CN113362265B - Low-cost rapid geographical splicing method for orthographic images of unmanned aerial vehicle - Google Patents
Low-cost rapid geographical splicing method for orthographic images of unmanned aerial vehicle Download PDFInfo
- Publication number
- CN113362265B CN113362265B CN202110914018.2A CN202110914018A CN113362265B CN 113362265 B CN113362265 B CN 113362265B CN 202110914018 A CN202110914018 A CN 202110914018A CN 113362265 B CN113362265 B CN 113362265B
- Authority
- CN
- China
- Prior art keywords
- images
- image
- unmanned aerial
- aerial vehicle
- tif
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 230000009466 transformation Effects 0.000 claims abstract description 15
- 239000011159 matrix material Substances 0.000 claims abstract description 12
- 238000005457 optimization Methods 0.000 claims abstract description 10
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims abstract description 6
- 230000004927 fusion Effects 0.000 claims description 17
- 238000000605 extraction Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 5
- 238000005452 bending Methods 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims 1
- 230000001131 transforming effect Effects 0.000 claims 1
- 230000000694 effects Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 230000008030 elimination Effects 0.000 description 5
- 238000003379 elimination reaction Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 230000004044 response Effects 0.000 description 4
- 230000032669 eclosion Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000013519 translation Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 240000004282 Grewia occidentalis Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013095 identification testing Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
- G06T3/4038—Scaling the whole image or part thereof for image mosaicing, i.e. plane images composed of plane sub-images
-
- G06T3/02—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration by the use of more than one image, e.g. averaging, subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Abstract
The invention discloses a low-cost rapid geographical splicing method for an orthoimage of an unmanned aerial vehicle, which comprises the following steps: firstly, extracting and describing features of the unmanned aerial vehicle image; searching images by using EXIF information in the images, simultaneously using cosine similarity as a similarity criterion of a descriptor, and using a point with a ratio of nearest neighbor to next neighbor smaller than a preset threshold as a matching point; adding constraints in optimization by using a GPS in the EXIF information of the unmanned aerial vehicle image, and positioning and attitude determination and recovering the internal parameters and distortion coefficients of the camera by using a global SfM module; triangularization is carried out on every two images to obtain UTM absolute coordinates, meanwhile, the ratio of image overlapping degree to image range of registration point ratio is calculated, after the images are filtered, an affine transformation matrix from each image to the UTM coordinate system is calculated, and the images are transformed to obtain TIF images; and fusing and splicing the TIF images to form feathering. The invention has low cost, can generate measurable 2.5D data to be provided for the emergency disaster-responding department, and meets the requirement of the emergency disaster-responding department on quick decision planning.
Description
Technical Field
The invention relates to the technical field of unmanned aerial vehicle image splicing, in particular to a low-cost method for quickly and geographically splicing an orthoimage of an unmanned aerial vehicle.
Background
Along with the wide popularization of unmanned aerial vehicles, it is more convenient and timely to attach various sensors and obtain data. At present, images acquired based on an unmanned aerial vehicle play a key role in the field of emergency disaster response, the traditional emergency disaster response is provided for relevant departments to perform decision planning by performing true three-dimensional modeling on the images acquired by the unmanned aerial vehicle, the three-dimensional modeling process is generally completed by the procedures of feature extraction, feature matching, adjustment of a light beam method, dense reconstruction and complex point cloud grids and texture maps, and although the method can achieve good effects in precision and visualization, for reconstruction of hundreds of image 3D models, the original resolution image processing may need several hours, which is undoubtedly difficult to meet the requirement of 'quick' decision of disaster departments.
In order to meet the requirement of emergency disaster, the image stitching technology becomes the mainstream means at present, wherein the core part of the image stitching is to determine the position and the posture of the camera. The current commercial software such as PhotoScan, Smart3D and SfM algorithm in RealityCapture can realize the function, but the commercial software can easily generate track drift phenomenon for positioning and attitude determination of pure images of large scenes due to no constraint of other conditions; the current SLAM technology of fire and heat can also determine the position and the posture of the camera and can achieve the real-time effect, but the SLAM system needs to calibrate the camera in advance, so that the method is a difficult thing for an unmanned aerial vehicle user; in addition, some users use onboard high-precision inertial navigation to obtain the motion trail of the camera, but the high-precision inertial navigation is too high in cost and is unacceptable for most users, so that the current common practice is still based on the SfM technology.
