CN114677591A - Image data processing method, system, electronic equipment and storage medium - Google Patents
Image data processing method, system, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114677591A CN114677591A CN202210317547.9A CN202210317547A CN114677591A CN 114677591 A CN114677591 A CN 114677591A CN 202210317547 A CN202210317547 A CN 202210317547A CN 114677591 A CN114677591 A CN 114677591A
- Authority
- CN
- China
- Prior art keywords
- image data
- aerial vehicle
- unmanned aerial
- image
- processing method
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 47
- 238000000034 method Methods 0.000 claims abstract description 60
- 238000012545 processing Methods 0.000 claims abstract description 58
- 230000008569 process Effects 0.000 claims abstract description 30
- 238000013439 planning Methods 0.000 claims abstract description 24
- 238000002372 labelling Methods 0.000 claims abstract description 22
- 238000001514 detection method Methods 0.000 claims description 43
- 238000012549 training Methods 0.000 claims description 29
- 238000004590 computer program Methods 0.000 claims description 11
- 230000006870 function Effects 0.000 description 12
- 230000011218 segmentation Effects 0.000 description 12
- 238000004458 analytical method Methods 0.000 description 11
- 238000004422 calculation algorithm Methods 0.000 description 10
- 238000007726 management method Methods 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 7
- 230000004044 response Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 238000011161 development Methods 0.000 description 6
- 230000018109 developmental process Effects 0.000 description 6
- 230000004927 fusion Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000013527 convolutional neural network Methods 0.000 description 3
- 238000013500 data storage Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000001931 thermography Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000474 nursing effect Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000035484 reaction time Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012732 spatial analysis Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/32—Indexing scheme for image data processing or generation, in general involving image mosaicing
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention provides an image data processing method and system, comprising the following steps: planning a route for acquiring image data by the unmanned aerial vehicle, wherein the route comprises a plurality of waypoints for acquiring the image data; receiving image data acquired by the unmanned aerial vehicle at each waypoint in real time, and performing rapid splicing and structural processing on all the image data to acquire an orthophoto map of a target area; and inputting the orthophoto map into an intelligent recognition engine so as to identify and label the elements in the orthophoto map, obtain result data of the identification and labeling, and display the result data. According to the image data processing method and system provided by the invention, the unmanned aerial vehicle carries the remote sensing equipment to obtain the image data, the image data is spliced and structurally processed, then element identification and marking are carried out, finally, a series of element data generated in the operation process are displayed, and the positions of all elements in the target area can be quickly and accurately positioned.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to an image data processing method, an image data processing system, an electronic device, and a storage medium.
Background
Digital ortho-Map (DOM) is an image with both Map geometric accuracy and image characteristics, has the advantages of high accuracy, rich information, intuition, vividness, rapidness in acquisition and the like, and can be used as Map analysis background information.
Most of the existing digital orthophoto images are acquired through a remote sensing satellite or loaded into an aviation airplane, and most of the existing methods are that an unmanned aerial vehicle stores all shot multi-frame image data and then integrally splices the data through image splicing software.
Disclosure of Invention
The invention provides an image data processing method and system, which are used for solving the defects that in the prior art, a digital orthophoto map cannot be constructed in real time through an image acquired by a remote sensing satellite, and relevant element information in a target area can be quickly acquired through identification of the digital orthophoto map, so that real-time construction and updating of the digital orthophoto map can be effectively realized, and data support can be provided for image identification and application in different scenes.
In a first aspect, the present invention provides an image data processing method, including: planning a route for acquiring image data by an unmanned aerial vehicle, wherein the route comprises a plurality of waypoints for acquiring the image data; receiving image data acquired by the unmanned aerial vehicle at each waypoint in real time, and performing rapid splicing and structural processing on all the image data to acquire an orthophoto map of a target area; inputting the ortho image map into an intelligent recognition engine to identify and label the elements in the ortho image map, and acquiring result data of identification and labeling; and displaying the result data of the identification mark.
According to the image data processing method provided by the invention, after the image data collected by the unmanned aerial vehicle at each waypoint is received in real time and before all the image data are subjected to rapid splicing and structural processing, the method further comprises the following steps: storing image data received in real time and acquired by the unmanned aerial vehicle at each waypoint; each frame of image data is a two-dimensional ortho image and is provided with a waypoint coordinate label and an acquisition time label.
According to an image data processing method provided by the present invention, after storing image data collected by the unmanned aerial vehicle at each waypoint received in real time, the method further includes: switching and displaying image data acquired at different acquisition times at the same navigation point through a time axis; when the image data are displayed, the flight parameters of the unmanned aerial vehicle are displayed at the same time.
According to the image data processing method provided by the invention, a plurality of different types of target detection models are stored in the intelligent recognition engine; the inputting the orthophoto map into an intelligent recognition engine to identify and label elements in the orthophoto map comprises: matching an optimal target detection model from all target detection models according to the identification and marking requirements of the input orthophoto map; inputting the orthophoto map into the optimal target detection model to obtain result data output by the optimal target detection model; the optimal target detection model is obtained after training by using an image sample with an achievement data label.
According to the image data processing method provided by the invention, the planning of the air route for collecting the image data collected by the unmanned aerial vehicle comprises the following steps: downloading a satellite image map of a target area under the condition of good network condition; according to project requirements, a flight area of the unmanned aerial vehicle is defined on the satellite image map, and a plurality of waypoints for acquiring the image data are determined according to the flight area; setting flight parameters of the unmanned aerial vehicle, wherein the flight parameters comprise flight height, flight angle and flight speed; and determining the route of the unmanned aerial vehicle according to the plurality of waypoints and the flight parameters.
