CN112734904A - Portable rapid image splicing processing system for police - Google Patents
Portable rapid image splicing processing system for police Download PDFInfo
- Publication number
- CN112734904A CN112734904A CN202011593322.3A CN202011593322A CN112734904A CN 112734904 A CN112734904 A CN 112734904A CN 202011593322 A CN202011593322 A CN 202011593322A CN 112734904 A CN112734904 A CN 112734904A
- Authority
- CN
- China
- Prior art keywords
- module
- image
- processing engine
- feature matching
- opencv
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012545 processing Methods 0.000 title claims abstract description 100
- 238000012216 screening Methods 0.000 claims abstract description 23
- 238000000034 method Methods 0.000 claims abstract description 19
- 238000012163 sequencing technique Methods 0.000 claims abstract description 5
- 238000004422 calculation algorithm Methods 0.000 claims description 16
- 239000011159 matrix material Substances 0.000 claims description 16
- 238000004891 communication Methods 0.000 claims description 12
- 238000005457 optimization Methods 0.000 claims description 12
- 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 description 10
- 230000009466 transformation Effects 0.000 claims description 10
- 238000001514 detection method Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 7
- 238000012937 correction Methods 0.000 claims description 4
- 238000003702 image correction Methods 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 3
- 238000012935 Averaging Methods 0.000 claims description 2
- 230000003993 interaction Effects 0.000 claims description 2
- 239000000126 substance Substances 0.000 claims description 2
- 230000001131 transforming effect Effects 0.000 claims description 2
- 238000011835 investigation Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 description 1
- ATJFFYVFTNAWJD-UHFFFAOYSA-N Tin Chemical compound [Sn] ATJFFYVFTNAWJD-UHFFFAOYSA-N 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 230000002547 anomalous effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24147—Distances to closest patterns, e.g. nearest neighbour classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a portable quick image splicing processing system for police, which comprises a 360-degree panorama processing engine, an orthophoto map processing engine and a three-dimensional live-action map processing engine; the 360-degree panorama processing engine comprises a confidence coefficient screening module which is used for sequencing the confidence coefficients of the images, deleting the image matching with the confidence coefficient lower than a threshold value and obtaining an image sequence capable of being correctly matched; the orthophoto map processing engine comprises a feature matching screening module, a feature matching processing module and a feature matching processing module, wherein the feature matching processing module is used for performing feature matching based on KNN nearest neighbor search by using a FLANN method, and screening excellent feature points from all matched key points according to a set distance threshold; the three-dimensional live-action image processing engine is realized by adopting open source framework-based WebODM. The three image processing engines are integrated to form a portable and integrated rapid image processing device, so that the three images can be automatically and rapidly processed and generated.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a portable rapid image splicing processing system for police.
Background
Unmanned aerial vehicle technique of taking photo by plane. Aerial photography has been around for a long time, the first aerial photography of human history was carried out in the sky in paris by nadal, a french photographer, as early as 1858. Technical innovation makes unmanned aerial vehicle's control threshold constantly reduce, since 2016 the small-size unmanned aerial vehicle that represents in great Xinjiang started rapid development, utilize unmanned aerial vehicle to take photo by plane gradually becomes the new favorite of the hobbyist of photography. Unmanned aerial vehicle aerial photography can be applied to public security criminal case investigation field equally, and it can provide global visual angle for case investigation, provides brand-new thinking for case analysis, and practice proves that unmanned aerial vehicle aerial photography has played irreplaceable effect to the promotion of case investigation rate and investigation efficiency. Unmanned aerial vehicle takes photo by plane carries on high definition digtal camera and accomplishes shooting aloft through unmanned aerial vehicle. At early unmanned aerial vehicle in-process of taking photo by plane, need the whole flight and the camera angle of passing through remote controller control unmanned aerial vehicle of flying hand, along with the progress of technique, automatic function of taking photo by plane has been released to recent flight control APP software, and the flying hand selects the data acquisition task type of taking photo by plane on software promptly, has planned the task execution airspace, and after having configured relevant parameter, unmanned aerial vehicle can be automatically in planning the airspace and carry out the data acquisition task of taking photo by plane.
A 360 ° panorama generation technique. The panoramic technology is an image-based stitching and rendering technology, continuously acquires images on a visual field range at one point in space, forms a seamless panoramic image of the viewpoint through image stitching and fusion processing, and simulates a three-dimensional virtual scene observed from any angle of the viewpoint on a computer by utilizing a panoramic display engine. The three-dimensional virtual scene is constructed without specific modeling of the scene in the field, and is a pseudo-3D technology, but the three-dimensional virtual scene has the advantage of reflecting the surrounding environment of a circumstantial region quickly and really.
