CN106529538A - Method and device for positioning aircraft - Google Patents
Method and device for positioning aircraft Download PDFInfo
- Publication number
- CN106529538A CN106529538A CN201611044625.3A CN201611044625A CN106529538A CN 106529538 A CN106529538 A CN 106529538A CN 201611044625 A CN201611044625 A CN 201611044625A CN 106529538 A CN106529538 A CN 106529538A
- Authority
- CN
- China
- Prior art keywords
- field picture
- pixel
- characteristic point
- point
- aircraft
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- 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
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/245—Aligning, centring, orientation detection or correction of the image by locating a pattern; Special marks for positioning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
Abstract
The invention discloses a method and a device for positioning an aircraft, which are used for reducing a positioning error of the aircraft and improving the positioning accuracy of the aircraft. The method provided by the embodiment of the invention for positioning the aircraft comprises the steps of respectively performing feature point detection and calculation on images photographed in real time by a downward camera configured by the aircraft so as to acquire feature points of a first frame image and feature points of a second frame image, wherein the first frame image and the second frame image are images acquired by respectively photographing two adjacent frames; performing feature point matching processing on the feature points of the first frame image and the feature points of the second frame image; if features points between a first pixel point in the first frame image and a second pixel point in the second frame image are successfully matched, calculating a rotation matrix and a translation vector between the first pixel point and the second pixel point; and calculation current position and attitude information of the aircraft according to the current height of the aircraft, the rotation matrix and the translation vector.
Description
Technical field
The present invention relates to field of computer technology, more particularly to a kind of localization method and device of aircraft.
Background technology
UAV is referred to as aircraft, and aircraft has many applications in national economy, military affairs, flies at present
Device oneself be widely used in taking photo by plane photography, electric inspection process, environmental monitoring, forest fire protection, disaster inspection, anti-terrorism lifesaving, military affairs detect
Examine, the field such as battle assessment, aircraft be using radio robot and the presetting apparatus provided for oneself manipulate it is not manned
Aircraft.Without driving cabin on machine, but the equipment such as automatic pilot, presetting apparatus, information collecting device are installed, remote control station people
Member by the equipment such as radar, which is tracked, is positioned, remote control, remote measurement and Digital Transmission.
In prior art, aircraft generally adopts following three kinds of schemes in positioning：1st, aircraft is based on global positioning system
(Global Positioning System, GPS) is positioned, 2, aircraft positioned based on light stream camera, 3, aircraft
Positioned based on inertial sensor.For existing method 1, the GPS device in aircraft are needed in outdoor, high building is avoided,
Can just be positioned in the case of the woods, tunnel etc. shelter, and the ratio of precision of GPS location is poor, general error is arrived 5
Between 10 meters, GPS needs to wait search of satellite signal so that aircraft quickly can not take off when aircraft starts in addition.It is right
In existing method 2, light stream camera detects the object of motion using optical flow method, in actual applications, due to blocking property, more light
The reasons such as source, the transparency and noise so that the gray scale conservation assumed condition of optical flow field fundamental equation can not meet, light stream camera are fixed
The method of position can only carry out the positioning of aircraft indoors, while most optical flow computation method is considerably complicated, amount of calculation is huge
Greatly, it is impossible to meet and require in real time, therefore be not particularly suited for the aircraft higher to precision and requirement of real-time.For existing
Method 3, inertial sensor positioning shortcoming be to have accumulative error, this error is relevant with the precision of sensor, so as to
The positioning precision of aircraft can be reduced.
To sum up, the existing localization method of aircraft cannot be realized being accurately positioned in prior art.
The content of the invention
The localization method and device of a kind of aircraft are embodiments provided, the positioning for reducing aircraft is missed
Difference, improves the positioning precision of aircraft.
To solve above-mentioned technical problem, the embodiment of the present invention provides technical scheme below：
In a first aspect, the embodiment of the present invention provides a kind of localization method of aircraft, including：
The detection of characteristic point is carried out respectively to the image that the camera captured in real-time downward of aircraft configuration is obtained
Calculate, obtain the characteristic point of the characteristic point and the second two field picture of the first two field picture, first two field picture and the second frame figure
Seem that adjacent two frame shoots the image for obtaining respectively；
The characteristic point of characteristic point and second two field picture to first two field picture carries out the matching treatment of characteristic point；
If feature between the second pixel in the first pixel and second two field picture in first two field picture
Point matching success, then calculate the spin matrix and translation vector between first pixel and second pixel；
Present level, the spin matrix and the amount of being translated towards according to the aircraft calculates the current position of the aircraft
Appearance information.
Second aspect, the embodiment of the present invention also provide a kind of positioner of aircraft, including：
Feature point detection module, for the image point obtained to the camera captured in real-time downward of aircraft configuration
The detection for not carrying out characteristic point is calculated, and obtains the characteristic point of the characteristic point and the second two field picture of the first two field picture, first frame
Image and second two field picture are that adjacent two frame shoots the image for obtaining respectively；
Feature Points Matching module, the feature for the characteristic point to first two field picture and second two field picture are clicked through
The matching treatment of row characteristic point；
Rotation and translation computing module, if for the first pixel in first two field picture and second two field picture
In the second pixel between Feature Points Matching success, then calculate the rotation between first pixel and second pixel
Torque battle array and translation vector；
Pose computing module, calculates for the present level according to the aircraft, the spin matrix and the amount of being translated towards
The current posture information of the aircraft.
As can be seen from the above technical solutions, the embodiment of the present invention has advantages below：
In embodiments of the present invention, the image for first the camera captured in real-time downward of aircraft configuration being obtained
The detection for carrying out characteristic point respectively is calculated, and obtains the characteristic point of the characteristic point and the second two field picture of the first two field picture, the first frame figure
Picture and the second two field picture are that adjacent two frame shoots the image for obtaining respectively, then the characteristic point to the first two field picture and the second frame figure
The characteristic point of picture carries out the matching treatment of characteristic point, if second in the first pixel and the second two field picture in the first two field picture
Feature Points Matching success between pixel, then calculate the spin matrix between the first pixel and the second pixel and be translated towards
Amount, the present level, spin matrix and the amount of being translated towards finally according to aircraft calculate the current posture information of aircraft.The present invention
Camera can be set in the lower section of aircraft in embodiment, the camera carries out captured in real-time, so as to obtain multiple frame moment
Image, calculate for the image at multiple frame moment can be carried out feature point detection frame by frame, the picture in two two field pictures
Between vegetarian refreshments during Feature Points Matching success, by calculating the spin matrix peace between the pixel respectively from two two field pictures
The amount of shifting to, the present level, spin matrix and the amount of being translated towards finally according to aircraft calculate the current posture information of aircraft, lead to
Cross the current posture information of aircraft and complete the positioning to aircraft, only need in the embodiment of the present invention using downward on aircraft
The camera real-time image acquisition of setting, obtains the pose letter of aircraft by the process and optimization of the image to multiple frame moment
Breath, therefore the positioning of aircraft does not receive outdoor indoor context restrictions, the process and optimization of image is with the accurate advantage of calculating.
Description of the drawings
For the technical scheme being illustrated more clearly that in the embodiment of the present invention, below will be to making needed for embodiment description
Accompanying drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the present invention, for
For those skilled in the art, can be with according to these other accompanying drawings of accompanying drawings acquisition.
Fig. 1 is a kind of process blocks schematic diagram of the localization method of aircraft provided in an embodiment of the present invention；
Fig. 2 is the workflow schematic diagram of vision positioning algorithm provided in an embodiment of the present invention；
Fig. 3 is the application scenarios schematic diagram of ORB Feature Points Matchings algorithm provided in an embodiment of the present invention；
Fig. 4-a are a kind of composition structural representation of the positioner of aircraft provided in an embodiment of the present invention；
Fig. 4-b are the composition structural representation of the positioner of another kind of aircraft provided in an embodiment of the present invention；
Fig. 4-c are a kind of rotation provided in an embodiment of the present invention and the composition structural representation for translating computing module；
Fig. 5 is the composition structural representation that the localization method of aircraft provided in an embodiment of the present invention is applied to aircraft.
Specific embodiment
The localization method and device of a kind of aircraft are embodiments provided, the positioning for reducing aircraft is missed
Difference, improves the positioning precision of aircraft.
To enable goal of the invention of the invention, feature, advantage more obvious and understandable, below in conjunction with the present invention
Accompanying drawing in embodiment, is clearly and completely described to the technical scheme in the embodiment of the present invention, it is clear that disclosed below
Embodiment be only a part of embodiment of the invention, and not all embodiments.Based on the embodiment in the present invention, this area
The every other embodiment obtained by technical staff, belongs to the scope of protection of the invention.
Term " comprising " and " having " in description and claims of this specification and above-mentioned accompanying drawing and they
Any deformation, it is intended that cover it is non-exclusive includes, so as to include a series of units process, method, system, product or set
It is standby to be not necessarily limited to those units, but may include clearly not list or for these processes, method, product or equipment are solid
Other units having.
It is described in detail individually below.
One embodiment of the localization method of aircraft of the present invention, specifically can apply to flying during aircraft flight
In the real-time positioning scene of row device, aircraft can be specifically unmanned plane, can also be telecontrolled aircraft, aeromodelling airplane etc..The present invention
Embodiment realizes the lower images captured in real-time to aircraft by the camera that aircraft is carried, and the flying height of aircraft can
With by the device Real-time Collection such as barometer, the lower images for collecting are carried out in image the detection of characteristic point and matched,
Calculate the spin matrix and translation vector between different two field pictures, then the conversion of the flying height by aircraft, it is possible to
The current pose of aircraft is calculated, the embodiment of the present invention is conducive to aircraft without the need for the built-in additional devices in aircraft
Miniaturization.Refer to shown in Fig. 1, the localization method of the aircraft that one embodiment of the invention is provided can include as follows
Step：
101st, characteristic point is carried out respectively to the image that the camera captured in real-time downward of aircraft configuration is obtained
Detection is calculated, and obtains the characteristic point of the characteristic point and the second two field picture of the first two field picture.
Wherein, the first two field picture and the second two field picture are that adjacent two frame shoots the image for obtaining respectively.
In embodiments of the present invention, be provided with camera downward in aircraft, the camera to aircraft institute
Lower images in position carry out captured in real-time, and generate the image shot at the different frame moment, fly in the embodiment of the present invention
The camera installed on device can be camera vertically downward, if camera on aircraft downward is deposited when mounted
Error when during error, can be met vertically downward by advance correction, therefore be installed, can pass through mathematical computations
Mode adjusting image, internal reference demarcation is for example carried out to the camera downward of aircraft, internal reference can be camera
Radial distortion (such as barrel distortion) and tangential distortion parameter.
Camera collection in the embodiment of the present invention can obtain the image at multiple frame moment in the image at different frame moment,
Wherein in order to distinguish the image at above-mentioned multiple frame moment, it is first that camera is shot the image definition that obtains at the first frame moment
Two field picture, it is the second two field picture, the first two field picture and the second frame that camera is shot the image definition that obtains at the second frame moment
Image is only intended to distinguish the image that camera was photographed at the different frame moment.
In embodiments of the present invention, for the first two field picture obtained in the shooting of the first frame moment carries out the detection of characteristic point
Calculating can obtain the characteristic point of the first two field picture, for the second two field picture obtained in the shooting of the second frame moment carries out characteristic point
Detection calculate and can obtain the characteristic point of the second two field picture.Wherein, images match of the characteristic point of image in distinguished point based
There is highly important effect in algorithm, image characteristic point can reflect image substantive characteristics, can be identified for that object in image
Body, can complete the matching of image by the matching of characteristic point, and the characteristic point of embodiment of the present invention image can be topography
Characteristic point, for the feature point extraction of the first two field picture and the second two field picture can have various implementations, for example, can be ORB
(English name：ORiented Binary Robust Independent Elementary Features) characteristic point carries
The extraction of robust features (Speeded Up Robust Features, SURF) is taken, or accelerated, can also be yardstick not
Become extraction of eigentransformation (Scale-Invariant Feature Transform, SIFT) etc., therefore in the embodiment of the present invention
Topography's feature can be ORB characteristic points, SURF characteristic points, SIFT feature point.
In some embodiments of the invention, camera captured in real-time downward of the step 101 to aircraft configuration
The image for obtaining carries out the detection of characteristic point respectively and calculates, and obtains the characteristic point of the characteristic point and the second two field picture of the first two field picture
Before, the localization method of aircraft provided in an embodiment of the present invention, can also comprise the steps：
A1, process is zoomed in and out respectively to the image that camera captured in real-time is obtained；
A2, scaling is processed after image be converted to gray-scale map, and equalization processing is carried out to gray-scale map.
Specifically, realizing under scene in aforementioned execution step A1 and step A2, direction of the step 101 to aircraft configuration
The image that the camera captured in real-time of lower section is obtained carries out the detection of characteristic point respectively and calculates, and obtains the characteristic point of the first two field picture
With the characteristic point of the second two field picture, including：
A3, the detection calculating for carrying out characteristic point to the gray-scale map after equalization processing respectively, obtain the spy of the first two field picture
Levy the characteristic point of a little He the second two field picture.
Wherein, for camera shoots the image of the lower section of aircraft position, if there is disturbed condition, can also be right
Image is pre-processed, for example, can zoom in and out the equalization processing of process, cutting process and grey level histogram.Wherein, it is right
The image that camera can be collected when processing by the scaling of image zooms to one respectively and is appropriate to target obstacle identification
Ratio, for example can also downscaled images with enlarged drawing.For the cutting of image, left and right two can be punctured when processing
Multiple pixels of width image border, can so reduce the amount of calculation of visual processes.In other embodiments of the present invention,
If the pixel of a sub-picture is occupied many gray levels and is evenly distributed, then such image often have high-contrast and
Changeable gray tone.Histogram equalization is also referred to as to the equalization processing of gray-scale map, is exactly that one kind can only lean on input picture
Histogram information automatically achieves the transforming function transformation function of this effect.Its basic thought is to the gray level more than number of pixels in image
Enter line broadening, and the gray scale few to number of pixels in image is compressed, so as to extend the dynamic range of pixel value, improve
The change of contrast and gray tone, becomes apparent from image.By the aforementioned pretreatment to image, the light of image can also be made
According to equilibrium, image is sized for mobile device process.
The realizing under scene of abovementioned steps A1 and step A2 is performed in the embodiment of the present invention, for camera reality in aircraft
When the image that collects, if equalization processing has first been carried out to the gray-scale map that the image is converted to, when characteristic point is calculated
The image of needs is exactly the gray-scale map after equalization processing, carries out the detection of characteristic point to the gray-scale map after equalization processing respectively
Calculate, obtain the characteristic point of the characteristic point and the second two field picture of the first two field picture.
In some embodiments of the invention, camera captured in real-time downward of the step 101 to aircraft configuration
The image for obtaining carries out the detection of characteristic point respectively and calculates, and obtains the feature of the characteristic point and the second two field picture of the first two field picture
Point, including：
B1, after camera shoots the first two field picture for obtaining at the first frame moment, detect the local of the first two field picture
Image characteristic point, and calculate description of the local image characteristics point of the first two field picture；
B2, after camera shoots the second two field picture for obtaining at the second frame moment, detect the local of the second two field picture
Image characteristic point, and calculate description of the local image characteristics point of the second two field picture, the first frame moment and the second frame moment be
Two adjacent frame moment.
In embodiments of the present invention, the first frame moment and the second frame moment are the adjacent two frame moment, respectively first
The camera of frame moment and the second frame moment using aircraft downward carries out IMAQ, is often collecting a two field picture
When, it is possible to the detection of local image characteristics point is carried out for the two field picture, then calculate the description of the local image characteristics point
Sub (Feature Descriptor), wherein, description of local image characteristics point is used for the attribute of Expressive Features point, for example
The core concept of BRIEF algorithms chooses that N number of point is right around key point P with certain pattern, this N number of point to comparison knot
Fruit directly obtains ORB characteristic point using the ORB feature point extraction functions that OpenCV is provided in combination as description, the present invention
Description son.
102nd, to the first two field picture characteristic point and the characteristic point of the second two field picture carries out the matching treatment of characteristic point.
In embodiments of the present invention, for the detection that the first two field picture and the second two field picture enter characteristic point respectively calculates it
Afterwards, the characteristic point of the characteristic point and the second two field picture of the first two field picture can be obtained.Then for the characteristic point of two two field pictures
Matching treatment is carried out, for example, the computer vision storehouse OpenCV that increases income can be adopted to complete the matching treatment of characteristic point.
Further, realizing under scene in aforementioned execution step B1 and step B2, the spy of the first two field picture of step 102 pair
The characteristic point for levying a little He the second two field picture carries out the matching treatment of characteristic point, including：
C1, judge the first two field picture local image characteristics point description son and the second two field picture local image characteristics point
Description son it is whether identical；
If C2, the sub- identical local image characteristics point of presence description, determine corresponding to description from the first two field picture
The pixel of sub- identical local image characteristics point is the first pixel, and phase sub- corresponding to description is determined from the second two field picture
The pixel of same local image characteristics point is the second pixel.
Wherein, whether description that can pass through local image characteristics point in the embodiment of the present invention is identical so that it is determined that going out phase
Mutually the characteristic point of matching, can adopt the Brute Force Matcher characteristic points of OpenCV offers in the embodiment of the present invention
Orchestration and K- neighbours (K-Nearest Neighbors, KNN) algorithm realizing the matching of characteristic point and the matching of deletion error,
The second pixel for determining first pixel and the second two field picture of the first two field picture is successful two pictures of Feature Points Matching
Vegetarian refreshments.
If the 103, characteristic point between the second pixel in the first pixel and the second two field picture in the first two field picture
With success, then the spin matrix and translation vector between the first pixel and the second pixel is calculated.
In embodiments of the present invention, the first two field picture and the second two field picture were shot under aircraft direction at the different frame moment
, there is the characteristic point being mutually matched in the two images, it is assumed that first pixel and the second frame of the first two field picture in the image of side
Second pixel of image is successful two pixels of Feature Points Matching, can calculate the first pixel using figure optimized algorithm
Spin matrix and translation vector between point and the second pixel, wherein, spin matrix and translation vector are used to describe aircraft
The anglec of rotation and translational movement of aircraft when being moved to for the second frame moment from the first frame moment, so as to depict flying for aircraft
Row track.
In some embodiments of the invention, step 103 calculates the spin moment between the first pixel and the second pixel
Battle array and translation vector, including：
D1, the internal reference information for obtaining camera, internal reference information include：The radial distortion parameter of camera and tangential distortion ginseng
Number；
D2, the pixel coordinate and depth value that calculate the first pixel, and the pixel coordinate and depth for calculating the second pixel
Angle value；
D3, by the internal reference information of camera, the pixel coordinate of the first pixel, depth value and characteristic point, the second pixel
Pixel coordinate, depth value and characteristic point be input to figure optimization storehouse, export the first pixel and the second pixel by scheming optimization storehouse
Spin matrix and translation vector between point.
Wherein, obtain the internal reference information of camera, the internal reference information includes the radial distortion parameter of camera and tangential
Distortion parameter, then calculates pixel coordinate and depth value, the pixel coordinate of the second pixel and the depth value of the first pixel, the
The depth value of one pixel refers to the vertical range between the plane and camera at the impact point place of shooting, gets step
Internal reference information, the pixel coordinate of the first pixel and depth value, the pixel coordinate of the second pixel and depth in D1 and step D2
After angle value, reuse figure optimization storehouse (graph-based optimization) and the first pixel and the second picture can be calculated
Spin matrix and translation vector between vegetarian refreshments, such as the figure optimization storehouse are specially g2o storehouses.
104th, according to aircraft the current posture information of present level, spin matrix and the amount of being translated towards calculating aircraft.
In embodiments of the present invention, calculate the spin matrix and translation vector between the first pixel and the second pixel
Afterwards, by spin matrix and translation vector describe aircraft from the first frame moment be moved to for the second frame moment when the aircraft
The anglec of rotation and translational movement, by the spin matrix produced between the two neighboring frame moment and translation vector, working as with reference to aircraft
Front height carries out the pose conversion of real space, can obtain the current posture information of aircraft, and such as pose vector includes：Fly
The attitude angle (such as yaw angle) of the current three-dimensional position of row device (such as the coordinate value on three-dimensional), aircraft.
By description of the above example to the embodiment of the present invention, can be under aircraft in the embodiment of the present invention
Side arranges camera, and the camera carries out captured in real-time, so as to obtain the image at multiple frame moment, for the figure at multiple frame moment
As the feature point detection that can be carried out frame by frame is calculated, when Feature Points Matching success between the pixel in two two field pictures,
By calculating spin matrix and translation vector between the pixel respectively from two two field pictures, working as finally according to aircraft
Front height, spin matrix and the amount of being translated towards calculate the current posture information of aircraft, complete by the current posture information of aircraft
The positioning of aircraft, only needs in the embodiment of the present invention using camera Real-time Collection figure down-set on aircraft in pairs
Picture, obtains the posture information of aircraft by the process and optimization of the image to multiple frame moment, therefore the positioning of aircraft is not
By outdoor indoor context restrictions, the process and optimization of image is with the accurate advantage of calculating.
For ease of being better understood from and implementing the such scheme of the embodiment of the present invention, corresponding application scenarios of illustrating below come
It is specifically described.
Refer to shown in Fig. 2, be the workflow schematic diagram of vision positioning algorithm provided in an embodiment of the present invention, next
Illustrate by taking aircraft specially unmanned plane as an example, based on ORB characteristic points local image characteristics point and the unmanned plane of figure optimization
Vision positioning algorithm workflow includes following process：Unmanned plane is real by the monocular cam collection vertically downward which carries
When image, wherein, camera is met in mathematics aspect vertically downward, and error during installation can be by way of mathematical computations
To adjust image.The ORB characteristic points per two field picture are calculated respectively, and what is do not limited is, it is also possible to using SIFT and SURF characteristic points
Etc., present frame is matched with the characteristic point of the same position of previous frame.Next two are calculated according to the characteristic point for matching
Spin matrix and translation vector between two field picture.Obtain finally according to the current elevation information of unmanned plane and figure optimized algorithm
Spin matrix and translation vector can be calculated the actual anglec of rotation of unmanned plane and shift length.Wherein, spin matrix and
Translation vector can also be separated into two matrixes, it is also possible to a matrix, the height letter of aircraft are made by matrix multiplication
Breath can be obtained by the ultrasonic probe of unmanned plane, barometer etc..Obtain three-dimensional position and the rotation of current time unmanned plane
After angle, it is possible to complete the positioning of unmanned plane.
Next the characteristic point of image used in the embodiment of the present invention is matched and image optimization is carried out illustrating
It is bright, refer to shown in Fig. 3, be the application scenarios schematic diagram of ORB Feature Points Matchings algorithm provided in an embodiment of the present invention.
ORB detects characteristic point using FAST (Features from Accelerated Segment Test) algorithms.
This defines the image intensity value around distinguished point based, detects the pixel value for making a circle in candidate feature point week, if candidate point
Surrounding has enough pixels enough big with the gray value difference of the candidate point in field, then it is assumed that the candidate point is a feature
Point, detects characteristic point using the method for FAST feature point detections, then using the measure of Harris angle points, special from FAST
Levy a little from the maximum N number of characteristic point of Harris angle points response is picked out, Expressive Features are come with BRIEF algorithms after obtaining characteristic point
Point attribute.The output of these attributes is referred to as description of this feature point, and ORB calculates a characteristic point using BRIEF algorithms
Description, it is right that the core concept of BRIEF algorithms chooses N number of point with certain pattern around key point P, this N number of point
To comparative result in combination as description son.The present invention is directly obtained using the ORB feature point extraction functions that OpenCV is provided
Obtain description of ORB characteristic points.
Under 3D scenes, as shown in figure 3, camera 1 obtains pixel coordinate 1 first to characteristic point actual position X shooting images,
Then the image of characteristic point actual position X after camera 1 is moved, is shot, pixel coordinate 2 is obtained, the characteristic point of current frame image is needed
To match with the character pair of previous frame point.As illustrated, two two field pictures that same camera shoots, represent a camera
Displacement, shoot same impact point and obtain two different pixel coordinates, hanging down from characteristic point actual position X to imaging plane
Depth value of the straight distance for pixel.Understand referring to Epipolar geometry, it is have a spin matrix R to match between paired pixel
With the relation of translation vector t, following target is exactly asking for this R and t according to the point for matching.Adopt in the present invention
BruteForceMatcher minutiae matchers that OpenCV is provided and K- nearest neighbor algorithms are realizing the matching and deletion of characteristic point
The matching of mistake.
Next the figure optimized algorithm adopted in introducing the embodiment of the present invention, optimizes the pose of unmanned plane using the method
Information so as to which the result for obtaining can be optimized, reduces the impact of error.One-to-one two in given n two field pictures
Pixel, respectively：
Wherein, N indicates N number of corresponding characteristic point.
Spin matrix R and translation vector t can be solved by below equation：
Wherein, j represents j-th characteristic point in N number of point, and Z represents the two-dimensional coordinate of an image.C is camera internal reference,
λ1And λ2Represent the depth value of two pixels.Traditional solution mode of this problem, is that (X represents actual the X in two equations
The three-dimensional coordinate of certain point of the physical world of observation) eliminate, obtain the relational expression only with respect to z, R and t.In theory, need big
Can just calculate in the match points of 8.But match point is not necessarily accurately mate, due to the presence of various noises, by choosing
Take the match point of more than 8 and resolve equation and just directly obtain the mode of R and t and there is less error.So the embodiment of the present invention
The covariance of their errors can also be optimized to obtain an optimum R and t.Measurement with the presence of error, characteristic point
Be also with the presence of error, therefore the direct solution R and t that obtained by way of equation group be comprising error inside.Base
In above reason, using the principle of least square method, the covariance formula of error is set up, then seek that cause covariance minimum
Group R and t, here it is optimal solution.Its formula is as follows：
Used in embodiment, General Graph Optimization (g2o) come real in this figure optimization storehouse in the present invention
It is existing.Only need to the positional information current matching good ORB characteristic points office, the match information between characteristic point, vertical camera away from
The height λ on ground1And λ2And in camera internal reference input g2o storehouses.The linear equation solver CHOLDMOD that g2o is provided is selected just
R and t can be obtained.During input G2O storehouses, input feature vector point, construction feature to be come according to the Feature Points Matching pair of two interframe of in front and back
Constraint diagram between point, the covariance formula before setting us using G2O is asking for its optimal solution.
By aforesaid illustration, in the embodiment of the present invention, unmanned plane camera needs real-time image acquisition, root
The posture information of unmanned plane is calculated according to the change of frame before and after image, posture information includes：Three-dimensional position (X, Y, Z), while
Including the attitude angle of unmanned plane, the error of pose estimation is reduced using the mode of figure optimization.
It should be noted that for aforesaid each method embodiment, in order to be briefly described, therefore which is all expressed as a series of
Combination of actions, but those skilled in the art should know, the present invention do not limited by described sequence of movement because
According to the present invention, some steps can adopt other orders or while carry out.Secondly, those skilled in the art should also know
Know, embodiment described in this description belongs to preferred embodiment, involved action and module are not necessarily of the invention
It is necessary.
For ease of the such scheme for preferably implementing the embodiment of the present invention, it is also provided below for implementing the phase of such scheme
Close device.
Refer to shown in Fig. 4-a, a kind of positioner 400 of aircraft provided in an embodiment of the present invention can include：It is special
Levy a detection module 401, Feature Points Matching module 402, rotation and translate computing module 403, pose computing module 404, wherein,
Feature point detection module 401, for the figure obtained to the camera captured in real-time downward of aircraft configuration
As the detection for carrying out characteristic point respectively is calculated, the characteristic point of the characteristic point and the second two field picture of the first two field picture is obtained, described the
One two field picture and second two field picture are that adjacent two frame shoots the image for obtaining respectively；
Feature Points Matching module 402, for the characteristic point to first two field picture and the feature of second two field picture
Point carries out the matching treatment of characteristic point；
Rotation and translation computing module 403, if for the first pixel in first two field picture and second frame
Feature Points Matching success between the second pixel in image, then calculate between first pixel and second pixel
Spin matrix and translation vector；
Pose computing module 404, for according to the present level of the aircraft, the spin matrix and being translated towards gauge
Calculate the current posture information of the aircraft.
In some embodiments of the invention, refer to shown in Fig. 4-b, the positioner 400 of the aircraft also includes：
Image pre-processing module 405, wherein,
Described image pretreatment module 405, for the feature point detection module 401 to aircraft configuration downward
The image that obtains of camera captured in real-time carry out the detection of characteristic point respectively and calculate, obtain the characteristic point and the of the first two field picture
Before the characteristic point of two two field pictures, process is zoomed in and out respectively to the image that the camera captured in real-time is obtained；At scaling
Image after reason is converted to gray-scale map, and carries out equalization processing to the gray-scale map；
The feature point detection module 401, specifically for carrying out characteristic point respectively to the gray-scale map after equalization processing
Detection is calculated, and obtains the characteristic point of the characteristic point and the second two field picture of the first two field picture.
In some embodiments of the invention, the feature point detection module 401, specifically for when the camera is the
The local image characteristics point of first two field picture after one frame moment shot the first two field picture for obtaining, is detected, and calculates institute
State description of the local image characteristics point of the first two field picture；When the camera shoots the second frame for obtaining at the second frame moment
The local image characteristics point of second two field picture after image, is detected, and it is special to calculate the topography of second two field picture
Description a little is levied, the first frame moment and the second frame moment are the adjacent two frame moment.
In some embodiments of the invention, refer to shown in Fig. 4-c, the Feature Points Matching module 401, including：
Sub- judge module 4011 is described, for judging description and the institute of the local image characteristics point of first two field picture
Whether description for stating the local image characteristics point of the second two field picture is identical；
Pixel searching modul 4012, if for there is the sub- identical local image characteristics point of description, from described first
Determine in two field picture that the pixel corresponding to the sub- identical local image characteristics point of the description is the first pixel, from described
Determine in second two field picture that corresponding to the pixel for describing sub- identical local image characteristics point be the second pixel.
In some embodiments of the invention, refer to shown in Fig. 4-c, it is described to rotate and translate computing module 403, bag
Include：
Internal reference acquisition module 4031, for obtaining the internal reference information of the camera, the internal reference information includes：It is described to take the photograph
As the radial distortion parameter and tangential distortion parameter of head；
Pixel computing module 4032, for calculating the pixel coordinate and depth value of first pixel, and calculates
The pixel coordinate and depth value of second pixel；
Figure optimization module 4033, for by the internal reference information of the camera, the pixel coordinate of first pixel, depth
Angle value and characteristic point, the pixel coordinate of second pixel, depth value and characteristic point are input to figure optimization storehouse, by the figure
Optimization storehouse exports spin matrix and translation vector between first pixel and second pixel.
Description by more than to the embodiment of the present invention, can be arranged in the lower section of aircraft in the embodiment of the present invention
Camera, the camera carry out captured in real-time, so as to obtain the image at multiple frame moment, for the image at multiple frame moment all may be used
Calculated with the feature point detection for carrying out frame by frame, when Feature Points Matching success between the pixel in two two field pictures, by meter
Calculate respectively from the spin matrix and translation vector between the pixel of two two field pictures, finally according to the current height of aircraft
Degree, spin matrix and the amount of being translated towards calculate the current posture information of aircraft, complete right by the current posture information of aircraft
The positioning of aircraft, only needs in the embodiment of the present invention using camera real-time image acquisition down-set on aircraft, leads to
The process and optimization for crossing the image to multiple frame moment obtains the posture information of aircraft, therefore the positioning of aircraft not by outdoor
Indoor context restrictions, the process and optimization of image is with the accurate advantage of calculating.
Fig. 5 is a kind of structural representation of aircraft provided in an embodiment of the present invention, the aircraft 1100 can because of configuration or
Performance is different and the larger difference of producing ratio, can include one or more central processing units (central
Processing units, CPU) 1122 (for example, one or more processors) and memory 1132, one or one with
It is upper storage application program 1142 or data 1144 storage medium 1130 (such as one or more mass memory units), take the photograph
Picture 1152, sensor 1162.Wherein, memory 1132 and storage medium 1130 can be of short duration storage or persistently store.Deposit
Storage can include one or more modules (diagram is not marked) in the program of storage medium 1130, and each module can include
Series of instructions in aircraft is operated.Further, central processing unit 1122 could be arranged to and storage medium 1130
Communication, performs the series of instructions operation in storage medium 1130 on aircraft 1100.It will be understood by those skilled in the art that
The Flight Vehicle Structure illustrated in Fig. 5 does not constitute the restriction to aircraft, can include than illustrating more or less of part, or
Person combines some parts, or different part arrangements.
Aircraft 1100 can also include one or more power supplys 1126, one or more radio network interfaces
1150, one or more input/output interfaces 1158, and/or, one or more operating systems 1141, such as Android
System etc..
The camera 1152 that aircraft includes, the camera can be specifically that digital camera, or simulation are taken the photograph
As head, camera 1152 are specially binocular camera, the resolution ratio of camera can be selected according to actual needs, camera
Construction package can include：Camera lens, imageing sensor can be configured with reference to concrete scene.
Aircraft can also include：Sensor 1162, such as motion sensor and other sensors.Specifically, as
One kind of motion sensor, the size of (generally three axles) acceleration in the detectable all directions of accelerometer sensor, when static
Can detect that size and the direction of gravity, can be used for recognize attitude of flight vehicle application (such as vehicle yaw angle, roll angle,
The measuring and calculating of the angle of pitch, magnetometer pose calibrating), identification correlation function etc.；The gyroscope that can also configure as aircraft, air pressure
The other sensors such as meter, hygrometer, thermometer, infrared ray sensor, will not be described here.
The localization method step of the aircraft in above-described embodiment by performed by aircraft can be based on flying shown in the Fig. 5
Row device structure.
In addition it should be noted that, device embodiment described above is only schematic, wherein described as separating
The unit of part description can be or may not be it is physically separate, as the part that unit shows can be or
Can not be physical location, you can local to be located at one, or can also be distributed on multiple NEs.Can be according to reality
The needing of border selects some or all of module therein to realize the purpose of this embodiment scheme.In addition, what the present invention was provided
In device embodiment accompanying drawing, the annexation between module is represented, specifically can be implemented as one
Bar or a plurality of communication bus or holding wire.Those of ordinary skill in the art are not in the case where creative work is paid, you can with
Understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that the present invention can be borrowed
Software is helped to add the mode of required common hardware to realize, naturally it is also possible to include special IC, specially by specialized hardware
Realized with CPU, private memory, special components and parts etc..Generally, all functions of being completed by computer program can
Easily with corresponding hardware realizing, and, for realizing that the particular hardware structure of same function can also be various many
Sample, such as analog circuit, digital circuit or special circuit etc..But, it is more for the purpose of the present invention in the case of software program reality
It is now more preferably embodiment.Based on such understanding, technical scheme is substantially made to prior art in other words
The part of contribution can be embodied in the form of software product, and the computer software product is stored in the storage medium that can read
In, floppy disk, USB flash disk such as computer, portable hard drive, read-only storage (ROM, Read-Only Memory), random access memory
Device (RAM, Random Access Memory), magnetic disc or CD etc., use so that a computer sets including some instructions
Standby (can be personal computer, server, or network equipment etc.) performs the method described in each embodiment of the invention.
In sum, above example is only to illustrate technical scheme, rather than a limitation；Although with reference to upper
State embodiment to be described in detail the present invention, it will be understood by those within the art that：Which still can be to upper
State the technical scheme described in each embodiment to modify, or equivalent is carried out to which part technical characteristic；And these
Modification is replaced, and does not make the essence of appropriate technical solution depart from the spirit and scope of various embodiments of the present invention technical scheme.
Claims (10)
1. a kind of localization method of aircraft, it is characterised in that include：
The detection for carrying out characteristic point to the image that the camera captured in real-time downward of aircraft configuration is obtained respectively is calculated,
The characteristic point of the characteristic point and the second two field picture of the first two field picture is obtained, first two field picture and second two field picture are phases
Adjacent two frames shoot the image for obtaining respectively；
The characteristic point of characteristic point and second two field picture to first two field picture carries out the matching treatment of characteristic point；
If characteristic point between the second pixel in the first pixel and second two field picture in first two field picture
With success, then the spin matrix and translation vector between first pixel and second pixel is calculated；
Present level, the spin matrix and the amount of being translated towards according to the aircraft calculates the current pose letter of the aircraft
Breath.
2. method according to claim 1, it is characterised in that the camera reality downward to aircraft configuration
When shoot the image that obtains and carry out the detection of characteristic point respectively and calculate, obtain the characteristic point and the second two field picture of the first two field picture
Before characteristic point, methods described also includes：
Process is zoomed in and out respectively to the image that the camera captured in real-time is obtained；
Image after scaling is processed is converted to gray-scale map, and carries out equalization processing to the gray-scale map；
The image that the camera captured in real-time downward to aircraft configuration is obtained carries out the detection of characteristic point respectively
Calculate, obtain the characteristic point of the characteristic point and the second two field picture of the first two field picture, including：
The detection for carrying out characteristic point to the gray-scale map after equalization processing respectively is calculated, and obtains the characteristic point and the of the first two field picture
The characteristic point of two two field pictures.
3. method according to claim 1, it is characterised in that the camera reality downward to aircraft configuration
When shoot the image that obtains and carry out the detection of characteristic point respectively and calculate, obtain the characteristic point and the second two field picture of the first two field picture
Characteristic point, including：
After the camera shoots the first two field picture for obtaining at the first frame moment, the local of first two field picture is detected
Image characteristic point, and calculate description of the local image characteristics point of first two field picture；
After the camera shoots the second two field picture for obtaining at the second frame moment, the local of second two field picture is detected
Image characteristic point, and calculate description of the local image characteristics point of second two field picture, the first frame moment and described
Second frame moment was the adjacent two frame moment.
4. method according to claim 3, it is characterised in that the characteristic point and described to first two field picture
The characteristic point of two two field pictures carries out the matching treatment of characteristic point, including：
Judge the local image characteristics of sub and described second two field picture of description of the local image characteristics point of first two field picture
Whether description of point is identical；
If there is the sub- identical local image characteristics point of description, determine corresponding to the description from first two field picture
The pixel of sub- identical local image characteristics point is the first pixel, is determined corresponding to described from second two field picture
The pixel for describing sub- identical local image characteristics point is the second pixel.
5. method according to any one of claim 1 to 4, it is characterised in that the calculating first pixel and
Spin matrix and translation vector between second pixel, including：
The internal reference information of the camera is obtained, the internal reference information includes：The radial distortion parameter of the camera and tangential
Distortion parameter；
Calculate the pixel coordinate and depth value of first pixel, and the pixel coordinate and depth for calculating second pixel
Angle value；
By the internal reference information of the camera, the pixel coordinate of first pixel, depth value and characteristic point, second picture
The pixel coordinate of vegetarian refreshments, depth value and characteristic point are input to figure optimization storehouse, optimize storehouse by the figure and export first pixel
Spin matrix and translation vector between point and second pixel.
6. a kind of positioner of aircraft, it is characterised in that include：
Feature point detection module, for entering to the image that the camera captured in real-time downward of aircraft configuration is obtained respectively
The detection of row characteristic point is calculated, and obtains the characteristic point of the characteristic point and the second two field picture of the first two field picture, first two field picture
It is that adjacent two frame shoots the image that obtains respectively with second two field picture；
Feature Points Matching module, for carrying out spy to the characteristic point of the characteristic point of first two field picture and second two field picture
Levy matching treatment a little；
Rotation and translation computing module, if in the first pixel in first two field picture and second two field picture
Feature Points Matching success between second pixel, then calculate the spin moment between first pixel and second pixel
Battle array and translation vector；
Pose computing module, described in being calculated according to the present level of the aircraft, the spin matrix and the amount of being translated towards
The current posture information of aircraft.
7. device according to claim 6, it is characterised in that the positioner of the aircraft also includes：Image is located in advance
Reason module, wherein,
Described image pretreatment module, for camera reality downward of the feature point detection module to aircraft configuration
When shoot the image that obtains and carry out the detection of characteristic point respectively and calculate, obtain the characteristic point and the second two field picture of the first two field picture
Before characteristic point, process is zoomed in and out respectively to the image that the camera captured in real-time is obtained；Image after scaling is processed
Gray-scale map is converted to, and equalization processing is carried out to the gray-scale map；
The feature point detection module, the detection meter specifically for carrying out characteristic point to the gray-scale map after equalization processing respectively
Calculate, obtain the characteristic point of the characteristic point and the second two field picture of the first two field picture.
8. device according to claim 6, it is characterised in that the feature point detection module, specifically for described taking the photograph
As head is after the first frame moment shot the first two field picture for obtaining, the local image characteristics point of first two field picture is detected,
And calculate description of the local image characteristics point of first two field picture；Obtain when the camera was shot at the second frame moment
The second two field picture after, detect the local image characteristics point of second two field picture, and calculate the office of second two field picture
Description of portion's image characteristic point, the first frame moment and the second frame moment are the adjacent two frame moment.
9. device according to claim 8, it is characterised in that the Feature Points Matching module, including：
Sub- judge module is described, sub and described second frame of the description for judging the local image characteristics point of first two field picture
Whether description of the local image characteristics point of image is identical；
Pixel searching modul, if for there is the sub- identical local image characteristics point of description, from first two field picture
Determine that corresponding to the pixel for describing sub- identical local image characteristics point be the first pixel, from the second frame figure
Determine that corresponding to the pixel for describing sub- identical local image characteristics point be the second pixel as in.
10. the device according to any one of claim 6 to 9, it is characterised in that the rotation and translation computing module,
Including：
Internal reference acquisition module, for obtaining the internal reference information of the camera, the internal reference information includes：The footpath of the camera
To distortion parameter and tangential distortion parameter；
Pixel computing module, for calculating the pixel coordinate and depth value of first pixel, and calculates described second
The pixel coordinate and depth value of pixel；
Figure optimization module, for by the internal reference information of the camera, the pixel coordinate of first pixel, depth value and spy
Levy point, the pixel coordinate of second pixel, depth value and characteristic point and be input to figure optimization storehouse, storehouse is optimized by the figure defeated
The spin matrix gone out between first pixel and second pixel and translation vector.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611044625.3A CN106529538A (en) | 2016-11-24 | 2016-11-24 | Method and device for positioning aircraft |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611044625.3A CN106529538A (en) | 2016-11-24 | 2016-11-24 | Method and device for positioning aircraft |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106529538A true CN106529538A (en) | 2017-03-22 |
Family
ID=58356829
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611044625.3A Pending CN106529538A (en) | 2016-11-24 | 2016-11-24 | Method and device for positioning aircraft |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106529538A (en) |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107289910A (en) * | 2017-05-22 | 2017-10-24 | 上海交通大学 | A kind of light stream alignment system based on TOF |
| CN107292929A (en) * | 2017-05-08 | 2017-10-24 | 深圳市唯内德软件开发有限公司 | Low-power consumption characteristic point image position method and device |
| CN108335329A (en) * | 2017-12-06 | 2018-07-27 | 腾讯科技（深圳）有限公司 | Applied to the method for detecting position and device, aircraft in aircraft |
| CN108444468A (en) * | 2018-02-06 | 2018-08-24 | 浙江大学 | The bearing compass of vision and inertial navigation information is regarded under a kind of fusion |
| CN108496352A (en) * | 2017-05-24 | 2018-09-04 | 深圳市大疆创新科技有限公司 | Image pickup method and device, image processing method and device |
| CN108713179A (en) * | 2017-09-18 | 2018-10-26 | 深圳市大疆创新科技有限公司 | Mobile article body controlling means, equipment and system |
| CN108804161A (en) * | 2018-06-21 | 2018-11-13 | 北京字节跳动网络技术有限公司 | Initial method, device, terminal and the storage medium of application |
| WO2018205803A1 (en) * | 2017-05-09 | 2018-11-15 | 北京京东尚科信息技术有限公司 | Pose estimation method and apparatus |
| CN108932737A (en) * | 2018-06-15 | 2018-12-04 | 深圳地平线机器人科技有限公司 | In-vehicle camera pitch angle scaling method and device, electronic equipment and vehicle |
| CN109073385A (en) * | 2017-12-20 | 2018-12-21 | 深圳市大疆创新科技有限公司 | A kind of localization method and aircraft of view-based access control model |
| CN109211185A (en) * | 2017-06-30 | 2019-01-15 | 北京臻迪科技股份有限公司 | A kind of flight equipment, the method and device for obtaining location information |
| WO2019019132A1 (en) * | 2017-07-28 | 2019-01-31 | Qualcomm Incorporated | Image output adjustment in a robotic vehicle |
| CN109523570A (en) * | 2017-09-20 | 2019-03-26 | 杭州海康威视数字技术股份有限公司 | Beginning parameter transform model method and device |
| CN109739254A (en) * | 2018-11-20 | 2019-05-10 | 国网浙江省电力有限公司信息通信分公司 | Using the unmanned plane and its localization method of visual pattern positioning in a kind of electric inspection process |
| CN109782012A (en) * | 2018-12-29 | 2019-05-21 | 中国电子科技集团公司第二十研究所 | A kind of speed-measuring method based on photoelectric image feature association |
| CN110337668A (en) * | 2018-04-27 | 2019-10-15 | 深圳市大疆创新科技有限公司 | Image stability augmentation method and apparatus |
| CN110717937A (en) * | 2019-09-29 | 2020-01-21 | 深圳市图郅创新科技有限公司 | Image correction method and system, electronic device and storable medium |
| CN110728245A (en) * | 2019-10-17 | 2020-01-24 | 珠海格力电器股份有限公司 | Optimization method and device for VSLAM front-end processing, electronic equipment and storage medium |
| CN110858403A (en) * | 2018-08-22 | 2020-03-03 | 杭州萤石软件有限公司 | Method for determining scale factor in monocular vision reconstruction and mobile robot |
| CN111176307A (en) * | 2019-12-24 | 2020-05-19 | 广州极飞科技有限公司 | Control method and device for unmanned aerial vehicle, unmanned aerial vehicle and storage medium |
| CN111540016A (en) * | 2020-04-27 | 2020-08-14 | 深圳南方德尔汽车电子有限公司 | Pose calculation method and device based on image feature matching, computer equipment and storage medium |
| WO2020259481A1 (en) * | 2019-06-27 | 2020-12-30 | Oppo广东移动通信有限公司 | Positioning method and apparatus, electronic device, and readable storage medium |
| CN112907662A (en) * | 2021-01-28 | 2021-06-04 | 北京三快在线科技有限公司 | Feature extraction method and device, electronic equipment and storage medium |
| CN112987764A (en) * | 2021-02-01 | 2021-06-18 | 鹏城实验室 | Landing method, landing device, unmanned aerial vehicle and computer-readable storage medium |
| WO2021139583A1 (en) * | 2020-01-07 | 2021-07-15 | 影石创新科技股份有限公司 | Panoramic video rendering method capable of automatically adjusting angle of view, and storage medium and computer device |
| CN113342055A (en) * | 2021-06-30 | 2021-09-03 | 广州极飞科技股份有限公司 | Unmanned aerial vehicle flight control method and device, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102435188A (en) * | 2011-09-15 | 2012-05-02 | 南京航空航天大学 | Monocular vision/inertia autonomous navigation method for indoor environment |
| CN104154910A (en) * | 2014-07-22 | 2014-11-19 | 清华大学 | Indoor micro unmanned aerial vehicle location method |
| CN104615146A (en) * | 2015-02-05 | 2015-05-13 | 广州快飞计算机科技有限公司 | Unmanned aerial vehicle spraying operation automatic navigation method without need of external navigation signal |
-
2016
- 2016-11-24 CN CN201611044625.3A patent/CN106529538A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102435188A (en) * | 2011-09-15 | 2012-05-02 | 南京航空航天大学 | Monocular vision/inertia autonomous navigation method for indoor environment |
| CN104154910A (en) * | 2014-07-22 | 2014-11-19 | 清华大学 | Indoor micro unmanned aerial vehicle location method |
| CN104615146A (en) * | 2015-02-05 | 2015-05-13 | 广州快飞计算机科技有限公司 | Unmanned aerial vehicle spraying operation automatic navigation method without need of external navigation signal |
Cited By (42)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107292929A (en) * | 2017-05-08 | 2017-10-24 | 深圳市唯内德软件开发有限公司 | Low-power consumption characteristic point image position method and device |
| WO2018205803A1 (en) * | 2017-05-09 | 2018-11-15 | 北京京东尚科信息技术有限公司 | Pose estimation method and apparatus |
| CN107289910B (en) * | 2017-05-22 | 2020-06-19 | 上海交通大学 | Optical flow positioning system based on TOF |
| CN107289910A (en) * | 2017-05-22 | 2017-10-24 | 上海交通大学 | A kind of light stream alignment system based on TOF |
| CN108496352B (en) * | 2017-05-24 | 2021-02-09 | 深圳市大疆创新科技有限公司 | Shooting method and device, image processing method and device |
| CN108496352A (en) * | 2017-05-24 | 2018-09-04 | 深圳市大疆创新科技有限公司 | Image pickup method and device, image processing method and device |
| CN109211185A (en) * | 2017-06-30 | 2019-01-15 | 北京臻迪科技股份有限公司 | A kind of flight equipment, the method and device for obtaining location information |
| CN110998235A (en) * | 2017-07-28 | 2020-04-10 | 高通股份有限公司 | Image output adjustment in a robotic vehicle |
| CN110998235B (en) * | 2017-07-28 | 2024-03-01 | 高通股份有限公司 | Image output adjustment in robotic vehicles |
| US11244468B2 (en) | 2017-07-28 | 2022-02-08 | Qualcomm Incorporated | Image output adjustment in a robotic vehicle |
| WO2019019132A1 (en) * | 2017-07-28 | 2019-01-31 | Qualcomm Incorporated | Image output adjustment in a robotic vehicle |
| CN108713179A (en) * | 2017-09-18 | 2018-10-26 | 深圳市大疆创新科技有限公司 | Mobile article body controlling means, equipment and system |
| CN109523570A (en) * | 2017-09-20 | 2019-03-26 | 杭州海康威视数字技术股份有限公司 | Beginning parameter transform model method and device |
| CN109523570B (en) * | 2017-09-20 | 2021-01-22 | 杭州海康威视数字技术股份有限公司 | Motion parameter calculation method and device |
| CN108335329B (en) * | 2017-12-06 | 2021-09-10 | 腾讯科技（深圳）有限公司 | Position detection method and device applied to aircraft and aircraft |
| CN108335329A (en) * | 2017-12-06 | 2018-07-27 | 腾讯科技（深圳）有限公司 | Applied to the method for detecting position and device, aircraft in aircraft |
| CN109073385A (en) * | 2017-12-20 | 2018-12-21 | 深圳市大疆创新科技有限公司 | A kind of localization method and aircraft of view-based access control model |
| CN108444468A (en) * | 2018-02-06 | 2018-08-24 | 浙江大学 | The bearing compass of vision and inertial navigation information is regarded under a kind of fusion |
| WO2019205087A1 (en) * | 2018-04-27 | 2019-10-31 | 深圳市大疆创新科技有限公司 | Image stabilization method and device |
| CN110337668B (en) * | 2018-04-27 | 2021-08-31 | 深圳市大疆创新科技有限公司 | Image stability augmentation method and device |
| CN110337668A (en) * | 2018-04-27 | 2019-10-15 | 深圳市大疆创新科技有限公司 | Image stability augmentation method and apparatus |
| CN108932737B (en) * | 2018-06-15 | 2021-02-26 | 深圳地平线机器人科技有限公司 | Vehicle-mounted camera pitch angle calibration method and device, electronic equipment and vehicle |
| CN108932737A (en) * | 2018-06-15 | 2018-12-04 | 深圳地平线机器人科技有限公司 | In-vehicle camera pitch angle scaling method and device, electronic equipment and vehicle |
| CN108804161A (en) * | 2018-06-21 | 2018-11-13 | 北京字节跳动网络技术有限公司 | Initial method, device, terminal and the storage medium of application |
| CN108804161B (en) * | 2018-06-21 | 2022-03-04 | 北京字节跳动网络技术有限公司 | Application initialization method, device, terminal and storage medium |
| CN110858403A (en) * | 2018-08-22 | 2020-03-03 | 杭州萤石软件有限公司 | Method for determining scale factor in monocular vision reconstruction and mobile robot |
| CN109739254A (en) * | 2018-11-20 | 2019-05-10 | 国网浙江省电力有限公司信息通信分公司 | Using the unmanned plane and its localization method of visual pattern positioning in a kind of electric inspection process |
| CN109739254B (en) * | 2018-11-20 | 2021-11-09 | 国网浙江省电力有限公司信息通信分公司 | Unmanned aerial vehicle adopting visual image positioning in power inspection and positioning method thereof |
| CN109782012A (en) * | 2018-12-29 | 2019-05-21 | 中国电子科技集团公司第二十研究所 | A kind of speed-measuring method based on photoelectric image feature association |
| WO2020259481A1 (en) * | 2019-06-27 | 2020-12-30 | Oppo广东移动通信有限公司 | Positioning method and apparatus, electronic device, and readable storage medium |
| CN110717937A (en) * | 2019-09-29 | 2020-01-21 | 深圳市图郅创新科技有限公司 | Image correction method and system, electronic device and storable medium |
| CN110728245A (en) * | 2019-10-17 | 2020-01-24 | 珠海格力电器股份有限公司 | Optimization method and device for VSLAM front-end processing, electronic equipment and storage medium |
| CN111176307A (en) * | 2019-12-24 | 2020-05-19 | 广州极飞科技有限公司 | Control method and device for unmanned aerial vehicle, unmanned aerial vehicle and storage medium |
| CN111176307B (en) * | 2019-12-24 | 2023-09-01 | 广州极飞科技股份有限公司 | Method and device for controlling unmanned aerial vehicle, unmanned aerial vehicle and computer storage medium |
| WO2021139583A1 (en) * | 2020-01-07 | 2021-07-15 | 影石创新科技股份有限公司 | Panoramic video rendering method capable of automatically adjusting angle of view, and storage medium and computer device |
| CN111540016A (en) * | 2020-04-27 | 2020-08-14 | 深圳南方德尔汽车电子有限公司 | Pose calculation method and device based on image feature matching, computer equipment and storage medium |
| CN111540016B (en) * | 2020-04-27 | 2023-11-10 | 深圳南方德尔汽车电子有限公司 | Pose calculation method and device based on image feature matching, computer equipment and storage medium |
| CN112907662A (en) * | 2021-01-28 | 2021-06-04 | 北京三快在线科技有限公司 | Feature extraction method and device, electronic equipment and storage medium |
| CN112907662B (en) * | 2021-01-28 | 2022-11-04 | 北京三快在线科技有限公司 | Feature extraction method and device, electronic equipment and storage medium |
| CN112987764A (en) * | 2021-02-01 | 2021-06-18 | 鹏城实验室 | Landing method, landing device, unmanned aerial vehicle and computer-readable storage medium |
| CN112987764B (en) * | 2021-02-01 | 2024-02-20 | 鹏城实验室 | Landing method, landing device, unmanned aerial vehicle and computer-readable storage medium |
| CN113342055A (en) * | 2021-06-30 | 2021-09-03 | 广州极飞科技股份有限公司 | Unmanned aerial vehicle flight control method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106529538A (en) | Method and device for positioning aircraft | |
| Zhao et al. | Detection, tracking, and geolocation of moving vehicle from uav using monocular camera | |
| CN109974693B (en) | Unmanned aerial vehicle positioning method and device, computer equipment and storage medium | |
| CN110070615B (en) | Multi-camera cooperation-based panoramic vision SLAM method | |
| CN106529495A (en) | Obstacle detection method of aircraft and device | |
| CN106339006B (en) | A kind of method for tracking target and device of aircraft | |
| CN108711166A (en) | A kind of monocular camera Scale Estimation Method based on quadrotor drone | |
| CN107808407A (en) | Unmanned plane vision SLAM methods, unmanned plane and storage medium based on binocular camera | |
| CN111126304A (en) | Augmented reality navigation method based on indoor natural scene image deep learning | |
| CN105955308A (en) | Aircraft control method and device | |
| CN109961497A (en) | Real-time three-dimensional method for reconstructing based on unmanned plane image | |
| CN110334701B (en) | Data acquisition method based on deep learning and multi-vision in digital twin environment | |
| CN107560592B (en) | Precise distance measurement method for photoelectric tracker linkage target | |
| CN115439424A (en) | Intelligent detection method for aerial video image of unmanned aerial vehicle | |
| CN113850126A (en) | Target detection and three-dimensional positioning method and system based on unmanned aerial vehicle | |
| CN109214254B (en) | Method and device for determining displacement of robot | |
| CN114022560A (en) | Calibration method and related device and equipment | |
| CN111899345B (en) | Three-dimensional reconstruction method based on 2D visual image | |
| CN106250898B (en) | A kind of image local area feature extracting method based on scale prediction | |
| CN111583342B (en) | Target rapid positioning method and device based on binocular vision | |
| CN114219855A (en) | Point cloud normal vector estimation method and device, computer equipment and storage medium | |
| Müller et al. | Squeezeposenet: Image based pose regression with small convolutional neural networks for real time uas navigation | |
| CN108320310A (en) | Extraterrestrial target 3 d pose method of estimation based on image sequence | |
| Koizumi et al. | Development of attitude sensor using deep learning | |
| CN117115252A (en) | Bionic ornithopter space pose estimation method based on vision |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170322 |
|
| RJ01 | Rejection of invention patent application after publication |