For example, patent application No. CN201910841797.0 discloses an ortho image real-time generation method and system based on SLAM technology, and the scheme discloses an ortho image real-time generation method and system based on SLAM technology, which can perform the following processing on a single frame image in a single frame image sequence obtained by decomposing video stream data acquired by an unmanned aerial vehicle to obtain a digital ortho image in real time, and the steps include: (1) removing the camera distortion of the single-frame image and extracting feature points; (2) acquiring and optimizing the high-precision absolute position and posture of a single-frame image; (3) and converting the four-corner point pixel coordinates of the single-frame image after the pose optimization into the coordinates of the projection image, obtaining the homography transformation relation of the single-frame image and the projection image and generating the orthoimage. Although the scheme realizes synchronous data acquisition and high-precision orthoimage generation of the unmanned aerial vehicle, registration and fusion are not carried out during image splicing, and splicing seams are eliminated after fusion, so that the image resolution precision is improved.
For example, patent application with application number CN201810444565.7 discloses a method for stitching an unmanned aerial vehicle-mounted hyperspectral line array remote sensing image, which comprises the steps of firstly collecting hyperspectral remote sensing images to be stitched, and selecting and matching feature points of the hyperspectral remote sensing images; selecting an image transformation model based on the matched feature points to carry out image registration to obtain a registered image; feathering and color balancing processing are carried out on the overlapped area based on the registered image, and then mosaic based on pixels is carried out to obtain a spliced hyperspectral image; and carrying out geographic registration on the spliced hyperspectral images based on the area array orthographic images with geographic coordinates to obtain the hyperspectral images with real geographic coordinates. Although the method can solve the problem that the coverage of a single image of the unmanned aerial vehicle is small, when image features are matched, the matching speed is low, position constraint is not added in the image registration process, and the final track of the obtained image is easy to bend.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, and realizes a low-cost rapid geographical splicing method of unmanned aerial vehicle images by combining with a GPS (global positioning system), and generates measurable 2.5D data to be provided for emergency disaster-response departments, so that the relevant departments can know disaster information as soon as possible and make correct decisions, call rescue workers and distribute necessary materials.
The purpose of the invention is realized by the following technical scheme:
a low-cost rapid geographical splicing method for orthographic images of unmanned aerial vehicles is realized according to the following steps:
the method comprises the following steps: extracting and describing features, namely extracting and describing the features of the unmanned aerial vehicle image by using a feature extraction and description algorithm;
step two: matching features, namely, searching images by using EXIF information in the images by adopting a matching algorithm, simultaneously using cosine similarity as a similarity criterion of a descriptor, and obtaining a matching point by enabling the ratio of nearest neighbor to next nearest neighbor to be smaller than a preset threshold;
step three: adding constraints in optimization by using a GPS in the EXIF information of the unmanned aerial vehicle image, and positioning and attitude determination and recovering the internal parameters and distortion coefficients of the camera by using a global SfM module fused with the GPS;
step four: triangularization is carried out on every two images according to the result of the third step to obtain UTM absolute coordinates, meanwhile, the ratio of the image overlapping degree to the image range of the registration point proportion is calculated, images which do not meet a preset threshold value are filtered, then, an affine transformation matrix from each image to the UTM coordinate system is calculated, and the images are transformed to obtain TIF images;
step five: and performing fusion and joint feathering on the TIF images after the registration in the step four.
Specifically, the third step specifically comprises the following steps:
s31, performing similarity transformation, and converting the three-dimensional reconstruction data into the same coordinate system by using GPS information;
s32, eliminating the track bending phenomenon by adding position constraint to the bundle adjustment.
The specific step four specifically comprises: triangularization is carried out on the images in pairs by using the matching relation obtained in the second step and the camera position and posture and camera internal reference and distortion coefficient obtained in the third step to obtain UTM coordinates, and then a similarity transformation matrix is estimated, wherein the formula is as follows:
wherein: a, B, C, D, E, F are the parameters to be found in a 2 x 3 matrix, x and y are pixel coordinates and 'and y' are utm coordinates, and the images are registered by the above formula to generate TIF images.
Specifically, the step five specifically comprises: and for the registered TIF images, calculating a distance change graph of each image, then globally searching for a splicing seam, rapidly feathering the seam by using pixel weighted average of left and right preset widths of the splicing seam, and finally fusing to form a panoramic image capable of performing geographic measurement.
Specifically, the feature extraction and description algorithm adopted in the step one is a DSP-SIFT algorithm.
