CN116091796B - Unmanned aerial vehicle acquisition data processing method and system based on artificial intelligence - Google Patents

Unmanned aerial vehicle acquisition data processing method and system based on artificial intelligence Download PDF

Info

Publication number
CN116091796B
CN116091796B CN202310381912.7A CN202310381912A CN116091796B CN 116091796 B CN116091796 B CN 116091796B CN 202310381912 A CN202310381912 A CN 202310381912A CN 116091796 B CN116091796 B CN 116091796B
Authority
CN
China
Prior art keywords
image
data
exemplary
vector
richness
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202310381912.7A
Other languages
Chinese (zh)
Other versions
CN116091796A (en
Inventor
刘学亮
徐杰
任继远
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tianzhiyi Suzhou Technology Co ltd
Original Assignee
Tianzhiyi Suzhou Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Tianzhiyi Suzhou Technology Co ltd filed Critical Tianzhiyi Suzhou Technology Co ltd
Priority to CN202310381912.7A priority Critical patent/CN116091796B/en
Publication of CN116091796A publication Critical patent/CN116091796A/en
Application granted granted Critical
Publication of CN116091796B publication Critical patent/CN116091796B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/72—Data preparation, e.g. statistical preprocessing of image or video features
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
    • G06V10/763—Non-hierarchical techniques, e.g. based on statistics of modelling distributions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/7715—Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
    • G06V10/806—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of extracted features
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/98—Detection or correction of errors, e.g. by rescanning the pattern or by human intervention; Evaluation of the quality of the acquired patterns
    • G06V10/987—Detection or correction of errors, e.g. by rescanning the pattern or by human intervention; Evaluation of the quality of the acquired patterns with the intervention of an operator
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/98—Detection or correction of errors, e.g. by rescanning the pattern or by human intervention; Evaluation of the quality of the acquired patterns
    • G06V10/993—Evaluation of the quality of the acquired pattern
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/17—Terrestrial scenes taken from planes or by drones
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Databases & Information Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Quality & Reliability (AREA)
  • Remote Sensing (AREA)
  • Probability & Statistics with Applications (AREA)
  • Image Analysis (AREA)

Abstract

The invention provides an unmanned aerial vehicle acquisition data processing method and system based on artificial intelligence, and relates to the technical field of artificial intelligence. In the invention, the image data to be processed, which is acquired by the target unmanned aerial vehicle, is extracted; performing image content richness evaluation operation on the image data to be processed through an image richness evaluation network subjected to network optimization processing so as to output image content richness characterization data corresponding to the image data to be processed; based on the image content richness characterization data, screening operation is carried out on at least one image to be processed, which is included in the image data to be processed, so as to form corresponding target image data, wherein the target image data includes at least one image to be processed, and a positive correlation corresponding relation exists between the screening proportion of the screening operation and the image content richness characterization data; and carrying out user pushing operation on the target image data. Based on the above, the reliability of data push can be improved to some extent.

