CN102201115A - Real-time panoramic image stitching method of aerial videos shot by unmanned plane - Google Patents
Real-time panoramic image stitching method of aerial videos shot by unmanned plane Download PDFInfo
- Publication number
- CN102201115A CN102201115A CN2011100855966A CN201110085596A CN102201115A CN 102201115 A CN102201115 A CN 102201115A CN 2011100855966 A CN2011100855966 A CN 2011100855966A CN 201110085596 A CN201110085596 A CN 201110085596A CN 102201115 A CN102201115 A CN 102201115A
- Authority
- CN
- China
- Prior art keywords
- frame
- image
- unmanned plane
- panorama
- match
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 88
- 230000009466 transformation Effects 0.000 claims abstract description 54
- 238000001514 detection method Methods 0.000 claims abstract description 10
- 230000008569 process Effects 0.000 claims abstract description 9
- 230000004927 fusion Effects 0.000 claims abstract description 8
- 239000011159 matrix material Substances 0.000 claims description 31
- 230000008878 coupling Effects 0.000 claims description 19
- 238000010168 coupling process Methods 0.000 claims description 19
- 238000005859 coupling reaction Methods 0.000 claims description 19
- 238000006243 chemical reaction Methods 0.000 claims description 18
- 230000005540 biological transmission Effects 0.000 claims description 14
- 238000005516 engineering process Methods 0.000 claims description 12
- 239000004744 fabric Substances 0.000 claims description 10
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 claims description 9
- 230000000007 visual effect Effects 0.000 claims description 9
- 230000008901 benefit Effects 0.000 claims description 7
- 230000000903 blocking effect Effects 0.000 claims description 6
- 230000002708 enhancing effect Effects 0.000 claims description 6
- 238000005304 joining Methods 0.000 claims description 6
- 230000007704 transition Effects 0.000 claims description 6
- 238000009825 accumulation Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 238000002156 mixing Methods 0.000 claims description 4
- 238000007667 floating Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 239000000779 smoke Substances 0.000 claims description 3
- 238000005728 strengthening Methods 0.000 claims description 3
- 238000013519 translation Methods 0.000 claims description 3
- 230000001186 cumulative effect Effects 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 7
- 238000010276 construction Methods 0.000 abstract 1
- 230000033001 locomotion Effects 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 239000000443 aerosol Substances 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000009877 rendering Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
Images
Landscapes
- Image Processing (AREA)
- Studio Circuits (AREA)
Abstract
The invention discloses a real-time panoramic image stitching method of aerial videos shot by an unmanned plane. The method comprises the steps of: utilizing a video acquisition card to acquire images which are transmitted to a base station in real time by an unmanned plane through microwave channels, carrying out key frame selection on an image sequence, and carrying out image enhancement on key frames; in the image splicing process, firstly carrying out characteristic detection and interframe matching on image frames by adopting an SURF (speeded up robust features) detection method with good robustness; then reducing the series-multiplication accumulative errors of images in a frame-to-mosaic image transformation mode, determining images which are not adjacent in time sequence but adjacent in space on a flight path according to the GPS (global positioning system) position information of the unmanned plane, optimizing the frame-to-mosaic transformation relation, determining image overlapping areas, thereby realizing image fusion and the panoramic image construction and realizing real-time effect of carrying out flying and stitching simultaneously; and in image transformation, based on adjacent frame information in a vision field and adjacent frame information in airspace, optimizing image transformation to obtain the accurate panoramic images. The stitching method has good real-time performance, is fast and accurate and meets the requirements of application occasions in multiple fields.
Description
Technical field
The present invention relates to the splicing of video image panorama sketch, relate in particular to the unmanned plane that adopts modern video scene splicing the to combine real-time video Panoramagram montage method of taking photo by plane with UAV Flight Control System.
Background technology
In recent years, along with the development of technology such as automatic control, wireless transmission, unmanned plane all develops rapidly on military, civilian.Carry out video capture by unmanned plane lift-launch video camera and brought into play huge effect at aspects such as military surveillance, advertisement photography, the condition of a disaster judgements.But,, often comprise the full detail of whole scene in the video of whole flight course, and the information of single-frame images is very limited, thereby has been born the video image splicing owing to always exist difference between the coverage of video camera and the resolution.The video image splicing is that video sequence image is converted into the panoramic picture that a width of cloth comprises the wide visual angle, big visual field of these all information of sequence, has solved the problem that the shooting angle that exists because of picture pick-up device restriction is little, can't panorama observe.
Owing to far and vertically take over the ground apart from ground when unmanned plane during flying is taken, therefore can reasonably image be assumed to be by optical axis camera shooting parallel to each other and obtain, only there is shift transformation between the image.Practitioner Heung-Yeung Shum (Heung Yeung Shum is arranged the nineties in 20th century, Rendering with concentric mosaics.Proceeding of SIGGRAPH ' 99, Los Angeles, California:1999.8-13) (be translated into: the concentric circles view rendering) propose concentric mosaic, investigative technique is ripe relatively at present, splicing effect is also better, has obtained being extensive use of.But this method is based on the particular camera motion, and promptly camera need be fixed on captured scenery center with tripod, obviously is not suitable for our unmanned airborne camera video image mosaic.Other has practitioner D.Lowe (Matthew Brown, David G.Lowe, Automatic Panoramic Image Stitching using Invariant Features, IJCV 2007) (being translated into: adopt the automatic panoramic picture splicing of unchangeability feature) for the iPhone mobile phones design of Apple Autostitch scene image splicing system, its key step is: 1, adopt the SIFT method to carry out the feature detection of picture frame; 2, adopt the k-d tree to carry out adjacent image frame search and Feature Points Matching; 3, the list that utilizes matching result to adopt the RANSAC method to carry out between the image should calculate; 4, all images is bundled adjustment, optimize the position of two field picture in panorama; 5, multiband image co-registration.
In addition, the image panorama of comparative maturity splicing software also have Hugin (http://hugin.sf.net.) and autopano-sift (
Http:// user.cs.tu-berlin.de/～nowozin/autopano-sift/index.html). its main thought is similar with Autositch.The subject matter that exists has: 1, these joining methods all are that the image set that has obtained is spliced, can't realize the effect that unmanned plane splices while flying, 2, the less scene of all only suitable image set number of these softwares is recovered, can't handle the very long image sequence of sequential, 3, adopt SIFT to carry out feature detection and full images bundle frame adjustment strategy, time efficiency is low.
Traditional adopts frame to the frame mode at flight sequential top overlap stitching algorithm usually, by the local alignment process adjacent image is connected in turn, concrete steps are: at first adjacent image is carried out feature point extraction, carry out Feature Points Matching again, then according to the coupling point set that obtains, carry out the Robust Estimation of plane motion conversion between two images, obtain a series of partial transformation matrix T thus
I, i+1, i.e. the transformation matrix of i two field picture and i+1 interframe.If after selecting first two field picture to be reference frame (being panoramic picture), the k frame (2≤k≤N) image can be obtained by following formula to the transformation matrix between panoramic picture:
Last according to the T that obtains
Ref, k, each two field picture is mapped to the panoramic picture coordinate system, and utilizes image fusion technology to form panoramic picture.By above splicing as can be known, what we calculated each time is the kinematic relation of adjacent image, connect by matrix and take advantage of the corresponding relation that obtains present frame and reference frame, and the conversion T between adjacent image
I, i+1By feature point set being adopted nonlinear optimization algorithm estimate to obtain, the conversion that this explanation is tried to achieve can only be the optimal movement parameter under the least square meaning, certainly exists certain error.Therefore, along with the continuous increase of k value, the T that tries to achieve
Ref, kThe middle accumulation of error that exists is just big more.
Summary of the invention
The objective of the invention is problem at the captured big visual field Panoramagram montage existence of unmanned airborne video camera flight course, comprehensive modern video scene splicing, microwave transmission technology, the UAV Flight Control System etc. of adopting, by technological innovation and integration, and propose a kind of be embedded into UAV Flight Control System, simple to operate, real-time good, can realize while flying the joining method taking the limit splicing, generate the scene panorama sketch when flight finishes, can satisfy by microwave signal to transmit video image real-time demand of splicing on sequential of returning.