The invention has the beneficial effects that:
1. the invention restrains global SfM by means of the low-cost GPS, thereby avoiding the problem of the curve of the camera track. In addition, by using the result of the global SfM module fused with the GPS, the method carries out constrained geographic registration on the orthoimage of the unmanned aerial vehicle, fusion of the registered images and elimination of the splicing seam of the images.
2. The invention can complete the whole process within 10 minutes of about 200 original resolution images (resolution 5472 x 3648) in performance, and the image splicing has registration and fusion functions and elimination of splicing seams after fusion.
Drawings
Fig. 1 is a block diagram of an orthophoto geostitching pipeline according to the present invention.
Fig. 2 is a conventional global SfM module camera track diagram.
FIG. 3 is a diagram of the global SfM module camera trajectory for the weighted fusion GPS of the present invention.
FIG. 4 is a schematic diagram of image overlapping degree according to the present invention.
Fig. 5 is a range diagram of the registration point-to-ratio image of the present invention.
Fig. 6 is a distance transform diagram of the present invention.
FIG. 7 is a diagram of the measurable results of orthoimage stitching according to the present invention.
Detailed Description
In order to clearly understand the technical features, objects and effects of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments.
All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The first embodiment is as follows:
in the embodiment, the method integrates a low-cost GPS, geographic registration of an image coordinate and a UTM coordinate, and joint gap eclosion on the basis of global SfM. The pipeline is shown in figure 1, and the splicing method is realized according to the following steps:
the method comprises the following steps: extracting and describing features, namely extracting and describing the features of the unmanned aerial vehicle image by using a feature extraction and description algorithm;
step two: matching features, namely, searching images by using EXIF information in the images by adopting a matching algorithm, simultaneously using cosine similarity as a similarity criterion of a descriptor, and obtaining a matching point by enabling the ratio of nearest neighbor to next nearest neighbor to be smaller than a preset threshold;
step three: adding constraints in optimization by using a GPS in the EXIF information of the unmanned aerial vehicle image, and positioning and attitude determination and recovering the internal parameters and distortion coefficients of the camera by using a global SfM module fused with the GPS;
step four: triangularization is carried out on every two images according to the result of the third step to obtain UTM absolute coordinates, meanwhile, the ratio of the image overlapping degree to the image range of the registration point proportion is calculated, images which do not meet a preset threshold value are filtered, then, an affine transformation matrix from each image to the UTM coordinate system is calculated, and the images are transformed to obtain TIF images;
step five: and performing fusion and joint feathering on the TIF images after the registration in the step four.
In the embodiment, the unmanned aerial vehicle image of the large scene has large illumination change and more repeated textures and low texture regions, so that the feature extraction and description algorithm selects DSP-SIFT, the DSP-SIFT is an improved version of SIFT, the operator improves the quality of the operator under the condition of keeping the dimension of a 128-dimensional vector of the SIFT operator unchanged, the operator is superior to a CNN method and other object identification algorithms in a large-range image identification test, and particularly has better performance for the low texture regions.
The embodiment can achieve the following technical effects:
the embodiment combines a GPS to realize a low-cost rapid geographical splicing method for unmanned aerial vehicle images, and generates measurable 2.5D data to be provided for emergency disaster-handling departments, so that the relevant departments can know disaster information as soon as possible and make correct decisions, call rescue workers and distribute necessary materials.
Example two:
in the embodiment, the method integrates a low-cost GPS, geographic registration of an image coordinate and a UTM coordinate, and joint gap eclosion on the basis of global SfM. The splicing method is realized according to the following steps:
the method comprises the following steps: extracting and describing features, namely extracting and describing the features of the unmanned aerial vehicle image by using a feature extraction and description algorithm;
step two: matching features, namely, searching images by using EXIF information in the images by adopting a matching algorithm, simultaneously using cosine similarity as a similarity criterion of a descriptor, and obtaining a matching point by enabling the ratio of nearest neighbor to next nearest neighbor to be smaller than a preset threshold;
step three: adding constraints in optimization by using a GPS in the EXIF information of the unmanned aerial vehicle image, and positioning and attitude determination and recovering the internal parameters and distortion coefficients of the camera by using a global SfM module fused with the GPS;
step four: triangularization is carried out on every two images according to the result of the third step to obtain UTM absolute coordinates, meanwhile, the ratio of the image overlapping degree to the image range of the registration point proportion is calculated, images which do not meet a preset threshold value are filtered, then, an affine transformation matrix from each image to the UTM coordinate system is calculated, and the images are transformed to obtain TIF images;
step five: and performing fusion and joint feathering on the TIF images after the registration in the step four.
In this embodiment, regarding the feature matching algorithm, in the embodiment, a spatial matching algorithm is adopted, an image in a neighborhood of a preset range is searched by using EXIF information in the image, a cosine similarity is used as a similarity criterion of a descriptor, a ratio of nearest neighbor to next nearest neighbor is smaller than a preset threshold to obtain a matching point, and the spatial matching algorithm has a better performance in speed for a large number of images.
The flow of the traditional global SfM module is as follows: the first step is a running average, the formula is as follows:
wherein R isi ，Rj Is the absolute rotation amount of each node, i.e. the amount to be optimized;
is the relative rotation between two frames and is known observation data; next is the translational averaging, the formula is as follows:
whereinC i ，C j Is the absolute translation amount of each node, namely the amount to be optimized;t ij is the amount of translation between each two and is known observed value data.
The target function of the translational average is as follows, namely, the difference value of the relative estimation translational quantity and the absolute translational quantity is minimized:
the traditional global SfM module is similar to a graph optimization problem, and is better than incremental SfM in efficiency because only global optimization is carried out. However, since the global SfM module is sensitive to data quality, especially the transformation operating is sensitive to noise anomaly, the final track is easy to be curved.
In this embodiment, constraints are added in optimization by using the GPS in the EXIF information of the unmanned aerial vehicle image, that is, the positions of t and the prior GPS estimated by the weighted minimization SfM, and the algorithm of this link is divided into two steps, and the formula is as follows:
where weight is the weight of GPS,
translation amount representing sfm and GPSThe poor norm of the position is minimal.
The first step is similarity transformation, which converts the three-dimensional reconstruction data into the same coordinate system by using the GPS information, and the second step is to add position constraint in bundle adjustment to eliminate the track bending phenomenon, as shown in fig. 2 and fig. 3, fig. 2 is a conventional global SfM, which has the track bending phenomenon, and fig. 3 is the effect of the global SfM of the weighting fusion GPS of the embodiment.
The embodiment can achieve the following effects:
the present embodiment constrains global SfM with low cost GPS, thereby avoiding the problem of camera trajectory curvature. In addition, by using the result of the global SfM module fused with the GPS, the method carries out constrained geographic registration on the orthoimage of the unmanned aerial vehicle, fusion of the registered images and elimination of the splicing seam of the images.
Example three:
in the embodiment, the method integrates a low-cost GPS, geographic registration of an image coordinate and a UTM coordinate, and joint gap eclosion on the basis of global SfM. The splicing method is realized according to the following steps:
the method comprises the following steps: extracting and describing features, namely extracting and describing the features of the unmanned aerial vehicle image by using a feature extraction and description algorithm;
step two: matching features, namely, searching images by using EXIF information in the images by adopting a matching algorithm, simultaneously using cosine similarity as a similarity criterion of a descriptor, and obtaining a matching point by enabling the ratio of nearest neighbor to next nearest neighbor to be smaller than a preset threshold;
step three: adding constraints in optimization by using a GPS in the EXIF information of the unmanned aerial vehicle image, and positioning and attitude determination and recovering the internal parameters and distortion coefficients of the camera by using a global SfM module fused with the GPS;
step four: triangularization is carried out on every two images according to the result of the third step to obtain UTM absolute coordinates, meanwhile, the ratio of the image overlapping degree to the image range of the registration point proportion is calculated, images which do not meet a preset threshold value are filtered, then, an affine transformation matrix from each image to the UTM coordinate system is calculated, and the images are transformed to obtain TIF images;
step five: and performing fusion and joint feathering on the TIF images after the registration in the step four.
In this embodiment, geographic registration of the images is performed, triangulation of two images is performed by using the matching relationship obtained in the second step, the camera position and posture and the camera internal reference and distortion coefficient obtained in the third step to obtain UTM coordinates, and then a similarity transformation matrix is estimated, wherein the formula is as follows:
wherein: a, B, C, D, E, F are the parameters to be found in a 2 x 3 matrix, x and y are pixel coordinates and 'and y' are utm coordinates, and the images are registered by the above formula to generate TIF images.
In the present embodiment, in the process of generating the TIF image by image registration, constraints are added, and images with poor quality are filtered by referring to fig. 4 for image overlapping degree and fig. 5 for the size of the registration point in the image range.
In this embodiment, for the registered TIF images, a distance change map of each image is calculated, then a splicing seam is globally found, a seam is rapidly feathered by using a pixel weighted average of left and right preset widths of the splicing seam, the distance change map is shown in fig. 6, and finally a panoramic image capable of geographic measurement is formed by fusion, as shown in fig. 7.