According to the image data processing method provided by the invention, in the process of receiving the image data acquired by the unmanned aerial vehicle at each waypoint, if the image data acquired at any waypoint is lost or the unmanned aerial vehicle cannot complete the planned route from any waypoint, the unmanned aerial vehicle is controlled to start from any waypoint again, and the waypoints which are not subjected to image data acquisition are continuously flown.
According to an image data processing method provided by the present invention, after acquiring an orthophoto map of a target region, the method further includes: and after image slicing processing is carried out on the orthophoto map according to a preset rule, a spatial index is established and data service is issued so as to display any image slice generated after the image slicing processing is carried out through the spatial index.
In a second aspect, the present invention also provides an image data processing system comprising: unmanned aerial vehicle airline planning unit, image acquisition processing unit, intelligent recognition engine unit, platform display unit, wherein:
the unmanned aerial vehicle route planning unit is used for planning a route acquired by an unmanned aerial vehicle and acquiring image data, and the route comprises a plurality of waypoints for acquiring the image data;
the image data acquisition unit is used for receiving image data acquired by the unmanned aerial vehicle at each navigation point in real time, and performing rapid splicing and structural processing on all the image data to acquire an orthophoto map of a target area;
the intelligent recognition engine unit is used for recognizing and labeling the elements in the input orthophoto map and outputting result data of the recognition and labeling;
and the platform display unit is used for displaying the result data of the identification mark.
In a third aspect, the present invention provides an electronic device, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the image data processing method as described in any one of the above when executing the program.
In a fourth aspect, the invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored, which computer program, when executed by a processor, performs the steps of the image data processing method as described in any one of the above.
Generally, compared with the prior art, the above technical solution conceived by the present invention has the following beneficial effects: according to the image data processing method and system provided by the invention, the unmanned aerial vehicle carries the remote sensing equipment to obtain the image data, the image data is spliced and structurally processed, then element identification and marking are carried out, finally, a series of element data generated in the operation process are displayed, and the positions of all elements in the target area can be quickly and accurately positioned.
Drawings
In order to more clearly illustrate the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of an image data processing method according to the present invention;
FIG. 2 is a second schematic flowchart of an image data processing method according to the present invention;
FIG. 3 is a schematic diagram of an image data processing system provided by the present invention;
fig. 4 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. 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.
It should be noted that in the description of the embodiments of the present invention, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element. The terms "upper", "lower", and the like, indicate orientations or positional relationships that are based on the orientations or positional relationships shown in the drawings, are only used for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the system or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention. Unless expressly stated or limited otherwise, the terms "mounted," "connected," and "coupled" are to be construed broadly and encompass, for example, both fixed and removable coupling as well as integral coupling; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
The terms first, second and the like in the description and in the claims of the present application are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that embodiments of the application may be practiced in sequences other than those illustrated or described herein, and that the terms "first," "second," and the like are generally used herein in a generic sense and do not limit the number of terms, e.g., the first term can be one or more than one. In addition, "and/or" in the specification and claims means at least one of connected objects, a character "/" generally means that a preceding and succeeding related objects are in an "or" relationship.
The following describes an image data processing method and system provided by the embodiment of the invention with reference to fig. 1 to 4.
Fig. 1 is a schematic flow chart of an image data processing method according to an embodiment of the present invention, as shown in fig. 1, including, but not limited to, the following steps:
step 101: planning a route for acquiring image data by an unmanned aerial vehicle, wherein the route comprises a plurality of waypoints for acquiring the image data.
The image data processing method provided by the invention mainly utilizes the unmanned aerial vehicle to carry the remote sensing equipment to acquire multi-frame image data in the target area, and realizes the identification and release of elements in the target area by processing all the image data and combining with flight data acquisition software, thereby realizing the target tracking.
Optionally, the collected related image data can be transmitted to a server through a network in real time for processing and analysis, and the result data can be displayed on a command center system for real-time mastering of the fighting situation.
The air route for collecting image data of the unmanned aerial vehicle is planned, and planning and control operation can be performed on the air route of the unmanned aerial vehicle through unmanned aerial vehicle flight control software by means of the mobile terminal according to different scene collection requirements.
Wherein the scene acquisition requirement may be a teaching and research requirement, including at least one of the following: a subject of training; the main training subjects and topics of various training objects; the training mode (including group operation, grouping operation, unilateral exercise, countermeasure exercise, etc.) and the training flow adopted by each training subject and topic; the content of the operation and the expression form of the result in the training process; the system and content of command commands and intervention commands to be used; the content, mode, main index and data acquisition mode of the training evaluation.
The cloud deck camera can be mounted on the unmanned aerial vehicle, for example, a visible light camera, a thermal imaging camera, an infrared camera and the like can meet different scene requirements, namely, the image data can be data obtained by digitizing a color high-definition image, a thermal imaging image, a thermal infrared image and the like.
It should be noted that the invention can also meet the specialized requirements, and when the unmanned aerial vehicle collects data, the course overlapping rate can be not less than 75%, and the side direction overlapping rate can be not less than 60%. And the image data collected at each waypoint has accurate coordinate information and is shot in an orthographic mode, namely each frame of image data meets the condition of shooting vertically downwards.
The unmanned aerial vehicle for image data acquisition has an ortho-image mode and is used for acquiring image data (also called ortho-image data) of an ortho-view angle of each waypoint, and the unmanned aerial vehicle acquires the ortho-image data of a flight path area according to a planned flight path and transmits the ortho-image data in real time in the flight process to realize simultaneous drawing of the flying.
Step 102: and receiving image data acquired by the unmanned aerial vehicle at each navigation point in real time, and performing rapid splicing and structural processing on all the image data to acquire an orthophoto map of a target area.
The image data processing method provided by the invention is different from the prior art, can receive the image data acquired by the unmanned aerial vehicle in real time, and can generate the structured orthographic projection image by utilizing the image splicing technology in time, and has the advantages of singleness, easiness in checking and the like.
In consideration of the large data volume and the large number of photos collected in the field of the unmanned aerial vehicle, which is inconvenient for later analysis, statistics and management, the invention adopts the image splicing technology to realize the rapid splicing of the image data collected in the target area, thereby achieving the simplification management of scattered data and facilitating the calling of the photos in the later image recognition process.
As an alternative embodiment, the present invention provides a method for generating an orthophoto map, including but not limited to the following steps:
step 1, the unmanned aerial vehicle calculates the flying height and the flying path of the unmanned aerial vehicle according to a pre-planned route (including all waypoints on the route) and shooting parameters, namely shooting image precision, image horizontal overlapping rate, image vertical overlapping rate and shooting area, wherein the flying path of the unmanned aerial vehicle can adopt a reciprocating type full coverage path.
And 2, determining an overlapping area of every two adjacent images according to the image data received in real time, and performing SURF algorithm feature matching on the overlapping area.
And 3, after the image matching processing is finished, carrying out image fusion on the image data after the image registration, wherein optionally, the image fusion algorithm can adopt an image pyramid multi-scale fusion algorithm to carry out image fusion.
And 4, iteratively executing the steps 2 to 3, and sequentially performing image matching processing and image fusion processing on the newly received image data and the image subjected to image fusion in the step 3 until the traversal of each navigation point is completed, so as to obtain a spliced orthophoto map.
Step 103: and inputting the ortho image map into an intelligent recognition engine so as to identify and label the elements in the ortho image map and acquire result data of identification and labeling.
The image data processing method provided by the invention can be rapidly developed to work after an emergency occurs, field data acquisition personnel use the unmanned aerial vehicle to plan a flight path, and acquire image data (or video data) of a field target area in real time to an intelligent recognition engine platform for processing, so that elements in each frame of image data are recognized and labeled by using a pre-trained deep learning model, and all recognition results are integrated into result data.
As an optional embodiment, the training and recognition performance of the target detection model preloaded in the intelligent recognition engine adopted by the invention is mainly determined by an algorithm and machine configuration, and the adopted algorithm can ensure high accuracy while ensuring recognition efficiency.
For example, the intelligent recognition engine of the present invention can implement intelligent recognition of an orthophoto map according to different elements to be labeled, including: and (4) performing operations such as image classification, target detection, semantic segmentation, instance segmentation and the like, and taking the result of the identification and the labeling as result data.
Step 104: and displaying the result data of the identification mark.
The device for displaying the achievement data may be a mobile terminal, a large screen located in the command center system, or may be displayed in a desktop application, which is not limited in the present invention. Because the invention adopts a mode of displaying the result data in real time, the data transmission mode can be serial communication and parallel communication, as long as the speed meets the requirements of rapidness and high efficiency of remote data transmission and the requirement of remote decision making.
Furthermore, the invention can also mark points, lines and faces on the result data, such as three-dimensional models, Digital ortho-image (DOM) data and the like, and support multi-terminal sharing, and the command center can command according to the marked information.
Optionally, while the achievement data is displayed, a series of element data in the working process can be displayed, such as: flight data of the drone, image data acquired at each waypoint, and the like.
Optionally, the image data processing method provided by the invention can also realize the function of performing real-time video live broadcast on the shot real-time picture in the flight shooting process of the unmanned aerial vehicle, and a user can check the real-time picture live broadcast of the unmanned aerial vehicle in real time.
According to the image data processing method provided by the invention, the unmanned aerial vehicle carries the remote sensing equipment to obtain the image data, the image data is spliced and structurally processed, then element identification and marking are carried out, finally, a series of element data generated in the operation process are displayed, and the positions of all elements in the target area can be quickly and accurately positioned.
Based on the content of the foregoing embodiment, as an optional embodiment, after receiving image data acquired by the unmanned aerial vehicle at each waypoint in real time and before performing fast stitching and structuring processing on all the image data, the method further includes: storing image data received in real time and acquired by the unmanned aerial vehicle at each waypoint; each frame of image data is a two-dimensional ortho image and is provided with a waypoint coordinate label and an acquisition time label.
Fig. 2 is a second schematic flow chart of the image data processing method provided by the present invention, and as shown in fig. 2, the present invention can also implement remote cloud storage of image data acquired by the unmanned aerial vehicle in real time.
For example, image data shot by each waypoint is uniformly stored in an iTelluro.Server map service management platform according to the acquisition time or waypoint coordinates, and the data is managed in a time axis mode, so that the data is convenient to view and read. The user can realize the publishing and service of two-dimensional and three-dimensional data through the WebGIS management platform, all the services support the standard OGC interface, the calling with other map controls can be realized, and the space query, the retrieval and the analysis of the Web service are facilitated.
Based on the content of the above embodiment, after storing the image data acquired by the drone at each waypoint received in real time, the method further includes: switching and displaying image data acquired at different acquisition times at the same navigation point through a time axis; when the image data are displayed, the flight parameters of the unmanned aerial vehicle are displayed at the same time.
By adopting the cloud storage mode, for the same shooting waypoint, the collected image data are shot at different times, the stored data are processed through original data processing, image intelligent identification marks, training element marks and the like, and flight parameters (such as flight height and shooting angle) of the unmanned aerial vehicle when shooting each frame of image data can be switched and displayed by dragging a time axis.
Since the data storage speed is mainly determined by the server performance and the network bandwidth, and since the data storage speed of the server is much higher than the data transmission speed of the network, the data storage speed is mainly determined by the network bandwidth. In view of this, in the image data processing method provided by the present invention, the network uplink speed of the drone is preferably not less than 2M/s.
According to the image data processing method provided by the invention, the image data acquired in real time and the corresponding flight parameters of the unmanned aerial vehicle are stored in a time axis mode by utilizing cloud storage, and a user can inquire and switch and display historical data in a time axis dragging mode according to needs, so that the situation study, analysis and decision are facilitated.
Based on the content of the above embodiments, as an optional embodiment, a plurality of different types of object detection models are stored in the intelligent recognition engine;
the inputting the orthophoto map into an intelligent recognition engine to identify and label elements in the orthophoto map comprises:
matching an optimal target detection model from all target detection models according to the identification and marking requirements on the input orthophoto map;
inputting the orthophoto map into the optimal target detection model to obtain result data output by the optimal target detection model;
the optimal target detection model is obtained after training by using an image sample with an achievement data label.
With reference to fig. 2, the image data processing method provided by the present invention supports image recognition and automatic position information labeling of elements on the basis of performing certain structural processing on image data shot in different deduction processes, performs structural processing on result data, and finally releases the result data into map data that can be directly previewed and viewed by a platform.
The intelligent recognition engine is pre-stored with multiple types of target detection models for the user to select according to the need of recognition marking, if including: image classification models, object detection, semantic segmentation models, instance segmentation models, and the like.
Image classification refers to determining which classified elements are contained in an image, and the adopted classification algorithm can be a ResNet network or other convolutional neural networks.
The target detection means determining which elements are contained in an image and the position of each element, and is represented by a rectangular box, and the adopted detection algorithm can be fast R-CNN, an algorithm of target detection based on YOLO, and the like.
Semantic segmentation is also called target segmentation, namely, pixel points of each point in a graph are distinguished, the pixel points are not only framed by a rectangular frame, but different examples of the same element do not need to be separated, and the adopted detection algorithm can be FCN, SegNet, Deeplab and other segmentation algorithms.
Example segmentation is essentially a combination of object detection and semantic segmentation. The example segmentation can be accurate to the edge of each element relative to the bounding box of the target detection; compared with semantic segmentation, the example segmentation needs to mark different individuals of the same element on the image and can be realized by adopting a Mask R-CNN algorithm.
Before the target detection model in the intelligent recognition engine is used for recognition and marking, training elements (namely elements) can be marked on each sample based on image data samples collected preliminarily, and then model pre-training is carried out on each target detection model respectively, so that a target detection model library is established through continuous training and learning.
After the target detection model library is established, the target detection model library can be managed in a unified mode, and after image data are collected and identification and marking are completed each time, the identification range and the identification precision of the identification model library are further enriched.
The invention can adopt a mode of manually and manually selecting elements in the sample as a training sample to pre-train the model, and the mode of manually selecting the elements supports the marking of point cache, line cache, points, straight lines, broken lines, rectangles, squares, polygons and circles, thereby being convenient for selecting the range and the area of data analysis data.
As an optional embodiment, the image data processing method provided by the present invention not only supports real-time display of result data of identification and labeling, but also supports display of process data of whole data processing, and mainly includes:
1) the data display function of the platform is as follows: after the unmanned aerial vehicle acquires the image data, the image data are transmitted to the terminal equipment, the terminal equipment is matched with the rear-end server cluster to complete structural processing on the image data, effect display is carried out on intermediate and achievement data generated in the processes of image data acquisition, recognition, model training and the like, and the analysis and decision making are facilitated.
2) Marking function of elements: the user can draw the primitives of the elements to realize labeling and drawing in different forms, and data is stored in the server, so that secondary multiplexing and searching are facilitated, and backtracking query can be recorded in the operation process and the like of the whole user.
3) And by the training and management functions of the target detection model, a user can select elements needing to be trained through a primitive plotting tool, pre-train the model, and store and manage the trained target detection model as an identification reference. And the functions of adding, deleting, changing and searching a target detection model in the intelligent recognition engine are also supported. And after selecting the optimal target detection model, the user can submit an image recognition task, and supports to check the currently recognized progress and detailed information, and superimposes the recognized result on the platform for display.
4) The development and switching function of the overlay region layer mainly comprises the following steps: automatic layer switching during image recognition, layer development and switching during training element marking, layer development and switching for data display and the like.
The automatic layer switching during image recognition refers to: when the intelligent recognition engine is used for carrying out image recognition automatic labeling, the switching of layers of image overlapping regions can be supported, so that the recognition labeling of elements of a target layer is realized, the influence on image recognition caused by shielding due to different shooting angles is avoided, and dead-angle-free image recognition and labeling of the shooting overlapping regions are realized.
The layer development and switching during the marking of the training elements are as follows: when element marking is carried out on an image data sample, switching of layers of different view angles in an image overlapping area can be supported, and therefore marking of blocked elements (elements which are blocked in one layer and can be displayed in the other layer) is achieved, and accuracy of strip model training is further improved.
The layer development and switching of data display means that when data display is carried out, development of different layers in a shooting overlapping area can be supported, and the function of switching layers with different viewing angles is realized.
5) The image data processing method provided by the invention can support the functions of processing and storing the data shot and collected in the same shooting area at different times, processing the data through original data, intelligently identifying and marking images, marking training elements and the like, and carrying out switching display by dragging the time axis.
According to the image data processing method provided by the invention, various types of target detection models are integrated into the intelligent recognition engine, so that the recognition and labeling requirements of different elements can be met according to the requirements of training items; meanwhile, in consideration of the interference of the overlapped layers in the image structuring nursing process to the recognition result in the model pre-training and model recognition processes, an interface which can be directly switched by a user on multiple layers is provided, and the layers can be switched to the corresponding layers according to the actual condition, so that the accuracy of image recognition is effectively improved.
Based on the content of the above embodiment, as an optional embodiment, the planning of the route for acquiring the image data by the unmanned aerial vehicle mentioned in the above step may specifically include the following steps:
downloading a satellite image map of a target area under the condition of good network condition; according to project requirements, a flight area of the unmanned aerial vehicle is defined on the satellite image map, and a plurality of waypoints for acquiring the image data are determined according to the flight area;
setting flight parameters of the unmanned aerial vehicle, wherein the flight parameters comprise flight height, flight angle and flight speed;
and determining the route of the unmanned aerial vehicle according to the plurality of waypoints and the flight parameters.
The image data processing method provided by the invention mainly collects the image data of each waypoint by means of the remote sensing equipment carried by the unmanned aerial vehicle, and carries out flight parameter collection by combining with flight control software so as to monitor the flight path track, flight parameters and other information in the collection process.
Optionally, according to project requirements, a suitable flight mode can be selected to acquire image pictures at different angles and regions. In order to meet the requirements of flying different scenes, the flying device can be divided into a rectangular area, a circular area, a self-defined flying area and the like. And setting flight parameters such as flight height, angle, flight speed and the like. And supporting the operation of re-execution of the incomplete flight mission and the like. The collected data need to be uploaded to a server for structured storage management, and later-stage calling and checking are facilitated.
The air route planning is mainly divided into a rectangular air route, a circular air route, a user-defined air route and the like, and is used for meeting the diversified demands of users on the flight of the unmanned aerial vehicle. The user can realize the enlargement, the reduction and the rotation of the target area on a target area map (which can be an off-line map) by controlling the unmanned aerial vehicle to fly on a mobile terminal screen in a finger frame pulling mode, and can select flight parameters by sliding corresponding icons to complete the planning of the air route.
It should be noted that the method supports two functions of saving the flight path and directly taking off after the flight path planning is finished.
Under the condition of good network condition, the user can realize the functions of downloading the satellite image map of the target area and managing the downloaded off-line map in a frame pulling mode. The off-line map can meet the requirement that a user views and uses the off-line map in the open-air forests, canyons and the like which lack 4G network signals, and comprises the steps of using the off-line map to plan routes, completing flight tasks and the like.
Furthermore, after the unmanned aerial vehicle finishes the flight task, a user can manually check the number, quality and the like of the photos of the task, the photos can be downloaded to the mobile terminal and uploaded to the platform terminal, and the photos of the task flight can be consulted after the photos are uploaded successfully.
According to the route planning method provided by the invention, a user can customize different target areas on a map according to project requirements, set corresponding waypoints according to the size, the shape and the like of the target areas, combine flight parameters of the unmanned aerial vehicle, prepare and plan the route of each task, and can meet the use requirements of different scenes by supporting and storing the route and directly taking off after the route is customized.
Based on the content of the above embodiment, as an optional embodiment, in the process of receiving the image data acquired by the unmanned aerial vehicle at each waypoint, if the image data acquired at any waypoint is lost or the unmanned aerial vehicle cannot complete a planned route from any waypoint, the unmanned aerial vehicle is controlled to start from any waypoint again, and the unmanned aerial vehicle continues to fly to the waypoint which is not subjected to image data acquisition.
The image data processing method provided by the invention is also provided with an intelligent continuous flight function, and aims to solve the problems that an unmanned aerial vehicle control program (APP) exits unexpectedly due to wrong operation, the electric quantity of the unmanned aerial vehicle is insufficient, and a planned route cannot be completed. In the process of executing the task by the unmanned aerial vehicle, the phenomenon of APP flash back occurs, after the unmanned aerial vehicle re-enters the APP, the last flight task can be continued by clicking to continue flying; during the flight process of the unmanned aerial vehicle, when the electric quantity is not enough to complete the task, the user can continue the task flight after the battery is replaced after the unmanned aerial vehicle returns.
In the incomplete flight mission air route, flying waypoints are displayed as green, waypoints which are not flying are displayed as grey, the positions of the continuous flight points need to be displayed, and when the continuous flight is executed, the unmanned aerial vehicle directly flies to the continuous flight points to continue to complete the flight mission.