Orthophoto map generation techniques. The digital ortho-image is a digital ortho-image and related data generated by cutting an obtained image range through projecting each pixel of a digital aerial image obtained through scanning based on a digital elevation model (DEM for short) or a TIN model and then splicing the images. The digital ortho image has the following characteristics: (1) digital orthoimages have a huge library of information that is not accessible compared to digital vector terrain maps and digital terrain models. The details of the digital ortho image are displayed clearly, and compared with other images, more and more information can be extracted along with gradual amplification, so that the digital ortho image can be applied to wider fields; (2) the digital ortho-image is subjected to standard correction processing according to an unprocessed basic image, the position of the scale and the relative ground point is more accurate, the map is accurately drawn, and various requirements of a user can be well met; (3) the operation is fast and convenient, and the updating is carried out at any time. The advanced unmanned aerial vehicle sensor can be used for updating the required real-time geographic information more quickly and conveniently; (4) the digital orthophoto map is simple and easy to read, so that the relevant research of the orthophoto image of the unmanned aerial vehicle becomes simple, and the popularization and the promotion can be better.
Three-dimensional live-action image generation technology. The three-dimensional virtual display technology is a three-dimensional virtual display technology which is used for shooting an existing scene from multiple angles by using a digital camera, then performing later stage stitching, and loading and displaying through playing software. The three-dimensional live-action can be zoomed in, zoomed out, moved, watched in multiple angles and the like by an observer in browsing. Through deep programming, hot spot linking in scenes, virtual roaming among multiple scenes, radar azimuth navigation and other functions can be realized. Three-dimensional live-action technology has been widely used in many fields.
In the current investigation work, a 360-degree panorama is generally manually generated by using client software such as PtGui, an orthophoto map is manually generated by using Pix4D software, and a three-dimensional live view is manually generated by using Smart3D software. The generation mode is relatively time-consuming due to many manual participation processes from photo collection to input and editing, and has certain influence on the case investigation and analysis progress, and higher requirements on software operation skills of personnel, so that a simple and easy-to-operate image generation system capable of automatically processing collected images to obtain image processing results is urgently needed to be provided.
Disclosure of Invention
The invention aims to overcome the technical defects and provides a police portable rapid image splicing processing system, which achieves the purposes of automatically processing the acquired image to obtain an image processing result, and is simple and easy to operate.
In order to achieve the technical purpose, the technical scheme of the invention provides a portable rapid image splicing processing system for police, which comprises a 360-degree panorama processing engine, an orthophoto map processing engine and a three-dimensional live-action map processing engine; wherein the content of the first and second substances,
the 360-degree panorama processing engine comprises a confidence coefficient screening module, wherein the confidence coefficient screening module is used for sequencing the confidence coefficients of the images, deleting the image matching with the confidence coefficient lower than a threshold value, and obtaining an image sequence capable of being correctly matched;
the orthophoto map processing engine comprises a feature matching screening module, wherein the feature matching screening module is used for performing feature matching based on KNN nearest neighbor search by using a FLANN method in OpenCV and screening excellent feature points from all matched key points according to a set distance threshold;
the three-dimensional live-action image processing engine is realized by adopting open source framework-based WebODM.
Compared with the prior art, the invention integrates the 360-degree panoramic image processing engine, the orthophoto map processing engine and the three-dimensional live-action image processing engine to form a portable and integrated rapid image processing device, so that three images of the 360-degree panoramic image, the orthophoto map and the three-dimensional live-action image can be automatically and rapidly processed and generated, and the requirements of tasks such as large-scale movable security, criminal case investigation, emergency rescue and disaster relief can be met; the system supports two working modes of off-line and on-line at the same time, and can adapt to various network operating environments; the operation is simple, and the user can use the case without training, so that the case investigation efficiency can be improved.
Drawings
FIG. 1 is a structural diagram of the working principle of a portable rapid image stitching processing system for police according to an embodiment of the present invention;
fig. 2 is a block diagram of a 360 ° panorama processing engine in a portable rapid image stitching processing system for police according to an embodiment of the present invention;
FIG. 3 is a block diagram of an orthophoto processing engine in a portable rapid image stitching processing system for police according to an embodiment of the present invention;
fig. 4 is a block diagram of a three-dimensional live-action image processing engine in a portable rapid image stitching processing system for police according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As shown in fig. 1, an embodiment of the present invention provides a police portable rapid image stitching processing system, which includes a 360 ° panorama processing engine, an orthophoto map processing engine, and a three-dimensional live-action map processing engine.
