CN113239752A - Unmanned aerial vehicle aerial image automatic identification system - Google Patents
Unmanned aerial vehicle aerial image automatic identification system Download PDFInfo
- Publication number
- CN113239752A CN113239752A CN202110461261.3A CN202110461261A CN113239752A CN 113239752 A CN113239752 A CN 113239752A CN 202110461261 A CN202110461261 A CN 202110461261A CN 113239752 A CN113239752 A CN 113239752A
- Authority
- CN
- China
- Prior art keywords
- image
- edge
- module
- result
- identification
- 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
- 230000008676 import Effects 0.000 claims abstract description 21
- 238000012986 modification Methods 0.000 claims abstract description 17
- 230000004048 modification Effects 0.000 claims abstract description 17
- 238000004458 analytical method Methods 0.000 claims abstract description 16
- 238000001914 filtration Methods 0.000 claims description 18
- 238000004422 calculation algorithm Methods 0.000 claims description 16
- 238000010586 diagram Methods 0.000 claims description 14
- 238000000034 method Methods 0.000 claims description 10
- 238000001514 detection method Methods 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 9
- 238000003708 edge detection Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 7
- 238000007619 statistical method Methods 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 5
- 238000012217 deletion Methods 0.000 claims description 3
- 230000037430 deletion Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 8
- 238000002372 labelling Methods 0.000 description 8
- 239000003208 petroleum Substances 0.000 description 8
- 230000006870 function Effects 0.000 description 4
- 238000007689 inspection Methods 0.000 description 4
- 239000000284 extract Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite 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
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- 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
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Image Analysis (AREA)
Abstract
The invention belongs to the technical field of image processing, and particularly provides an automatic identification system for aerial images of unmanned aerial vehicles, which comprises a file import module, an image file identification module, an identification result marking module, a marking result modification module and a result analysis and export module, and solves the problems that the subsequent analysis and processing aspects of the aerial images of the existing unmanned aerial vehicles depend on manual identification, the identification automation level is lower, the efficiency of manual identification and marking is lower, and the required time and cost are higher. The cost is reduced.
Description
Technical Field
The invention belongs to the technical field of image processing, and particularly relates to an automatic identification system for aerial images of an unmanned aerial vehicle.
Background
In recent years, unmanned aerial vehicles are more and more widely applied to industries such as routing inspection and surveying and mapping, and the unmanned aerial vehicles are enabled to be more intelligent and automatic by virtue of the advantages of simplicity and convenience in operation, low cost, high flexibility, strong adaptability and the like.
Unmanned aerial vehicle patrols and examines, surveys and draws and generally requires to carry on camera equipment on the unmanned aerial vehicle, shoots the picture in many target areas in succession to record information such as position and angle that the image was shot, then the two-dimentional or three-dimensional image of synthetic target area carries out relevant analysis afterwards, gathers and marks the key data in the image, files image data at last.
The image synthesis technology is relatively mature and can be completely completed by a computer, and software such as Pix4Dmapper and the like can automatically synthesize a two-dimensional image of a target area with higher quality.
However, the subsequent analysis and processing of the image is relatively little, for example, labeling residential areas, hospitals, schools, roads, various key facilities and the like all need to be identified by manpower, and the automation level of identification is relatively low. The efficiency of manual identification marking is low, and the required time and cost are high.
Disclosure of Invention
The invention provides an automatic identification system for aerial images of unmanned aerial vehicles, and aims to solve the problems that in the prior art, the subsequent analysis and processing of aerial images of unmanned aerial vehicles depend on manual identification, the automation level of identification is low, the efficiency of manual identification and marking is low, and the required time and cost are high.
Therefore, the invention provides an automatic identification system for aerial images of unmanned aerial vehicles, which comprises a file import module, an image file identification module, an identification result marking module, a marking result modification module and a result analysis and export module, wherein the file import module imports an image selected by a user into the image file identification module; the image file identification module identifies the imported image and transmits an identification result to the identification result marking module; the identification result marking module marks the identification result on the image selected by the user; the marking result modification module modifies the problematic identification result; and the result analysis and export module is used for carrying out statistical analysis and storage on the identification result.
The file import module imports the image selected by the user, and comprises the following steps: and reading the image selected by the user into an internal memory, decoding and uniformly converting the image into a two-dimensional lattice image in an RGB format for storage.