The embodiment can achieve the following technical effects:
1. the present embodiment constrains global SfM with low cost GPS, thereby avoiding the problem of camera trajectory curvature. In addition, by using the result of the global SfM module fused with the GPS, the method carries out constrained geographic registration on the orthoimage of the unmanned aerial vehicle, fusion of the registered images and elimination of the splicing seam of the images.
2. In the embodiment, the whole process can be completed within 10 minutes by about 200 original resolution images (resolution 5472 x 3648) in performance, image splicing has registration and fusion functions and elimination of splicing seams after fusion, the cost is low, only an unmanned aerial vehicle with a low-cost GPS needs to be carried, and the final splicing effect also meets the requirement of rapid decision planning of emergency disaster response departments.
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (3)
1. A low-cost rapid geographical splicing method for an orthographic image of an unmanned aerial vehicle is characterized by comprising the following steps:
the method comprises the following steps: extracting and describing features, acquiring unmanned aerial vehicle images, and extracting and describing the features of the unmanned aerial vehicle images; the adopted feature extraction and description algorithm is a DSP-SIFT algorithm;
step two: matching features, namely searching images by using EXIF information in the images by adopting a matching algorithm, simultaneously using cosine similarity as a similarity criterion of a descriptor, and using a point with the ratio of nearest neighbor to next nearest neighbor smaller than a preset threshold value as a matching point;
step three: adding constraints in optimization by using a GPS in the EXIF information of the unmanned aerial vehicle image, and positioning and attitude determination and recovering the internal parameters and distortion coefficients of the camera by using a global SfM module fused with the GPS; the third step specifically comprises the following steps:
s31, performing similarity transformation, and converting the three-dimensional reconstruction data into the same coordinate system by using GPS information;
s32, eliminating track bending phenomenon by adding position constraint on beam adjustment;
step four: triangularization is carried out on every two images according to the result of the third step to obtain UTM absolute coordinates, meanwhile, the ratio of the image overlapping degree to the image range of the registration point is calculated, images which do not meet a preset threshold value are filtered, and then TIF images are obtained through calculation; the fourth step specifically comprises: triangularization is carried out on the images in pairs by using the matching relation obtained in the second step and the camera position and posture and camera internal reference and distortion coefficient obtained in the third step to obtain UTM coordinates, and then a similarity transformation matrix is estimated, wherein the formula is as follows:
wherein: a, B, C, D, E and F are parameters to be solved in a matrix of 2 x 3, x and y are pixel coordinates, x 'and y' are utm coordinates, and images are registered through the above formula to generate a TIF image;
step five: and performing fusion and joint feathering on the TIF images after the registration in the step four.
2. The method for fast geographic stitching of orthoimages of unmanned aerial vehicles at low cost according to claim 1, wherein the fifth step specifically comprises: and for the registered TIF images, calculating a distance change graph of each image, then globally searching for a splicing seam, rapidly feathering the seam by using pixel weighted average of left and right preset widths of the splicing seam, and finally fusing to form a panoramic image capable of performing geographic measurement.
3. The method for fast geographic stitching of orthoimages of unmanned aerial vehicles at low cost according to claim 1, wherein the process of calculating and acquiring the TIF images specifically comprises: and respectively calculating an affine transformation matrix from each image to the UTM coordinate system and transforming the image to obtain a TIF image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110914018.2A CN113362265B (en) | 2021-08-10 | 2021-08-10 | Low-cost rapid geographical splicing method for orthographic images of unmanned aerial vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110914018.2A CN113362265B (en) | 2021-08-10 | 2021-08-10 | Low-cost rapid geographical splicing method for orthographic images of unmanned aerial vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113362265A CN113362265A (en) | 2021-09-07 |
| CN113362265B true CN113362265B (en) | 2021-11-16 |
Family
ID=77540779