As shown in fig. 2, the 360-degree panorama processing engine includes a feature extraction module, a feature matching module, a confidence screening module, a matrix estimation module, an image correction module, an image stitching module, and an image optimization module.
The characteristic extraction module is used for detecting characteristic points of the input picture according to a characteristic extraction algorithm; specifically, a SURF or ORB feature extraction algorithm in OpenCV is used for detecting feature points of an input picture.
The feature matching module is used for matching feature points of the image by using a fast nearest neighbor approximation search function library; the method specifically comprises the steps of matching feature points of an image by using a FLANN (fast Library for approximation neighbor neighbors) fast Nearest neighbor approximation search function Library in OpenCV, and then storing the confidence degrees of two optimal matches by using a KNN (Nearest neighbor and next Nearest neighbor) method in OpenCV. The KNN nearest neighbor method is characterized in that feature points are screened based on distance, one SUFT key point in one image of two optimally matched images is selected, the first two key points with the nearest Euclidean distance in the other image are found out, in the two key points, if the ratio obtained by dividing the nearest distance by the next nearest distance is smaller than a certain set threshold value T, the pair of matched points is accepted, and the threshold value T can be used for adjusting and configuring parameters according to the effect achieved by actual output requirements.
The confidence coefficient screening module is used for sequencing the confidence coefficients of the images, deleting the image matching with the confidence coefficient lower than a threshold value, and obtaining an image sequence capable of being correctly matched; the confidence of the images is sorted by a quick sorting method, the images with high confidence are stored in the same set, the matching between the images with lower confidence is deleted, and an image sequence capable of being correctly matched is obtained, so that all the matches with the confidence higher than a threshold value are combined into one set, and the threshold value can be configured by a system according to the actual effect.
The matrix estimation module is used for carrying out camera parameter estimation on all images and calculating a rotation matrix; the matrix estimation module comprises a rough estimation submodule and a precise estimation submodule, wherein the rough estimation submodule is used for carrying out camera parameter rough estimation on all images by using a stopping _ detail program interface in OpenCV and then calculating a rotation matrix; the accurate estimation submodule is used for further accurately estimating a rotation matrix by using a beam averaging method in a stopping _ detail program interface in OpenCV.
The image correction module is used for carrying out waveform correction on the image; i.e. waveform correction of the image using the stopping _ detail program interface in OpenCV. Because the angle is not always the same when the photos are taken, the spliced photos can cause the panoramic image to appear as an airplane curve, so that the waveform of the image is corrected, and mainly a rising vector of each image is searched to correct the image into the same horizontal or vertical angle.
The picture splicing module is used for executing picture splicing; i.e. picture stitching is performed using the pinning _ detail program interface in OpenCV.
The picture optimization module is used for respectively carrying out complementary day optimization, vertical angle optimization and chromatic aberration optimization on the image. And (4) because the upper part is black after the picture splicing is finished, mirror image expansion is utilized, namely, pixels adjacent to the black edge of the picture are extracted and filled to the black part to finish the sky-complementing optimization. The original spliced pictures cannot see the vertical angle, and the vertical angle is optimized after the pictures are adjusted in a ratio of 2: 1. And respectively acquiring histograms of left and right partial pixels at the joint seam, and performing mean value processing to optimize the phenomenon that the color difference at the seam is obvious, namely color difference optimization.
As shown in fig. 3, the orthophoto map processing engine includes a boundary extension module, a gray scale processing module, a feature detection module, a feature matching and screening module, an affine transformation module, and an image stitching module.
The boundary expansion module is used for performing boundary expansion on two pictures arranged according to an input sequence from four directions by using a copy MakeBorder function in OpenCV;
the gray processing module is used for carrying out gray processing on the two expansion images by using a cvtColor function in OpenCV respectively.
The feature detection module is used for performing feature detection on the gray level picture by using an SIFT feature matching algorithm in OpenCV to obtain a key point list and a descriptor. The SIFT feature matching algorithm is to map (transform) an image into a local feature vector set; the characteristic vector has the invariance of translation, scaling and rotation, and simultaneously has certain invariance to illumination change, affine and projection transformation; therefore, the SIFT feature matching algorithm can process the matching problem under the conditions of translation, rotation and affine transformation between two images, and has strong matching capability.