Description

Unmanned aerial vehicle acquisition data processing method and system based on artificial intelligence
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to an unmanned aerial vehicle acquisition data processing method and system based on artificial intelligence.
Background
In the fields of monitoring, information acquisition, etc., unmanned aerial vehicles are often used as carriers to achieve reliable coverage of the acquisition area. After the unmanned aerial vehicle collects the image data, the image data needs to be pushed to a corresponding user based on certain requirements so as to perform visualization and other processing. However, in the prior art, in the process of pushing image data, the collected image data is generally pushed to the corresponding user, so that the reliability of image data pushing is poor.
Disclosure of Invention
In view of the above, the present invention aims to provide an unmanned aerial vehicle data collection processing method and system based on artificial intelligence, so as to improve the reliability of data pushing to a certain extent.
In order to achieve the above purpose, the embodiment of the present invention adopts the following technical scheme:
an unmanned aerial vehicle acquisition data processing method based on artificial intelligence comprises the following steps:
extracting to-be-processed image data acquired by a target unmanned aerial vehicle, wherein the to-be-processed image data comprises at least one to-be-processed image acquired by the target unmanned aerial vehicle;
performing image content richness evaluation operation on the image data to be processed through an image richness evaluation network subjected to network optimization processing to output image content richness characterization data corresponding to the image data to be processed, wherein the image content richness characterization data is used for reflecting the content richness of the image to be processed in the image data to be processed;
Based on the image content richness characterization data, screening the at least one image to be processed, which is included in the image data to be processed, so as to form corresponding target image data, wherein the target image data includes at least one image to be processed, and the screening proportion of the screening operation has a positive correlation corresponding relation with the image content richness characterization data;
and carrying out user pushing operation on the target image data.
In some preferred embodiments, in the above unmanned aerial vehicle acquisition data processing method based on artificial intelligence, the unmanned aerial vehicle acquisition data processing method based on artificial intelligence further includes:
extracting user description data of an exemplary image data and an image analysis user, wherein the image analysis user belongs to a user for analyzing and evaluating the content richness of the exemplary image data, the user description data comprises user attribute description data of the image analysis user and analysis and evaluation data formed by the image analysis user for analyzing and evaluating the content richness of the exemplary image data, and the user attribute description data at least comprises user identity information of the image analysis user and preference description information of the image data;
Performing key information mining operation on the exemplary image data through an initial image richness evaluation network to form an image key information description vector corresponding to the exemplary image data;
performing feature space mapping operation on the user attribute description data of the image analysis user through the image richness evaluation network to form a user attribute mapping vector corresponding to the image analysis user;
performing aggregation operation on the user attribute mapping vector to aggregate the user attribute mapping vector into an image key information description vector corresponding to the exemplary image data to form a corresponding image user aggregation vector, wherein the image user aggregation vector carries image characteristic information of the exemplary image data and user characteristic information of the image analysis user;
and performing network optimization operation on the image richness evaluation network through the analysis evaluation data, the image key information description vector and the image user aggregation vector so as to form a corresponding image richness evaluation network subjected to network optimization processing.
In some preferred embodiments, in the unmanned aerial vehicle acquisition data processing method based on artificial intelligence, the step of performing key information mining operation on the exemplary image data through an initial image richness assessment network to form an image key information description vector corresponding to the exemplary image data includes:
Performing image segmentation operation on the exemplary image data to form a plurality of exemplary image sub-data corresponding to the exemplary image data;
performing key information mining operation on each of the plurality of exemplary image sub-data through an initial image richness evaluation network to output a key information description vector of image granularity corresponding to each of the exemplary image sub-data, wherein the key information description vector of image granularity corresponding to the exemplary image sub-data is used for representing image feature information of each of the exemplary images included in the exemplary image sub-data;
determining an image key information description vector corresponding to the exemplary image data according to the key information description vector of the image granularity corresponding to each exemplary image sub-data, wherein the key information description vector of each image granularity in the image key information description vector is ordered based on the time sequence relationship of the corresponding exemplary image sub-data in the exemplary image data, and the image key information description vector is used for representing the image characteristic information of each exemplary image in the exemplary image data.
In some preferred embodiments, in the above unmanned aerial vehicle acquisition data processing method based on artificial intelligence, the exemplary image data includes a plurality of acquisition positions, and the step of performing an image segmentation operation on the exemplary image data to form a plurality of exemplary image sub-data corresponding to the exemplary image data includes:
determining a first image segmentation parameter and a second image segmentation parameter, wherein the first image segmentation parameter is used for representing the distance between two adjacent exemplary image sub-data formed by segmentation, and the second image segmentation parameter is used for representing the number of acquisition positions included in the exemplary image sub-data formed by segmentation;
and performing image segmentation operation on the exemplary image data based on the first image segmentation parameter and the second image segmentation parameter to form a plurality of exemplary image sub-data corresponding to the exemplary image data.
In some preferred embodiments, in the unmanned aerial vehicle acquisition data processing method based on artificial intelligence, the image key information description vector includes a key information description vector of image granularity corresponding to each exemplary image sub-data; the step of aggregating the user attribute mapping vectors to aggregate the image key information description vectors corresponding to the exemplary image data to form corresponding image user aggregate vectors includes:
Respectively carrying out aggregation operation on the user attribute mapping vector and the key information description vector of the image granularity corresponding to each exemplary image sub-data to form a user aggregation vector of the image granularity corresponding to each exemplary image sub-data;
and based on the time sequence relation of the corresponding exemplary image sub-data in the exemplary image data, carrying out sequential combination operation on the user aggregate vector of the image granularity corresponding to each exemplary image sub-data so as to form the image user aggregate vector corresponding to the exemplary image data.
In some preferred embodiments, in the unmanned aerial vehicle acquisition data processing method based on artificial intelligence, the key information description vector of the image granularity corresponding to each of the exemplary image sub-data includes an individual key information description vector of each of the exemplary images included in the corresponding exemplary image sub-data; any one of the exemplary image sub-data corresponding to the exemplary image data is used as first exemplary image sub-data;
the step of performing an aggregation operation on the user attribute mapping vector and the key information description vector of the image granularity corresponding to each exemplary image sub-data to form a user aggregation vector of the image granularity corresponding to each exemplary image sub-data includes:
Performing aggregation operation on the user attribute mapping vector and the individual key information description vector of each exemplary image included in the first exemplary image sub-data to form an individual image user aggregation vector corresponding to each exemplary image, so that the individual image user aggregation vector corresponding to the exemplary image carries image feature information of the exemplary image and user feature information of the image analysis user;
and determining the user aggregate vector of the image granularity corresponding to the first exemplary image sub-data according to the individual image user aggregate vector corresponding to each exemplary image.
In some preferred embodiments, in the unmanned aerial vehicle collecting data processing method based on artificial intelligence, the step of performing network optimization operation on the image richness assessment network by using the analysis assessment data, the image key information description vector and the image user aggregation vector to form a corresponding image richness assessment network subjected to network optimization processing includes:
performing image content richness assessment operation on the exemplary image data according to the image key information description vector and the image user aggregation vector through the image richness assessment network so as to output exemplary content richness assessment data corresponding to the exemplary image data;
Analyzing a network learning cost index corresponding to the image richness evaluation network according to the distinguishing information between the exemplary content richness evaluation data and the analysis evaluation data;
and carrying out network optimization operation on the image richness evaluation network based on the network learning cost index to form a corresponding image richness evaluation network subjected to network optimization processing.
In some preferred embodiments, in the unmanned aerial vehicle collecting data processing method based on artificial intelligence, the step of performing, by the image richness assessment network, an image content richness assessment operation on the exemplary image data according to the image key information description vector and the image user aggregation vector to output exemplary content richness assessment data corresponding to the exemplary image data includes:
performing image content richness assessment operation on the exemplary image data according to the image key information description vector through the image richness assessment network so as to output content richness assessment data of image dimensions corresponding to the exemplary image data; and performing image content richness assessment operation on the exemplary image data according to the image user aggregation vector through the image richness assessment network to output content richness assessment data of an aggregation dimension corresponding to the exemplary image data; and analyzing the exemplary content-richness estimation data corresponding to the exemplary image data based on the content-richness estimation data of the image dimension and the content-richness estimation data of the aggregation dimension;
The step of performing, by the image richness evaluation network, an image content richness evaluation operation on the exemplary image data according to the image key information description vector to output content richness evaluation data of an image dimension corresponding to the exemplary image data includes:
performing vector integration operation on the key information description vector of the image granularity corresponding to each exemplary image sub-data through the image richness evaluation network to form an integrated key information description vector corresponding to each exemplary image sub-data, wherein the key information description vector of the image granularity corresponding to each exemplary image sub-data comprises individual key information description vectors of the respective exemplary images included in the corresponding exemplary image sub-data, and an operation object of the vector integration operation is the individual key information description vector of the respective exemplary images included in the exemplary image sub-data;
performing content richness assessment operation on the corresponding exemplary image sub-data according to the integrated key information description vector corresponding to each exemplary image sub-data so as to output content richness assessment sub-data corresponding to each exemplary image sub-data;
And carrying out fusion operation on content richness assessment sub-data corresponding to a plurality of example image sub-data included in the example image data so as to form content richness assessment data of image dimensions corresponding to the example image data.
In some preferred embodiments, in the unmanned aerial vehicle collecting data processing method based on artificial intelligence, the step of performing content richness assessment operation on each of the exemplary image sub-data according to the integrated key information description vector corresponding to each of the exemplary image sub-data to output content richness assessment sub-data corresponding to each of the exemplary image sub-data includes:
exciting the integrated key information description vector corresponding to each exemplary image sub-data through a circular excitation function to realize the content richness assessment operation of the corresponding exemplary image sub-data, and outputting initial content richness assessment sub-data corresponding to each exemplary image sub-data;
performing a weighting operation on the initial content richness assessment sub-data based on a first adjustment parameter, and performing a superposition operation on the result of the weighting operation based on a second adjustment parameter to form content richness assessment sub-data corresponding to the exemplary image sub-data;
The step of performing a fusion operation on content richness assessment sub-data corresponding to a plurality of exemplary image sub-data included in the exemplary image data to form content richness assessment data of an image dimension corresponding to the exemplary image data includes:
and carrying out average value calculation operation on content richness assessment sub-data corresponding to a plurality of example image sub-data included in the example image data so as to form content richness assessment data of image dimensions corresponding to the example image data.
The embodiment of the invention also provides an unmanned aerial vehicle acquisition data processing system based on artificial intelligence, which comprises a processor and a memory, wherein the memory is used for storing a computer program, and the processor is used for executing the computer program so as to realize an unmanned aerial vehicle acquisition data processing method based on artificial intelligence.
According to the unmanned aerial vehicle acquisition data processing method and system based on artificial intelligence, the image data to be processed acquired by the target unmanned aerial vehicle can be extracted first; performing image content richness evaluation operation on the image data to be processed through an image richness evaluation network subjected to network optimization processing so as to output image content richness characterization data corresponding to the image data to be processed; based on the image content richness characterization data, screening operation is carried out on at least one image to be processed, which is included in the image data to be processed, so as to form corresponding target image data, wherein the target image data includes at least one image to be processed, and a positive correlation corresponding relation exists between the screening proportion of the screening operation and the image content richness characterization data; and carrying out user pushing operation on the target image data. Based on the foregoing, before the user pushing operation, the image data is screened, and the basis of the screening is the assessed image content richness characterization data, so that the reliability of the screening of the image data is higher, the reliability of the user pushing operation on the screened target image data can be ensured, and the reliability of the data pushing is improved to a certain extent.
In order to make the above objects, features and advantages of the present invention more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
Fig. 1 is a block diagram of an artificial intelligence-based unmanned aerial vehicle acquisition data processing system according to an embodiment of the present invention.
Fig. 2 is a schematic flow chart of steps involved in an artificial intelligence-based unmanned aerial vehicle acquisition data processing method according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of each module included in an artificial intelligence-based unmanned aerial vehicle acquisition data processing device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, the embodiment of the invention provides an unmanned aerial vehicle acquisition data processing system based on artificial intelligence. Wherein, the unmanned aerial vehicle collection data processing system based on artificial intelligence can include memory and processor.
In detail, the memory and the processor are electrically connected directly or indirectly to realize transmission or interaction of data. For example, electrical connection may be made to each other via one or more communication buses or signal lines. The memory may store at least one software functional module (computer program) that may exist in the form of software or firmware. The processor may be configured to execute the executable computer program stored in the memory, so as to implement the unmanned aerial vehicle acquisition data processing method based on artificial intelligence provided by the embodiment of the invention.
It should be appreciated that in some embodiments, the Memory may be, but is not limited to, random access Memory (Random Access Memory, RAM), read Only Memory (ROM), programmable Read Only Memory (Programmable Read-Only Memory, PROM), erasable Read Only Memory (Erasable Programmable Read-Only Memory, EPROM), electrically erasable Read Only Memory (Electric Erasable Programmable Read-Only Memory, EEPROM), and the like.
It should be appreciated that in some embodiments, the processor may be a general purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), a System on Chip (SoC), etc.; but also Digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), field Programmable Gate Arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
It should be appreciated that in some embodiments, the artificial intelligence based unmanned aerial vehicle acquisition data processing system may be a server with data processing capabilities.
With reference to fig. 2, the embodiment of the invention further provides an unmanned aerial vehicle acquisition data processing method based on artificial intelligence, which can be applied to the unmanned aerial vehicle acquisition data processing system based on artificial intelligence. The method steps defined by the flow related to the unmanned aerial vehicle acquisition data processing method based on the artificial intelligence can be realized by the unmanned aerial vehicle acquisition data processing system based on the artificial intelligence.
The specific flow shown in fig. 2 will be described in detail.
Step S110, extracting image data to be processed, which is acquired by the target unmanned aerial vehicle.
In the embodiment of the invention, the unmanned aerial vehicle acquisition data processing system based on artificial intelligence can extract the image data to be processed acquired by the target unmanned aerial vehicle. The image data to be processed comprises at least one image to be processed acquired by the target unmanned aerial vehicle, and the at least one image to be processed can be ordered according to the corresponding acquisition time.
Step S120, performing an image content richness evaluation operation on the image data to be processed through an image richness evaluation network subjected to network optimization processing, so as to output image content richness characterization data corresponding to the image data to be processed.
In the embodiment of the invention, the unmanned aerial vehicle acquisition data processing system based on artificial intelligence can perform image content richness evaluation operation on the image data to be processed through an image richness evaluation network subjected to network optimization processing so as to output image content richness characterization data corresponding to the image data to be processed. The image content richness characterization data is used for reflecting the content richness of the image to be processed in the image data to be processed.
Step S130, performing a filtering operation on the at least one image to be processed included in the image data to be processed based on the image content richness characterization data, so as to form corresponding target image data.
In the embodiment of the invention, the unmanned aerial vehicle acquisition data processing system based on artificial intelligence can perform screening operation on the at least one to-be-processed image included in the to-be-processed image data based on the image content richness characterization data so as to form corresponding target image data. The target image data comprises at least one image to be processed, and a screening proportion for screening operation and the image content richness characterization data have a positive correlation corresponding relation.
Step S140, performing a user pushing operation on the target image data.
In the embodiment of the invention, the unmanned aerial vehicle data collection processing system based on artificial intelligence can perform user pushing operation on the target image data, for example, the target image data can be sent to terminal equipment corresponding to a target user, and the like.
Based on the foregoing (i.e., the content corresponding to the above-described step S110-step S140), since the filtering of the image data is performed before the user pushing operation, and the basis of the filtering is the evaluated image content richness characterization data, the reliability of the filtering of the image data can be higher, so that the reliability of the user pushing operation performed on the filtered target image data can be ensured, and the reliability of the data pushing can be improved to a certain extent.
It should be appreciated that in some embodiments, the unmanned aerial vehicle acquisition data processing method based on artificial intelligence may further include the following detailed implementation:
extracting user description data of an exemplary image data and an image analysis user, wherein the image analysis user belongs to a user for analyzing and evaluating the content richness of the exemplary image data, the user description data comprises user attribute description data of the image analysis user and analysis and evaluation data formed by the image analysis user for analyzing and evaluating the content richness of the exemplary image data, and the user attribute description data at least comprises user identity information of the image analysis user and preference description information of the image data;
performing key information mining operation on the exemplary image data through an initial image richness evaluation network to form an image key information description vector corresponding to the exemplary image data;
performing feature space mapping operation on the user attribute description data of the image analysis user through the image richness evaluation network to form a user attribute mapping vector corresponding to the image analysis user, wherein the feature space mapping operation may refer to mapping the user attribute description data to a feature space to represent the user attribute description data in a vector form;
Performing aggregation operation on the user attribute mapping vector to aggregate the user attribute mapping vector into an image key information description vector corresponding to the exemplary image data to form a corresponding image user aggregation vector, wherein the image user aggregation vector carries image characteristic information of the exemplary image data and user characteristic information of the image analysis user;
and carrying out network optimization operation on the image richness evaluation network through the analysis evaluation data, the image key information description vector and the image user aggregation vector to form a corresponding network-optimized image richness evaluation network, wherein the network-optimized image richness evaluation network is used for evaluating image content richness characterization data, and the image content richness characterization data is used for carrying out image data screening related to user pushing operation, namely, the final target is related to user pushing, so that in the process of carrying out network optimization operation, the image user aggregation vector carrying user characteristic information of an image analysis user is adopted, so that some information related to the user can be learned, and the matching performance with the user pushing is improved.
It should be appreciated that, in some embodiments, the step of performing, through the initial image richness assessment network, the key information mining operation on the exemplary image data to form the image key information description vector corresponding to the exemplary image data may further include the following detailed implementation matters:
performing image segmentation operation on the exemplary image data to form a plurality of exemplary image sub-data corresponding to the exemplary image data;
performing key information mining operation, namely feature extraction, on each of the plurality of exemplary image sub-data through an initial image richness evaluation network, wherein the key information description vector of the image granularity corresponding to each of the exemplary image sub-data is output and used for representing the image feature information of each of the exemplary images included in the exemplary image sub-data;
and determining an image key information description vector corresponding to the exemplary image data according to the key information description vector of the image granularity corresponding to each exemplary image sub-data, wherein the key information description vector of each image granularity in the image key information description vector is ordered based on the time sequence relationship of the corresponding exemplary image sub-data in the exemplary image data, and the image key information description vector is used for representing the image characteristic information of each exemplary image in the exemplary image data, for example, the exemplary image data sequentially comprises the exemplary image sub-data 1, the exemplary image sub-data 2 and the exemplary image sub-data 3, so that the image key information description vector can be { the key information description vector of the image granularity corresponding to the exemplary image sub-data 1, the key information description vector of the image granularity corresponding to the exemplary image sub-data 2, and the key information description vector of the image granularity corresponding to the exemplary image sub-data 3 }.
It should be appreciated that in some embodiments, the exemplary image data may include a plurality of acquisition positions, based on which the step of performing an image segmentation operation on the exemplary image data to form a plurality of exemplary image sub-data corresponding to the exemplary image data may further include the following detailed implementation:
determining a first image segmentation parameter for characterizing a distance (which may refer to the number of spaced exemplary images) between two adjacent exemplary image sub-data formed by segmentation and a second image segmentation parameter for characterizing the number of acquisition positions comprised by the exemplary image sub-data formed by segmentation, i.e. the number of exemplary images comprised by one exemplary image sub-data;
and performing an image segmentation operation on the exemplary image data based on the first image segmentation parameter and the second image segmentation parameter to form a plurality of exemplary image sub-data corresponding to the exemplary image data, wherein the number of the exemplary images included in each of the exemplary image sub-data may be equal to the second image segmentation parameter.
It should be appreciated that, in some embodiments, the image key information description vector includes a key information description vector of an image granularity corresponding to each exemplary image sub-data, and based on the foregoing related description, the step of aggregating the user attribute mapping vector into the image key information description vector corresponding to the exemplary image data to form a corresponding image user aggregate vector may further include the following detailed implementation content:
respectively carrying out aggregation operation on the user attribute mapping vector and the key information description vector of the image granularity corresponding to each exemplary image sub-data to form a user aggregation vector of the image granularity corresponding to each exemplary image sub-data, so that the user attribute mapping vector can be aggregated to the key information description vector of the image granularity corresponding to each exemplary image sub-data;
and based on the time sequence relation of the corresponding exemplary image sub-data in the exemplary image data, carrying out sequential combination operation on the user aggregate vector of the image granularity corresponding to each exemplary image sub-data so as to form the image user aggregate vector corresponding to the exemplary image data.
It should be understood that, in some embodiments, the key information description vector of the image granularity corresponding to each of the exemplary image sub-data includes an individual key information description vector of each of the exemplary images included in the corresponding exemplary image sub-data, that is, by performing the key information mining operation on the exemplary image, a corresponding individual key information description vector may be obtained, where, it should be noted that the individual key information description vector, the key information description vector of the image granularity, and the image key information description vector refer to the mined key information description vector, and the difference is that the individual key information description vector indicates an individual level of the exemplary image, the key information description vector of the image granularity indicates an exemplary image sub-data level, and the image key information description vector indicates an exemplary image data level. The step of aggregating the user attribute mapping vector and the key information description vector of the image granularity corresponding to each of the exemplary image sub-data to form a user aggregate vector of the image granularity corresponding to each of the exemplary image sub-data may further include the following detailed implementation content, where any one of the exemplary image sub-data corresponding to the exemplary image data is taken as the first exemplary image sub-data (each of the exemplary image sub-data may be taken as the first exemplary image sub-data sequentially or in parallel):
Performing aggregation operation on the user attribute mapping vector and the individual key information description vector of each exemplary image included in the first exemplary image sub-data to form an individual image user aggregation vector corresponding to each exemplary image, so that the individual image user aggregation vector corresponding to the exemplary image carries image feature information of the exemplary image and user feature information of the image analysis user;
and determining the user aggregate vector of the image granularity corresponding to the first exemplary image sub-data according to the individual image user aggregate vector corresponding to each exemplary image, for example, performing cascade combination operation on the individual image user aggregate vector corresponding to each exemplary image to form the user aggregate vector of the image granularity corresponding to the first exemplary image sub-data.
Wherein, it should be understood that, in some embodiments, the step of aggregating the user attribute mapping vector and the individual key information description vector of each exemplary image included in the first exemplary image sub-data to form an individual image user aggregate vector corresponding to each exemplary image may further include the following detailed implementation matters:
And for the individual key information description vector of each exemplary image included in the first exemplary image sub-data, performing cascade combination operation on the individual key information description vector and the user attribute mapping vector to form an individual image user aggregation vector corresponding to the exemplary image.
Wherein, it should be understood that, in some embodiments, the step of aggregating the user attribute mapping vector and the individual key information description vector of each exemplary image included in the first exemplary image sub-data to form an individual image user aggregate vector corresponding to each exemplary image may further include the following detailed implementation matters:
for each exemplary image included in the first exemplary image sub-data, performing mapping operation (such as multiplication operation) on the individual key information description vector based on the first mapping matrix to form a first vector to be processed;
mapping the user attribute mapping vector based on a second mapping matrix and a third mapping matrix to form a second vector to be processed and a third vector to be processed, wherein the first mapping matrix, the second mapping matrix and the third mapping matrix can be objects of network optimization;
Multiplying the rank-permutation result of the vector parameters of the second to-be-processed vector and the first to-be-processed vector to form a corresponding similarity characterization parameter, and adjusting the similarity characterization parameter based on the vector dimension of the first to-be-processed vector to form a corresponding adjusted similarity characterization parameter, for example, in the process of performing the adjustment operation, the ratio, such as the power of 0.5, between the similarity characterization parameter and the power operation result of the vector dimension of the first to-be-processed vector can be calculated to obtain the corresponding adjusted similarity characterization parameter;
performing a weighting operation (such as a multiplication operation) on the third to-be-processed vector based on the adjusted similarity characterization parameter to form a corresponding similarity description vector;
and carrying out superposition operation on the similarity description vector and the corresponding individual key information description vector to form an individual image user aggregation vector corresponding to the corresponding exemplary image.
Wherein, it should be understood that, in some embodiments, the step of aggregating the user attribute mapping vector and the individual key information description vector of each exemplary image included in the first exemplary image sub-data to form an individual image user aggregate vector corresponding to each exemplary image may further include the following detailed implementation matters:
According to the time sequence relationship, sequencing and numbering each exemplary image included in the first exemplary image sub-data;
for a first exemplary image, performing mapping operation on an individual key information description vector corresponding to the exemplary image based on a first mapping matrix to form a first to-be-processed vector corresponding to the exemplary image, performing mapping operation on the user attribute mapping vector based on a second mapping matrix and a third mapping matrix to form a second to-be-processed vector and a third to-be-processed vector, performing multiplication operation on a rank-column exchange result of vector parameters of the second to-be-processed vector and the first to-be-processed vector corresponding to the exemplary image to form a corresponding similarity characterization parameter, performing adjustment operation on the similarity characterization parameter based on a vector dimension of the first to-be-processed vector corresponding to the exemplary image to form a corresponding adjustment similarity characterization parameter, performing weighting operation on the third to-be-processed vector based on the adjustment similarity characterization parameter to form a corresponding similarity description vector, and performing superposition operation on the similarity description vector and the individual key information description vector corresponding to the exemplary image to form an individual user aggregate vector corresponding to the exemplary image;
For each example image except the first example image, mapping operation is performed on individual key information description vectors corresponding to the example image based on the first mapping matrix to form a first to-be-processed vector corresponding to the example image, mapping operation is performed on individual image user aggregate vectors corresponding to the previous example image based on the second mapping matrix and the third mapping matrix to form a fourth to-be-processed vector and a fifth to-be-processed vector, multiplication operation is performed on a row-column exchange result of vector parameters of the fourth to-be-processed vector and the first to-be-processed vector corresponding to the example image to form a corresponding similarity characterization parameter, adjustment operation is performed on the similarity characterization parameter based on vector dimensions of the first to-be-processed vector corresponding to the example image to form a corresponding adjustment similarity characterization parameter, weighting operation is performed on the fifth to-be-processed vector based on the adjustment similarity characterization parameter to form a corresponding similarity description, and superposition operation is performed on individual key information of the similarity description vectors corresponding to the example image to form an individual description vector.
Wherein, it should be understood that, in some embodiments, the step of performing key information mining operation on the exemplary image to obtain corresponding individual key information description vectors includes:
performing feature space mapping operation on the exemplary image to form an exemplary image mapping vector corresponding to the exemplary image;
for a first exemplary image, performing filtering operation on an exemplary image mapping vector corresponding to the exemplary image based on a first filtering unit in a plurality of configured cascaded filtering units to form an individual key information description vector corresponding to the exemplary image;
for each of the example images other than the first example image, determining a filtering unit which is the same as the order of the example image in the plurality of filtering units, marking the filtering unit as a target filtering unit corresponding to the example image, performing aggregation operation on the example image mapping vector corresponding to the example image and the individual key information description vector corresponding to the previous example image to form an aggregation vector corresponding to the example image corresponding to the target filtering unit, and performing filtering operation on the aggregation vector through the target filtering unit to form the individual key information description vector corresponding to the example image.
Wherein, it should be understood that, in some embodiments, the step of aggregating the exemplary image mapping vector corresponding to the exemplary image and the individual key information description vector corresponding to the previous exemplary image to form an aggregate vector corresponding to the exemplary image corresponding to the target filtering unit includes:
performing cascade combination operation on the exemplary image mapping vector corresponding to the exemplary image and the individual key information description vector corresponding to the previous exemplary image to form a cascade combination vector, and performing compression operation, such as pooling operation, on the cascade combination vector to obtain a compression cascade combination vector with the same vector size and dimension as those of the exemplary image mapping vector;
performing mapping operation on the exemplary image mapping vector corresponding to the exemplary image based on a fourth mapping matrix to form a corresponding exemplary mapping vector;
mapping the compressed cascade combination vector based on a fifth mapping matrix and a sixth mapping matrix to form a corresponding first cascade mapping vector and a second cascade mapping vector, wherein the fourth mapping matrix, the fifth mapping matrix and the sixth mapping matrix can be objects of network optimization so as to continuously perform optimization adjustment in the optimization process of the corresponding neural network;
And performing multiplication operation on the row-column exchange result of the vector parameters of the first cascade mapping vector and the exemplary mapping vector to form a corresponding correlation characterization parameter, performing adjustment operation on the correlation characterization parameter based on the vector dimension of the exemplary mapping vector to form a corresponding adjustment correlation characterization parameter, performing weighting operation on the second cascade mapping vector based on the adjustment correlation characterization parameter, and performing superposition operation on the result of the weighting operation and the exemplary image mapping vector corresponding to the exemplary image to form a corresponding aggregate vector.
It should be appreciated that, in some embodiments, the step of performing a network optimization operation on the image richness estimation network to form a corresponding network-optimized image richness estimation network through the analysis estimation data, the image key information description vector and the image user aggregation vector may further include the following detailed implementation matters:
performing image content richness assessment operation on the exemplary image data according to the image key information description vector and the image user aggregation vector through the image richness assessment network so as to output exemplary content richness assessment data corresponding to the exemplary image data;
Analyzing a network learning cost index corresponding to the image richness evaluation network according to the distinguishing information between the exemplary content richness evaluation data and the analysis evaluation data;
and performing network optimization operation on the image richness evaluation network based on the network learning cost index to form a corresponding image richness evaluation network subjected to network optimization processing, for example, adjusting network parameters of the image richness evaluation network to reduce the network learning cost index, and determining to complete network optimization under the condition that the network learning cost index is smaller than a preset index to form the image richness evaluation network subjected to network optimization processing.
It should be appreciated that, in some embodiments, the step of performing, by the image richness assessment network, an image content richness assessment operation on the exemplary image data according to the image key information description vector and the image user aggregation vector to output exemplary content richness assessment data corresponding to the exemplary image data may further include the following detailed implementation contents:
Through the image richness evaluation network, performing image content richness evaluation operation on the exemplary image data according to the image key information description vector, for example, performing full connection processing firstly, and then performing activation output on the result of the full connection processing, for example, based on softmax function implementation, so as to output content richness evaluation data of image dimensions corresponding to the exemplary image data;
through the image richness evaluation network, performing image content richness evaluation operation on the exemplary image data according to the image user aggregate vector, for example, performing full connection processing firstly, and then performing activation output on the result of the full connection processing, for example, based on softmax function implementation, so as to output content richness evaluation data of aggregate dimension corresponding to the exemplary image data;
based on the content richness estimation data of the image dimension and the content richness estimation data of the aggregation dimension, analyzing the exemplary content richness estimation data corresponding to the exemplary image data, for example, weighting and summing the content richness estimation data of the image dimension and the content richness estimation data of the aggregation dimension may be performed to obtain the exemplary content richness estimation data.
It should be understood that, in some embodiments, the image key information description vector may include a key information description vector of an image granularity corresponding to each exemplary image sub-data, based on which, the step of performing, by the image richness assessment network, an image content richness assessment operation on the exemplary image data according to the image key information description vector to output content richness assessment data of an image dimension corresponding to the exemplary image data may further include the following detailed implementation contents:
performing vector integration operation on the key information description vector of the image granularity corresponding to each exemplary image sub-data through the image richness evaluation network to form an integrated key information description vector corresponding to each exemplary image sub-data, wherein the key information description vector of the image granularity corresponding to each exemplary image sub-data comprises individual key information description vectors of the respective exemplary images included in the corresponding exemplary image sub-data, and an operation object of the vector integration operation is the individual key information description vector of the respective exemplary images included in the exemplary image sub-data;
Performing content richness assessment operation on the corresponding exemplary image sub-data according to the integrated key information description vector corresponding to each exemplary image sub-data so as to output content richness assessment sub-data corresponding to each exemplary image sub-data;
and carrying out fusion operation on content richness assessment sub-data corresponding to a plurality of example image sub-data included in the example image data so as to form content richness assessment data of image dimensions corresponding to the example image data.
It should be understood that, in some embodiments, the step of performing, by the image richness assessment network, a vector integration operation on the key information description vector of the image granularity corresponding to each of the exemplary image sub-data to form an integrated key information description vector corresponding to each of the exemplary image sub-data may further include the following detailed implementation matters:
for the individual key information description vector of each exemplary image included in the exemplary image sub-data, multiplying the individual key information description vector by a configured one-dimensional parameter matrix, and then performing interval mapping of vector parameters on the multiplied result, for example, mapping to intervals 0 to 1, so as to obtain a mapped individual key information description vector corresponding to the individual key information description vector, wherein the one-dimensional parameter matrix can be used as a network optimization object;
Performing a row parameter and column parameter transposition operation on the vector parameters of the mapped individual key information description vector to form a corresponding transposition individual key information description vector;
multiplying the individual key information description vector and the corresponding swap individual key information description vector of the individual key information description vector to form an individual integration key information description vector corresponding to the individual key information description vector;
and carrying out cascade combination operation on individual integration key information description vectors corresponding to the individual key information description vectors of each exemplary image included in the exemplary image sub-data so as to form integration key information description vectors corresponding to the exemplary image sub-data.
It should be appreciated that, in some embodiments, the step of performing the content richness assessment operation on each of the exemplary image sub-data according to the integrated key information description vector corresponding to each of the exemplary image sub-data to output the content richness assessment sub-data corresponding to each of the exemplary image sub-data may further include the following detailed implementation contents:
exciting the integrated key information description vector corresponding to each exemplary image sub-data through a round excitation function, so as to realize the content richness assessment operation of the corresponding exemplary image sub-data, and outputting initial content richness assessment sub-data corresponding to each exemplary image sub-data, wherein the round excitation function can be a tanh function;
And carrying out weighting operation on the initial content richness assessment sub-data based on a first adjustment parameter, and carrying out superposition operation on the result of the weighting operation based on a second adjustment parameter to form the content richness assessment sub-data corresponding to the exemplary image sub-data, wherein the first adjustment parameter and the second adjustment parameter can be used as network parameters of a neural network to participate in network optimization, and in the initial stage, the first adjustment parameter can be equal to 1, and the second adjustment parameter can also be equal to 1.
It should be appreciated that, in some embodiments, the step of performing the fusion operation on the content richness assessment sub-data corresponding to the plurality of exemplary image sub-data included in the exemplary image data to form the content richness assessment data of the image dimension corresponding to the exemplary image data may further include the following detailed implementation contents:
and carrying out average value calculation operation on content richness assessment sub-data corresponding to a plurality of exemplary image sub-data included in the exemplary image data to form content richness assessment data of an image dimension corresponding to the exemplary image data, namely carrying out average value calculation operation on the plurality of content richness assessment sub-data to obtain the content richness assessment data of the image dimension.
With reference to fig. 3, the embodiment of the invention further provides an unmanned aerial vehicle acquisition data processing device (a virtual device) based on artificial intelligence, which can be applied to the unmanned aerial vehicle acquisition data processing system based on artificial intelligence. Wherein, unmanned aerial vehicle gathers data processing apparatus based on artificial intelligence can include:
the image data extraction module is used for extracting to-be-processed image data acquired by the target unmanned aerial vehicle, wherein the to-be-processed image data comprises at least one to-be-processed image acquired by the target unmanned aerial vehicle;
the content richness evaluation module is used for performing image content richness evaluation operation on the image data to be processed through an image richness evaluation network subjected to network optimization processing so as to output image content richness characterization data corresponding to the image data to be processed, wherein the image content richness characterization data is used for reflecting the content richness of the image to be processed in the image data to be processed;
the image data screening module is used for carrying out screening operation on the at least one image to be processed included in the image data to be processed based on the image content richness characterization data so as to form corresponding target image data, wherein the target image data comprises at least one image to be processed, and the screening proportion of the screening operation has a positive correlation corresponding relation with the image content richness characterization data;
And the image data pushing module is used for carrying out user pushing operation on the target image data.
In summary, the unmanned aerial vehicle acquisition data processing method and system based on artificial intelligence provided by the invention can firstly extract the image data to be processed acquired by the target unmanned aerial vehicle; performing image content richness evaluation operation on the image data to be processed through an image richness evaluation network subjected to network optimization processing so as to output image content richness characterization data corresponding to the image data to be processed; based on the image content richness characterization data, screening operation is carried out on at least one image to be processed, which is included in the image data to be processed, so as to form corresponding target image data, wherein the target image data includes at least one image to be processed, and a positive correlation corresponding relation exists between the screening proportion of the screening operation and the image content richness characterization data; and carrying out user pushing operation on the target image data. Based on the foregoing, before the user pushing operation, the image data is screened, and the basis of the screening is the assessed image content richness characterization data, so that the reliability of the screening of the image data is higher, the reliability of the user pushing operation on the screened target image data can be ensured, and the reliability of the data pushing is improved to a certain extent.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1. An unmanned aerial vehicle acquisition data processing method based on artificial intelligence is characterized by comprising the following steps:
extracting to-be-processed image data acquired by a target unmanned aerial vehicle, wherein the to-be-processed image data comprises at least one to-be-processed image acquired by the target unmanned aerial vehicle;
performing image content richness evaluation operation on the image data to be processed through an image richness evaluation network subjected to network optimization processing to output image content richness characterization data corresponding to the image data to be processed, wherein the image content richness characterization data is used for reflecting the content richness of the image to be processed in the image data to be processed;
based on the image content richness characterization data, performing screening operation on the at least one image to be processed, which is included in the image data to be processed, so as to form corresponding target image data, wherein the target image data includes at least one image to be processed, and the screening proportion of the screening operation and the image content richness characterization data have a positive correlation corresponding relation;
And carrying out user pushing operation on the target image data.
2. The unmanned aerial vehicle acquisition data processing method based on artificial intelligence of claim 1, wherein the unmanned aerial vehicle acquisition data processing method based on artificial intelligence further comprises:
extracting user description data of an exemplary image data and an image analysis user, wherein the image analysis user belongs to a user for analyzing and evaluating the content richness of the exemplary image data, the user description data comprises user attribute description data of the image analysis user and analysis and evaluation data formed by the image analysis user for analyzing and evaluating the content richness of the exemplary image data, and the user attribute description data at least comprises user identity information of the image analysis user and preference description information of the image data;
performing key information mining operation on the exemplary image data through an initial image richness evaluation network to form an image key information description vector corresponding to the exemplary image data;
performing feature space mapping operation on the user attribute description data of the image analysis user through the image richness evaluation network to form a user attribute mapping vector corresponding to the image analysis user;
Performing aggregation operation on the user attribute mapping vector to aggregate the user attribute mapping vector into an image key information description vector corresponding to the exemplary image data to form a corresponding image user aggregation vector, wherein the image user aggregation vector carries image characteristic information of the exemplary image data and user characteristic information of the image analysis user;
and performing network optimization operation on the image richness evaluation network through the analysis evaluation data, the image key information description vector and the image user aggregation vector so as to form a corresponding image richness evaluation network subjected to network optimization processing.
3. The unmanned aerial vehicle collected data processing method based on artificial intelligence of claim 2, wherein the step of performing key information mining operation on the exemplary image data through an initial image richness assessment network to form an image key information description vector corresponding to the exemplary image data comprises:
performing image segmentation operation on the exemplary image data to form a plurality of exemplary image sub-data corresponding to the exemplary image data;
performing key information mining operation on each of the plurality of exemplary image sub-data through an initial image richness evaluation network to output a key information description vector of image granularity corresponding to each of the exemplary image sub-data, wherein the key information description vector of image granularity corresponding to the exemplary image sub-data is used for representing image feature information of each of the exemplary images included in the exemplary image sub-data;
Determining an image key information description vector corresponding to the exemplary image data according to the key information description vector of the image granularity corresponding to each exemplary image sub-data, wherein the key information description vector of each image granularity in the image key information description vector is ordered based on the time sequence relationship of the corresponding exemplary image sub-data in the exemplary image data, and the image key information description vector is used for representing the image characteristic information of each exemplary image in the exemplary image data.
4. The unmanned aerial vehicle acquisition data processing method of claim 3, wherein the exemplary image data includes a plurality of acquisition locations, and wherein the step of performing an image segmentation operation on the exemplary image data to form a plurality of exemplary image sub-data corresponding to the exemplary image data comprises:
determining a first image segmentation parameter and a second image segmentation parameter, wherein the first image segmentation parameter is used for representing the distance between two adjacent exemplary image sub-data formed by segmentation, and the second image segmentation parameter is used for representing the number of acquisition positions included in the exemplary image sub-data formed by segmentation;
And performing image segmentation operation on the exemplary image data based on the first image segmentation parameter and the second image segmentation parameter to form a plurality of exemplary image sub-data corresponding to the exemplary image data.
5. The unmanned aerial vehicle acquisition data processing method based on artificial intelligence of claim 2, wherein the image key information description vector comprises a key information description vector of image granularity corresponding to each exemplary image sub-data; the step of aggregating the user attribute mapping vectors to aggregate the image key information description vectors corresponding to the exemplary image data to form corresponding image user aggregate vectors includes:
respectively carrying out aggregation operation on the user attribute mapping vector and the key information description vector of the image granularity corresponding to each exemplary image sub-data to form a user aggregation vector of the image granularity corresponding to each exemplary image sub-data;
and based on the time sequence relation of the corresponding exemplary image sub-data in the exemplary image data, carrying out sequential combination operation on the user aggregate vector of the image granularity corresponding to each exemplary image sub-data so as to form the image user aggregate vector corresponding to the exemplary image data.
6. The unmanned aerial vehicle acquisition data processing method based on artificial intelligence of claim 5, wherein the key information description vector of the image granularity corresponding to each of the exemplary image sub-data comprises individual key information description vectors of the respective exemplary images included in the corresponding exemplary image sub-data; any one of the exemplary image sub-data corresponding to the exemplary image data is used as first exemplary image sub-data;
the step of performing an aggregation operation on the user attribute mapping vector and the key information description vector of the image granularity corresponding to each exemplary image sub-data to form a user aggregation vector of the image granularity corresponding to each exemplary image sub-data includes:
performing aggregation operation on the user attribute mapping vector and the individual key information description vector of each exemplary image included in the first exemplary image sub-data to form an individual image user aggregation vector corresponding to each exemplary image, so that the individual image user aggregation vector corresponding to the exemplary image carries image feature information of the exemplary image and user feature information of the image analysis user;
And determining the user aggregate vector of the image granularity corresponding to the first exemplary image sub-data according to the individual image user aggregate vector corresponding to each exemplary image.
7. The unmanned aerial vehicle data collection processing method according to claim 2, wherein the step of performing a network optimization operation on the image richness assessment network by the analysis assessment data, the image key information description vector and the image user aggregation vector to form a corresponding network-optimized image richness assessment network comprises:
performing image content richness assessment operation on the exemplary image data according to the image key information description vector and the image user aggregation vector through the image richness assessment network so as to output exemplary content richness assessment data corresponding to the exemplary image data;
analyzing a network learning cost index corresponding to the image richness evaluation network according to the distinguishing information between the exemplary content richness evaluation data and the analysis evaluation data;
and carrying out network optimization operation on the image richness evaluation network based on the network learning cost index to form a corresponding image richness evaluation network subjected to network optimization processing.
8. The unmanned aerial vehicle collected data processing method based on artificial intelligence of claim 7, wherein the step of performing an image content richness assessment operation on the exemplary image data according to the image key information description vector and the image user aggregation vector by the image richness assessment network to output exemplary content richness assessment data corresponding to the exemplary image data comprises:
performing image content richness assessment operation on the exemplary image data according to the image key information description vector through the image richness assessment network so as to output content richness assessment data of image dimensions corresponding to the exemplary image data; and performing image content richness assessment operation on the exemplary image data according to the image user aggregation vector through the image richness assessment network to output content richness assessment data of an aggregation dimension corresponding to the exemplary image data; and analyzing the exemplary content-richness estimation data corresponding to the exemplary image data based on the content-richness estimation data of the image dimension and the content-richness estimation data of the aggregation dimension;
The step of performing, by the image richness evaluation network, an image content richness evaluation operation on the exemplary image data according to the image key information description vector to output content richness evaluation data of an image dimension corresponding to the exemplary image data includes:
performing vector integration operation on the key information description vector of the image granularity corresponding to each exemplary image sub-data through the image richness evaluation network to form an integrated key information description vector corresponding to each exemplary image sub-data, wherein the key information description vector of the image granularity corresponding to each exemplary image sub-data comprises individual key information description vectors of the respective exemplary images included in the corresponding exemplary image sub-data, and an operation object of the vector integration operation is the individual key information description vector of the respective exemplary images included in the exemplary image sub-data;
performing content richness assessment operation on the corresponding exemplary image sub-data according to the integrated key information description vector corresponding to each exemplary image sub-data so as to output content richness assessment sub-data corresponding to each exemplary image sub-data;
And carrying out fusion operation on content richness assessment sub-data corresponding to a plurality of example image sub-data included in the example image data so as to form content richness assessment data of image dimensions corresponding to the example image data.
9. The unmanned aerial vehicle collected data processing method of claim 8, wherein the step of performing a content-richness estimation operation on each of the exemplary image sub-data according to the integrated key information description vector corresponding to each of the exemplary image sub-data to output the content-richness estimation sub-data corresponding to each of the exemplary image sub-data comprises:
exciting the integrated key information description vector corresponding to each exemplary image sub-data through a circular excitation function to realize the content richness assessment operation of the corresponding exemplary image sub-data, and outputting initial content richness assessment sub-data corresponding to each exemplary image sub-data;
performing a weighting operation on the initial content richness assessment sub-data based on a first adjustment parameter, and performing a superposition operation on the result of the weighting operation based on a second adjustment parameter to form content richness assessment sub-data corresponding to the exemplary image sub-data;
The step of performing a fusion operation on content richness assessment sub-data corresponding to a plurality of exemplary image sub-data included in the exemplary image data to form content richness assessment data of an image dimension corresponding to the exemplary image data includes:
and carrying out average value calculation operation on content richness assessment sub-data corresponding to a plurality of example image sub-data included in the example image data so as to form content richness assessment data of image dimensions corresponding to the example image data.
10. An artificial intelligence based unmanned aerial vehicle acquisition data processing system comprising a processor and a memory, the memory for storing a computer program, the processor for executing the computer program to implement the method of any of claims 1-9.
CN202310381912.7A 2023-04-11 2023-04-11 Unmanned aerial vehicle acquisition data processing method and system based on artificial intelligence Active CN116091796B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310381912.7A CN116091796B (en) 2023-04-11 2023-04-11 Unmanned aerial vehicle acquisition data processing method and system based on artificial intelligence

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310381912.7A CN116091796B (en) 2023-04-11 2023-04-11 Unmanned aerial vehicle acquisition data processing method and system based on artificial intelligence

Publications (2)

Publication Number Publication Date
CN116091796A CN116091796A (en) 2023-05-09
CN116091796B true CN116091796B (en) 2023-06-02

Family

ID=86208667

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310381912.7A Active CN116091796B (en) 2023-04-11 2023-04-11 Unmanned aerial vehicle acquisition data processing method and system based on artificial intelligence

Country Status (1)

Country Link
CN (1) CN116091796B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116662415B (en) * 2023-07-28 2023-10-20 泰山学院 Intelligent matching method and system based on data mining
CN117150065B (en) * 2023-08-16 2024-05-28 内蒙古惠强科技有限公司 Image information acquisition method and system

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2354973A1 (en) * 2010-02-05 2011-08-10 Research In Motion Limited Display placeholders for rich media content
CN104079800A (en) * 2014-06-24 2014-10-01 上海波汇通信科技有限公司 Shaking preventing method for video image in video surveillance
CN109409221A (en) * 2018-09-20 2019-03-01 中国科学院计算技术研究所 Video content description method and system based on frame selection
CN110147851A (en) * 2019-05-29 2019-08-20 北京达佳互联信息技术有限公司 Method for screening images, device, computer equipment and storage medium
JP2022096883A (en) * 2020-12-18 2022-06-30 凸版印刷株式会社 Evaluation system, method for evaluation, and program
CN115170838A (en) * 2022-07-11 2022-10-11 杭州海康威视数字技术股份有限公司 Data screening method and device
CN115588144A (en) * 2022-10-25 2023-01-10 山东海量信息技术研究院 Real-time attitude capturing method, device and equipment based on Gaussian dynamic threshold screening

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2354973A1 (en) * 2010-02-05 2011-08-10 Research In Motion Limited Display placeholders for rich media content
CN104079800A (en) * 2014-06-24 2014-10-01 上海波汇通信科技有限公司 Shaking preventing method for video image in video surveillance
CN109409221A (en) * 2018-09-20 2019-03-01 中国科学院计算技术研究所 Video content description method and system based on frame selection
CN110147851A (en) * 2019-05-29 2019-08-20 北京达佳互联信息技术有限公司 Method for screening images, device, computer equipment and storage medium
JP2022096883A (en) * 2020-12-18 2022-06-30 凸版印刷株式会社 Evaluation system, method for evaluation, and program
CN115170838A (en) * 2022-07-11 2022-10-11 杭州海康威视数字技术股份有限公司 Data screening method and device
CN115588144A (en) * 2022-10-25 2023-01-10 山东海量信息技术研究院 Real-time attitude capturing method, device and equipment based on Gaussian dynamic threshold screening

Also Published As

Publication number Publication date
CN116091796A (en) 2023-05-09

Similar Documents

Publication Publication Date Title
CN116091796B (en) Unmanned aerial vehicle acquisition data processing method and system based on artificial intelligence
CN115205765B (en) FPGA-based video analysis method and system
CN116126947B (en) Big data analysis method and system applied to enterprise management system
CN114140713A (en) Image recognition system and image recognition method
CN115687674A (en) Big data demand analysis method and system serving smart cloud service platform
CN116310914B (en) Unmanned aerial vehicle monitoring method and system based on artificial intelligence
CN114187763A (en) Vehicle driving data screening method and system for intelligent traffic
CN113902993A (en) Environmental state analysis method and system based on environmental monitoring
CN116610745B (en) AI scene information pushing processing method and system applying digital twin technology
CN116757870A (en) Intelligent energy monitoring data processing method and system for energy Internet of things
CN116070149A (en) Data analysis method and system based on artificial intelligence and cloud platform
CN116109988A (en) Anomaly monitoring method and system based on artificial intelligence and unmanned aerial vehicle
CN115174638B (en) Networking method and system for photovoltaic panel data acquisition equipment
CN115620243A (en) Pollution source monitoring method and system based on artificial intelligence and cloud platform
CN115757900A (en) User demand analysis method and system applying artificial intelligence model
CN115616408A (en) Battery thermal management data processing method and system
CN116662415B (en) Intelligent matching method and system based on data mining
CN115753776B (en) Solar cell data processing method and system
CN117171390B (en) Information pushing method and system based on big data
CN115620210B (en) Method and system for determining performance of electronic wire material based on image processing
CN117150065B (en) Image information acquisition method and system
CN114156495B (en) Laminated battery assembly processing method and system based on big data
CN117058084A (en) Rail damage detection method and system
CN116662574A (en) Big data acquisition method and system for anti-fraud AI prediction model
CN116958838A (en) Forest resource monitoring method and system based on unmanned aerial vehicle aerial survey technology

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