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110914018.2A Active CN113362265B (en) | 2021-08-10 | 2021-08-10 | Low-cost rapid geographical splicing method for orthographic images of unmanned aerial vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113362265B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114519671B (en) * | 2022-02-16 | 2022-11-01 | 天津中科无人机应用研究院 | Unmanned aerial vehicle remote sensing image dynamic rapid splicing method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109658450A (en) * | 2018-12-17 | 2019-04-19 | 武汉天乾科技有限责任公司 | A kind of quick orthography generation method based on unmanned plane |
| CN110097093A (en) * | 2019-04-15 | 2019-08-06 | 河海大学 | A kind of heterologous accurate matching of image method |
| CN111383354A (en) * | 2020-04-02 | 2020-07-07 | 西安因诺航空科技有限公司 | SFM-based three-dimensional point cloud orientation correction method |
| CN111798373A (en) * | 2020-06-11 | 2020-10-20 | 西安视野慧图智能科技有限公司 | Rapid unmanned aerial vehicle image stitching method based on local plane hypothesis and six-degree-of-freedom pose optimization |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170243084A1 (en) * | 2015-11-06 | 2017-08-24 | The Regents Of The University Of California | Dsp-sift: domain-size pooling for image descriptors for image matching and other applications |
| US10565789B2 (en) * | 2016-01-13 | 2020-02-18 | Vito Nv | Method and system for geometric referencing of multi-spectral data |
| CN110232683A (en) * | 2019-06-10 | 2019-09-13 | 北京工业大学 | A kind of landslide detection method based on unmanned plane point cloud |
-
2021
- 2021-08-10 CN CN202110914018.2A patent/CN113362265B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109658450A (en) * | 2018-12-17 | 2019-04-19 | 武汉天乾科技有限责任公司 | A kind of quick orthography generation method based on unmanned plane |
| CN110097093A (en) * | 2019-04-15 | 2019-08-06 | 河海大学 | A kind of heterologous accurate matching of image method |
| CN111383354A (en) * | 2020-04-02 | 2020-07-07 | 西安因诺航空科技有限公司 | SFM-based three-dimensional point cloud orientation correction method |
| CN111798373A (en) * | 2020-06-11 | 2020-10-20 | 西安视野慧图智能科技有限公司 | Rapid unmanned aerial vehicle image stitching method based on local plane hypothesis and six-degree-of-freedom pose optimization |
Non-Patent Citations (2)
| Title |
|---|
| GPS改进的移动球形全景影像三维重建方法;尹双双等;《测绘科学》;20200530;第45卷(第5期);第13页右栏第一段，第1.4-1.5节 * |
| 三维重建的定位定姿算法;cheng.li@3D_Vision;《https://blog.csdn.net/qq_15642411/article/details/109166837》;20201019;第2页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113362265A (en) | 2021-09-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112435325B (en) | VI-SLAM and depth estimation network-based unmanned aerial vehicle scene density reconstruction method | |
| CN107316325B (en) | Airborne laser point cloud and image registration fusion method based on image registration | |
| CN108534782B (en) | Binocular vision system-based landmark map vehicle instant positioning method | |
| Teller et al. | Calibrated, registered images of an extended urban area | |
| CN107492069B (en) | Image fusion method based on multi-lens sensor | |
| CN107194991B (en) | Three-dimensional global visual monitoring system construction method based on skeleton point local dynamic update | |
| KR102200299B1 (en) | A system implementing management solution of road facility based on 3D-VR multi-sensor system and a method thereof | |
| CN110319772B (en) | Visual large-span distance measurement method based on unmanned aerial vehicle | |
| Taneja et al. | Registration of spherical panoramic images with cadastral 3d models | |
| CN108519102B (en) | Binocular vision mileage calculation method based on secondary projection | |
| US8547375B2 (en) | Methods for transferring points of interest between images with non-parallel viewing directions | |
| CN111815765B (en) | Heterogeneous data fusion-based image three-dimensional reconstruction method | |
| JP2012118666A (en) | Three-dimensional map automatic generation device | |
| CN109900274B (en) | Image matching method and system | |
| WO2019100219A1 (en) | Output image generation method, device and unmanned aerial vehicle | |
| CN105005964A (en) | Video sequence image based method for rapidly generating panorama of geographic scene | |
| CN112348775B (en) | Vehicle-mounted looking-around-based pavement pit detection system and method | |
| CN116883251B (en) | Image orientation splicing and three-dimensional modeling method based on unmanned aerial vehicle video | |
| Moussa et al. | A fast approach for stitching of aerial images | |
| CN113362265B (en) | Low-cost rapid geographical splicing method for orthographic images of unmanned aerial vehicle | |
| Kang et al. | An automatic mosaicking method for building facade texture mapping using a monocular close-range image sequence | |
| Tsao et al. | Stitching aerial images for vehicle positioning and tracking | |
| CN115423863B (en) | Camera pose estimation method and device and computer readable storage medium | |
| Qin et al. | 3D reconstruction through fusion of cross-view images | |
| KR102225321B1 (en) | System and method for building road space information through linkage between image information and position information acquired from a plurality of image sensors |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |