image on direction carries out the database of corresponding storage.In the present embodiment, because each default fixed point can including two Moving direction: moving horizontally direction and vertical shift direction, Gu each default fixed point all corresponds to two presetting point images, one is secondary It is along the image for moving horizontally direction shooting, another width is the image shot along the vertical direction.

Presetting point image is exactly the standard ground image between two neighboring default fixed point, wherein each default fixed point Image further includes image direction mark, to state the shooting direction of the presetting point image.In the present embodiment, image direction mark It includes horizontal and vertical for knowing.

In step S30, server can be identified accessible direction as target direction, be inquired in pre-set image inquiry library The corresponding all presetting point images of identical image direction mark are identified with target direction, query context is locked, is taken with reducing The calculating time of business device, conducive to the presetting point image most like with real scene shooting fixed point image is quickly found.

S40. feature extraction algorithm is used, is obtained from least one presetting point image most like with real scene shooting fixed point image Pinpoint image, using the corresponding fixed point coordinate of pinpoint image as starting point coordinate.

Wherein, feature extraction algorithm (Oriented FAST and Rotated BRIEF, hereinafter referred to as ORB algorithm) is A kind of algorithm that rapid characteristic points are extracted and described.This algorithm is by Ethan Rublee, Vincent Rabaud, Kurt Konolige and Gary R.Bradski " ORB:An Efficient Alternative to SIFTor SURF " this Article in propose, to compare to the image characteristic point in two width figures, obtain the similarity of two width figures.Wherein, image Characteristic point can be understood as more significant point in image, as dark in the bright spot and brighter areas in profile point, darker area Point etc..

Pinpoint image is default fixed point corresponding with the most default fixed point of the common trait point of real scene shooting fixed point image Image.

Specifically, real scene shooting fixed point image can be obtained using feature extraction algorithm and each presetting point image is corresponding Real scene shooting image feature and pre-set image feature.It is obtained from each pre-set image feature with the common trait of real scene shooting image feature most The corresponding presetting point image of more pre-set image features is pinpoint image.It can be in default figure based on the pinpoint image As obtaining corresponding fixed point coordinate as starting point coordinate in inquiry library.

In step S40, server can pinpoint images match according to real scene shooting and obtain pinpoint image, inquire in pre-set image Server confirmation follow shot end is conducive to pre- as starting point coordinate according to the corresponding fixed point coordinate of the pinpoint image in library If corresponding position (namely corresponding fixed point coordinate) in navigation map, and technology is provided for servers' layout target navigation route Basis, which is not limited by hardware detection range, simple and fast.

S50. terminal point coordinate is obtained, at least two recommendation navigation routines are generated according to starting point coordinate and terminal point coordinate.

Wherein, to be user wish that follow shot end is final for determination by what user end to server was sent to terminal point coordinate The terminal of arrival is attended a banquet, that is, wish follow shot end on pre-set navigational map along specified default fixed point move after reach Terminal.Recommending navigation routine is the route of coordinate of reaching home that sets out along each movable direction of pre- starting point coordinate, wherein institute Have and include at least the shortest route of a paths in optimal route, as shown in Figure 4.

Specifically, by step S10 it is found that follow shot end from starting point coordinate coordinate of reaching home include at least one Movable direction.Server calculates starting point coordinate and terminal point coordinate input A star algorithm, can obtain follow shot end every At least two recommendation navigation routines on one movable direction.Wherein, A star algorithm be popular heuristic search algorithm it One, it is widely used in path optimization field.The unique distinction of A star algorithm is each possible presetting in inspection shortest path Global information in pre-set navigational map is introduced when point, and estimation is made to the distance of current starting point coordinate from home coordinate, And as the measurement for evaluating a possibility that default fixed point is on minimal path.

In step S50, server is handled the starting point coordinate and terminal point coordinate at follow shot end using A star algorithm, At least two recommendation navigation routines of the follow shot end on each movable direction can be obtained, all recommendations are led to subsequent Target navigation route preparation techniques basis is screened in the line of air route.

S60. the avoidance detection result for follow shot end at least two being recommended with navigation routine is obtained, avoidance detection knot is chosen Fruit is free of obstacles and the shortest recommendation navigation routine of distance is target navigation route, and target navigation route is sent to shifting Dynamic shooting end, control follow shot end are mobile according to target navigation route.

Wherein, target navigation route is that the adjacent fixed point in navigation routine on starting point coordinate to movable direction is recommended to sit Clear exists between mark, and the shortest route in path between starting point coordinate to terminal point coordinate.

In the present embodiment, barrier is detected using infrared detector, because detection range be limited to current starting point coordinate and Between adjacent fixed point coordinate on next movable direction, namely when infrared detector does not detect barrier, illustrate rising Barrier is not present between adjacent fixed point coordinate on point coordinate and next movable direction, can control follow shot end according to target Navigation routine continues to be moved to next fixed point coordinate from starting point coordinate.

In step S60, server can be detected by the infrared detector being mounted on follow shot end starting point coordinate and Whether there are obstacles between next fixed point coordinate on movable direction, and barrier is not present in selection, and from starting point coordinate To the shortest recommendation navigation routine of the distance between terminal point coordinate as target navigation route, to guide follow shot end to be moved to Terminal point coordinate.The step influences follow shot end by barrier in moving process, smoothly mobile from starting point coordinate Indoor moving task is completed to terminal point coordinate.