The invention can effectively improve the efficiency of image data processing tasks each time by supporting automatic continuous flight, avoids the perusal of fighters caused by the need of data acquisition again in the case of accidents, also reduces the complexity of data processing and improves the anti-interference capability of the whole method.
Based on the content of the foregoing embodiment, as an alternative embodiment, after acquiring the orthophoto map of the target area, the method further includes:
and after image slicing processing is carried out on the orthophoto map according to a preset rule, a spatial index is established and data service is issued so as to display any image slice generated after the image slicing processing is carried out through the spatial index.
The orthophoto map generated by the image splicing technology is structured picture data and has the advantages of being single, easy to check and the like, but when the area of a target area is large, the data volume of a single orthophoto map is large, and great memory pressure is caused to the checking, analyzing and identifying of a server. In view of the above, the present invention can effectively reduce the processing pressure of the image recognition server by performing the structured slicing process on the radiographic image and establishing the spatial index to facilitate the search for the slice at the specific location.
The invention does not specifically limit the slicing processing mode of the orthophoto map, and can be realized by adopting the existing Photoshop software and the like.
Fig. 3 is a schematic structural diagram of the image data processing system provided in the present invention, and as shown in fig. 3, the system mainly includes an unmanned aerial vehicle route planning unit 31, an image acquisition processing unit 32, an intelligent recognition engine unit 33, and a platform display unit 34, where:
the unmanned aerial vehicle route planning unit 31 is mainly used for planning a route for collecting image data collected by an unmanned aerial vehicle, and the route comprises a plurality of waypoints for collecting the image data;
the image data acquisition unit 32 is mainly used for receiving image data acquired by the unmanned aerial vehicle at each waypoint in real time, performing fast splicing and structuring processing on all the image data, and acquiring an orthophoto map of a target area;
the intelligent recognition engine unit 33 is mainly used for recognizing and labeling the elements in the input orthophoto map and outputting result data of the recognition and labeling;
the platform display unit 34 is mainly used for displaying the result data of the identification mark.
The image data processing system may be integrated on an independent server, and may adopt a distributed deployment manner, which is not limited in this invention.
In general, the server may have the following performance requirements, including: the method comprises the following steps of data acquisition requirements, data processing performance requirements, data cloud storage performance requirements, model training and recognition performance requirements, data query analysis performance requirements, application system and data service performance requirements, emergency response performance requirements and the like.
The data acquisition requirement in this embodiment preferably means: when the unmanned aerial vehicle collects data, the course overlapping rate is not lower than 75%, and the side direction overlapping rate is not lower than 60%. The pictures taken must have accurate coordinate information. All pictures of the ortho mode satisfy the condition of being taken vertically downward.
The data processing performance requirement in this embodiment preferably means: the data processing speed of the unmanned aerial vehicle needs to meet the image splicing speed, and if the data processing speed is not less than 2 pieces per minute on average.
The data cloud storage performance requirement in this embodiment preferably means: the network uplink speed is not less than 2M/s.
The model training and recognition performance requirements preferably refer to: the intelligent recognition engine unit is used for recognizing the output image with a precision greater than a preset precision.
The data query analysis performance requirement in this embodiment preferably means: the result data of element identification and marking, including map marking data and identification target data, are stored in the server in the form of spatial data. Under the condition of 10 thousands of records of spatial data, the response time of spatial analysis is less than or equal to 6 seconds, and the response time of thematic analysis is less than or equal to 6 seconds; the response time of more than 200 data queries in the map information query return records is not more than 3 seconds, and the response time of complex calculation statistics is not more than 6 seconds.
The application system and data service performance requirements in this embodiment preferably refer to: the application system and the data service meet the requirements of a business processing flow, are stable, reliable and practical, are friendly in human-computer interface for controlling the unmanned aerial vehicle, convenient to input and output, and simple and quick to retrieve and query. When the map service performance reaches 100 concurrency, the map response time is less than or equal to 3 seconds; the operation reaction time of the map of the client end such as zooming in/out, translation, selection (points, frames, circles and polygons), the global map, the magnifier and the like does not exceed 4 seconds.
The emergency response performance requirement in this embodiment preferably means: after an emergency occurs, the system can be rapidly unfolded to work, field data acquisition personnel provide image data and video data of a target area in real time to an intelligent recognition engine for processing by using an unmanned aerial vehicle air route control system, and results are loaded to a desktop end platform for displaying; the data transmission speed meets the requirement of remote data transmission; the data processing speed can be fast and efficient, and the requirements of remote decision making are met.
Further, the image data processing system provided by the invention can also meet the following interface requirements:
1) a data management interface: the system needs to upload and download the data acquired by the unmanned aerial vehicle in the operation process, call services such as data processing and the like to realize the functional requirements of image recognition, and return the recognized result data to the desktop for display and analysis. Stability, security, traceability and the like in the data transmission process need to be ensured in the secondary process.
2) Unmanned aerial vehicle data acquisition uploads interface: after the individual soldier executes the flight combat mission, the image data collected by the unmanned aerial vehicle is screened and uploaded to a server for processing.
3) Unmanned aerial vehicle data download interface: the system is used for downloading the collected original pictures uploaded to the server for the data processing service to call.
4) A data processing interface: and the interface is used for carrying out primary splicing processing on the originally acquired data.
5) A picture saving interface: and the method is used for storing the picture data after the initial splicing is finished.
6) Picture slicing and packaging interface: the method is used for initially splicing the pictures and storing the slices according to a specific rule, and is convenient to search, overlap and view.
7) Picture service publishing interface: for publishing the data of the picture slices into a service.
8) Picture service acquisition slice interface: the method is used for acquiring single data after the slice publishing service according to the picture index.
9) Machine learning model training interface: the method can be used for performing structured management (adding, deleting, modifying and checking), data backup and other functions on the generated model training data.
10) Machine model saving interface: for saving the object detection model to the model database.
11) Machine model acquisition interface: for invoking all object detection models.
12) The machine model deletes the interface: for deleting a particular object detection model.
13) Machine model editing interface: for editing a particular object detection model.
14) Machine model query interface: target detection models for querying specific conditions.
15) Picture recognition command interface: the method is used for data transmission such as image recognition scope, selected recognition model and the like.
16) An analysis command interface: the method is used for selecting a specific analytical model and calling an image recognition engine to process.
17) Analyzing a result return interface: and the data used for finishing the image recognition is returned to the calling end.
18) Platform marking tool interface: the method is used for realizing plotting of images, management of circled information of image recognition elements and the like.
19) Marking interfaces (add, delete, change, check): and the method is used for storing the point, line and face marks stored by the platform.
20) Acquiring a labeling interface: and the method is used for obtaining all point, line and surface mark loading platform displays.
21) Operating a log interface: basic operations for all calling interfaces and platforms in the process of running require log stores to be queryable. The method is implemented to specific personnel, time, operation flow and the like.
22) An operation log saving interface: for saving the detailed information of all the operation steps to the database.
23) An operation log obtaining interface: for retrieving detailed information of all operational steps from a database.
According to the image data processing system provided by the invention, the unmanned aerial vehicle carries the remote sensing equipment to obtain the image data, the image data is spliced and structurally processed, then element identification and marking are carried out, finally, a series of element data generated in the operation process are displayed, and the positions of all elements in the target area can be quickly and accurately positioned.
It should be noted that, in a specific operation, the image data processing system provided in the embodiment of the present invention may execute the image data processing method described in any of the above embodiments, which is not described in detail in this embodiment.
Fig. 4 is a schematic structural diagram of an electronic device provided in the present invention, and as shown in fig. 4, the electronic device may include: a processor (processor)410, a communication Interface 420, a memory (memory)430 and a communication bus 440, wherein the processor 410, the communication Interface 420 and the memory 430 are communicated with each other via the communication bus 440. The processor 410 may invoke logic instructions in the memory 430 to perform an image data processing method comprising: planning a route for acquiring image data by the unmanned aerial vehicle, wherein the route comprises a plurality of waypoints for acquiring the image data; receiving image data acquired by the unmanned aerial vehicle at each waypoint in real time, and performing rapid splicing and structural processing on all the image data to acquire an orthophoto map of a target area; and inputting the orthophoto map into an intelligent recognition engine so as to identify and label the elements in the orthophoto map, obtain result data of the identification and labeling, and display the result data.
In addition, the logic instructions in the memory 430 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform the image data processing method provided by the above methods, the method comprising: planning a route for acquiring image data by the unmanned aerial vehicle, wherein the route comprises a plurality of waypoints for acquiring the image data; receiving image data acquired by the unmanned aerial vehicle at each waypoint in real time, and performing rapid splicing and structural processing on all the image data to acquire an orthophoto map of a target area; and inputting the orthophoto map into an intelligent recognition engine so as to identify and label the elements in the orthophoto map, obtain result data of the identification and labeling, and display the result data.
In yet another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored, the computer program being implemented by a processor to perform the image data processing method provided by the above embodiments, the method including: planning a route for acquiring image data by the unmanned aerial vehicle, wherein the route comprises a plurality of waypoints for acquiring the image data; receiving image data acquired by the unmanned aerial vehicle at each waypoint in real time, and performing rapid splicing and structuring processing on all the image data to acquire an orthographic image of a target area; and inputting the orthophoto map into an intelligent recognition engine so as to identify and label the elements in the orthophoto map, obtain result data of the identification and labeling, and display the result data.
The above-described system embodiments are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, and not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it should 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 (10)
1. An image data processing method characterized by comprising:
planning a route for acquiring image data by an unmanned aerial vehicle, wherein the route comprises a plurality of waypoints for acquiring the image data;
receiving image data acquired by the unmanned aerial vehicle at each waypoint in real time, and performing rapid splicing and structural processing on all the image data to acquire an orthophoto map of a target area;
inputting the orthophoto map into an intelligent recognition engine to identify and label elements in the orthophoto map and acquire result data of identification and labeling;
and displaying the result data of the identification mark.
2. The image data processing method of claim 1, further comprising, after receiving in real time the image data acquired by the drone at each waypoint and before performing the fast stitching and structuring process on all the image data:
storing image data received in real time and acquired by the unmanned aerial vehicle at each waypoint;
each frame of image data is a two-dimensional orthographic image and is provided with a waypoint coordinate label and an acquisition time label.
3. The image data processing method of claim 2, further comprising, after storing the image data acquired by the drone at each waypoint received in real time:
switching and displaying image data acquired at different acquisition times at the same navigation point through a time axis;
when the image data are displayed, the flight parameters of the unmanned aerial vehicle are displayed at the same time.
4. The image data processing method according to claim 1, wherein a plurality of different types of object detection models are stored in the smart recognition engine;
the inputting the orthophoto map into an intelligent recognition engine to identify and label elements in the orthophoto map comprises:
matching an optimal target detection model from all target detection models according to the identification and marking requirements of the input orthophoto map;
inputting the orthophoto map into the optimal target detection model to obtain result data output by the optimal target detection model;
the optimal target detection model is obtained after training by using an image sample with an achievement data label.
5. The image data processing method of claim 1, wherein the planning of the route for the unmanned aerial vehicle to acquire the image data includes:
downloading a satellite image map of a target area under the condition of good network condition;
according to project requirements, a flight area of the unmanned aerial vehicle is defined on the satellite image map, and a plurality of waypoints for acquiring the image data are determined according to the flight area;
setting flight parameters of the unmanned aerial vehicle, wherein the flight parameters comprise flight height, flight angle and flight speed;
and determining the route of the unmanned aerial vehicle according to the plurality of waypoints and the flight parameters.
6. The image data processing method according to claim 1, wherein in the process of receiving the image data acquired by the unmanned aerial vehicle at each waypoint, if the image data acquired at any waypoint is lost or the unmanned aerial vehicle cannot complete the planned route from any waypoint, the unmanned aerial vehicle is controlled to start from any waypoint again and continue to fly to the waypoint where no image data is acquired.
7. The image data processing method according to claim 1, further comprising, after acquiring the orthophoto map of the target region:
and after image slicing processing is carried out on the orthophoto map according to a preset rule, a spatial index is established and data service is issued so as to display any image slice generated after the image slicing processing is carried out through the spatial index.
8. An image data processing system, comprising: the system comprises an unmanned aerial vehicle route planning unit, an image acquisition and processing unit, an intelligent recognition engine unit and a platform display unit;
the unmanned aerial vehicle route planning unit is used for planning a route acquired by an unmanned aerial vehicle and acquiring image data, and the route comprises a plurality of waypoints for acquiring the image data;
the image data acquisition unit is used for receiving image data acquired by the unmanned aerial vehicle at each navigation point in real time, and performing rapid splicing and structural processing on all the image data to acquire an orthophoto map of a target area;
the intelligent recognition engine unit is used for recognizing and labeling the elements in the input orthophoto map and outputting result data of the recognition and labeling;
and the platform display unit is used for displaying the result data of the identification mark.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the image data processing method steps according to any one of claims 1 to 7 when executing the computer program.
10. A non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the image data processing method steps of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210317547.9A CN114677591A (en) | 2022-03-29 | 2022-03-29 | Image data processing method, system, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210317547.9A CN114677591A (en) | 2022-03-29 | 2022-03-29 | Image data processing method, system, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114677591A true CN114677591A (en) | 2022-06-28 |
Family
ID=82076026
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210317547.9A Pending CN114677591A (en) | 2022-03-29 | 2022-03-29 | Image data processing method, system, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114677591A (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113920419A (en) * | 2021-11-01 | 2022-01-11 | 中国人民解放军国防科技大学 | Image data processing method and system |
-
2022
- 2022-03-29 CN CN202210317547.9A patent/CN114677591A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113920419A (en) * | 2021-11-01 | 2022-01-11 | 中国人民解放军国防科技大学 | Image data processing method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113920419A (en) | Image data processing method and system | |
| US20210142559A1 (en) | System and method for vegetation modeling using satellite imagery and/or aerial imagery | |
| US8244026B2 (en) | Apparatus and method for automatic airborne LiDAR data processing and mapping using data obtained thereby | |
| US8896696B2 (en) | Method apparatus system and computer program product for automated collection and correlation for tactical information | |
| CN111339347B (en) | Management method and device for inspection photos | |
| CN103679674B (en) | Method and system for splicing images of unmanned aircrafts in real time | |
| US20210072737A1 (en) | System for power plant management and device for building 3d virtual model of power plant | |
| JP5542530B2 (en) | Sampling position determination device | |
| WO2014112138A1 (en) | Information processing device, information processing system, and information processing program | |
| CN114399606A (en) | Interactive display system, method and equipment based on stereoscopic visualization | |
| CN109076173A (en) | Image output generation method, equipment and unmanned plane | |
| CN115649501B (en) | Unmanned aerial vehicle night lighting system and method | |
| CN106202140A (en) | Browsing data device and method for browsing data | |
| CN110414686A (en) | A kind of control unmanned plane acquisition image/video quantum of information software | |
| CN111222190A (en) | Ancient building management system | |
| CN112383745A (en) | Panoramic image-based digital presentation method for large-scale clustered construction project | |
| CN114020043A (en) | Unmanned aerial vehicle building project supervision system and method, electronic equipment and storage medium | |
| Tso et al. | A human factors testbed for command and control of unmanned air vehicles | |
| CN114677591A (en) | Image data processing method, system, electronic equipment and storage medium | |
| CN111738312A (en) | Power transmission line state monitoring method and device based on GIS and virtual reality fusion and computer readable storage medium | |
| Carreaud et al. | Automating the underground cadastral survey: a processing chain proposal | |
| Anwar et al. | Time–space diagram revisited | |
| CN112507053A (en) | Method for establishing visualization system and application method | |
| CN108875698A (en) | A kind of base station terrace parameter surveying method, system, device and server | |
| CN109523941A (en) | Interior based on cloud identification technology is with guidance method and device |
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 |