The image file identification module identifies the imported image and comprises the following steps:
1) preprocessing the imported image, wherein the preprocessing comprises the following steps: firstly, converting an imported image into a gray image, and removing noise points on the gray image; then carrying out edge detection and edge refinement on the gray level image without the noise point to obtain a skeleton diagram; finally, connecting the intervals in the skeleton diagram;
2) taking the skeleton graph in the step 1) as a plane graph, taking pixel points with a plurality of branches in the skeleton graph as nodes, and taking a path between the two nodes as an edge;
3) detecting all minimum loops in the skeleton diagram in the step 2);
4) screening all the minimum loops in the step 3), and filtering out all non-rectangular loops;
5) and cutting the imported image according to the residual loop after filtering in the step 4), and classifying after cutting to form an initial identification result.
The edge detection determines edges by detecting the rate of change of adjacent portions of the image.
The edge refinement is to refine the detected edge and refine the same line to a single pixel width.
The detection minimum loop adopts an algorithm, and the algorithm comprises the following steps: two nodes v connected for all edges0And v1Defining an order, traversing forward as v0→v1Reverse traversal is v1→v0(ii) a Two count values are kept for each edge: a isiAnd biWherein a isiIndicates whether this edge is traversed in the forward direction, biIndicating whether the edge is traversed reversely; in the initial state, a for all edges i, ai＝bi0; then, one of the conditions is arbitrarily selected to satisfy ai0 or biAn edge of 0 ifiIf 0, then the edge is traversed in the forward direction, otherwise there is biWhen the edge is equal to 0, the edge is traversed reversely until the edge is returned; if the edge is traversed in the forward direction, setting the initial current node as v1(ii) a Otherwise, setting the initial current node as v0(ii) a In the process of traversing, each timeNext selecting the next edge i in the clockwise direction of the current node for traversing, and setting a according to the traversing direction i1 or b i1 is ═ 1; after returning to the initial node, traversing is completed; finding out a minimum loop after traversing; if the graph still has edges satisfying a after the traversal is finishedi0 or biIf 0, the above steps are continued until all the edges satisfy ai1 and bi＝1。
The algorithm can additionally detect a loop which does not belong to the minimum loop, and after the loop which does not belong to the minimum loop is removed after the detection is finished, the rest loops are all the minimum loops in the skeleton diagram.
And 4, screening and filtering are carried out by calculating the similarity between the loop and the rectangle, and the screening and filtering comprise the following steps: enumerating the direction of a rectangle, finding out the position of the side of the rectangle by adopting a binary search mode, uniformly taking n points of each side, calculating the ratio of the distance between the point on a loop which is perpendicular to the line segment direction and is closest to the point and the corresponding side length of each point, finally obtaining the dissimilarity degree of the shape and the rectangle, filtering out the loop of which the dissimilarity degree is greater than a preset threshold value, namely filtering out all non-rectangular loops.
The dissimilarity degree is calculated by the formula
ns is dissimilarity, theta is the direction of the rectangle, the angle of theta is 0-360 degrees, T is a preset threshold value, i is a point, and l is the length of the corresponding edge.
When the marking result modification module modifies the problematic identification result, an operator checks whether the marking of the corresponding area is wrong, and performs addition/deletion/modification operation on the corresponding area to form a final marking result, namely the final identification result.
The invention has the beneficial effects that: according to the automatic identification system for the aerial images of the unmanned aerial vehicle, the file import module has a file import function and imports the images selected by the user into the image file identification module; the image file identification module has an image file identification function, extracts, screens and classifies key areas of image files imported by a user to form a primary classification result (identification result), and the identification result marking module marks the identification result on an image selected by the user; the marking result modification module modifies the problematic identification result; the result analysis and export module is used for carrying out statistical analysis and storage on the identification result and providing reference for application of related industries, the unmanned aerial vehicle aerial image automatic identification system can automatically process an aerial image, automatically find out key areas (houses/office buildings/plants/hospitals and the like) in the image and mark the key areas on the original image, so that the automation level of application of the related industries (such as petroleum pipeline high-consequence area identification) is improved, the workload is reduced, the efficiency of identification and marking is improved, the time is shortened, and the cost is reduced.
Drawings
The present invention will be described in further detail below with reference to the accompanying drawings.