In the intelligent navigation method that step S10 to S60 is provided, the real scene shooting shot by follow shot end in current location is fixed Point image is compared with each presetting point image in pre-set image inquiry library, to obtain most like pinpoint image To confirm follow shot end in the corresponding starting point coordinate in current location, using image comparison method to the current of follow shot end Position is positioned, and is not limited by hardware detection range, positioning method is simple and fast.It, can meanwhile in the intelligent navigation method Being cooked up according to the corresponding starting point coordinate in current location and terminal point coordinate can be with the target navigation route of avoidance, so that mobile clap It is mobile to take the photograph the short target navigation route that is based on, target navigation route can be adjusted according to road conditions in real time, the intelligent navigation method is same Sample is not influenced by hardware detection range, mode flexibility and reliability of navigating.

In one embodiment, as shown in figure 5, in step S20, that is, it is based at least one movable direction, obtains mobile clap It takes the photograph end and pinpoints image in the real scene shooting that accessible direction is shot, specifically comprise the following steps:

S201. it is based at least one movable direction, detects each movable direction at follow shot end, obtains at least one A accessible direction.

The purpose of the present embodiment is that being positioned to the position in pre-set navigational map where follow shot end, specifically The real scene shooting fixed point image that current location takes and the presetting point image that pre-set image is inquired in library are compared.Yu Benshi Example is applied, in order to accelerate the processing speed of server, can only select a real scene shooting fixed point image on accessible direction can be into Row comparison, namely only need an accessible direction that can meet the requirements.

In step S201, server can detect current location and every according to the infrared detector installed on follow shot end Whether there are obstacles in detection range on one movable direction, and selecting one, there is no the directions of barrier as accessible Direction is shot so that server is based on the accessible direction.

S202. control follow shot end is shot using accessible direction as shooting direction, is obtained real scene shooting and is pinpointed image.

Specifically, server control follow shot end pinpoints image in the shooting real scene shooting of accessible direction.In order to obtain movement Shooting end is currently located corresponding fixed point coordinate on pre-set navigational map, and the shooting distance of real scene shooting fixed point image should be greater than currently Position and the distance between next adjacent fixed point coordinate on accessible direction.

In the present embodiment, pre-set navigational map may specify that the distance between every two fixed point coordinate is that 1 meter namely real scene shooting are fixed The distance of point image shooting is also at least 1 meter.The shooting distance of specified real scene shooting fixed point image is also conducive to where follow shot end Position carry out more accurate positioning.It is to be appreciated that provide more detailed characteristics of image, be more conducive to server to image into Similar image is analyzed and matched to row.

In the embodiment that step S201 to S202 is provided, server can be according to the infrared detector installed on follow shot end It detects in detection range on current location and each movable direction that whether there are obstacles, selects one obstacle is not present The direction of object is shot as accessible direction so that server is based on the accessible direction.Server specifies real scene shooting simultaneously The shooting distance of fixed point image is also conducive to carry out the position where follow shot end more accurate positioning, including more images are special The real scene shooting fixed point image of sign is conducive to improve the accuracy of image analysis.

In one embodiment, presetting fixed point navigation map includes at least two default fixed points, and each default fixed point includes fixed Point coordinate and at least one movable direction.As shown in fig. 6, inquiring library before step S30 based on pre-set image, obtaining Before the step of at least one presetting point image equidirectional with real scene shooting fixed point image, which further includes as follows Step:

S301. each default fixed point is obtained in the presetting point image of each movable direction photographs.

Wherein, default fixed point is each intersection point in the grid that pre-set navigational map is constituted based on coordinate system, to refer to Draw follow shot end to move along specified default fixed point.

Presetting point image is exactly the standard ground image for including two neighboring default fixed point, wherein each default fixed point Image further includes image direction mark, to state the shooting direction of the presetting point image.In the present embodiment, image direction mark It includes horizontal and vertical for knowing.

In step S301, server shoots presetting point image to each default fixed point on each movable direction, Each presetting point image carries fixed point mark and image direction mark, and fixed point mark is corresponding default for uniquely specifying Fixed point, the image direction identify the shooting direction for stating the presetting point image, so that subsequent server can be based on difference Image direction mark screen presetting point image, reduce contrast range, accelerate search speed.

S302. the corresponding fixed point coordinate of each default fixed point of associated storage, image direction mark and with image direction mark Corresponding presetting point image forms pre-set image and inquires library.

Wherein, fixed point coordinate is each default fixed point corresponding coordinate position in coordinate system in pre-set navigational map.

Pre-set image inquiry library is preset will each preset fixed point and default pinpoint in movable direction in the server On presetting point image carry out the database of corresponding storage.In the present embodiment, because each default fixed point includes two removable Direction: moving horizontally direction and vertical shift direction, Gu each default fixed point all corresponds to two presetting point images, a pair is edge The image of direction shooting is moved horizontally, another width is the image (as shown in Figure 7) shot along the vertical direction, two presetting point diagrams As being distinguished by image direction mark.

In step S302, server by the corresponding fixed point coordinate of each default fixed point, image direction identify and with image side To corresponding presetting point image associated storage is identified, pre-set image inquiry library is established, it is default based on this to be conducive to subsequent server Each presetting point image matching real scene shooting fixed point image in image querying library carries out position positioning, and localization method is quick and easy.

For step S301 into S302, server shoots default fixed point to each default fixed point on each movable direction Image can be identified based on different image directions to subsequent server and screen presetting point image, reduce contrast range, accelerated Search speed.Server establishes pre-set image inquiry library, conducive to subsequent server based on each in pre-set image inquiry library Presetting point image matching real scene shooting fixed point image carries out position positioning, and localization method is quick and easy.

In one embodiment, as shown in figure 8, in step S40, that is, feature extraction algorithm is used, it is presetting from least one The pinpoint image most like with real scene shooting fixed point image is obtained in point image, and the corresponding fixed point coordinate of pinpoint image is made For starting point coordinate, specifically comprise the following steps:

S41. at least one presetting point image and real scene shooting fixed point image are compared using feature extraction algorithm, obtained each pre- Set the corresponding characteristic matching degree of point image.

Wherein, feature extraction algorithm (Oriented FAST and Rotated BRIEF, hereinafter referred to as ORB algorithm) is A kind of algorithm that rapid characteristic points are extracted and described.Wherein, image characteristic point can be understood as more significant point in image, such as Profile point, the bright spot in darker area, the dim spot etc. in brighter areas.ORB algorithm is divided into two parts, including feature point extraction and Feature Points Matching.Presetting point image is exactly the standard ground image for including two neighboring default fixed point.Real scene shooting pinpoints image Along the shooting of accessible direction including the ground image between current location and next default fixed point.Characteristic matching degree is that real scene shooting is fixed The similarity percentage of point image and presetting point image.

Specifically, using feature extraction algorithm (Oriented FAST and Rotated BRIEF, hereinafter referred to as ORB calculation Method) compare at least one presetting point image and real scene shooting fixed point image process it is as follows:

1. extracting the characteristic point in each presetting point image and real scene shooting fixed point image respectively.

Extract presetting point image characteristic point include: by point more significant in presetting point image, as profile point, compared with The dim spot etc. in bright spot and brighter areas in dark areas is set as candidate point, detects the circle specified around candidate point and choose radius Pixel value on circle, if there is the gray value difference of enough pixel and the candidate point enough big around candidate point in field, Then think that the candidate point is a characteristic point.

In order to obtain faster as a result, following detection accelerated methods also can be used: every an angle of 90 degrees around test candidate point 4 points, it should the gray value differences of at least 3 and candidate point are sufficiently large, otherwise do not have to calculate other points again, directly think this Candidate point is not characteristic point.The selection radius of circle around candidate point is an important parameter, be may specify to be simple and efficient Detection radius is 3, then there are 16 neighboring pixels and need to compare, as shown in Figure 9.In order to improve the efficiency compared, usually only make It is compared i.e. FAST-N with N number of neighboring pixel, generally recommendation FAST-9.

The characteristic point for extracting real scene shooting fixed point image is consistent with the process of characteristic point for extracting presetting point image, herein no longer It repeats.

2. calculating separately and saving feature point description of each presetting point image and the characteristic point of real scene shooting fixed point image Description.

Feature point description for calculating presetting point image includes: to need after obtaining the characteristic point of presetting point image with certain Kind mode describes the attribute of this feature point.The attribute output of characteristic point is exactly the description (Feature of this feature point DescritorS).ORB algorithm obtain characteristic point attribute process include:

(1) using characteristic point P as the center of circle, round O is by radius of d.

(2) N number of point pair is chosen in circle O.For convenience of explanation, optional N=4 in the present embodiment, it is as shown in Figure 10, practical N can take 512 in.

By currently choose 4 points to being respectively labeled as shown above:

P₁(A,B)、P₂(A,B)、P₃(A, B) and P₄(A,B)。

(3) T operation is defined

Wherein, I_AIndicate the gray scale of point A, I_BIndicate the gray scale of point B.

(4) respectively to the point chosen to T operation is carried out, obtained result is combined.Continued with aforementioned four point For illustrate description son:

T(P₁(A, B))=1

T(P₂(A, B))=0

T(P₃(A, B))=1

T(P₄(A, B))=1

Then characteristic point P final description is 1011.

It calculates feature point description of real scene shooting fixed point image and calculates the process of feature point description of presetting point image Unanimously, details are not described herein again.

3. by real scene shooting fixed point image feature point description and each presetting point image feature point description carry out by One comparison, obtains characteristic matching degree.It illustrates feature point description and a presetting point image of real scene shooting fixed point image The process that compares of feature point description:

The sub- A:10101011 of feature point description of one real scene shooting fixed point image

The sub- B:10101010 of feature point description of one presetting point image

A and B only has last difference in this example, and characteristic matching degree is 87.5%.Wherein, A and B is subjected to xor operation The characteristic matching degree of A and B can be calculated.And xor operation can be completed by hardware, have very high efficiency, be accelerated With speed.

Such as feature point description of above-mentioned calculating real scene shooting fixed point image and feature point description of a presetting point image Process, obtain each presetting point image feature point description pinpointed with respect to real scene shooting image feature point description feature Matching degree is simultaneously saved.

In step S41, server can be used ORB algorithm and retouch by the characteristic point that hardware obtains each presetting point image The characteristic matching degree for stating feature point description of the opposite real scene shooting fixed point image of son, gives the highest default fixed point of selected characteristic matching degree Image preparation techniques basis.

S42. the highest presetting point image of selected characteristic matching degree, as pinpoint image.

Wherein, pinpoint image is exactly to pinpoint the highest image of image similarity with real scene shooting in presetting point image.

Specifically, by step S41 it is found that server feature point description that has recorded each presetting point image is relatively real Clap the characteristic matching degree of feature point description of fixed point image, it is only necessary to it is highest that score value is chosen in above-mentioned all characteristic matching degree The corresponding presetting point image of percentage, is determined as pinpoint image.

In step S42, server can be by feature point description to each presetting point image with respect to real scene shooting fixed point figure The characteristic matching degree of feature point description of picture carries out size sequence, selects the highest characteristic matching degree of score value corresponding presetting Point image is conducive to the subsequent pinpoint image that is based on to the progress position positioning of follow shot end as pinpoint image.

S43. the fixed point coordinate based on pinpoint image in pre-set image inquiry library is as starting point coordinate.

Wherein, starting point coordinate is exactly follow shot end present position corresponding coordinate bit in pre-set navigational map It sets.

In step S43, server can inquire fixed point coordinate corresponding with pinpoint image in pre-set image inquiry library and make It for starting point coordinate, completes to position the position at follow shot end, while being conducive to server and navigation road is carried out based on the start position Line gauge is drawn.

Into S43, server uses ORB algorithm and obtains the feature of each presetting point image by hardware step S41 The characteristic matching degree of feature point description of the opposite real scene shooting fixed point image of point description, after characteristic matching degree is carried out size sequence Select the maximum presetting point image of characteristic matching degree as pinpoint image, acquisition and target in pre-set image inquiry library Pinpoint the corresponding fixed point coordinate of image and be used as starting point coordinate, position positioning of the completion to follow shot end, the positioning method not by The limitation of hardware detection range, it is simple and fast, while being conducive to server and being based on start position progress navigation route planning.

In one embodiment, as shown in figure 11, in step S50, that is, terminal point coordinate is obtained, is sat according to starting point coordinate and terminal Mark generates at least two recommendation navigation routines, specifically comprises the following steps:

S51. starting point coordinate and terminal point coordinate are determined on default fixed point navigation map.

Wherein, terminal point coordinate be follow shot end on pre-set navigational map along specified default fixed point move after reach Terminal.

In step S51, starting point coordinate and terminal point coordinate can be identified on pre-set navigational map respectively for server, benefit Intuitively know what the position that follow shot end is currently located and this movement will reach in the Background control personnel of server Terminal point coordinate.

S52. at least two recommendation navigation routines are obtained on default fixed point navigation map using A star algorithm.

Wherein, recommending navigation routine is the road of coordinate of reaching home of setting out along each movable direction of pre- starting point coordinate Line includes at least the shortest route of a paths in all optimal routes, as shown in Figure 4.

Specifically, it is obtained on a movable direction on default fixed point navigation map using A star algorithm and recommends navigation The realization process of route is as follows:

F=G+H is set, wherein F is shortest path, and G=is moved to the shifting for the default fixed point being currently located from starting point coordinate Dynamic path；

H=is moved to the estimation path of terminal point coordinate from the default fixed point being currently located.

1. a starting point coordinate addition can walk, (each node is each presetting on pre-set navigational map to node listing Point).

2. repeating following process:

A. the node listing that can walk is traversed, the smallest node of F value is searched, using the node found as current to be processed Default fixed point.

B. default fixed point is moved on to can not row-column list.

C. each node of four neighbors of fixed point is preset in analysis:

If neighbors is not accessible or can not ignore in row-column list.Otherwise, it is done as follows:

If the node listing that can walk is added not in the node listing that can walk, neighbors in neighbors, and current Node is set as father node, records F, G and the H value of the node.

If neighbors in the node listing that can walk, checks the path (reaching neighbors via present node) Whether G value is smaller.If it is, it is present node that its father node, which is arranged, and recalculate G the and F value of present node.

D. it when being added to terminal point coordinate in the node listing that can walk, then completes to search optimal guidance path at this time.

3. each node is moved along father node until starting point coordinate, exactly recommends navigation routine since terminal point coordinate.

In step S52, server can be used A star algorithm and obtain on each movable direction on default fixed point navigation map Recommendation navigation routine, be conducive to subsequent movement shooting end can according to road conditions (for example there are barriers in road) in real time replacement or Adjust route, the mobile flexibility in enhancing follow shot end.

Into S52, server can identify starting point coordinate and terminal point coordinate step S51 on pre-set navigational map respectively Come, intuitively knows that the position that follow shot end is currently located will be arrived with this movement conducive to the Background control personnel of server The terminal point coordinate reached.Server obtains the recommendation on each movable direction using A star algorithm on default fixed point navigation map Navigation routine, route can be replaced or adjust in real time according to road conditions by being conducive to subsequent movement shooting end, and enhancing follow shot end is mobile Flexibility.

In one embodiment, target navigation route includes at least one by way of fixed point.As shown in figure 12, in step S60, i.e., It is mobile according to target navigation route to control follow shot end, specifically comprises the following steps:

S61. control follow shot end is moved to according to target navigation route from starting point coordinate next by way of fixed point.

Approach fixed point is the next default fixed point of follow shot end according to target navigation routine being directed to move to.

In step S61, target navigation route is sent to follow shot end, follow shot end by wireless network by server After receiving the target navigation route, next approach can be moved to from current location according to the guide of the target navigation route and determined Point improves safety and reliability of the follow shot end in moving process.

S62. by follow shot end be moved to it is next by way of fixed point be updated to new starting point coordinate, if new starting point coordinate It is not terminal point coordinate, then repeats acquisition terminal point coordinate, at least two recommendations is generated according to starting point coordinate and terminal point coordinate and are led The step of air route line.

Specifically, because the range that barrier is detected at follow shot end every time is the distance between two default fixed points, work as shifting When according to target navigation routine is moved to next approach fixed point at dynamic shooting end, it is also necessary to continue to determine the safety of road, Ye Jixu Next approach fixed point is updated to starting point coordinate, should determine whether deposit between starting point coordinate and next approach coordinate again at this time In barrier.

It is to be appreciated that follow shot end can press mesh when barrier is not present between starting point coordinate and next approach fixed point Mark navigation routine continues to move to；When there are when barrier between starting point coordinate and next approach fixed point, it is necessary to which server is to weight New object of planning navigation routine, namely acquisition terminal point coordinate is repeated, at least two are generated according to starting point coordinate and terminal point coordinate Item recommends the step of navigation routine.The step of specifically repeating is consistent with step S50 to S60, and details are not described herein again.

In step S62, follow shot end is often moved to next approach fixed point, and do not reach home also coordinate when, will Whether there are obstacles between detection current location and next approach fixed point, improves in moving process and is adjusted in real time according to road conditions The flexibility of target navigation route and mobile security can ensure that follow shot end is smoothly reached home the position of coordinate.

Step S61 is into step S62, and server is by controlling follow shot end foundation target navigation route from current location It is moved to next default fixed point, improves safety and reliability of the follow shot end in moving process.The every shifting in follow shot end Move next approach fixed point, and do not reach home also coordinate when, will detect between current location and next approach fixed point is It is no there are barrier, improve in moving process and to adjust flexibility and the mobile security of target navigation route according to road conditions in real time Property can ensure that follow shot end is smoothly reached home the position of coordinate.

Intelligent navigation method provided in this embodiment pinpoints image in the real scene shooting that current location is shot by follow shot end It is compared with each presetting point image in pre-set image inquiry library, to obtain most like pinpoint image to really Recognize follow shot end in the corresponding starting point coordinate in current location, using image comparison method to the current location at follow shot end into Row positioning, is not limited, positioning method is simple and fast by hardware detection range.It, can be according to present bit in the intelligent navigation method It sets corresponding starting point coordinate and terminal point coordinate is cooked up and can be based on being somebody's turn to do so that follow shot is short with the target navigation route of avoidance Target navigation route is mobile, can adjust target navigation route according to road conditions in real time, the air navigation aid is not equally by hardware detection The influence of range, mode flexibility and reliability of navigating.

Further, the optional direction that barrier is not present of server is as accessible direction, so as to server It is shot based on the accessible direction.Server specifies the shooting distance of real scene shooting fixed point image to be also conducive to follow shot simultaneously Position where end carries out more accurate positioning, and the real scene shooting fixed point image including more characteristics of image is conducive to improve image analysis Accuracy.Server shoots presetting point image to each default fixed point on each movable direction, to subsequent clothes Being engaged in device can be based on the presetting point image of different image directions mark screening, diminution contrast range, quickening search speed.Server Pre-set image inquiry library is established, conducive to subsequent server based on each presetting point image matching in pre-set image inquiry library Real scene shooting pinpoints image and carries out position positioning, and localization method is quick and easy.Server is completed using ORB algorithm and by hardware to shifting The position positioning at dynamic shooting end, while being conducive to server and navigation route planning is carried out based on the start position.Server can will rise Point coordinate and terminal point coordinate are identified on pre-set navigational map respectively, intuitively obtain conducive to the Background control personnel of server Know the position that follow shot end is currently located and the terminal point coordinate that this movement will reach.Server is using A star algorithm pre- The recommendation navigation routine on each movable direction is obtained on set point navigation map, being conducive to subsequent movement shooting end can be according to road Route, the mobile flexibility in enhancing follow shot end are replaced or adjusted in real time to condition.Server is every by control follow shot end Be moved to next approach fixed point, and do not reach home also coordinate when, will detect between current location and next approach fixed point Whether there are obstacles, improves flexibility and the mobile security for adjusting target navigation route in moving process according to road conditions in real time Property can ensure that follow shot end is smoothly reached home the position of coordinate.

It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit It is fixed.

In one embodiment, a kind of intelligent navigation device is provided, which intelligently leads with above-described embodiment Boat method corresponds.As shown in figure 13, which includes setting moving direction module 10, obtains real scene shooting image mould Block 20 acquisition fixed point image module 30, obtains starting point coordinate module 40, generates recommended route module 50 and the movement of control mobile terminal Module 60.Detailed description are as follows for each functional module:

Moving direction module 10 is set, it is removable for obtaining at least one of follow shot end on pre-set navigational map Direction.

Real scene shooting image module 20 is obtained, for being based at least one movable direction, obtains follow shot end accessible The real scene shooting of direction shooting pinpoints image.

Fixed point image module 30 is obtained, for inquiring library based on pre-set image, is obtained equidirectional with real scene shooting fixed point image At least one presetting point image.

Starting point coordinate module 40 is obtained, for using feature extraction algorithm, is obtained from least one presetting point image The most like pinpoint image with real scene shooting fixed point image, using the corresponding fixed point coordinate of pinpoint image as starting point coordinate.

Recommended route module 50 is generated, for obtaining terminal point coordinate, generates at least two according to starting point coordinate and terminal point coordinate Item recommends navigation routine.

Mobile terminal mobile module 60 is controlled, recommends the avoidance of navigation routine to visit at least two for obtaining follow shot end It surveys as a result, choosing avoidance detection result is free of obstacles and the shortest recommendation navigation routine of distance is target navigation route, and Target navigation route is sent to follow shot end, control follow shot end is mobile according to target navigation route.

Preferably, obtaining real scene shooting image module 20 includes obtaining accessible direction unit 21 and acquisition real scene shooting image unit 22。

Accessible direction unit 21 is obtained, for being based at least one movable direction, detects each of follow shot end Movable direction obtains at least one accessible direction.

Real scene shooting image unit 22 is obtained, is shot for controlling follow shot end using accessible direction as shooting direction, It obtains real scene shooting and pinpoints image.

Preferably, which further includes obtaining presetting point image module 301 and formation image querying library mould Block 302.

Presetting point image module 301 is obtained, for obtaining each default fixed point in each movable direction photographs Presetting point image.

Image querying library module 302 is formed, for the corresponding fixed point coordinate of each default fixed point of associated storage, image direction Mark and presetting point image corresponding with image direction mark form pre-set image and inquire library.

Preferably, obtaining starting point coordinate module 40 includes obtaining characteristic matching degree unit 401, as pinpoint image list Member 402 and as starting point coordinate unit 403.

Obtain characteristic matching degree unit 401, for using feature extraction algorithm compare at least one presetting point image and Real scene shooting pinpoints image, obtains the corresponding characteristic matching degree of each presetting point image.

As pinpoint elementary area 402, it is used for the highest presetting point image of selected characteristic matching degree, as target Pinpoint image.

As starting point coordinate unit 403, for the fixed point coordinate based on pinpoint image in pre-set image inquiry library As starting point coordinate.

Preferably, generating recommended route module 50 includes determining starting point coordinate unit 501 and acquisition recommended route unit 502。

Starting point coordinate unit 501 is determined, for determining starting point coordinate and terminal point coordinate on default fixed point navigation map.

Recommended route unit 502 is obtained, is pushed away for obtaining at least two on default fixed point navigation map using A star algorithm Recommend navigation routine.

Preferably, control mobile terminal mobile module 60 includes controlling to shoot short mobile unit 601 and generate to recommend road of navigating Line unit 602.

Control shoots short mobile unit 601, moves according to target navigation route from starting point coordinate for controlling follow shot end It moves next by way of fixed point.

It generates and recommends navigation routine unit 602, next be updated to newly by way of fixed point for be moved to follow shot end Starting point coordinate acquisition terminal point coordinate is repeated, according to starting point coordinate and end if new starting point coordinate is not terminal point coordinate The step of point at least two recommendation navigation routines of Coordinate generation.

Specific about intelligent navigation device limits the restriction that may refer to above for intelligent navigation method, herein not It repeats again.Modules in above-mentioned intelligent navigation device can be realized fully or partially through software, hardware and combinations thereof.On Stating each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also store in a software form In memory in computer equipment, the corresponding operation of the above modules is executed in order to which processor calls.

In one embodiment, a kind of computer equipment is provided, which can be server, internal structure Figure can be as shown in figure 14.The computer equipment includes processor, the memory, network interface sum number connected by system bus According to library.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory of the computer equipment includes Non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating The database of machine equipment is used for the relevant data of intelligent navigation method.The network interface of the computer equipment is used for and external end End passes through network connection communication.To realize a kind of intelligent navigation method when the computer program is executed by processor.

In one embodiment, a kind of computer equipment is provided, including memory, processor and storage are on a memory simultaneously The computer program that can be run on a processor, processor perform the steps of acquisition follow shot when executing computer program Hold at least one movable direction on pre-set navigational map；Based at least one movable direction, follow shot end is obtained In accessible direction, the real scene shooting of shooting pinpoints image；Library is inquired based on pre-set image, is obtained equidirectional with real scene shooting fixed point image At least one presetting point image；Using feature extraction algorithm, obtains from least one presetting point image and pinpointed with real scene shooting The most like pinpoint image of image, using the corresponding fixed point coordinate of pinpoint image as starting point coordinate；Terminal is obtained to sit Mark generates at least two recommendation navigation routines according to starting point coordinate and terminal point coordinate；Follow shot end is obtained to push away at least two The avoidance detection result of navigation routine is recommended, choosing avoidance detection result is free of obstacles and the shortest recommendation navigation routine of distance For target navigation route, and target navigation route is sent to follow shot end, control follow shot end is according to target navigation road Line is mobile.

In one embodiment, it is based at least one movable direction, obtains what follow shot end was shot in accessible direction Real scene shooting pinpoints image, comprising: is based at least one movable direction, detects each movable direction at follow shot end, obtains At least one accessible direction；Control follow shot end is shot using accessible direction as shooting direction, obtains real scene shooting fixed point Image.

In one embodiment, presetting fixed point navigation map includes at least two default fixed points, and each default fixed point includes fixed Point coordinate and at least one movable direction；Library is being inquired based on pre-set image, is being obtained equidirectional extremely with real scene shooting fixed point image Before the step of few presetting point image, processor also performs the steps of acquisition when executing computer program each pre- Presetting point image of the set point in each movable direction photographs；The each default fixed point of associated storage corresponding fixed point seat Mark, image direction mark and presetting point image corresponding with image direction mark, form pre-set image and inquire library.

In one embodiment, it using feature extraction algorithm, obtains from least one presetting point image and is pinpointed with real scene shooting The most like pinpoint image of image, using the corresponding fixed point coordinate of pinpoint image as starting point coordinate, comprising: using special Sign extraction algorithm compares at least one presetting point image and real scene shooting fixed point image, obtains the corresponding spy of each presetting point image Levy matching degree；The highest presetting point image of selected characteristic matching degree, as pinpoint image；Existed based on pinpoint image Pre-set image inquires the fixed point coordinate in library as starting point coordinate.

In one embodiment, terminal point coordinate is obtained, at least two recommendation navigation are generated according to starting point coordinate and terminal point coordinate Route, comprising: determine starting point coordinate and terminal point coordinate on default fixed point navigation map；It is led using A star algorithm in default fixed point At least two recommendation navigation routines are obtained on boat map.

In one embodiment, target navigation route includes at least one by way of fixed point；Follow shot end is controlled according to target Navigation routine is mobile, comprising: control follow shot end is moved to according to target navigation route from starting point coordinate next by way of fixed point； By follow shot end be moved to it is next by way of fixed point be updated to new starting point coordinate, if new starting point coordinate be not terminal sit Mark, then repeat acquisition terminal point coordinate, and the step of at least two recommendation navigation routines is generated according to starting point coordinate and terminal point coordinate Suddenly.

In one embodiment, a kind of computer readable storage medium is provided, computer program, computer are stored thereon with It is removable that at least one of acquisition follow shot end on pre-set navigational map is performed the steps of when program is executed by processor Direction；Based at least one movable direction, follow shot end is obtained in the real scene shooting that accessible direction is shot and pinpoints image；It is based on Pre-set image inquires library, obtains and pinpoints at least one equidirectional presetting point image of image with real scene shooting；It is calculated using feature extraction Method obtains the pinpoint image most like with real scene shooting fixed point image, by pinpoint from least one presetting point image The corresponding fixed point coordinate of image is as starting point coordinate；Terminal point coordinate is obtained, generates at least two according to starting point coordinate and terminal point coordinate Item recommends navigation routine；The avoidance detection result that navigation routine is recommended at least two at follow shot end is obtained, avoidance is chosen and visits Survey result is free of obstacles and the shortest recommendation navigation routine of distance is target navigation route, and target navigation route is sent Follow shot end is given, control follow shot end is mobile according to target navigation route.

In one embodiment, presetting fixed point navigation map includes at least two default fixed points, and each default fixed point includes fixed Point coordinate and at least one movable direction；Library is being inquired based on pre-set image, is being obtained equidirectional extremely with real scene shooting fixed point image It is each that acquisition is also performed the steps of before the step of few presetting point image, when computer program is executed by processor Presetting point image of the default fixed point in each movable direction photographs；The each default fixed point of associated storage corresponding fixed point seat Mark, image direction mark and presetting point image corresponding with image direction mark, form pre-set image and inquire library.

Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with Relevant hardware is instructed to complete by computer program, it is readable which can be stored in a non-volatile computer It takes in storage medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, this Shen Please any reference used in each embodiment to memory, storage, database or other media, may each comprise non-volatile And/or volatile memory.Nonvolatile memory may include that read-only memory (ROM), programming ROM (PROM), electricity can be compiled Journey ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms, such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) directly RAM (RDRAM), straight Connect memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..

It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function Can unit, module division progress for example, in practical application, can according to need and by above-mentioned function distribution by different Functional unit, module are completed, i.e., the internal structure of described device is divided into different functional unit or module, more than completing The all or part of function of description.

The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although with reference to the foregoing embodiments Invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each implementation Technical solution documented by example is modified or equivalent replacement of some of the technical features；And these modification or Replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution should all include Within protection scope of the present invention.

Claims

1. a kind of intelligent navigation method characterized by comprising

Based on movable direction described at least one, the real scene shooting fixed point figure that the follow shot end is shot in accessible direction is obtained Picture；

Library is inquired based on pre-set image, obtains and pinpoints at least one equidirectional presetting point image of image with the real scene shooting；

Using feature extraction algorithm, obtained from presetting point image described at least one most like with real scene shooting fixed point image Pinpoint image, using the corresponding fixed point coordinate of the pinpoint image as starting point coordinate；

Terminal point coordinate is obtained, at least two recommendation navigation routines are generated according to the starting point coordinate and the terminal point coordinate；

Follow shot end is obtained at least two avoidance detection results for recommending navigation routine, choosing avoidance detection result is Free of obstacles and the shortest recommendation navigation routine of distance are target navigation route, and the target navigation route is sent to shifting Dynamic shooting end, it is mobile according to the target navigation route to control the follow shot end.

2. intelligent navigation method as described in claim 1, which is characterized in that described to be based at least one described removable side To obtaining the real scene shooting that the follow shot end is shot in accessible direction and pinpoint image, comprising:

Based on movable direction described at least one, each movable direction at follow shot end is detected, at least one nothing is obtained Obstacle direction；

It controls the follow shot end to be shot using the accessible direction as shooting direction, obtains real scene shooting and pinpoint image.

3. intelligent navigation method as described in claim 1, which is characterized in that the default fixed point navigation map includes at least two A default fixed point, each default fixed point includes fixed point coordinate and at least one movable direction；

Library is inquired based on pre-set image described, obtains and pinpoints at least one equidirectional presetting point diagram of image with the real scene shooting Before the step of picture, the intelligent navigation method further include:

Each default fixed point is obtained in the presetting point image of each movable direction photographs；

The corresponding fixed point coordinate of each default fixed point of associated storage, movable direction and corresponding with the movable direction Presetting point image forms pre-set image and inquires library.

4. intelligent navigation method as claimed in claim 3, which is characterized in that it is described to use feature extraction algorithm, from least one The pinpoint image most like with real scene shooting fixed point image is obtained in a presetting point image, by the pinpoint The corresponding fixed point coordinate of image is as starting point coordinate, comprising:

At least one presetting point image and real scene shooting fixed point image are compared using feature extraction algorithm, obtain each institute State the corresponding characteristic matching degree of presetting point image；

The highest presetting point image of the characteristic matching degree is chosen, as the pinpoint image；

Fixed point coordinate based on the pinpoint image in pre-set image inquiry library is as starting point coordinate.

5. intelligent navigation method as claimed in claim 3, which is characterized in that the acquisition terminal point coordinate, according to the starting point Coordinate and the terminal point coordinate generate at least two recommendation navigation routines, comprising:

The starting point coordinate and the terminal point coordinate are determined on the default fixed point navigation map；

At least two recommendation navigation routines are obtained on the default fixed point navigation map using A star algorithm.

6. intelligent navigation method as described in claim 1, which is characterized in that the target navigation route includes at least one way Through pinpointing；

The control follow shot end is mobile according to the target navigation route, comprising:

Control the follow shot end be moved to according to the target navigation route from starting point coordinate it is next by way of fixed point；

By follow shot end be moved to it is described it is next by way of fixed point be updated to new starting point coordinate, if the new starting point coordinate It is not the terminal point coordinate, then repeats the acquisition terminal point coordinate, it is raw according to the starting point coordinate and the terminal point coordinate The step of at least two recommendation navigation routines.

7. a kind of intelligent navigation device characterized by comprising

Moving direction module is set, for obtaining at least one movable direction of follow shot end on pre-set navigational map；

Real scene shooting image module is obtained, for being based at least one described movable direction, obtains the follow shot end in no barrier The real scene shooting fixed point image for hindering direction to shoot；

Obtain starting point coordinate module, for use feature extraction algorithm, from presetting point image described at least one obtain with The most like pinpoint image of the real scene shooting fixed point image, using the corresponding fixed point coordinate of the pinpoint image as starting point Coordinate；

Recommended route module is generated, for obtaining terminal point coordinate, is generated at least according to the starting point coordinate and the terminal point coordinate Two recommendation navigation routines；

Mobile terminal mobile module is controlled, at least two avoidances for recommending navigation routine are detected for obtaining follow shot end As a result, choosing, avoidance detection result is free of obstacles and the shortest recommendation navigation routine of distance is target navigation route, and will The target navigation route is sent to follow shot end, and it is mobile according to the target navigation route to control the follow shot end.

8. intelligent navigation device as claimed in claim 7, which is characterized in that the acquisition real scene shooting image module includes:

Accessible direction unit is obtained, for being based at least one described movable direction, detection each of follow shot end can Moving direction obtains at least one accessible direction；

Real scene shooting image unit is obtained, is clapped for controlling the follow shot end using the accessible direction as shooting direction It takes the photograph, obtains real scene shooting and pinpoint image.

9. a kind of computer equipment, including memory, processor and storage are in the memory and can be in the processor The computer program of upper operation, which is characterized in that the processor realized when executing the computer program as claim 1 to The step of any one of 6 intelligent navigation method.

10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists In the step of realization intelligent navigation method as described in any one of claim 1 to 6 when the computer program is executed by processor Suddenly.