The feature matching and screening module is used for performing feature matching based on KNN nearest neighbor search by using a FLANN algorithm in OpenCV and screening excellent feature points from all matched key points according to a set distance threshold; the FLANN algorithm uses KDTreeIndex configuration indexes, the number of density trees is 5, and the recursion times are 50. The number of neighbors based on KNN nearest neighbor search is set to 2, and if the first neighboring distance is smaller than 0.6 times the second neighboring distance, the next affine transformation matrix calculation is performed, and otherwise, the affine transformation matrix calculation is discarded. At least 10 feature points of the two graphs are successfully matched until the matching is successful.
The affine transformation module is used for calculating an affine transformation matrix between two pictures by using a RANSAC random sampling consensus algorithm in OpenCV, and transforming the second picture to be placed at a position corresponding to the first picture; the RANSAC Random Sample Consensus (RANSAC) algorithm iteratively estimates parameters of a mathematical model from a set of observed data that includes outliers. The RANSAC algorithm assumes that the data contains both correct data and anomalous data (otherwise known as noise). Correct data are denoted as inner points (inliers) and abnormal data are denoted as outer points (outliers). RANSAC also assumes that, given a correct set of data, there is a way to calculate the model parameters that fit into the data. The core idea of the algorithm is randomness and hypothesis, wherein the randomness is to randomly select sampling data according to the occurrence probability of correct data, and the randomness simulation can approximately obtain a correct result according to a law of large numbers. The hypothesis is that the sampled data are all correct data, then the correct data are used to calculate other points through the model satisfied by the problem, and then the result is scored.
The image splicing module is used for splicing the two pictures by using a locking _ detail program interface in OpenCV.
As shown in fig. 4, the three-dimensional live-action processing engine includes an account creation module, a project creation module, a task creation module, a model splicing module, a state acquisition module, and a model acquisition module.
The account creation module is used for calling a login interface of the WebODM, creating a login account and sending a login authentication request;
the project creating module is used for calling a project creating interface of the WebODM and executing a project creating command;
the task creating module is used for calling a task creating interface of the WebODM under the created project and executing a task creating command;
the model splicing module is used for calling a task execution interface of the WebODM, executing the task and splicing the three-dimensional model;
the state acquisition module is used for calling an acquisition state interface of the WebODM and acquiring a task execution state in real time;
and the model acquisition module is used for downloading the task result through the HTTP request after the task is executed, and acquiring the three-dimensional model.
The portable rapid image splicing processing system for police further comprises a wireless communication module, wherein the wireless communication module is respectively in communication connection with the 360-degree panorama processing engine, the orthophoto map processing engine and the three-dimensional real scene map processing engine and is in communication connection with the image acquisition system; the wireless communication module is used for respectively establishing information interaction channels between the image acquisition system and the 360-degree panorama processing engine, the orthophoto map processing engine and the three-dimensional real scene processing engine.
After the unmanned aerial vehicle executes the aerial photography data acquisition task, the unmanned aerial vehicle lands on the ground. The working personnel introduces the photos in the SD card of the unmanned aerial vehicle into the system, one or more of a 360-degree panorama processing engine, an orthophoto map processing engine and a three-dimensional live-action image processing engine are selected to execute image processing tasks, and image processing results are automatically generated and obtained based on the selected image processing engine.
The device supports both offline and online working modes, and is suitable for different network environments. When the online mode is adopted, the unmanned aerial vehicle immediately transmits the pictures back to the police portable rapid image splicing processing system by calling the wireless communication module in the process of executing the flight task to shoot the pictures, one or more of a 360-degree panorama processing engine, an orthophoto map processing engine and a three-dimensional live-action map processing engine are selected to execute the image processing tasks, and an image processing result is automatically generated and obtained based on the processing steps according to the selected image processing engine. The unmanned aerial vehicle does not need to be taken down in the whole image processing process, the model can be generated quickly, precious time can be saved, parallel work can be carried out under the condition that the network communication condition is good, the working efficiency is improved, and then the case detection efficiency is improved. After the task is executed, the result file can be checked locally, and can also be guided to be sent to a related case detection unit for analysis.
Those of ordinary skill in the art would appreciate that the modules, elements, and/or method steps of the various embodiments described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (8)
1. A portable quick image splicing processing system for police is characterized by comprising a 360-degree panorama processing engine, an orthophoto map processing engine and a three-dimensional live-action map processing engine; wherein the content of the first and second substances,
the 360-degree panorama processing engine comprises a confidence coefficient screening module, wherein the confidence coefficient screening module is used for sequencing the confidence coefficients of the images, deleting the image matching with the confidence coefficient lower than a threshold value, and obtaining an image sequence capable of being correctly matched;
the orthophoto map processing engine comprises a feature matching screening module, wherein the feature matching screening module is used for performing feature matching based on KNN nearest neighbor search by using a FLANN method in OpenCV and screening excellent feature points from all matched key points according to a set distance threshold;
the three-dimensional live-action image processing engine is realized by adopting open source framework-based WebODM.
2. The police portable rapid image stitching processing system according to claim 1, wherein the 360 ° panorama processing engine comprises a feature extraction module, a feature matching module, a confidence screening module, a matrix estimation module, an image correction module, and an image stitching module;
the characteristic extraction module is used for detecting characteristic points of the input picture according to a characteristic extraction algorithm;
the feature matching module is used for matching feature points of the image by using a fast nearest neighbor approximation search function library;
the confidence coefficient screening module is used for sequencing the confidence coefficients of the images, deleting the image matching with the confidence coefficient lower than a threshold value, and obtaining an image sequence capable of being correctly matched;
the matrix estimation module is used for carrying out camera parameter estimation on all images and calculating a rotation matrix;
the image correction module is used for carrying out waveform correction on the image;
the picture splicing module is used for executing picture splicing.
3. The police portable rapid image stitching processing system according to claim 2, wherein the matrix estimation module comprises a rough estimation sub-module and a precise estimation sub-module, the rough estimation sub-module is configured to perform camera parameter rough estimation on all images by using a stopping _ detail program interface in OpenCV, and then calculate a rotation matrix; the accurate estimation submodule is used for further accurately estimating a rotation matrix by using a beam averaging method in a stopping _ detail program interface in OpenCV.
4. The police portable rapid image stitching processing system according to claim 1, wherein the 360 ° panorama processing engine further comprises a picture optimization module, and the picture optimization module is configured to perform a complementary-day optimization, a vertical-angle optimization, and a color difference optimization on the image, respectively.
5. The police portable rapid image stitching processing system according to claim 1, wherein the orthophoto map processing engine comprises a boundary extension module, a gray scale processing module, a feature detection module, a feature matching screening module, an affine transformation module, and an image stitching module;
the boundary expansion module is used for performing boundary expansion on two pictures arranged according to an input sequence from four directions by using a copy MakeBorder function in OpenCV;
the gray processing module is used for performing gray processing on the two expansion images by using a cvtColor function in OpenCV respectively;
the characteristic detection module is used for carrying out characteristic detection on the gray level picture by using an SIFT characteristic matching algorithm in OpenCV to obtain a key point list and a descriptor;
the feature matching and screening module is used for performing feature matching based on KNN nearest neighbor search by using a FLANN algorithm in OpenCV and screening excellent feature points from all matched key points according to a set distance threshold;
the affine transformation module is used for calculating an affine transformation matrix between two pictures by using a RANSAC random sampling consensus algorithm in OpenCV, and transforming the second picture to be placed at a position corresponding to the first picture;
the image splicing module is used for splicing the two pictures by using a locking _ detail program interface in OpenCV.
6. The police portable rapid image stitching processing system according to claim 5, wherein the FLANN algorithm in the feature matching filter module uses a KDTreeIndex configuration index.
7. The police portable rapid image stitching processing system according to claim 1, wherein the three-dimensional live-action image processing engine comprises an account creation module, a project creation module, a task creation module, a model stitching module, a state acquisition module, and a model acquisition module;
the account creation module is used for calling a login interface of the WebODM, creating a login account and sending a login authentication request;
the project creating module is used for calling a project creating interface of the WebODM and executing a project creating command;
the task creating module is used for calling a task creating interface of the WebODM under the created project and executing a task creating command;
the model splicing module is used for calling a task execution interface of the WebODM, executing the task and splicing the three-dimensional model;
the state acquisition module is used for calling an acquisition state interface of the WebODM and acquiring a task execution state in real time;
and the model acquisition module is used for downloading the task result through the HTTP request after the task is executed, and acquiring the three-dimensional model.
8. The portable police rapid image stitching processing system according to claim 1, further comprising a wireless communication module, wherein the wireless communication module is in communication connection with the 360 ° panorama processing engine, the orthophoto map processing engine and the three-dimensional real scene map processing engine respectively, and is in communication connection with the image acquisition system; the wireless communication module is used for respectively establishing information interaction channels between the image acquisition system and the 360-degree panorama processing engine, the orthophoto map processing engine and the three-dimensional real scene processing engine.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011593322.3A CN112734904A (en) | 2020-12-29 | 2020-12-29 | Portable rapid image splicing processing system for police |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011593322.3A CN112734904A (en) | 2020-12-29 | 2020-12-29 | Portable rapid image splicing processing system for police |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112734904A true CN112734904A (en) | 2021-04-30 |
Family
ID=75607406
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011593322.3A Pending CN112734904A (en) | 2020-12-29 | 2020-12-29 | Portable rapid image splicing processing system for police |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112734904A (en) |
Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102201115A (en) * | 2011-04-07 | 2011-09-28 | 湖南天幕智能科技有限公司 | Real-time panoramic image stitching method of aerial videos shot by unmanned plane |
| US20160217611A1 (en) * | 2015-01-26 | 2016-07-28 | Uber Technologies, Inc. | Map-like summary visualization of street-level distance data and panorama data |
| CN106709983A (en) * | 2016-11-18 | 2017-05-24 | 航天图景（北京）科技有限公司 | Three-dimensional model acquisition and application system and method |
| CN107743222A (en) * | 2017-11-22 | 2018-02-27 | 中国安全生产科学研究院 | A kind of image processing method and three-dimensional panorama VR collectors based on collector |
| CN107784632A (en) * | 2016-08-26 | 2018-03-09 | 南京理工大学 | A kind of infrared panorama map generalization method based on infra-red thermal imaging system |
| CN107907803A (en) * | 2017-11-23 | 2018-04-13 | 南京杰迈视讯科技有限公司 | A kind of portable augmented reality ultraviolet imagery system |
| CN108038822A (en) * | 2017-11-23 | 2018-05-15 | 极翼机器人(上海)有限公司 | A kind of mobile phone holder distant view photograph joining method |
| CN108416732A (en) * | 2018-02-02 | 2018-08-17 | 重庆邮电大学 | A kind of Panorama Mosaic method based on image registration and multi-resolution Fusion |
| CN109493278A (en) * | 2018-10-24 | 2019-03-19 | 北京工业大学 | A kind of large scene image mosaic system based on SIFT feature |
| CN109905612A (en) * | 2019-03-25 | 2019-06-18 | 山东省交通规划设计院 | Portable Road Design full-view image field investigation system and method |
| CN110930310A (en) * | 2019-12-09 | 2020-03-27 | 中国科学技术大学 | Panoramic image splicing method |
| CN110930439A (en) * | 2019-12-04 | 2020-03-27 | 长光卫星技术有限公司 | High-grade product automatic production system suitable for high-resolution remote sensing image |
| CN111161154A (en) * | 2019-12-31 | 2020-05-15 | 航天图景（北京）科技有限公司 | Real-time and rapid orthoscopic splicing system and method for videos of unmanned aerial vehicle |
| CN111311492A (en) * | 2020-02-04 | 2020-06-19 | 西安电子科技大学 | Crack image splicing method |
| CN111476251A (en) * | 2020-03-26 | 2020-07-31 | 中国人民解放军战略支援部队信息工程大学 | Remote sensing image matching method and device |
| CN111553845A (en) * | 2020-04-29 | 2020-08-18 | 南京邮电大学 | Rapid image splicing method based on optimized three-dimensional reconstruction |
| CN112017222A (en) * | 2020-09-08 | 2020-12-01 | 北京正安维视科技股份有限公司 | Video panorama stitching and three-dimensional fusion method and device |
| CN112085844A (en) * | 2020-09-11 | 2020-12-15 | 中国人民解放军军事科学院国防科技创新研究院 | Unmanned aerial vehicle image rapid three-dimensional reconstruction method for field unknown environment |
| CN112085845A (en) * | 2020-09-11 | 2020-12-15 | 中国人民解放军军事科学院国防科技创新研究院 | Outdoor scene rapid three-dimensional reconstruction device based on unmanned aerial vehicle image |
-
2020
- 2020-12-29 CN CN202011593322.3A patent/CN112734904A/en active Pending
Patent Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102201115A (en) * | 2011-04-07 | 2011-09-28 | 湖南天幕智能科技有限公司 | Real-time panoramic image stitching method of aerial videos shot by unmanned plane |
| US20160217611A1 (en) * | 2015-01-26 | 2016-07-28 | Uber Technologies, Inc. | Map-like summary visualization of street-level distance data and panorama data |
| CN107784632A (en) * | 2016-08-26 | 2018-03-09 | 南京理工大学 | A kind of infrared panorama map generalization method based on infra-red thermal imaging system |
| CN106709983A (en) * | 2016-11-18 | 2017-05-24 | 航天图景（北京）科技有限公司 | Three-dimensional model acquisition and application system and method |
| CN107743222A (en) * | 2017-11-22 | 2018-02-27 | 中国安全生产科学研究院 | A kind of image processing method and three-dimensional panorama VR collectors based on collector |
| CN107907803A (en) * | 2017-11-23 | 2018-04-13 | 南京杰迈视讯科技有限公司 | A kind of portable augmented reality ultraviolet imagery system |
| CN108038822A (en) * | 2017-11-23 | 2018-05-15 | 极翼机器人(上海)有限公司 | A kind of mobile phone holder distant view photograph joining method |
| CN108416732A (en) * | 2018-02-02 | 2018-08-17 | 重庆邮电大学 | A kind of Panorama Mosaic method based on image registration and multi-resolution Fusion |
| CN109493278A (en) * | 2018-10-24 | 2019-03-19 | 北京工业大学 | A kind of large scene image mosaic system based on SIFT feature |
| CN109905612A (en) * | 2019-03-25 | 2019-06-18 | 山东省交通规划设计院 | Portable Road Design full-view image field investigation system and method |
| CN110930439A (en) * | 2019-12-04 | 2020-03-27 | 长光卫星技术有限公司 | High-grade product automatic production system suitable for high-resolution remote sensing image |
| CN110930310A (en) * | 2019-12-09 | 2020-03-27 | 中国科学技术大学 | Panoramic image splicing method |
| CN111161154A (en) * | 2019-12-31 | 2020-05-15 | 航天图景（北京）科技有限公司 | Real-time and rapid orthoscopic splicing system and method for videos of unmanned aerial vehicle |
| CN111311492A (en) * | 2020-02-04 | 2020-06-19 | 西安电子科技大学 | Crack image splicing method |
| CN111476251A (en) * | 2020-03-26 | 2020-07-31 | 中国人民解放军战略支援部队信息工程大学 | Remote sensing image matching method and device |
| CN111553845A (en) * | 2020-04-29 | 2020-08-18 | 南京邮电大学 | Rapid image splicing method based on optimized three-dimensional reconstruction |
| CN112017222A (en) * | 2020-09-08 | 2020-12-01 | 北京正安维视科技股份有限公司 | Video panorama stitching and three-dimensional fusion method and device |
| CN112085844A (en) * | 2020-09-11 | 2020-12-15 | 中国人民解放军军事科学院国防科技创新研究院 | Unmanned aerial vehicle image rapid three-dimensional reconstruction method for field unknown environment |
| CN112085845A (en) * | 2020-09-11 | 2020-12-15 | 中国人民解放军军事科学院国防科技创新研究院 | Outdoor scene rapid three-dimensional reconstruction device based on unmanned aerial vehicle image |
Non-Patent Citations (16)
| Title |
|---|
| CZL389: "图像拼接（十）：OPenCV stitching和stitching_detailed", 《CSDN,HTTPS://BLOG.CSDN.NET/CZL389/ARTICLE/DETAILS/60767654/》, pages 1 - 2 * |
| DAVIDAC: "如何使用OpenDroneMap对航拍图像快速建模", 《SEGMENTFAULT，HTTPS://SEGMENTFAULT.COM/A/1190000010612098》 * |
| DAVIDAC: "如何使用OpenDroneMap对航拍图像快速建模", 《SEGMENTFAULT，HTTPS://SEGMENTFAULT.COM/A/1190000010612098》, 11 August 2017 (2017-08-11), pages 1 - 6 * |
| HAIRUIJY: "Flann特征点匹配简述", 《CSDN，HTTPS://BLOG.CSDN.NET/U010368556/ARTICLE/DETAILS/82939404》 * |
| HAIRUIJY: "Flann特征点匹配简述", 《CSDN，HTTPS://BLOG.CSDN.NET/U010368556/ARTICLE/DETAILS/82939404》, 4 October 2018 (2018-10-04), pages 1 - 2 * |
| WEIPING ZHANG 等: "Remote sensing image mosaic technology based on SURF algorithm in agriculture", 《SPRINGER》, pages 1 - 9 * |
| YONG ZHAO 等: "Real-Time Orthophoto Mosaicing on Mobile Devices for Sequential Aerial Images with Low Overlap", 《REMOTE SENSING》, pages 1 - 15 * |
| ŽARKO ZEČEVIĆ 等: "Cloud Based Solution for Automatic Image Mosaicking and Georeferencing", 《22ND INTERNATIONAL SCIENTIFIC-PROFESSIONAL CONFERENCE INFORMATION TECHNOLOGY 2017》, vol. 1, pages 257 - 258 * |
| ŽARKO ZEČEVIĆ等: "Cloud Base Solution for Automatic Image Mosaicking and Georeferencing", 《22ND INTERNATIONAL SCIENTIFIC-PROFESSIONAL CONFERENCE INFORMATION TECHNOLOGY 2017》 * |
| ŽARKO ZEČEVIĆ等: "Cloud Base Solution for Automatic Image Mosaicking and Georeferencing", 《22ND INTERNATIONAL SCIENTIFIC-PROFESSIONAL CONFERENCE INFORMATION TECHNOLOGY 2017》, 13 May 2018 (2018-05-13), pages 1 - 5 * |
| ZHANGPYI: "【计算机视觉】stitching_detail算法介绍", 《博客园，HTTPS://WWW.CNBLOGS.COM/HUTY/P/8516981.HTML》, pages 1 - 16 * |
| 余建军等: "天地一体全景影像快速获取与应用技术", 《测绘通报》 * |
| 余建军等: "天地一体全景影像快速获取与应用技术", 《测绘通报》, no. 07, 25 July 2017 (2017-07-25), pages 103 - 107 * |
| 小金乌会发光-Z&M: "图像拼接（image stitching）", 《博客园，HTTPS://WWW.CNBLOGS.COM/CARSONZHU/P/11649414.HTML》, pages 1 - 14 * |
| 杨毅等: "融合图像语义的动态视频拼接方法", 《系统工程与电子技术》 * |
| 杨毅等: "融合图像语义的动态视频拼接方法", 《系统工程与电子技术》, no. 12, 31 December 2018 (2018-12-31), pages 2845 - 2854 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109741257B (en) | Full-automatic panorama shooting and splicing system and method | |
| CN108702444B (en) | Image processing method, unmanned aerial vehicle and system | |
| CN109272530B (en) | Target tracking method and device for space-based monitoring scene | |
| CN109387186B (en) | Surveying and mapping information acquisition method and device, electronic equipment and storage medium | |
| CN108401112B (en) | Image processing method, device, terminal and storage medium | |
| CN111640181A (en) | Interactive video projection method, device, equipment and storage medium | |
| CN110799921A (en) | Shooting method and device and unmanned aerial vehicle | |
| CN110599445A (en) | Target robust detection and defect identification method and device for power grid nut and pin | |
| WO2023280038A1 (en) | Method for constructing three-dimensional real-scene model, and related apparatus | |
| CN110430359A (en) | Shoot householder method, device, computer equipment and storage medium | |
| CN108509621B (en) | Scenic spot identification method, device, server and storage medium for scenic spot panoramic image | |
| WO2023011013A1 (en) | Splicing seam search method and apparatus for video image, and video image splicing method and apparatus | |
| CN108320304A (en) | A kind of automatic edit methods and system of unmanned plane video media | |
| Castillo-Carrión et al. | SIFT optimization and automation for matching images from multiple temporal sources | |
| JP2019045991A (en) | Generation device, generation method and program | |
| CN111105351B (en) | Video sequence image splicing method and device | |
| CN111527375B (en) | Planning method and device for surveying and mapping sampling point, control terminal and storage medium | |
| US20190172226A1 (en) | System and method for generating training images | |
| CN112270748B (en) | Three-dimensional reconstruction method and device based on image | |
| CN107343142A (en) | The image pickup method and filming apparatus of a kind of photo | |
| CN114627252B (en) | Unmanned plane for acquiring surface temperature distribution and surface temperature distribution map acquisition method | |
| CN112734904A (en) | Portable rapid image splicing processing system for police | |
| CN114066731A (en) | Method and device for generating panorama, electronic equipment and storage medium | |
| CN112561795A (en) | Spark and OpenCV-based real-time panoramic image generation implementation system and method | |
| Fotia et al. | Applying 3D and photogrammetric scanning systems to the case of cultural heritage |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210430 |
|
| RJ01 | Rejection of invention patent application after publication |