Fig. 1 is a flow chart of an automatic identification system for aerial images of an unmanned aerial vehicle;
FIG. 2 is a schematic diagram of image skeleton optimization;
FIG. 3 is a definition of nodes and edges of an image skeleton;
FIG. 4 is a minimum loop schematic;
FIG. 5 is a schematic illustration of the distance of a point on a rectangle to a corresponding point on a loop;
FIG. 6 is an exemplary aerial image of the description of the embodiments;
FIG. 7 is the results of the pretreatment of FIG. 6;
FIG. 8 is the loop extraction result of FIG. 7;
fig. 9 shows the result of the preliminary identification marked on the original image in fig. 6.
Detailed Description
Example 1:
as shown in fig. 1, an automatic identification system for aerial images of an unmanned aerial vehicle comprises a file import module, an image file identification module, an identification result labeling module, a labeling result modification module, and a result analysis and export module, wherein the file import module imports an image selected by a user into the image file identification module; the image file identification module identifies the imported image and transmits an identification result to the identification result marking module; the identification result marking module marks the identification result on the image selected by the user; the marking result modification module modifies the problematic identification result; and the result analysis and export module is used for carrying out statistical analysis and storage on the identification result.
The unmanned aerial vehicle aerial image automatic identification system comprises a front-end display part and a back-end processing algorithm part, wherein the front-end display part comprises a file import module, an identification result marking module, a marking result modification module and a result analysis and export module, is responsible for providing a user interface, is convenient for user operation, displays a processing result and allows a user to manually modify the result; the back-end processing algorithm comprises an image file identification module and provides core algorithm support for the system;
the file import module has an image file import function, and a user selects an image file, imports the image file into the image file identification module and supports multiple image formats such as jpg \ bmp \ gif \ png and the like; the image file identification module has an image file identification function, extracts, screens and classifies key areas of image files imported by a user to form a primary classification result (identification result), and the identification result marking module marks the identification result on an image selected by the user; the marking result modification module modifies the problematic identification result, and allows a user to manually adjust the problematic identification result during modification; the result analysis and export module is used for carrying out statistical analysis and storage on the identification result and providing reference for application of related industries, the unmanned aerial vehicle aerial image automatic identification system can automatically process an aerial image, automatically find out key areas (houses/office buildings/plants/hospitals and the like) in the image and mark the key areas on the original image, so that the automation level of application of the related industries (such as petroleum pipeline high-consequence area identification) is improved, the workload is reduced, the efficiency of identification and marking is improved, the time is shortened, and the cost is reduced.
Example 2:
on the basis of the embodiment 1, further, the importing the image selected by the user by the file importing module comprises the following steps: and reading the image selected by the user into an internal memory, decoding and uniformly converting the image into a two-dimensional lattice image in an RGB format for storage. Supports multiple image formats such as jpg \ bmp \ gif \ png and the like, has strong adaptability, and the part is mainly participated by the front end.
Further, the identification of the imported image by the image file identification module includes the following steps:
1) preprocessing the imported image, wherein the preprocessing comprises the following steps: firstly, converting an imported image into a gray image, and removing noise points on the gray image; then carrying out edge detection and edge refinement on the gray level image without the noise point to obtain a skeleton diagram; finally, connecting the intervals in the skeleton diagram; after the skeleton map is obtained, connecting intervals in the skeleton map (shown in figure 2), and optimizing the skeleton map;
2) taking the skeleton graph in the step 1) as a plane graph, taking pixel points with a plurality of branches in the skeleton graph as nodes, and taking a path between the two nodes as an edge (as shown in fig. 3); in the graph thus created, the degree d of each nodei(the number of edges connected to a node) satisfies: d is not less than 3i≤8；
3) Detecting all minimum loops in the skeleton diagram in the step 2); the minimum loop is a loop that cannot be split into two or more smaller loops (as shown in fig. 4, there are 5 minimum loops);
4) screening all the minimum loops in the step 3), and filtering out all non-rectangular loops;
5) and cutting the imported image according to the residual loop after filtering in the step 4), and classifying after cutting to form an initial identification result.
Further, the edge detection determines an edge by detecting a rate of change of adjacent portions of the image; the gradient value is a change rate, an algorithm for edge detection is a known technique, and a portion having a large change rate is selected as an edge during detection. The method has the advantages of simple edge determination and high definition accuracy.
Further, the edge refinement is to refine the detected edge and refine the same line to a single-pixel width. The obtained image skeleton is more accurate.
Further, the detection of the minimum loop adopts an algorithm, and the algorithm comprises the following steps: two nodes v connected for all edges0And v1Defining an order, traversing forward as v0→v1Reverse traversal is v1→v0(ii) a Two count values are kept for each edge: a isiAnd biWherein a isiIndicates whether this edge is traversed in the forward direction, biIndicating whether the edge is traversed reversely; in the initial state, a for all edges i, ai＝bi0; then, one of the conditions is arbitrarily selected to satisfy ai0 or biAn edge of 0 ifiIf 0, then the edge is traversed in the forward direction, otherwise there is biWhen the edge is equal to 0, the edge is traversed reversely until the edge is returned; if the edge is traversed in the forward direction, setting the initial current node as v1(ii) a Otherwise, setting the initial current node as v0(ii) a In the process of traversing, selecting the next edge i in the clockwise direction of the current node every time for traversing, and setting a according to the traversing direction i1 or b i1 is ═ 1; after returning to the initial node, traversing is completed; finding out a minimum loop after traversing; if the graph still has edges satisfying a after the traversal is finishedi0 or biIf 0, the above steps are continued until all the edges satisfy ai1 and bi＝1。
Furthermore, the algorithm additionally detects a loop which does not belong to the minimum loop, and after the loop which does not belong to the minimum loop is removed after the detection is finished, the rest loops are all the minimum loops in the skeleton diagram. The above-mentioned detection algorithm will additionally detect a loop that does not belong to the minimum loop, which is a loop that surrounds the outside of the whole graph (such as the loop a → B → C → D → E in fig. 4), so after the detection algorithm is executed, the loop with the largest surrounding area needs to be removed, and all the remaining loops are the minimum loops.
Further, in the step 4, a filtering process is performed by calculating the similarity between the loop and the rectangle, and the filtering process includes the following steps: enumerating the direction of the rectangle, and finding out the rectangle by adopting a binary search modeFor each side, uniformly taking n points (4 n points in total) of the side, and calculating the distance r between the point on the loop which is perpendicular to the line segment direction and is closest to the point and the point on the loop, wherein the distance r is perpendicular to the line segment directioniAs shown in fig. 5) and the length of the corresponding edge, finally obtaining the dissimilarity between the shape and the rectangle, and filtering out loops whose dissimilarity is greater than a preset threshold, i.e., filtering out all non-rectangular loops.
Further, the dissimilarity is calculated by the formula
Further, when the labeling result modification module modifies the problematic identification result, an operator checks whether the labeling of the corresponding area is incorrect, and performs addition/deletion/modification operation on the corresponding area to form a final labeling result, which is the final identification result.
The software displays the original aerial image on an interface as a bottom plate; secondly, superposing the primary identification result on a bottom plate for marking, wherein the primary identification result comprises the range of all key areas and the classification result of the key areas; the operator can check whether the labeling of the corresponding area is wrong, and directly carry out adding/deleting/modifying operation on the corresponding area on the interface, thereby adjusting the result and forming the final labeling result. Allowing the operator to adjust the annotation results to obtain more accurate results.
Further, the result analysis and export module is used for carrying out statistical analysis and storage on the identification result. The specific implementation is that relevant information is counted according to the final recognition result, some additional items can be calculated according to a self-defined formula provided by an operator, and the additional items are finally written into an Excel table specified by a user for reference. The automatic identification system can automatically count, analyze and identify results (such as the number of buildings, the estimated number of population, the number of population near flammable and explosive substances (such as petroleum pipelines) and the like) and derive Excel reports, so that workers in related industries can more conveniently perform data arrangement work, and reference is provided for industrial application.
Example 3:
on the basis of embodiment 2, the following description of the application of the unmanned aerial vehicle aerial image automatic identification system in the petroleum pipeline inspection field is provided with the accompanying drawings:
FIG. 6 is an exemplary illustration of an aerial image of a petroleum pipeline inspection tour.
Firstly, importing an aerial image picture (figure 6) of petroleum pipeline inspection into an identification system, and preprocessing the imported picture by the identification system to obtain a skeleton picture (figure 7); then detecting all minimum loops in the skeleton diagram, screening all the minimum loops which are detected, and screening out loops which do not accord with the rule, wherein the result is shown in fig. 8;
then the system identifies the corresponding area in the original image by using a classifier, and the identification result is marked on the original image (figure 9); FIG. 9 shows all buildings identified and the rooftop building classified as a plant; however, there are some misidentifications, and 3 smaller non-buildings in the graph are identified as buildings, and at this time, adjustment is manually performed on the software interface to delete 3 misidentified areas.
Finally, the system can carry out statistics and analysis on the final result to generate a form of an Excel table for subsequent statistical analysis. The table lists the number of buildings near the petroleum pipeline, the number of key buildings (the number of hospitals, schools and gas stations) and the estimated population number (a calculation formula is defined by an operator, and the system can automatically calculate according to the formula), so that the method can provide help for identifying the high-consequence area of the petroleum pipeline.
In the description of the present invention, it is to be understood that the terms "comprises" and "comprising," if any, are used in the sense of being interpreted as being based on the orientation or positional relationship shown in the drawings, and not as indicating or implying that the referenced device or element must have a particular orientation, configuration, or operation in a particular orientation.
The above examples are merely illustrative of the present invention and should not be construed as limiting the scope of the invention, which is intended to be covered by the claims and any design similar or equivalent to the scope of the invention.
Claims (10)
1. The utility model provides an unmanned aerial vehicle image automatic identification system that takes photo by plane which characterized in that: comprises a file import module, an image file identification module, an identification result marking module, a marking result modification module and a result analysis and export module,
the file import module imports the image selected by the user into the image file identification module;
the image file identification module identifies the imported image and transmits an identification result to the identification result marking module;
the identification result marking module marks the identification result on the image selected by the user;
the marking result modification module modifies the problematic identification result;
and the result analysis and export module is used for carrying out statistical analysis and storage on the identification result.
2. The unmanned aerial vehicle aerial image automatic identification system of claim 1, characterized in that: the file import module imports the image selected by the user, and comprises the following steps: and reading the image selected by the user into an internal memory, decoding and uniformly converting the image into a two-dimensional lattice image in an RGB format for storage.
3. The unmanned aerial vehicle aerial image automatic identification system of claim 1, characterized in that: the image file identification module identifies the imported image and comprises the following steps:
1) preprocessing the imported image, wherein the preprocessing comprises the following steps: firstly, converting an imported image into a gray image, and removing noise points on the gray image; then carrying out edge detection and edge refinement on the gray level image without the noise point to obtain a skeleton diagram; finally, connecting the intervals in the skeleton diagram;
2) taking the skeleton graph in the step 1) as a plane graph, taking pixel points with a plurality of branches in the skeleton graph as nodes, and taking a path between the two nodes as an edge;
3) detecting all minimum loops in the skeleton diagram in the step 2);
4) screening all the minimum loops in the step 3), and filtering out all non-rectangular loops;
5) and cutting the imported image according to the residual loop after filtering in the step 4), and classifying after cutting to form an initial identification result.
4. The unmanned aerial vehicle aerial image automatic identification system of claim 3, characterized in that: the edge detection determines edges by detecting the rate of change of adjacent portions of the image.
5. The unmanned aerial vehicle aerial image automatic identification system of claim 3, characterized in that: the edge refinement is to refine the detected edge and refine the same line to a single pixel width.
6. The unmanned aerial vehicle aerial image automatic identification system of claim 3, characterized in that: the detection minimum loop adopts an algorithm, and the algorithm comprises the following steps: two nodes v connected for all edges0And v1Defining an order, traversing forward as v1→v0Reverse traversal is v1→v0(ii) a Two count values are kept for each edge: a isiAnd biWherein a isiIndicates whether this edge is traversed in the forward direction, biIndicating whether the edge is traversed reversely; in the initial state, a for all edges i, ai＝bi0; then, one of the conditions is arbitrarily selected to satisfy ai0 or biAn edge of 0 ifiIf 0, then the edge is traversed in the forward direction, otherwise there is biWhen the edge is equal to 0, the edge is traversed reversely until the edge is returned; if the edge is traversed in the forward direction, setting the initial current node as v1(ii) a Otherwise, setting the initial current node as v0(ii) a In the process of traversing, each time of selection is carried outTraversing the next edge i of the front node in the clockwise direction, and setting a according to the traversing directioni1 or bi1 is ═ 1; after returning to the initial node, traversing is completed; finding out a minimum loop after traversing; if the graph still has edges satisfying a after the traversal is finishedi0 or biIf 0, the above steps are continued until all the edges satisfy ai1 and bi＝1。
7. The unmanned aerial vehicle aerial image automatic identification system of claim 6, characterized in that: the algorithm can additionally detect a loop which does not belong to the minimum loop, and after the loop which does not belong to the minimum loop is removed after the detection is finished, the rest loops are all the minimum loops in the skeleton diagram.
8. The unmanned aerial vehicle aerial image automatic identification system of claim 3, characterized in that: and 4, screening and filtering are carried out by calculating the similarity between the loop and the rectangle, and the screening and filtering comprise the following steps: enumerating the direction of a rectangle, finding out the position of the side of the rectangle by adopting a binary search mode, uniformly taking n points of each side, calculating the ratio of the distance between the point on a loop which is perpendicular to the line segment direction and is closest to the point and the corresponding side length of each point, finally obtaining the dissimilarity degree of the shape and the rectangle, filtering out the loop of which the dissimilarity degree is greater than a preset threshold value, namely filtering out all non-rectangular loops.
9. The unmanned aerial vehicle aerial image automatic identification system of claim 8, characterized in that: the dissimilarity degree is calculated by the formula
ns is dissimilarity, theta is the direction of the rectangle, the angle of theta is 0-360 degrees, T is a preset threshold value, i is a point, and l is the length of the corresponding edge.
10. The unmanned aerial vehicle aerial image automatic identification system of claim 3, characterized in that: when the marking result modification module modifies the problematic identification result, an operator checks whether the marking of the corresponding area is wrong, and performs addition/deletion/modification operation on the corresponding area to form a final marking result, namely the final identification result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110461261.3A CN113239752B (en) | 2021-04-27 | 2021-04-27 | Unmanned aerial vehicle aerial image automatic identification system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110461261.3A CN113239752B (en) | 2021-04-27 | 2021-04-27 | Unmanned aerial vehicle aerial image automatic identification system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113239752A true CN113239752A (en) | 2021-08-10 |
| CN113239752B CN113239752B (en) | 2024-06-18 |
Family
ID=77129483
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110461261.3A Active CN113239752B (en) | 2021-04-27 | 2021-04-27 | Unmanned aerial vehicle aerial image automatic identification system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113239752B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060062442A1 (en) * | 2004-09-16 | 2006-03-23 | Imaging Therapeutics, Inc. | System and method of predicting future fractures |
| CN101567046A (en) * | 2009-06-11 | 2009-10-28 | 北京航空航天大学 | Target recognition method of unmanned aerial vehicle based on minimum circle-cover matching |
| US20100296693A1 (en) * | 2009-05-22 | 2010-11-25 | Thornberry Dale R | System and process for roof measurement using aerial imagery |
| US20150199557A1 (en) * | 2014-01-13 | 2015-07-16 | Here Global B.V. | Systems and Methods for Refining Building Alignment in an Aerial Image |
| CN105825212A (en) * | 2016-02-18 | 2016-08-03 | 江西洪都航空工业集团有限责任公司 | Distributed license plate recognition method based on Hadoop |
| CN106096497A (en) * | 2016-05-28 | 2016-11-09 | 安徽省（水利部淮河水利委员会）水利科学研究院 | A kind of house vectorization method for polynary remotely-sensed data |
| CN106570468A (en) * | 2016-10-25 | 2017-04-19 | 中国人民解放军空军工程大学 | Method for reconstructing LiDAR original point cloud building contour |
| CN106650663A (en) * | 2016-12-21 | 2017-05-10 | 中南大学 | Building true/false change judgement method and false change removal method comprising building true/false change judgement method |
| CN108761237A (en) * | 2018-05-29 | 2018-11-06 | 福州大学 | Unmanned plane electric inspection process image vital electrical component diagnoses automatically and labeling system |
| CN112270234A (en) * | 2020-10-20 | 2021-01-26 | 天津大学 | Power transmission line insulation sub-target identification method based on aerial image |
-
2021
- 2021-04-27 CN CN202110461261.3A patent/CN113239752B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060062442A1 (en) * | 2004-09-16 | 2006-03-23 | Imaging Therapeutics, Inc. | System and method of predicting future fractures |
| US20100296693A1 (en) * | 2009-05-22 | 2010-11-25 | Thornberry Dale R | System and process for roof measurement using aerial imagery |
| CN101567046A (en) * | 2009-06-11 | 2009-10-28 | 北京航空航天大学 | Target recognition method of unmanned aerial vehicle based on minimum circle-cover matching |
| US20150199557A1 (en) * | 2014-01-13 | 2015-07-16 | Here Global B.V. | Systems and Methods for Refining Building Alignment in an Aerial Image |
| CN105825212A (en) * | 2016-02-18 | 2016-08-03 | 江西洪都航空工业集团有限责任公司 | Distributed license plate recognition method based on Hadoop |
| CN106096497A (en) * | 2016-05-28 | 2016-11-09 | 安徽省（水利部淮河水利委员会）水利科学研究院 | A kind of house vectorization method for polynary remotely-sensed data |
| CN106570468A (en) * | 2016-10-25 | 2017-04-19 | 中国人民解放军空军工程大学 | Method for reconstructing LiDAR original point cloud building contour |
| CN106650663A (en) * | 2016-12-21 | 2017-05-10 | 中南大学 | Building true/false change judgement method and false change removal method comprising building true/false change judgement method |
| CN108761237A (en) * | 2018-05-29 | 2018-11-06 | 福州大学 | Unmanned plane electric inspection process image vital electrical component diagnoses automatically and labeling system |
| CN112270234A (en) * | 2020-10-20 | 2021-01-26 | 天津大学 | Power transmission line insulation sub-target identification method based on aerial image |
Non-Patent Citations (1)
| Title |
|---|
| 索红军: ""赋权图的最小环路遍历路径分析与研究"", 《渭南师范学院学报》, vol. 27, no. 10, pages 78 - 80 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113239752B (en) | 2024-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ukhwah et al. | Asphalt pavement pothole detection using deep learning method based on YOLO neural network | |
| CN110390258A (en) | Image object three-dimensional information mask method | |
| CN111460984A (en) | Global lane line detection method based on key point and gradient balance loss | |
| CN104850850A (en) | Binocular stereoscopic vision image feature extraction method combining shape and color | |
| AU2020103716A4 (en) | Training method and device of automatic identification device of pointer instrument with numbers in natural scene | |
| CN102609723B (en) | Image classification based method and device for automatically segmenting videos | |
| CN111368690A (en) | Deep learning-based video image ship detection method and system under influence of sea waves | |
| CN111414954B (en) | Rock image retrieval method and system | |
| CN105005760A (en) | Pedestrian re-identification method based on finite mixture model | |
| CN113158891B (en) | Cross-camera pedestrian re-identification method based on global feature matching | |
| CN113850799A (en) | YOLOv 5-based trace DNA extraction workstation workpiece detection method | |
| CN113239753A (en) | Improved traffic sign detection and identification method based on YOLOv4 | |
| CN110837839A (en) | High-precision unmanned aerial vehicle orthoimage manufacturing and data acquisition method | |
| Almutairy et al. | Arts: Automotive repository of traffic signs for the united states | |
| CN114241332A (en) | Deep learning-based solid waste field identification method and device and storage medium | |
| CN112700476A (en) | Infrared ship video tracking method based on convolutional neural network | |
| CN109657082A (en) | Remote sensing images multi-tag search method and system based on full convolutional neural networks | |
| CN112634447A (en) | Outcrop rock stratum layering method, device, equipment and storage medium | |
| CN116310285B (en) | Automatic pointer instrument reading method and system based on deep learning | |
| CN113239752A (en) | Unmanned aerial vehicle aerial image automatic identification system | |
| CN115222988B (en) | Fine classification method for urban ground object PointEFF based on laser radar point cloud data | |
| CN116452826A (en) | Coal gangue contour estimation method based on machine vision under shielding condition | |
| CN116129327A (en) | Infrared vehicle detection method based on improved YOLOv7 algorithm | |
| CN108399413B (en) | Picture shooting area identification and geographical positioning method and device | |
| CN109377479B (en) | Butterfly satellite antenna target detection method based on remote sensing image |
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 |