To achieve these goals, the present invention is by the following technical solutions:
The unmanned plane of the present invention real-time video Panoramagram montage method of taking photo by plane comprises flight control system, and described real-time video Panoramagram montage method may further comprise the steps:
(1) transmission of video image and collection
Unmanned plane carries analog video camera to be taken the scene of flight course, by microwave channel the control base station is gone back in the transmission of real-time video then, image pick-up card is installed on the video receiver picture frame is gathered, be transferred to working computer then, realize obtaining of picture frame;
(2) selection of key images frame
The video image frame frequency height that obtains from capture card, with 20-30 frame/second, repeat region is bigger between the image of consecutive frame, in order to reduce calculated amount, should not all splice every two field picture, so the selection that this method adopts content-based image key frame selection technology to carry out the image key frame is used for the splicing of image; At first, image is carried out piecemeal handle, be generally 64 * 64, add up gray feature, textural characteristics, shape facility then respectively; At last these features are carried out measuring similarity,, promptly splice as key frame if the similarity of adjacent two frames surpasses certain threshold value; The image key frame sequence mark that will obtain on time shaft is I
0, I
1, I
2... I
t, t is expressed as t key frame, simultaneously, writes down the pairing positional information of every frame, and this positional information is provided by the GPS navigation instrument that unmanned plane carries, and is respectively P
0, P
1, P
2..., P
t,
(3) image pre-service
According to the actual application background difference, may be subjected to inclement weather during the unmanned plane capture video (as dense fog, rainy day), the perhaps influence of the condition of a disaster environment shooting conditions such as (as fire hazard aerosol fogs), cause the image definition and the visibility of shooting all very low, make image quality poor on the one hand, on the other hand, make the detection difficult of characteristics of image, so, algorithm for image enhancement need be applied to the preprocessor part of native system, realize selecting automatically algorithm for image enhancement, this method adopts the two platform operations technology of the blocking with plyability that image is gone smoke treated, and its concrete steps comprise: earlier image is carried out blocking and handle, then the gray-scale value of each piece is added up, the height platform that the gray level statistics numbers is set respectively scabbles processing to statistics, realize the enhancing of monolithic image, simultaneously, utilize the overlapping region that has between the adjacent block, the notable difference that interblock can not occur is realized the enhancing of image;
(4) image characteristics extraction and registration
This method has adopted SURF (H Bay, et al, SURF:Speeded up robust features[J] .ECCV, 2006.) (be translated into: the robust features of acceleration) method is carried out the detection and the description of image characteristic point, after by SURF unique point being detected and describes, each unique point is the vector descriptor of a higher-dimension, and this method adopts KNN (K neighborhood recently) method to carry out the coupling of unique point, realizes the registration of adjacent two width of cloth images;
(5) image transformation
Obtain coupling point set between adjacent image by registration, obtain homograph matrix between two width of cloth images by the match point centralized procurement with RANSAC and L-M method, carry out parameter estimation, obtain the transformation model of image, achieve frame is to the transformation relation of frame, can can suppose to have only translation relation between the image according to vertically shooting and highly higher over the ground of unmanned plane like this;
(6) frame is to the conversion of panorama
By above step, method has obtained the transformation relation of frame to frame, realize the structure of panorama sketch, necessary first achieve frame is to the conversion of panorama, this method adopts is the connecting method of a kind of frame based on the unmanned plane during flying path to panorama sketch (frame-to-mosaic), can directly ask for the transformation parameter of present frame to panoramic picture (being reference frame), this is the real-time process of this method, and it further comprises following steps:
(6.1) the 0th frame image setting of unmanned plane being passed back to be spliced is panoramic picture reference frame, i.e. reference frame.When the 1st key frame arrives, realize strengthening by step (3), extracting the unique point of two two field picture overlapping regions according to the method for step (4), the calculating according to step (5) realization transformation relation obtains T
0,1
(6.2), obtain coupling point set match1 in the overlapping region, match by step (4) for the 1st key frame and the 2nd key frame
2After, according to T
0,1With match
1The point set coordinate Mapping obtains match ' in panoramic picture
1, these characteristic point coordinates are floating number, but content information is constant, according to match '
1And match
2This new coupling point set carries out the calculating of transformation relation according to step (5), obtains T
0,2, obtain the transformation matrix between the 2nd frame and global image;
(6.3) for the i+1 frame, the coupling point set of establishing with i frame overlapping region is match
i, match
I+1, the transformation matrix of i frame and panoramic picture is T
0, i, utilize T
0, iWith match
iThe corresponding point set that is transformed in the panoramic picture is match '
i, with new coupling point set match '
iAnd match
I+1Adopt the transformation matrix T between step (5) calculating i+1 frame and panoramic picture
0, i+1,
(6.4) by that analogy, repeating above step just can obviously, can reduce traditional transformation matrix in twos and even take advantage of the accumulation of error and the propagation that causes in the hope of Direct Transform matrix between any input picture and panoramic picture in solution procedure;
(7) unmanned plane return path temporal-spatial fusion picture frame splices to panorama
Although taked the transform method of the frame of step (6) to panorama, longer when the unmanned plane during flying time, scene is bigger, when flight path is not single direction flight, can cause the splicing effect of panorama sketch relatively poor, so, the present invention also needs in conjunction with the unmanned plane during flying path, merge the information of space-time two aspects, transformation calculations to picture frame is optimized, and specific practice is, when unmanned plane returns flight and carries out image registration, carry out registration according to picture frame adjacent on step (5), (6) elder generation and the sequential, obtain the conversion T of a frame to panorama
t 0, i+1The positional information that obtains according to step (2) is sought the consecutive frame on the space again, carries out characteristic matching, also obtains the conversion T of a frame to panorama
s 0, i+1, then these two conversion are weighted summation, obtain the transformation relation of new frame to panorama, calculating formula is: T
0, i+1=ω
t I+1T
t 0, i+1+ ω
s I+1+ T
s 0, i+1
(8) image co-registration generates panorama sketch
In order to make the overlapping region seamlessly transit, improve picture quality, adopt the linear method transition gradually of being fade-in fade-out, avoid occurring tangible border, the main thought of this method is: carry out the transition to another width of cloth image in the overlapping region linearly by piece image, the gray-scale value that is about to doubling of the image zone is according to the synthetic new image of certain weight addition, and the coloured image at unmanned plane is taken carries out interpolation to three passages of red, green, blue respectively and merges.
Utilization is fade-in the blending algorithm that gradually goes out, is simple and easy to implement, and can access visual effect preferably, and the panorama sketch of generation can satisfy the demand of this application scenario.
The present invention also provides a system with above and other advantage, and the present invention provides corresponding apparatus equally.Described in the present invention flight control system comprises high-resolution camera, computing machine and microwave video transmission system, the video acquisition system that unmanned spacecraft, no-manned machine distant control operating means, unmanned plane carry.
The unmanned plane that the present invention proposes is taken photo by plane the real-time video Panoramagram montage method compared with prior art, and the advantage and the beneficial effect that have are:
1, video scene splicing and UAV Flight Control System are combined, the video image of passing back from unmanned plane by microwave technology is carried out key frame to be selected, adopt strong robustness, SURF descriptor that efficient is high when describing the overlapping region being carried out unique point, can realize the registration of image fast; Realize the effect of limit overlap splicing on sequential, enlarge the scope of visible scene, per second can be realized the splicing of 3-4 key frame, has reached the requirement of real-time.
2, the arbitrary picture frame to splicing in the embodiments of the present invention owing to adopted the joining method of frame to panorama, has overcome cumulative errors and transmission error that matrix multiplies each other in twos and causes.
3, adopt technical scheme of the present invention, when unmanned plane when return path flies, not only utilized the characteristics of image point set in doubling of the image zone adjacent on sequential to carry out the transformation matrix calculating of frame to panorama, and in conjunction with the image key frame corresponding position information that GPS provided on the unmanned plane, searching non-conterminous but spatially adjacent picture frame on sequential, is the weighted mean of the transformation matrix that calculates of picture frame adjacent on time and the space with present frame to the transformation calculations of panorama, has optimized and has returned in the flight course picture frame to the transformation relation of panorama.
4, owing to adopted the blending algorithm that is fade-in gradually to go out, be simple and easy to implement, can access visual effect preferably, the panorama sketch of generation can satisfy the demand of this application scenario.
Method of the present invention can be widely used in military surveillance, the on-the-spot fire extinguishing commander of forest fire, the on-the-spot various fields such as side, the condition of a disaster judgement, evaluation decision, advertising shooting of seeing in real time of other disaster.
Description of drawings
Fig. 1 is the process flow diagram of image mosaic process of the present invention.
Fig. 2 is unmanned plane during flying of the present invention path and doubling of the image situation synoptic diagram.
Embodiment
The present invention relates to the splicing that unmanned plane carries the big visual field panorama sketch of captured video in the video camera flight course, especially, relate to unmanned plane take photo by plane real-time video Panoramagram montage method and equipment, the present invention has many outstanding characteristics, overcome the drawback that existing video image joining method is difficult to go beyond, can make the big visual field splicing technology of panorama drawing of capture video reach a new level.Further describe technical scheme of the present invention below in conjunction with accompanying drawing and by embodiment.
For carrying out splicing according to the present invention, major equipment comprises in the present embodiment: in high-resolution camera, computing machine that unmanned spacecraft, no-manned machine distant control operating means, unmanned plane carry and microwave video transmission system, video acquisition system.At first, hardware devices such as unmanned plane, telechiric device, Video transmission system are provided with, make it return video according to projected path flight and real-time Transmission, computing machine can collect video frame image.
Fig. 1, Fig. 2 show preferential embodiment of the present invention.The employing unmanned plane of the present invention real-time video Panoramagram montage method of taking photo by plane comprises flight control system, and its steps characteristic comprises:
(1) transmission of video image and collection
Unmanned plane carries analog video camera to be taken the scene of flight course, by microwave channel the control base station is gone back in the transmission of real-time video then, image pick-up card is installed on the video receiver picture frame is gathered, be transferred to working computer then, realize obtaining of picture frame.
(2) selection of key images frame
The video image frame frequency height (20-30 frame per second) that obtains from capture card, repeat region is bigger between the image of consecutive frame, in order to reduce calculated amount, should not all splice every two field picture, so, the selection that this method adopts content-based image key frame selection technology to carry out the image key frame is used for the splicing of image, at first, image is carried out piecemeal handle (being generally 64 * 64); Add up gray feature, textural characteristics, shape facility then respectively; At last these features are carried out measuring similarity, if the similarity of adjacent two frames surpasses certain threshold value, promptly splice as key frame, the image key frame sequence mark that will obtain on time shaft is I
0, I
1, I
2... I
t, t is expressed as t key frame, simultaneously, writes down the pairing positional information of every frame, and this positional information is provided by the GPS navigation instrument that unmanned plane carries, and is respectively P
0, P
1, P
2..., P
t...
(3) image pre-service
Application background difference according to reality, may be subjected to inclement weather during the unmanned plane capture video (as dense fog, rainy day), the perhaps influence of the condition of a disaster environment shooting conditions such as (as fire hazard aerosol fogs), cause the image definition and the visibility of shooting all very low, make image quality poor on the one hand, on the other hand, make the detection difficult of characteristics of image, so, algorithm for image enhancement need be applied to the preprocessor part of native system, realize selecting automatically algorithm for image enhancement, this method adopts the two platform operations technology of the blocking with plyability that image is gone smoke treated, and its concrete steps comprise: earlier image is carried out blocking and handle, then the gray-scale value of each piece is added up, the height platform that the gray level statistics numbers is set respectively scabbles processing to statistics, realize the enhancing of monolithic image, simultaneously, utilize the overlapping region that has between the adjacent block, the notable difference that interblock can not occur is realized the enhancing of image.
(4) image characteristics extraction and registration
This method has adopted SURF (H Bay, et al, SURF:Speeded up robust features[J] .ECCV, 2006.) (be translated into: the robust features of acceleration) method is carried out the detection and the description of image characteristic point, compare with the Autostitch method, do not have difference with its SIFT method that adopts when the feature detection aspect the robustness, but time efficiency improves greatly, its main difference is as follows:
Wherein, integral image (integral image) is a kind of image convolution algorithm, given input picture I and point (x, y), integral image is:
Calculating by integral image, a upright rectangular area just can reduce 4 times operand, be constant for size operation time, thereby this method is very effective to the calculating in big zone, uses this characteristic, and SURF uses the Box filter of different sizes and the convolution of original image, Hessian matrix: for space x=(x, y) and scale factor σ, the mode of pressing continuous function, the Hessian matrix is:
Wherein, L
Xx(x σ) is illustrated in dot image x=(x, the second order Gauss differential of y) locating
With the convolution of image, the definition of other three elements is similar.
After by SURF unique point being detected and describes, each unique point is the vector descriptor of a higher-dimension, and this method adopts KNN (K neighborhood recently) method to carry out the coupling of unique point, realizes the registration of adjacent two width of cloth images.
(5) image transformation
Obtain coupling point set between adjacent image by registration, obtain homograph matrix between two width of cloth images by the match point centralized procurement with RANSAC and L-M method, carry out parameter estimation, obtain the transformation model of image, achieve frame is to the transformation relation of frame, utilize vertically shooting and highly higher over the ground of unmanned plane like this, can suppose to have only translation relation between the image.
(6) frame is to the conversion of panorama
By above step, method has obtained the transformation relation of frame to frame, realize the structure of panorama sketch, necessary achieve frame is to the conversion of panorama, in background knowledge, pointed out the error accumulation problem that occurs in the traditional algorithm, this method adopts the connecting method of a kind of frame based on the unmanned plane during flying path to panorama sketch (frame-to-mosaic), can directly ask for the transformation parameter of present frame to panoramic picture (being reference frame), this is the real-time process of this method, and it further comprises four steps:
(6.1) the 0th frame image setting of unmanned plane being passed back to be spliced is the panoramic picture reference frame, it is reference frame, when the 1st key frame arrives, realize strengthening by step (3), extracting the unique point of two two field picture overlapping regions according to the method for step (4), calculating according to step (5) realization transformation relation obtains T
0,1
(6.2) (2) for the 1st key frame and the 2nd key frame, obtains coupling point set match in the overlapping region by step (4)
1, match
2After, according to T
0,1With match
1The point set coordinate Mapping obtains match ' in panoramic picture
1, these characteristic point coordinates are floating number, but content information is constant, according to match '
1And match
2This new coupling point set carries out the calculating of transformation relation according to step (5), obtains T
0,2, obtain the transformation matrix between the 2nd frame and global image;
(6.3) for the i+1 frame, the coupling point set of establishing with the frame overlapping region is match
i, match
I+1, the transformation matrix of i frame and panoramic picture is T
0, i, utilize T
0, iWith match
iThe corresponding point set that is transformed in the panoramic picture is match '
i, with new coupling point set match '
iAnd match
I+1Adopt the transformation matrix T between step (5) calculating i+1 frame and panoramic picture
0, i+1
(6.4) by that analogy, repeating above step just can obviously, can reduce traditional transformation matrix in twos and even take advantage of the accumulation of error and the propagation that causes in the hope of Direct Transform matrix between any input picture and panoramic picture in solution procedure.
(7) unmanned plane return path temporal-spatial fusion picture frame splices to panorama
Although taked the transform method of the frame of step (6) to panorama, longer when the unmanned plane during flying time, scene is bigger, when flight path is not single direction flight, can cause the splicing effect of panorama sketch relatively poor, so this is invented in conjunction with the unmanned plane during flying path, merge the information of space-time two aspects, the transformation calculations of picture frame is optimized.As shown in Figure 2, unmanned plane will be taken the information of a scene, often need take off in some places, among Fig. 2 shown in the A point, the solstics of flight is that the B A point that flies back then lands, in the process from A to B, the image sequence of taking only has overlapping in adjacent interframe of time, when unmanned plane returns, exist scene overlapping between the not only adjacent picture frame of the picture frame of taking with the time, and the time is non-conterminous but also exist scene overlapping between picture frame that the space is adjacent, as the t+2 key frame among Fig. 2, there is scene overlapping between not only adjacent t+1 key frame, and also has scene overlapping between non-conterminous t key frame of time with the time, when unmanned plane returns flight, for key frame I
I+1The joining method process comprise 3 contents:
(7.1) calculate key frame I according to step (2) to step (6)
I+1Conversion T to panorama
t 0, t+1, wherein the match point number of the overlapping region that is obtained by step (4) is n
t I+1
(7.2), determine and I according to space length
I+1Frame is contiguous on time series, but the image key frame I that on space length, is close to
Sn I+1, calculate I according to step (4)
I+1With I
Sn I+1The overlapping region feature point set, the match point number is n
s I+1, calculate I according to step (6) then
I+1Arrive by I
Sn I+1The transformation matrix T that determines to panorama
s 0, i+1
(7.3) calculate the temporal-spatial fusion frame to the panorama conversion:
T
0，i+1＝ω
t i+1T
t 0，i+1+ω
s i+1+T
s 0，i+1 (4)
Wherein
Like this, in conjunction with the information of two aspects of space-time, the transformation matrix of the key frame in the return course to panorama calculated.
(8) image co-registration generates panorama sketch
In order to make the overlapping region seamlessly transit, improve picture quality, adopt the linear method transition gradually of being fade-in fade-out, avoid occurring tangible border, the main thought of this method is: carry out the transition to another width of cloth image in the overlapping region linearly by piece image, the gray-scale value that is about to doubling of the image zone is according to the synthetic new image of certain weight addition.Coloured image at unmanned plane is taken carries out interpolation to three passages of red, green, blue respectively and merges.
Be fade-in the blending algorithm that gradually goes out, be simple and easy to implement, can access visual effect preferably, the panorama sketch of generation can satisfy the demand of this application scenario.
Below only be preferred implementation of the present invention, protection scope of the present invention also not only is confined to the foregoing description, and all technical schemes that belongs under the thinking of the present invention all belong to protection scope of the present invention.Should be pointed out that for those skilled in the art some improvement and conversion not breaking away under the principle of the invention prerequisite should be considered as protection scope of the present invention.
Claims (6)
1. unmanned plane real-time video Panoramagram montage method of taking photo by plane comprises flight control system, and it is characterized in that: described real-time video Panoramagram montage method is further comprising the steps of:
(1) transmission of video image and collection
Unmanned plane carries video camera to be taken the scene of flight course, by microwave channel the control base station is gone back in the transmission of real-time video then, image pick-up card is installed on the video receiver picture frame is gathered, be transferred to working computer then, realize obtaining of picture frame;
(2) selection of key images frame
The video image frame frequency height that obtains from capture card, be 20-30 frame/second, adopt content-based image key frame to select technology earlier image to be carried out being used for the splicing of image again with this key frame after the selection of key frame, and the pairing positional information that provides by GPS of this key frame is provided;
(3) image pre-service
According to the actual application background difference, algorithm for image enhancement is applied to the preprocessor part of native system, realize selecting automatically algorithm for image enhancement, this method is to adopt the two platform operations technology of the blocking with plyability that image is gone smoke treated, its concrete steps comprise: earlier image is carried out blocking and handle, then the gray-scale value of each piece is added up, the height platform that the gray level statistics numbers is set respectively scabbles processing to statistics, realize the enhancing of monolithic image, can utilize the overlapping region that has between the adjacent block like this, realize the enhancing of image;
(4) image characteristics extraction and registration
This method is that the robust features method that adopts SURF to quicken is carried out the detection and the description of image characteristic point, after by SURF unique point being detected and describes, making each unique point is the vector descriptor of a higher-dimension, adopt nearest K neighborhood method to carry out the coupling of unique point again, realize the registration of adjacent two width of cloth images;
(5) image transformation of frame road frame
Obtain coupling point set between adjacent image by step (4) registration, obtain homograph matrix between two width of cloth images by the match point centralized procurement with RANSAC and L-M method, carry out parameter estimation, obtain the transformation model of image, achieve frame is to the transformation relation of frame, according to vertically shooting and highly higher over the ground of unmanned plane, can suppose to be between the image translation relation like this;
(6) frame is to the conversion of panorama
By above step, method has obtained the transformation relation of frame to frame, for realizing the structure of panorama sketch, necessary first achieve frame is to the conversion of panorama, this method adopts the connecting method of a kind of frame based on the unmanned plane during flying path to panorama sketch (frame-to-mosaic), can directly ask for the transformation parameter of present frame to the reference frame of panoramic picture;
(7) unmanned plane return path temporal-spatial fusion picture frame splices to panorama
According to the frame of step (6) to the transform method of panorama in conjunction with the unmanned plane during flying path, merge the information of space-time two aspects, transformation calculations to picture frame is optimized, utilize space-time consecutive frame information to realize the conversion of picture frame simultaneously to panorama, can reduce image like this and even take advantage of cumulative errors, splice to panorama to realize unmanned plane return path temporal-spatial fusion picture frame;
(8) image co-registration generates panorama sketch
In order to make the overlapping region seamlessly transit, improve picture quality, adopt the linear method transition gradually of being fade-in fade-out, to avoid occurring tangible border, the concrete steps of this method comprise: carry out the transition to another width of cloth image in the overlapping region linearly by piece image, the gray-scale value that is about to doubling of the image zone is according to the synthetic new image of certain weight addition, coloured image at the unmanned plane shooting, respectively to red, green, blue three passages carry out interpolation and merge, utilization is fade-in the blending algorithm that gradually goes out and obtains visual effect preferably, and generation can be satisfied the panorama sketch of this application scenario.
2. the unmanned plane according to claim 1 real-time video Panoramagram montage method of taking photo by plane is characterized in that: the positional information of described this key frame of step (2) is to be provided by the GPS navigation instrument that unmanned plane carries.
3. the unmanned plane according to claim 1 real-time video Panoramagram montage method of taking photo by plane, it is characterized in that: the described frame of step (6) further comprises to the real-time process of the transform method of panorama:
(1) the 0th frame image setting of unmanned plane being passed back to be spliced is the panoramic picture reference frame, it is reference frame, when the 1st key frame arrives, realize strengthening by step (3), extracting the unique point of two two field picture overlapping regions according to the method for step (4), calculating according to step (5) realization transformation relation obtains T
0,1
(2), obtain coupling point set match in the overlapping region by step (4) for the 1st key frame and the 2nd key frame
1, match
2After, according to T
0,1With match
1The point set coordinate Mapping obtains match ' in panoramic picture
1, these characteristic point coordinates are floating number, but content information is constant, according to match '
1And match
2This new coupling point set carries out the calculating of transformation relation according to step (5), obtains T
0,2, obtain the transformation matrix between the 2nd frame and global image;
(3) for the i+1 frame, the coupling point set of establishing with the frame overlapping region is match
i, match
I+1, the transformation matrix of i frame and panoramic picture is T
0, i, utilize T
0, iWith match
iThe corresponding point set that is transformed in the panoramic picture is match '
i, with new coupling point set match '
iAnd match
I+1Adopt the transformation matrix T between step (5) calculating i+1 frame and panoramic picture
0, i+1
(4) by that analogy, repeating above step just can obviously, can reduce traditional transformation matrix in twos and even take advantage of the accumulation of error and the propagation that causes in the hope of Direct Transform matrix between any input picture and panoramic picture in solution procedure.
4. the unmanned plane according to claim 1 real-time video Panoramagram montage method of taking photo by plane, it is characterized in that: step (7) is to merge time domain when adopting in conjunction with unmanned plane GPS information of same and spatial information (si) is optimized the method for frame to the panorama transformation relation, and the joining method of described image key frame and panorama further comprises:
(1) calculates key frame I according to step (2) to step (6)
I+1Conversion T to panorama
t 0, i+1, wherein the match point number of the overlapping region that is obtained by step (4) is n
t I+1
(2), determine and I according to space length
I+1Frame is contiguous on time series, but the image key frame I that on space length, is close to
Sn I+1, calculate I according to step (4)
I+1With I
Sn I+1The overlapping region feature point set, the match point number is n
s I+1, calculate I according to step (6) then
I+1Arrive by I
Sn I+1The transformation matrix T that determines to panorama
s 0, i+1
(3) calculate the temporal-spatial fusion frame to the panorama conversion:
T
0，i+1＝ω
t i+1T
t 0，i+1+ω
s i+1+T
s 0，i+1 (4)
Wherein
Like this, in conjunction with the information of two aspects of space-time, the transformation matrix of the key frame in the return course to panorama calculated.
5. the unmanned plane according to claim 1 real-time video Panoramagram montage method of taking photo by plane is characterized in that: described flight control system comprises high-resolution camera, computing machine and microwave video transmission system, the video acquisition system that unmanned spacecraft, no-manned machine distant control operating means, unmanned plane carry.
6. the unmanned plane real-time video Panoramagram montage method of taking photo by plane according to claim 1 or 5, it is characterized in that: described video camera is the combination of one or one above video camera.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011100855966A CN102201115B (en) | 2011-04-07 | 2011-04-07 | Real-time panoramic image stitching method of aerial videos photography by unmanned plane |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011100855966A CN102201115B (en) | 2011-04-07 | 2011-04-07 | Real-time panoramic image stitching method of aerial videos photography by unmanned plane |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102201115A true CN102201115A (en) | 2011-09-28 |
| CN102201115B CN102201115B (en) | 2013-12-11 |
Family
ID=44661765
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011100855966A Expired - Fee Related CN102201115B (en) | 2011-04-07 | 2011-04-07 | Real-time panoramic image stitching method of aerial videos photography by unmanned plane |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102201115B (en) |
Cited By (100)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101984463A (en) * | 2010-11-02 | 2011-03-09 | 中兴通讯股份有限公司 | Method and device for synthesizing panoramic image |
| CN102980581A (en) * | 2012-12-07 | 2013-03-20 | 北京中海新图科技有限公司 | Irregular-island-based method for planning covered flight route of unmanned aerial vehicle |
| CN102982515A (en) * | 2012-10-23 | 2013-03-20 | 中国电子科技集团公司第二十七研究所 | Method of unmanned plane image real-time splicing |
| CN103226822A (en) * | 2013-05-15 | 2013-07-31 | 清华大学 | Medical image stitching method |
| CN103236037A (en) * | 2013-04-03 | 2013-08-07 | 北京航空航天大学 | Unmanned aerial vehicle real-time image simulation method based on hierarchical degradation model |
| CN103714524A (en) * | 2013-12-20 | 2014-04-09 | 鞍钢股份有限公司 | Automatic integration method for cold rolling strip steel surface image |
| CN103823470A (en) * | 2014-03-03 | 2014-05-28 | 青岛宏百川金属精密制品有限公司 | Panoramic real-time dynamic monitoring system of unmanned aerial vehicle |
| CN103905790A (en) * | 2014-03-14 | 2014-07-02 | 深圳市大疆创新科技有限公司 | Video processing method, device and system |
| CN103942273A (en) * | 2014-03-27 | 2014-07-23 | 北京空间机电研究所 | Dynamic monitoring system and method for aerial quick response |
| CN103985103A (en) * | 2013-02-07 | 2014-08-13 | 百度在线网络技术（北京）有限公司 | Method and device for generating panoramic picture |
| CN104062980A (en) * | 2014-06-10 | 2014-09-24 | 北京空间机电研究所 | Onboard panorama monitoring system of unmanned aerial vehicle |
| CN104166580A (en) * | 2014-08-18 | 2014-11-26 | 西北工业大学 | Synchronous online splicing method based on reference frame conversion and splicing size self-adaptation |
| CN104282005A (en) * | 2014-09-19 | 2015-01-14 | 天津航天中为数据系统科技有限公司 | Video image stitching method and device |
| CN104574278A (en) * | 2015-02-03 | 2015-04-29 | 中国人民解放军国防科学技术大学 | Aerial-photography image stitching method based on local feedback mechanism and sparse global adjustment |
| CN104601894A (en) * | 2015-02-06 | 2015-05-06 | 武汉大学 | 360 degrees panoramic shooting unit and method |
| CN104820965A (en) * | 2015-04-30 | 2015-08-05 | 武汉大学 | Geocoding-free rapid image splicing method of low-altitude unmanned plane |
| CN104994272A (en) * | 2015-06-12 | 2015-10-21 | 惠州Tcl移动通信有限公司 | Mobile terminal and method of realizing image scanning |
| CN105049812A (en) * | 2015-08-07 | 2015-11-11 | 清华大学深圳研究生院 | Unmanned aerial vehicle portable ground station processing method and system |
| CN105046909A (en) * | 2015-06-17 | 2015-11-11 | 中国计量学院 | Agricultural loss assessment assisting method based on small-sized unmanned aerial vehicle |
| CN105072393A (en) * | 2015-07-31 | 2015-11-18 | 深圳英飞拓科技股份有限公司 | Multi-lens panoramic network camera and method |
| CN105100688A (en) * | 2014-05-12 | 2015-11-25 | 索尼公司 | Image processing method, image processing device and monitoring system |
| CN105096255A (en) * | 2015-08-21 | 2015-11-25 | 上海联影医疗科技有限公司 | Image processing method and image processing system |
| CN105376500A (en) * | 2014-08-18 | 2016-03-02 | 三星电子株式会社 | Video processing apparatus for generating paranomic video and method thereof |
| CN105847750A (en) * | 2016-04-13 | 2016-08-10 | 中测新图(北京)遥感技术有限责任公司 | Geo-coding based unmanned aerial vehicle video image real time presenting method and apparatus |
| CN105898159A (en) * | 2016-05-31 | 2016-08-24 | 努比亚技术有限公司 | Image processing method and terminal |
| CN105976324A (en) * | 2016-05-19 | 2016-09-28 | 温州大学城市学院 | Vehicle image splicing method |
| CN106095774A (en) * | 2016-05-25 | 2016-11-09 | 深圳市创驰蓝天科技发展有限公司 | A kind of unmanned plane image panorama methods of exhibiting |
| CN106355555A (en) * | 2016-10-24 | 2017-01-25 | 北京林业大学 | Image stitching method and device |
| CN106447608A (en) * | 2016-08-25 | 2017-02-22 | 中国科学院长春光学精密机械与物理研究所 | Video image splicing method and device |
| CN106447611A (en) * | 2016-09-09 | 2017-02-22 | 国网福建省电力有限公司 | Method for displaying panoramic image of power transmission tower |
| CN106485751A (en) * | 2016-10-28 | 2017-03-08 | 湖北省建筑工程质量监督检验测试中心 | It is applied to the unmanned plane photographic imagery in pile detection and data processing method and system |
| CN106657789A (en) * | 2016-12-29 | 2017-05-10 | 核动力运行研究所 | Thread panoramic image synthesis method |
| CN106709894A (en) * | 2015-08-17 | 2017-05-24 | 北京亿羽舜海科技有限公司 | Real-time image splicing method and system |
| WO2017096548A1 (en) * | 2015-12-09 | 2017-06-15 | SZ DJI Technology Co., Ltd. | Systems and methods for auto-return |
| CN106920240A (en) * | 2017-03-09 | 2017-07-04 | 国家电网公司 | A kind of insulator identification and method for diagnosing faults based on infrared image |
| CN107016695A (en) * | 2017-04-13 | 2017-08-04 | 首都师范大学 | A kind of sub-pixel Image registration method and system |
| CN107123090A (en) * | 2017-04-25 | 2017-09-01 | 无锡中科智能农业发展有限责任公司 | It is a kind of that farmland panorama system and method are automatically synthesized based on image mosaic technology |
| CN107147879A (en) * | 2017-06-02 | 2017-09-08 | 太仓韬信信息科技有限公司 | A kind of real-time video joining method |
| CN107197275A (en) * | 2017-06-15 | 2017-09-22 | 武汉大学深圳研究院 | Cruise UAV Video compression method based on long-range Large Scale Background template |
| CN107256221A (en) * | 2017-04-26 | 2017-10-17 | 苏州大学 | Video presentation method based on multi-feature fusion |
| CN107545538A (en) * | 2016-06-24 | 2018-01-05 | 清华大学深圳研究生院 | A kind of Panorama Mosaic method and device based on unmanned plane |
| CN107748569A (en) * | 2017-09-04 | 2018-03-02 | 中国兵器工业计算机应用技术研究所 | Motion control method, device and UAS for unmanned plane |
| CN107861436A (en) * | 2017-12-01 | 2018-03-30 | 上海市环境科学研究院 | A kind of multi-rotor unmanned aerial vehicle high altitude environment detecting system |
| CN108492255A (en) * | 2018-04-10 | 2018-09-04 | 浙江知水信息技术有限公司 | A method of hydraulic engineering panorama sketch is shown based on mobile application end |
| CN108492256A (en) * | 2018-04-18 | 2018-09-04 | 中国人民解放军陆军工程大学 | The quick joining method of UAV Video |
| CN108513642A (en) * | 2017-07-31 | 2018-09-07 | 深圳市大疆创新科技有限公司 | A kind of image processing method, unmanned plane, ground control cabinet and its image processing system |
| CN108680137A (en) * | 2018-04-24 | 2018-10-19 | 天津职业技术师范大学 | Earth subsidence detection method and detection device based on unmanned plane and Ground Penetrating Radar |
| CN108718403A (en) * | 2018-06-08 | 2018-10-30 | 重庆交通职业学院 | Image panorama system for the unmanned hot air dirigible airship of more rotors |
| CN108900773A (en) * | 2018-07-27 | 2018-11-27 | 武汉禾木林科技有限公司 | A method of shooting very-high solution is taken photo by plane panorama sketch |
| CN108985319A (en) * | 2017-06-02 | 2018-12-11 | 宏达国际电子股份有限公司 | Image corresponds to judgment method and device |
| CN109410279A (en) * | 2018-08-31 | 2019-03-01 | 南京理工大学 | Image detection based on deep learning positions accelerated method |
| CN109547708A (en) * | 2018-12-04 | 2019-03-29 | 中国航空工业集团公司西安航空计算技术研究所 | A kind of synthetic vision image processing system |
| WO2019061295A1 (en) * | 2017-09-29 | 2019-04-04 | 深圳市大疆创新科技有限公司 | Video processing method and device, unmanned aerial vehicle and system |
| CN109597430A (en) * | 2019-01-18 | 2019-04-09 | 东北农业大学 | The UAV system of dimension analysis is risen based on photo |
| CN109712071A (en) * | 2018-12-14 | 2019-05-03 | 电子科技大学 | Unmanned plane image mosaic and localization method based on track constraint |
| CN109840017A (en) * | 2019-01-11 | 2019-06-04 | 博拉网络股份有限公司 | A kind of panoramic picture methods of exhibiting, system and storage medium |
| CN109902565A (en) * | 2019-01-21 | 2019-06-18 | 深圳市烨嘉为技术有限公司 | The Human bodys' response method of multiple features fusion |
| CN109995993A (en) * | 2018-01-02 | 2019-07-09 | 广州亿航智能技术有限公司 | Aircraft and its filming control method, device and terminal system |
| WO2019134516A1 (en) * | 2018-01-05 | 2019-07-11 | Oppo广东移动通信有限公司 | Method and device for generating panoramic image, storage medium, and electronic apparatus |
| CN110059651A (en) * | 2019-04-24 | 2019-07-26 | 北京计算机技术及应用研究所 | A kind of camera real-time tracking register method |
| CN110084743A (en) * | 2019-01-25 | 2019-08-02 | 电子科技大学 | Image mosaic and localization method based on more air strips starting track constraint |
| CN110097498A (en) * | 2019-01-25 | 2019-08-06 | 电子科技大学 | More air strips image mosaics and localization method based on unmanned aerial vehicle flight path constraint |
| CN110111250A (en) * | 2019-04-11 | 2019-08-09 | 中国地质大学（武汉） | A kind of automatic panorama unmanned plane image split-joint method and device of robust |
| CN110191311A (en) * | 2019-04-15 | 2019-08-30 | 贵州电网有限责任公司 | A kind of real-time video joining method based on multiple no-manned plane |
| CN110503621A (en) * | 2019-08-23 | 2019-11-26 | 上海圭目机器人有限公司 | Image overall joining method based on location data |
| CN110648281A (en) * | 2019-09-23 | 2020-01-03 | 华南农业大学 | Method, device and system for generating field panorama, server and storage medium |
| CN110889818A (en) * | 2019-11-22 | 2020-03-17 | 华南农业大学 | Low-altitude unmanned aerial vehicle image splicing method and system, computer equipment and storage medium |
| CN110969574A (en) * | 2018-09-29 | 2020-04-07 | 广州汽车集团股份有限公司 | Vehicle-mounted panoramic map creation method and device |
| CN111062341A (en) * | 2019-12-20 | 2020-04-24 | 广州市鑫广飞信息科技有限公司 | Video image area classification method, device, equipment and storage medium |
| CN111062984A (en) * | 2019-12-20 | 2020-04-24 | 广州市鑫广飞信息科技有限公司 | Method, device and equipment for measuring area of video image region and storage medium |
| CN111327840A (en) * | 2020-02-27 | 2020-06-23 | 努比亚技术有限公司 | Multi-frame special-effect video acquisition method, terminal and computer readable storage medium |
| CN111402136A (en) * | 2020-03-19 | 2020-07-10 | 贝壳技术有限公司 | Panorama generation method and device, computer readable storage medium and electronic equipment |
| CN111445429A (en) * | 2020-03-26 | 2020-07-24 | 北京易康医疗科技有限公司 | PET and MRI image fusion method based on feature points |
| CN111507901A (en) * | 2020-04-15 | 2020-08-07 | 中国电子科技集团公司第五十四研究所 | Aerial image splicing and positioning method based on aerial belt GPS and scale invariant constraint |
| CN111508181A (en) * | 2020-04-28 | 2020-08-07 | 江苏理工学院 | Forest fire prevention system based on multiple unmanned aerial vehicles and method thereof |
| CN111540059A (en) * | 2013-01-30 | 2020-08-14 | 英西图公司 | Enhanced video system providing enhanced environmental perception |
| CN111640187A (en) * | 2020-04-20 | 2020-09-08 | 中国科学院计算技术研究所 | Video splicing method and system based on interpolation transition |
| CN111680703A (en) * | 2020-06-01 | 2020-09-18 | 中国电建集团昆明勘测设计研究院有限公司 | 360-degree construction panorama linkage positioning method based on image feature point detection and matching |
| CN111708916A (en) * | 2020-06-21 | 2020-09-25 | 深圳天海宸光科技有限公司 | Unmanned aerial vehicle cluster video intelligent processing system and method |
| CN111768339A (en) * | 2020-06-29 | 2020-10-13 | 广西翼界科技有限公司 | Rapid splicing method for aerial images of unmanned aerial vehicle |
| CN111814536A (en) * | 2020-05-21 | 2020-10-23 | 闽江学院 | Breeding monitoring method and device |
| CN111951201A (en) * | 2019-05-16 | 2020-11-17 | 杭州海康机器人技术有限公司 | Unmanned aerial vehicle aerial image splicing method and device and storage medium |
| CN111951198A (en) * | 2019-05-16 | 2020-11-17 | 杭州海康机器人技术有限公司 | Unmanned aerial vehicle aerial image splicing optimization method and device and storage medium |
| CN111951158A (en) * | 2019-05-16 | 2020-11-17 | 杭州海康机器人技术有限公司 | Recovery method and device for splicing interruption of aerial image of unmanned aerial vehicle and storage medium |
| CN112734904A (en) * | 2020-12-29 | 2021-04-30 | 中国船舶重工集团公司第七0九研究所 | Portable rapid image splicing processing system for police |
| CN112887589A (en) * | 2021-01-08 | 2021-06-01 | 深圳市智胜科技信息有限公司 | Panoramic shooting method and device based on unmanned aerial vehicle |
| CN113298707A (en) * | 2021-01-27 | 2021-08-24 | 阿里巴巴集团控股有限公司 | Image frame splicing method, video inspection method, device, equipment and storage medium |
| CN113361552A (en) * | 2020-03-05 | 2021-09-07 | 西安邮电大学 | Positioning method and device |
| CN113631477A (en) * | 2019-04-02 | 2021-11-09 | 索尼集团公司 | Information processing apparatus, information processing method, and program |
| WO2021238317A1 (en) * | 2020-05-29 | 2021-12-02 | 华为技术有限公司 | Panoramic image capture method and device |
| CN113905190A (en) * | 2021-09-30 | 2022-01-07 | 中国电子科技集团公司第五十四研究所 | Panorama real-time splicing method for unmanned aerial vehicle video |
| CN114565516A (en) * | 2022-03-03 | 2022-05-31 | 上海核工程研究设计院有限公司 | Sensor data fused security shell surface area robust splicing method |
| CN114584839A (en) * | 2022-02-25 | 2022-06-03 | 智己汽车科技有限公司 | Clipping method and device for shooting vehicle-mounted video, electronic equipment and storage medium |
| CN114973028A (en) * | 2022-05-17 | 2022-08-30 | 中国电子科技集团公司第十研究所 | Aerial video image real-time change detection method and system |
| CN115439424A (en) * | 2022-08-23 | 2022-12-06 | 成都飞机工业（集团）有限责任公司 | Intelligent detection method for aerial video image of unmanned aerial vehicle |
| CN115620515A (en) * | 2022-09-30 | 2023-01-17 | 深圳技术大学 | Unmanned aerial vehicle video-based method for acquiring interchange traffic volume and related device |
| CN115861927A (en) * | 2022-12-01 | 2023-03-28 | 中国南方电网有限责任公司超高压输电公司大理局 | Image identification method and device for power equipment inspection image and computer equipment |
| CN115861859A (en) * | 2023-02-20 | 2023-03-28 | 中国科学院东北地理与农业生态研究所 | Slope farmland environment monitoring method and system |
| WO2023066412A1 (en) * | 2022-08-17 | 2023-04-27 | 中国科学院空天信息创新研究院 | Dynamic processing method and apparatus based on unmanned aerial vehicle video pyramid model |
| CN116186354A (en) * | 2023-04-27 | 2023-05-30 | 中关村科学城城市大脑股份有限公司 | Method, apparatus, electronic device, and computer-readable medium for displaying regional image |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106709868A (en) * | 2016-12-14 | 2017-05-24 | 云南电网有限责任公司电力科学研究院 | Image stitching method and apparatus |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101079151A (en) * | 2006-10-13 | 2007-11-28 | 浙江师范大学 | 360 degree around panorama generation method based on serial static image |
| CN101247513A (en) * | 2007-12-25 | 2008-08-20 | 谢维信 | Method for real-time generating 360 degree seamless full-view video image by single camera |
| US20080266408A1 (en) * | 2007-04-26 | 2008-10-30 | Core Logic, Inc. | Apparatus and method for generating panorama image and computer readable medium stored thereon computer executable instructions for performing the method |
| US7460730B2 (en) * | 2005-08-04 | 2008-12-02 | Microsoft Corporation | Video registration and image sequence stitching |
| CN101394573A (en) * | 2008-10-30 | 2009-03-25 | 清华大学 | Panoramagram generation method and system based on characteristic matching |
| CN101916452A (en) * | 2010-07-26 | 2010-12-15 | 中国科学院遥感应用研究所 | Method for automatically stitching unmanned aerial vehicle remote sensing images based on flight control information |
| WO2010151311A1 (en) * | 2009-06-26 | 2010-12-29 | Flight Landata, Inc. | Dual-swath imaging system |
-
2011
- 2011-04-07 CN CN2011100855966A patent/CN102201115B/en not_active Expired - Fee Related
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7460730B2 (en) * | 2005-08-04 | 2008-12-02 | Microsoft Corporation | Video registration and image sequence stitching |
| CN101079151A (en) * | 2006-10-13 | 2007-11-28 | 浙江师范大学 | 360 degree around panorama generation method based on serial static image |
| US20080266408A1 (en) * | 2007-04-26 | 2008-10-30 | Core Logic, Inc. | Apparatus and method for generating panorama image and computer readable medium stored thereon computer executable instructions for performing the method |
| CN101247513A (en) * | 2007-12-25 | 2008-08-20 | 谢维信 | Method for real-time generating 360 degree seamless full-view video image by single camera |
| CN101394573A (en) * | 2008-10-30 | 2009-03-25 | 清华大学 | Panoramagram generation method and system based on characteristic matching |
| WO2010151311A1 (en) * | 2009-06-26 | 2010-12-29 | Flight Landata, Inc. | Dual-swath imaging system |
| CN101916452A (en) * | 2010-07-26 | 2010-12-15 | 中国科学院遥感应用研究所 | Method for automatically stitching unmanned aerial vehicle remote sensing images based on flight control information |
Cited By (153)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101984463A (en) * | 2010-11-02 | 2011-03-09 | 中兴通讯股份有限公司 | Method and device for synthesizing panoramic image |
| CN102982515A (en) * | 2012-10-23 | 2013-03-20 | 中国电子科技集团公司第二十七研究所 | Method of unmanned plane image real-time splicing |
| CN102980581A (en) * | 2012-12-07 | 2013-03-20 | 北京中海新图科技有限公司 | Irregular-island-based method for planning covered flight route of unmanned aerial vehicle |
| CN111540059A (en) * | 2013-01-30 | 2020-08-14 | 英西图公司 | Enhanced video system providing enhanced environmental perception |
| CN111540059B (en) * | 2013-01-30 | 2023-12-01 | 英西图公司 | Enhanced video system providing enhanced environmental awareness |
| CN103985103A (en) * | 2013-02-07 | 2014-08-13 | 百度在线网络技术（北京）有限公司 | Method and device for generating panoramic picture |
| CN103236037A (en) * | 2013-04-03 | 2013-08-07 | 北京航空航天大学 | Unmanned aerial vehicle real-time image simulation method based on hierarchical degradation model |
| CN103236037B (en) * | 2013-04-03 | 2016-05-11 | 北京航空航天大学 | Unmanned plane realtime graphic analogy method based on layering degradation model |
| CN103226822A (en) * | 2013-05-15 | 2013-07-31 | 清华大学 | Medical image stitching method |
| CN103226822B (en) * | 2013-05-15 | 2015-07-29 | 清华大学 | Medical imaging joining method |
| CN103714524A (en) * | 2013-12-20 | 2014-04-09 | 鞍钢股份有限公司 | Automatic integration method for cold rolling strip steel surface image |
| CN103714524B (en) * | 2013-12-20 | 2016-05-11 | 鞍钢股份有限公司 | The automatic fusion method of a kind of Cold-strip Steel Surface image |
| CN103823470A (en) * | 2014-03-03 | 2014-05-28 | 青岛宏百川金属精密制品有限公司 | Panoramic real-time dynamic monitoring system of unmanned aerial vehicle |
| CN103905790A (en) * | 2014-03-14 | 2014-07-02 | 深圳市大疆创新科技有限公司 | Video processing method, device and system |
| CN103942273A (en) * | 2014-03-27 | 2014-07-23 | 北京空间机电研究所 | Dynamic monitoring system and method for aerial quick response |
| CN103942273B (en) * | 2014-03-27 | 2017-03-15 | 北京空间机电研究所 | A kind of aerial quick response dynamic monitoring system and its dynamic monitoring method |
| CN105100688B (en) * | 2014-05-12 | 2019-08-20 | 索尼公司 | Image processing method, image processing apparatus and monitoring system |
| CN105100688A (en) * | 2014-05-12 | 2015-11-25 | 索尼公司 | Image processing method, image processing device and monitoring system |
| CN104062980A (en) * | 2014-06-10 | 2014-09-24 | 北京空间机电研究所 | Onboard panorama monitoring system of unmanned aerial vehicle |
| US10334162B2 (en) | 2014-08-18 | 2019-06-25 | Samsung Electronics Co., Ltd. | Video processing apparatus for generating panoramic video and method thereof |
| CN104166580A (en) * | 2014-08-18 | 2014-11-26 | 西北工业大学 | Synchronous online splicing method based on reference frame conversion and splicing size self-adaptation |
| CN105376500B (en) * | 2014-08-18 | 2021-04-06 | 三星电子株式会社 | Video processing apparatus for generating panoramic video and method thereof |
| CN105376500A (en) * | 2014-08-18 | 2016-03-02 | 三星电子株式会社 | Video processing apparatus for generating paranomic video and method thereof |
| CN104282005A (en) * | 2014-09-19 | 2015-01-14 | 天津航天中为数据系统科技有限公司 | Video image stitching method and device |
| CN104574278A (en) * | 2015-02-03 | 2015-04-29 | 中国人民解放军国防科学技术大学 | Aerial-photography image stitching method based on local feedback mechanism and sparse global adjustment |
| CN104601894A (en) * | 2015-02-06 | 2015-05-06 | 武汉大学 | 360 degrees panoramic shooting unit and method |
| CN104820965A (en) * | 2015-04-30 | 2015-08-05 | 武汉大学 | Geocoding-free rapid image splicing method of low-altitude unmanned plane |
| CN104994272A (en) * | 2015-06-12 | 2015-10-21 | 惠州Tcl移动通信有限公司 | Mobile terminal and method of realizing image scanning |
| CN105046909A (en) * | 2015-06-17 | 2015-11-11 | 中国计量学院 | Agricultural loss assessment assisting method based on small-sized unmanned aerial vehicle |
| CN105072393A (en) * | 2015-07-31 | 2015-11-18 | 深圳英飞拓科技股份有限公司 | Multi-lens panoramic network camera and method |
| CN105049812B (en) * | 2015-08-07 | 2018-06-15 | 清华大学深圳研究生院 | A kind of unmanned plane portable type ground station processing method and system |
| WO2017024975A1 (en) * | 2015-08-07 | 2017-02-16 | 清华大学深圳研究生院 | Unmanned aerial vehicle portable ground station processing method and system |
| CN105049812A (en) * | 2015-08-07 | 2015-11-11 | 清华大学深圳研究生院 | Unmanned aerial vehicle portable ground station processing method and system |
| CN106709894A (en) * | 2015-08-17 | 2017-05-24 | 北京亿羽舜海科技有限公司 | Real-time image splicing method and system |
| CN106709894B (en) * | 2015-08-17 | 2020-10-27 | 北京亿羽舜海科技有限公司 | Image real-time splicing method and system |
| CN105096255A (en) * | 2015-08-21 | 2015-11-25 | 上海联影医疗科技有限公司 | Image processing method and image processing system |
| US11879737B2 (en) | 2015-12-09 | 2024-01-23 | SZ DJI Technology Co., Ltd. | Systems and methods for auto-return |
| WO2017096548A1 (en) * | 2015-12-09 | 2017-06-15 | SZ DJI Technology Co., Ltd. | Systems and methods for auto-return |
| US11300413B2 (en) | 2015-12-09 | 2022-04-12 | SZ DJI Technology Co., Ltd. | Systems and methods for auto-return |
| CN108292140B (en) * | 2015-12-09 | 2022-03-15 | 深圳市大疆创新科技有限公司 | System and method for automatic return voyage |
| US10670407B2 (en) | 2015-12-09 | 2020-06-02 | SZ DJI Technology Co., Ltd. | Systems and methods for auto-return |
| CN108292140A (en) * | 2015-12-09 | 2018-07-17 | 深圳市大疆创新科技有限公司 | System and method for making a return voyage automatically |
| CN105847750A (en) * | 2016-04-13 | 2016-08-10 | 中测新图(北京)遥感技术有限责任公司 | Geo-coding based unmanned aerial vehicle video image real time presenting method and apparatus |
| CN105847750B (en) * | 2016-04-13 | 2019-01-15 | 中测新图(北京)遥感技术有限责任公司 | The method and device of UAV Video image real-time display based on geocoding |
| CN105976324A (en) * | 2016-05-19 | 2016-09-28 | 温州大学城市学院 | Vehicle image splicing method |
| CN105976324B (en) * | 2016-05-19 | 2017-05-17 | 温州大学城市学院 | Vehicle image splicing method |
| CN106095774A (en) * | 2016-05-25 | 2016-11-09 | 深圳市创驰蓝天科技发展有限公司 | A kind of unmanned plane image panorama methods of exhibiting |
| CN105898159A (en) * | 2016-05-31 | 2016-08-24 | 努比亚技术有限公司 | Image processing method and terminal |
| CN105898159B (en) * | 2016-05-31 | 2019-10-29 | 努比亚技术有限公司 | A kind of image processing method and terminal |
| CN107545538A (en) * | 2016-06-24 | 2018-01-05 | 清华大学深圳研究生院 | A kind of Panorama Mosaic method and device based on unmanned plane |
| CN106447608A (en) * | 2016-08-25 | 2017-02-22 | 中国科学院长春光学精密机械与物理研究所 | Video image splicing method and device |
| CN106447608B (en) * | 2016-08-25 | 2017-11-07 | 中国科学院长春光学精密机械与物理研究所 | A kind of video image joining method and device |
| CN106447611A (en) * | 2016-09-09 | 2017-02-22 | 国网福建省电力有限公司 | Method for displaying panoramic image of power transmission tower |
| CN106355555A (en) * | 2016-10-24 | 2017-01-25 | 北京林业大学 | Image stitching method and device |
| CN106355555B (en) * | 2016-10-24 | 2019-06-18 | 北京林业大学 | A kind of image split-joint method and device |
| CN106485751B (en) * | 2016-10-28 | 2020-03-10 | 湖北省建筑科学研究设计院 | Unmanned aerial vehicle photographic imaging and data processing method and system applied to foundation pile detection |
| CN106485751A (en) * | 2016-10-28 | 2017-03-08 | 湖北省建筑工程质量监督检验测试中心 | It is applied to the unmanned plane photographic imagery in pile detection and data processing method and system |
| CN106657789A (en) * | 2016-12-29 | 2017-05-10 | 核动力运行研究所 | Thread panoramic image synthesis method |
| CN106920240A (en) * | 2017-03-09 | 2017-07-04 | 国家电网公司 | A kind of insulator identification and method for diagnosing faults based on infrared image |
| CN107016695B (en) * | 2017-04-13 | 2019-09-17 | 首都师范大学 | A kind of sub-pixel Image registration method and system |
| CN107016695A (en) * | 2017-04-13 | 2017-08-04 | 首都师范大学 | A kind of sub-pixel Image registration method and system |
| CN107123090A (en) * | 2017-04-25 | 2017-09-01 | 无锡中科智能农业发展有限责任公司 | It is a kind of that farmland panorama system and method are automatically synthesized based on image mosaic technology |
| CN107256221B (en) * | 2017-04-26 | 2020-11-03 | 苏州大学 | Video description method based on multi-feature fusion |
| CN107256221A (en) * | 2017-04-26 | 2017-10-17 | 苏州大学 | Video presentation method based on multi-feature fusion |
| CN107147879A (en) * | 2017-06-02 | 2017-09-08 | 太仓韬信信息科技有限公司 | A kind of real-time video joining method |
| CN108985319A (en) * | 2017-06-02 | 2018-12-11 | 宏达国际电子股份有限公司 | Image corresponds to judgment method and device |
| CN107197275A (en) * | 2017-06-15 | 2017-09-22 | 武汉大学深圳研究院 | Cruise UAV Video compression method based on long-range Large Scale Background template |
| CN108513642B (en) * | 2017-07-31 | 2021-08-27 | 深圳市大疆创新科技有限公司 | Image processing method, unmanned aerial vehicle, ground console and image processing system thereof |
| CN108513642A (en) * | 2017-07-31 | 2018-09-07 | 深圳市大疆创新科技有限公司 | A kind of image processing method, unmanned plane, ground control cabinet and its image processing system |
| CN107748569A (en) * | 2017-09-04 | 2018-03-02 | 中国兵器工业计算机应用技术研究所 | Motion control method, device and UAS for unmanned plane |
| CN107748569B (en) * | 2017-09-04 | 2021-02-19 | 中国兵器工业计算机应用技术研究所 | Motion control method and device for unmanned aerial vehicle and unmanned aerial vehicle system |
| CN113794840A (en) * | 2017-09-29 | 2021-12-14 | 深圳市大疆创新科技有限公司 | Video processing method, video processing equipment, unmanned aerial vehicle and video processing system |
| US11611811B2 (en) | 2017-09-29 | 2023-03-21 | SZ DJI Technology Co., Ltd. | Video processing method and device, unmanned aerial vehicle and system |
| CN110268704B (en) * | 2017-09-29 | 2021-09-28 | 深圳市大疆创新科技有限公司 | Video processing method, device, unmanned aerial vehicle and system |
| WO2019061295A1 (en) * | 2017-09-29 | 2019-04-04 | 深圳市大疆创新科技有限公司 | Video processing method and device, unmanned aerial vehicle and system |
| CN110268704A (en) * | 2017-09-29 | 2019-09-20 | 深圳市大疆创新科技有限公司 | Method for processing video frequency, equipment, unmanned plane and system |
| CN107861436A (en) * | 2017-12-01 | 2018-03-30 | 上海市环境科学研究院 | A kind of multi-rotor unmanned aerial vehicle high altitude environment detecting system |
| CN109995993A (en) * | 2018-01-02 | 2019-07-09 | 广州亿航智能技术有限公司 | Aircraft and its filming control method, device and terminal system |
| WO2019134516A1 (en) * | 2018-01-05 | 2019-07-11 | Oppo广东移动通信有限公司 | Method and device for generating panoramic image, storage medium, and electronic apparatus |
| CN108492255A (en) * | 2018-04-10 | 2018-09-04 | 浙江知水信息技术有限公司 | A method of hydraulic engineering panorama sketch is shown based on mobile application end |
| CN108492256A (en) * | 2018-04-18 | 2018-09-04 | 中国人民解放军陆军工程大学 | The quick joining method of UAV Video |
| CN108492256B (en) * | 2018-04-18 | 2022-03-04 | 中国人民解放军陆军工程大学 | Unmanned aerial vehicle video fast splicing method |
| CN108680137A (en) * | 2018-04-24 | 2018-10-19 | 天津职业技术师范大学 | Earth subsidence detection method and detection device based on unmanned plane and Ground Penetrating Radar |
| CN108718403A (en) * | 2018-06-08 | 2018-10-30 | 重庆交通职业学院 | Image panorama system for the unmanned hot air dirigible airship of more rotors |
| CN108900773A (en) * | 2018-07-27 | 2018-11-27 | 武汉禾木林科技有限公司 | A method of shooting very-high solution is taken photo by plane panorama sketch |
| CN109410279A (en) * | 2018-08-31 | 2019-03-01 | 南京理工大学 | Image detection based on deep learning positions accelerated method |
| CN110969574A (en) * | 2018-09-29 | 2020-04-07 | 广州汽车集团股份有限公司 | Vehicle-mounted panoramic map creation method and device |
| CN109547708A (en) * | 2018-12-04 | 2019-03-29 | 中国航空工业集团公司西安航空计算技术研究所 | A kind of synthetic vision image processing system |
| CN109712071A (en) * | 2018-12-14 | 2019-05-03 | 电子科技大学 | Unmanned plane image mosaic and localization method based on track constraint |
| CN109840017A (en) * | 2019-01-11 | 2019-06-04 | 博拉网络股份有限公司 | A kind of panoramic picture methods of exhibiting, system and storage medium |
| CN109597430B (en) * | 2019-01-18 | 2023-04-18 | 东北农业大学 | Unmanned aerial vehicle system based on photo dimension-rising analysis |
| CN109597430A (en) * | 2019-01-18 | 2019-04-09 | 东北农业大学 | The UAV system of dimension analysis is risen based on photo |
| CN109902565A (en) * | 2019-01-21 | 2019-06-18 | 深圳市烨嘉为技术有限公司 | The Human bodys' response method of multiple features fusion |
| CN110084743B (en) * | 2019-01-25 | 2023-04-14 | 电子科技大学 | Image splicing and positioning method based on multi-flight-zone initial flight path constraint |
| CN110084743A (en) * | 2019-01-25 | 2019-08-02 | 电子科技大学 | Image mosaic and localization method based on more air strips starting track constraint |
| CN110097498A (en) * | 2019-01-25 | 2019-08-06 | 电子科技大学 | More air strips image mosaics and localization method based on unmanned aerial vehicle flight path constraint |
| CN113631477A (en) * | 2019-04-02 | 2021-11-09 | 索尼集团公司 | Information processing apparatus, information processing method, and program |
| CN110111250A (en) * | 2019-04-11 | 2019-08-09 | 中国地质大学（武汉） | A kind of automatic panorama unmanned plane image split-joint method and device of robust |
| CN110111250B (en) * | 2019-04-11 | 2020-10-30 | 中国地质大学（武汉） | Robust automatic panoramic unmanned aerial vehicle image splicing method and device |
| CN110191311A (en) * | 2019-04-15 | 2019-08-30 | 贵州电网有限责任公司 | A kind of real-time video joining method based on multiple no-manned plane |
| CN110059651A (en) * | 2019-04-24 | 2019-07-26 | 北京计算机技术及应用研究所 | A kind of camera real-time tracking register method |
| CN110059651B (en) * | 2019-04-24 | 2021-07-02 | 北京计算机技术及应用研究所 | Real-time tracking and registering method for camera |
| CN111951198A (en) * | 2019-05-16 | 2020-11-17 | 杭州海康机器人技术有限公司 | Unmanned aerial vehicle aerial image splicing optimization method and device and storage medium |
| CN111951198B (en) * | 2019-05-16 | 2024-02-02 | 杭州海康威视数字技术股份有限公司 | Unmanned aerial vehicle aerial image stitching optimization method, device and storage medium |
| CN111951158A (en) * | 2019-05-16 | 2020-11-17 | 杭州海康机器人技术有限公司 | Recovery method and device for splicing interruption of aerial image of unmanned aerial vehicle and storage medium |
| CN111951201A (en) * | 2019-05-16 | 2020-11-17 | 杭州海康机器人技术有限公司 | Unmanned aerial vehicle aerial image splicing method and device and storage medium |
| CN111951201B (en) * | 2019-05-16 | 2024-01-23 | 杭州海康威视数字技术股份有限公司 | Unmanned aerial vehicle aerial image splicing method, device and storage medium |
| CN111951158B (en) * | 2019-05-16 | 2024-04-12 | 杭州海康威视数字技术股份有限公司 | Unmanned aerial vehicle aerial image splicing interruption recovery method, device and storage medium |
| CN110503621A (en) * | 2019-08-23 | 2019-11-26 | 上海圭目机器人有限公司 | Image overall joining method based on location data |
| CN110648281A (en) * | 2019-09-23 | 2020-01-03 | 华南农业大学 | Method, device and system for generating field panorama, server and storage medium |
| CN110889818A (en) * | 2019-11-22 | 2020-03-17 | 华南农业大学 | Low-altitude unmanned aerial vehicle image splicing method and system, computer equipment and storage medium |
| CN111062341A (en) * | 2019-12-20 | 2020-04-24 | 广州市鑫广飞信息科技有限公司 | Video image area classification method, device, equipment and storage medium |
| CN111062984B (en) * | 2019-12-20 | 2024-03-15 | 广州市鑫广飞信息科技有限公司 | Method, device, equipment and storage medium for measuring area of video image area |
| CN111062341B (en) * | 2019-12-20 | 2024-03-19 | 广州市鑫广飞信息科技有限公司 | Video image area classification method, device, equipment and storage medium |
| CN111062984A (en) * | 2019-12-20 | 2020-04-24 | 广州市鑫广飞信息科技有限公司 | Method, device and equipment for measuring area of video image region and storage medium |
| CN111327840A (en) * | 2020-02-27 | 2020-06-23 | 努比亚技术有限公司 | Multi-frame special-effect video acquisition method, terminal and computer readable storage medium |
| CN113361552A (en) * | 2020-03-05 | 2021-09-07 | 西安邮电大学 | Positioning method and device |
| CN113361552B (en) * | 2020-03-05 | 2024-02-20 | 西安远智电子科技有限公司 | Positioning method and device |
| CN111402136A (en) * | 2020-03-19 | 2020-07-10 | 贝壳技术有限公司 | Panorama generation method and device, computer readable storage medium and electronic equipment |
| CN111402136B (en) * | 2020-03-19 | 2023-12-15 | 如你所视(北京)科技有限公司 | Panorama generation method and device, computer readable storage medium and electronic equipment |
| CN111445429A (en) * | 2020-03-26 | 2020-07-24 | 北京易康医疗科技有限公司 | PET and MRI image fusion method based on feature points |
| CN111507901B (en) * | 2020-04-15 | 2023-08-15 | 中国电子科技集团公司第五十四研究所 | Aerial image splicing and positioning method based on aerial GPS and scale invariant constraint |
| CN111507901A (en) * | 2020-04-15 | 2020-08-07 | 中国电子科技集团公司第五十四研究所 | Aerial image splicing and positioning method based on aerial belt GPS and scale invariant constraint |
| CN111640187A (en) * | 2020-04-20 | 2020-09-08 | 中国科学院计算技术研究所 | Video splicing method and system based on interpolation transition |
| CN111640187B (en) * | 2020-04-20 | 2023-05-02 | 中国科学院计算技术研究所 | Video stitching method and system based on interpolation transition |
| CN111508181A (en) * | 2020-04-28 | 2020-08-07 | 江苏理工学院 | Forest fire prevention system based on multiple unmanned aerial vehicles and method thereof |
| CN111814536B (en) * | 2020-05-21 | 2023-11-28 | 闽江学院 | Culture monitoring method and device |
| CN111814536A (en) * | 2020-05-21 | 2020-10-23 | 闽江学院 | Breeding monitoring method and device |
| WO2021238317A1 (en) * | 2020-05-29 | 2021-12-02 | 华为技术有限公司 | Panoramic image capture method and device |
| CN111680703B (en) * | 2020-06-01 | 2022-06-03 | 中国电建集团昆明勘测设计研究院有限公司 | 360-degree construction panorama linkage positioning method based on image feature point detection and matching |
| CN111680703A (en) * | 2020-06-01 | 2020-09-18 | 中国电建集团昆明勘测设计研究院有限公司 | 360-degree construction panorama linkage positioning method based on image feature point detection and matching |
| CN111708916A (en) * | 2020-06-21 | 2020-09-25 | 深圳天海宸光科技有限公司 | Unmanned aerial vehicle cluster video intelligent processing system and method |
| CN111768339A (en) * | 2020-06-29 | 2020-10-13 | 广西翼界科技有限公司 | Rapid splicing method for aerial images of unmanned aerial vehicle |
| CN112734904A (en) * | 2020-12-29 | 2021-04-30 | 中国船舶重工集团公司第七0九研究所 | Portable rapid image splicing processing system for police |
| CN112887589A (en) * | 2021-01-08 | 2021-06-01 | 深圳市智胜科技信息有限公司 | Panoramic shooting method and device based on unmanned aerial vehicle |
| CN113298707B (en) * | 2021-01-27 | 2024-05-10 | 阿里巴巴集团控股有限公司 | Image frame splicing method, video inspection method, device, equipment and storage medium |
| CN113298707A (en) * | 2021-01-27 | 2021-08-24 | 阿里巴巴集团控股有限公司 | Image frame splicing method, video inspection method, device, equipment and storage medium |
| CN113905190A (en) * | 2021-09-30 | 2022-01-07 | 中国电子科技集团公司第五十四研究所 | Panorama real-time splicing method for unmanned aerial vehicle video |
| CN113905190B (en) * | 2021-09-30 | 2023-03-10 | 中国电子科技集团公司第五十四研究所 | Panorama real-time splicing method for unmanned aerial vehicle video |
| CN114584839A (en) * | 2022-02-25 | 2022-06-03 | 智己汽车科技有限公司 | Clipping method and device for shooting vehicle-mounted video, electronic equipment and storage medium |
| CN114565516B (en) * | 2022-03-03 | 2024-05-14 | 上海核工程研究设计院股份有限公司 | Sensor data fusion containment surface area robust splicing method |
| CN114565516A (en) * | 2022-03-03 | 2022-05-31 | 上海核工程研究设计院有限公司 | Sensor data fused security shell surface area robust splicing method |
| CN114973028B (en) * | 2022-05-17 | 2023-02-03 | 中国电子科技集团公司第十研究所 | Aerial video image real-time change detection method and system |
| CN114973028A (en) * | 2022-05-17 | 2022-08-30 | 中国电子科技集团公司第十研究所 | Aerial video image real-time change detection method and system |
| WO2023066412A1 (en) * | 2022-08-17 | 2023-04-27 | 中国科学院空天信息创新研究院 | Dynamic processing method and apparatus based on unmanned aerial vehicle video pyramid model |
| CN115439424B (en) * | 2022-08-23 | 2023-09-29 | 成都飞机工业（集团）有限责任公司 | Intelligent detection method for aerial video images of unmanned aerial vehicle |
| CN115439424A (en) * | 2022-08-23 | 2022-12-06 | 成都飞机工业（集团）有限责任公司 | Intelligent detection method for aerial video image of unmanned aerial vehicle |
| CN115620515B (en) * | 2022-09-30 | 2023-09-26 | 深圳技术大学 | Method and related device for collecting interchange traffic volume based on unmanned aerial vehicle video |
| CN115620515A (en) * | 2022-09-30 | 2023-01-17 | 深圳技术大学 | Unmanned aerial vehicle video-based method for acquiring interchange traffic volume and related device |
| CN115861927A (en) * | 2022-12-01 | 2023-03-28 | 中国南方电网有限责任公司超高压输电公司大理局 | Image identification method and device for power equipment inspection image and computer equipment |
| CN115861859A (en) * | 2023-02-20 | 2023-03-28 | 中国科学院东北地理与农业生态研究所 | Slope farmland environment monitoring method and system |
| CN116186354B (en) * | 2023-04-27 | 2023-07-18 | 中关村科学城城市大脑股份有限公司 | Method, apparatus, electronic device, and computer-readable medium for displaying regional image |
| CN116186354A (en) * | 2023-04-27 | 2023-05-30 | 中关村科学城城市大脑股份有限公司 | Method, apparatus, electronic device, and computer-readable medium for displaying regional image |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102201115B (en) | 2013-12-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102201115B (en) | Real-time panoramic image stitching method of aerial videos photography by unmanned plane | |
| CN110674746B (en) | Method and device for realizing high-precision cross-mirror tracking by using video spatial relationship assistance, computer equipment and storage medium | |
| US10297074B2 (en) | Three-dimensional modeling from optical capture | |
| JP4854819B2 (en) | Image information output method | |
| Kanade et al. | Advances in cooperative multi-sensor video surveillance | |
| Weiss et al. | Intuitive 3D maps for MAV terrain exploration and obstacle avoidance | |
| EP3885871B1 (en) | Surveying and mapping system, surveying and mapping method and apparatus, device and medium | |
| Yahyanejad et al. | Incremental mosaicking of images from autonomous, small-scale uavs | |
| KR102027587B1 (en) | Enhancing video using super-resolution | |
| CN101421747A (en) | System and method to combine multiple video streams | |
| CA2705809A1 (en) | Method and apparatus of taking aerial surveys | |
| CN112469967B (en) | Mapping system, mapping method, mapping device, mapping apparatus, and recording medium | |
| EP3818741A1 (en) | Method, apparatus and computer program for performing three dimensional radio model construction | |
| CN112815923B (en) | Visual positioning method and device | |
| KR101600456B1 (en) | Method, system and recording medium for providing augmented reality service and file distribution system | |
| JP2009217524A (en) | System for generating and browsing three-dimensional moving image of city view | |
| TWI444593B (en) | Ground target geolocation system and method | |
| CN105892638A (en) | Virtual reality interaction method, device and system | |
| JP2004265396A (en) | Image forming system and image forming method | |
| CN114674323A (en) | Intelligent indoor navigation method based on image target detection and tracking | |
| CN112884803B (en) | Real-time intelligent monitoring target detection method and device based on DSP | |
| Tang et al. | Content-based 3-D mosaics for representing videos of dynamic urban scenes | |
| CN111527375A (en) | Planning method and device for surveying and mapping sampling point, control terminal and storage medium | |
| CN111868656B (en) | Operation control system, operation control method, device, equipment and medium | |
| Liu et al. | LSFB: A low-cost and scalable framework for building large-scale localization benchmark |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20131211 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |