CN112327935A - AI technology-based unmanned aerial vehicle cloud object identification and tracking system and method - Google Patents
AI technology-based unmanned aerial vehicle cloud object identification and tracking system and method Download PDFInfo
- Publication number
- CN112327935A CN112327935A CN201910716631.6A CN201910716631A CN112327935A CN 112327935 A CN112327935 A CN 112327935A CN 201910716631 A CN201910716631 A CN 201910716631A CN 112327935 A CN112327935 A CN 112327935A
- Authority
- CN
- China
- Prior art keywords
- module
- image
- unmanned aerial
- cloud
- flight control
- 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
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000005516 engineering process Methods 0.000 title claims abstract description 16
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 claims abstract description 82
- 239000000284 extract Substances 0.000 claims abstract 2
- 238000004891 communication Methods 0.000 claims description 37
- 238000012545 processing Methods 0.000 claims description 31
- 238000012795 verification Methods 0.000 claims description 31
- 238000000605 extraction Methods 0.000 claims description 27
- 238000013135 deep learning Methods 0.000 claims description 24
- 230000005540 biological transmission Effects 0.000 claims description 9
- 238000007689 inspection Methods 0.000 claims description 8
- 230000002708 enhancing effect Effects 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/12—Target-seeking control
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based 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
- G06V10/94—Hardware or software architectures specially adapted for image or video understanding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Software Systems (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an AI technology-based unmanned aerial vehicle cloud object identification tracking system and method, which comprises a ground station system, an object identification cloud system, an unmanned aerial vehicle-end shooting system and a flight control system, wherein the shooting system shoots and collects images of an object, transmits the images to the object identification cloud system, analyzes and processes the shot images, extracts object type position information and transmits the object type position information to the ground station system and the flight control system, the ground station system displays the object information on a display screen after receiving the information, an operator sends an instruction of the object to be tracked, the instruction is processed by the object identification cloud system and then transmits the instruction to the flight control system, and the flight control system controls an unmanned aerial vehicle by combining the instruction and the identified object information to track the object. According to the invention, the ground station system is simultaneously connected with a plurality of unmanned aerial vehicles through the object identification cloud system, and simultaneously, the objects are subjected to image acquisition through the unmanned aerial vehicles and are processed by the object identification cloud system and fed back to the ground station system, so that a plurality of objects are tracked.
Description
Technical Field
The invention relates to the field of object identification and tracking, in particular to an unmanned aerial vehicle cloud object identification and tracking system and method based on an AI technology.
Background
In recent years, unmanned aerial vehicle systems are gradually and more widely applied in the fields of surveying and mapping, search and rescue, real estate, agriculture and the like due to the characteristics of flexibility, portability, strong space maneuverability and the like, and are popular with consumers as aerial or recreational unmanned aerial vehicles. People use more unmanned aerial vehicles to follow some objects in motion, or let unmanned aerial vehicle itself shoot some objects in the in-process of motion. And shooting in the motion process needs people to carry out accurate control to unmanned aerial vehicle or cloud platform and just can track the object, needs two or more personnel to accomplish this operation even. The use of drones would be extended if they could autonomously accomplish the tracking of some moving objects in motion.
Disclosure of Invention
The invention aims to provide an unmanned aerial vehicle cloud object identification and tracking system and method based on an AI technology, so as to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme:
the utility model provides an unmanned aerial vehicle high in clouds object identification tracker based on AI technique, includes:
ground station system, object identification cloud system and unmanned aerial vehicle end fly accuse system and shooting system, wherein:
the shooting system is used for shooting and collecting images of objects in a shooting range;
the object identification cloud system receives image processing acquired by the unmanned aerial vehicle shooting and analyzes the category and position information of an object in the image processing;
the ground station system is used for receiving the image shot by the unmanned aerial vehicle and the object information identified by the object identification cloud system and then appointing the type of the object to be tracked;
and the flight control system receives an instruction sent by the ground station system and controls the unmanned aerial vehicle to track and shoot the object to be tracked.
Furthermore, the shooting system comprises a camera and a data transmission module, the camera is carried on the unmanned aerial vehicle through a holder, the camera collects images within a shooting range, and the collected images are transmitted to the flight control system through the data transmission module.
Furthermore, the ground station system comprises a ground communication module, and a ground login verification module, a data processing module and an instruction input module which are electrically connected with the ground communication module, wherein the ground login verification module analyzes and identifies identity information input by an operator, an operation authority is granted after successful authentication, the operator inputs an instruction of an article to be tracked through the instruction input module, the instruction is sent to the object identification cloud system through the ground communication module, meanwhile, the ground communication module transmits data acquired by the object identification cloud system to the data processing module, and the data processing module analyzes the data information and displays the data information on a user interface for the operator to operate.
Further, the flight control system comprises a flight control communication module and a flight control login verification module electrically connected with the flight control communication module, a flight control module and a tripod head control module, the flight control communication module exchanges data with the ground station system and the shooting system, communication between the flight control login verification module and the ground station system and the shooting system is achieved, the flight control login verification module logs in the object identification cloud system through an unmanned aerial vehicle ID number and a private serial number, the flight control module and the tripod head control module acquire relative position information of an object to be tracked from the object identification cloud system, the flight control module controls the direction of flight tracking of the unmanned aerial vehicle, and the tripod head control module controls the angle of the tripod head connecting the camera and the unmanned aerial vehicle, which needs to deflect.
Further, the object identification cloud system comprises a cloud communication module, a cloud login verification module, an instruction analysis module and an object identification module, data transmission is carried out between the cloud communication module and the flight control system and the ground station system, the cloud login verification module is electrically connected with the cloud communication module and identifies the login request of the ground station system and the flight control system which are transmitted by the cloud login verification module, if the login request is legal, the ground station system or the flight control system is permitted to be added, after the login request is added, the instruction analysis module which is electrically connected with the cloud communication module analyzes the data transmitted by the ground station system and the flight control system, then the instruction of the ground station system is transmitted to the flight control system, meanwhile, the image shot by the unmanned aerial vehicle is transmitted to the object identification module to be analyzed, and the category and the position information of the object are identified.
Furthermore, the object identification module comprises an instruction safety inspection module, a deep learning classification module, a category position extraction module and a data distribution and subscription module, wherein the instruction safety inspection module inspects instruction loading conditions sent from the ground station, the deep learning classification module performs operation classification on data in videos shot by the camera and selects each object and the relative position of the image where the object is located, the category extraction module transparently transmits the type of each object and the relative position of the image where the object is located to the data distribution and subscription module, and the data distribution and subscription module sends the received data to the ground station system and the flight control system.
An unmanned aerial vehicle cloud object identification and tracking method based on AI technology comprises the following steps:
s1: the ground station system and the flight control systems of the unmanned aerial vehicles log in the object identification cloud system through the verification of the cloud login verification module, and the ground station system is connected with the unmanned aerial vehicles in a control mode through the object statistics identification cloud system;
s2: inputting a control instruction for each unmanned aerial vehicle in an instruction input module of the ground station system;
s3: the flight control system receives the instruction of the ground station and then triggers a corresponding function to control the unmanned aerial vehicle to fly;
s4: in the flight process of the unmanned aerial vehicle, the camera continuously collects images in a shooting range, and the collected images are transmitted to a flight control system;
s5: after the object identification cloud system receives the image data transmitted by the flight control system, the processing process is as follows:
the first step is as follows: the command and data safety inspection module inspects data sent from the ground station and module parameter loading conditions, and if the data are normal, the command is sent to the deep learning classification module;
the second step is that: the deep learning classification module is used for calculating and classifying object data in the image shot by the camera according to the trained parameters, selecting the relative positions of each object and the image where the object is located, and sending the relative positions to the classification position extraction module;
the third step: the category position extraction module transparently transmits the relative positions of each object and the image where the object is located, which are obtained in the deep learning classification module, to the data distribution and subscription module, then checks whether the object specified by the ground station is in the image, and if so, transmits the data to the data distribution module;
the fourth step: the data distribution and subscription module sends the received data to the ground station and the flight control module;
s6: after a data processing module of the ground station system receives statistical data of the flight control system, the data processing module analyzes the statistical data and displays the statistical data on a user interface;
s7: an operator selects an object to be tracked according to the statistical result and inputs a tracking instruction through the instruction input module;
s8: the command is transmitted to the object identification cloud system, and the command analysis module analyzes the command and transmits the analyzed command to the flight control system to control the unmanned aerial vehicle to track the target object;
s9: in the process of tracking the object by the unmanned aerial vehicle, if the proportion of the object in the shot image is more than 30%, the rotation is controlled; and if the ratio is less than 30%, the unmanned aerial vehicle is guided to fly close to the object, the ratio of 30% is kept, the image of the target object is continuously shot, then the image is transmitted to the object identification cloud system, and the image is analyzed and fed back to the ground station system for observation of an operator.
Further, the operation classification of the second deep learning classification module comprises the following steps:
step 1, a deep learning classification module receives image data;
step 2, pretreatment, comprising the following steps:
separating an image area from a background, avoiding feature extraction in an area without effective information, accelerating the speed of subsequent processing and improving the accuracy of image feature extraction and matching;
enhancing the image, improving the image quality and recovering the original structure;
c, carrying out image binarization, and converting the image from a gray level image into a binary image;
d, thinning the image, and converting a clear but non-uniform binary image into a point-line image with the line width of only one pixel;
step 3, feature extraction, namely expressing the features which can fully express the uniqueness of the image in a numerical form, reserving real features and filtering out false features;
step 4, image classification, namely distributing the images to different image libraries in an accurate and consistent method;
step 5, matching images, and comparing the current image characteristics with the stored template image characteristics;
and 6, sending each object and the relative position of the image of the object to a category position extraction module.
Compared with the prior art, the invention has the beneficial effects that: the unmanned aerial vehicle is controlled to fly through the flight control system, so that the camera on the unmanned aerial vehicle collects images in a designated area, the collected data are transmitted to the object identification cloud system for analysis and processing, the types of the objects in the objects are identified, the position information is extracted, the statistical result is transmitted to the ground station system for displaying, an operator designates the object to be tracked, the flight control system receives the image processing result transmitted by the object identification cloud system and an instruction sent by the ground station system, controls the unmanned aerial vehicle to track the object to be tracked, continuously collects the images and transmits the images to the object identification cloud system, and the images are displayed on the ground station system after being processed, so that the object is identified and tracked; meanwhile, the object identification cloud system connects the ground station system with the shooting systems and the flight control system at the ends of the multiple unmanned aerial vehicles, so that the ground station system can control the multiple unmanned aerial vehicles simultaneously and track the multiple objects simultaneously.
Drawings
FIG. 1 is a schematic view of the system of the present invention,
fig. 2 is a schematic view of the structure of the object recognition module according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the present invention provides a technical solution:
the utility model provides an unmanned aerial vehicle high in clouds object identification tracker based on AI technique, includes:
ground station system, object identification cloud system and unmanned aerial vehicle end fly accuse system and shooting system, wherein:
the shooting system is used for shooting and collecting images of objects in a shooting range;
the object identification cloud system receives image processing acquired by the unmanned aerial vehicle shooting and analyzes the category and position information of an object in the image processing;
the ground station system is used for receiving the image shot by the unmanned aerial vehicle and the object information identified by the object identification cloud system and then appointing the type of the object to be tracked;
and the flight control system receives an instruction sent by the ground station system and controls the unmanned aerial vehicle to track and shoot the object to be tracked.
The shooting system comprises an unmanned aerial vehicle, a camera and a data transmission module, the unmanned aerial vehicle acquires an object image by carrying the camera, then the image data is transmitted to the object identification cloud system through the data transmission module, the camera is connected with the unmanned aerial vehicle through a cloud platform, and the rotation of the flight matching cloud platform of the unmanned aerial vehicle realizes that the camera acquires images of objects at different positions.
The ground station system comprises a ground communication module, a ground login verification module, a data processing module and an instruction input module, wherein the ground login verification module is electrically connected with the ground communication module, the ground login verification module analyzes and identifies identity information input by an operator, operation authority is granted after successful authentication, the operator inputs an instruction of an article to be tracked through the instruction input module, the instruction is sent to the object identification cloud system through the ground communication module, meanwhile, the ground communication module transmits data acquired by the object identification cloud system to the data processing module, and the data processing module analyzes the data information and displays the data information on a user interface for the operator to operate.
The flight control system comprises a flight control communication module and a flight control login verification module electrically connected with the flight control communication module, a flight control module and a tripod head control module, the flight control communication module exchanges data with a ground station system and a shooting system, communication between the flight control login verification module and the ground station system and the shooting system is realized, the flight control login verification module logs in an object identification cloud system through an unmanned aerial vehicle ID number and a private serial number, the flight control module and the tripod head control module acquire relative position information of an object to be tracked from the object identification cloud system, the flight control module controls the direction of flight tracking of the unmanned aerial vehicle, and the tripod head control module controls the angle of deflection of a tripod head connecting a camera and the unmanned aerial vehicle.
The object identification cloud system comprises a cloud communication module, a cloud login verification module, an instruction analysis module and an object identification module, data transmission is carried out between the cloud communication module and the flight control system and the ground station system, the cloud login verification module is electrically connected with the cloud communication module and identifies the ground station system and the flight control system login requests transmitted by the cloud login verification module, if the cloud login verification module is legal, the ground station system or the flight control system is permitted to be added, after the cloud login verification module is added, the instruction analysis module electrically connected with the cloud communication module analyzes the data transmitted by the ground station system and the flight control system, then the instruction of the ground station system is transmitted to the flight control system, meanwhile, an image shot by the unmanned aerial vehicle is transmitted to the object identification module to be analyzed, and the type and the position information of the object are identified.
Referring to fig. 2, the object identification module includes an instruction security check module, a deep learning classification module, a category position extraction module and a data distribution and subscription module, the instruction safety inspection module inspects the instruction loading condition sent from the ground station, sends the instruction to the deep learning classification module electrically connected with the instruction after the instruction loading condition is normal, the deep learning classification module is used for calculating and classifying data in a video shot by the camera, selecting each object and the relative position of the image of the object, sending the relative positions to the classification position extraction module electrically connected with the object, the category extraction module transparently transmits the types of the objects and the relative positions of the images of the objects to the data distribution and subscription module, and simultaneously checks whether the objects specified by the ground station are in the images or not, if the data exists, the data is also sent to the data distribution and subscription module, and the data distribution and subscription module sends the received data to the ground station system and the flight control system.
The object identification module comprises an instruction safety inspection module, a deep learning classification module, a category position extraction module and a data distribution and subscription module, wherein the instruction safety inspection module inspects instruction loading conditions sent from a ground station, the deep learning classification module performs operation classification on data in videos shot by the camera and selects each object and the relative position of the image of the object, the category extraction module transparently transmits the type of each object and the relative position of the image of the object to the data distribution and subscription module, and the data distribution and subscription module sends the received data to the ground station system and the flight control system.
An unmanned aerial vehicle cloud object identification and tracking method based on AI technology comprises the following steps:
s1: the ground station system and the flight control systems of the unmanned aerial vehicles log in the object identification cloud system through the verification of the cloud login verification module, and the ground station system is connected with the unmanned aerial vehicles in a control mode through the object statistics identification cloud system;
s2: inputting a control instruction for each unmanned aerial vehicle in an instruction input module of the ground station system;
s3: the flight control system receives the instruction of the ground station and then triggers a corresponding function to control the unmanned aerial vehicle to fly;
s4: in the flight process of the unmanned aerial vehicle, the camera continuously collects images in a shooting range, and the collected images are transmitted to a flight control system;
s5: after the object identification cloud system receives the image data transmitted by the flight control system, the processing process is as follows:
the first step is as follows: the command and data safety inspection module inspects data sent from the ground station and module parameter loading conditions, and if the data are normal, the command is sent to the deep learning classification module;
the second step is that: the deep learning classification module is used for calculating and classifying object data in the image shot by the camera according to the trained parameters, selecting the relative positions of each object and the image where the object is located, and sending the relative positions to the classification position extraction module;
the third step: the category position extraction module transparently transmits the relative positions of each object and the image where the object is located, which are obtained in the deep learning classification module, to the data distribution and subscription module, then checks whether the object specified by the ground station is in the image, and if so, transmits the data to the data distribution module;
the fourth step: the data distribution and subscription module sends the received data to the ground station and the flight control module;
s6: after a data processing module of the ground station system receives statistical data of the flight control system, the data processing module analyzes the statistical data and displays the statistical data on a user interface;
s7: an operator selects an object to be tracked according to the statistical result and inputs a tracking instruction through the instruction input module;
s8: the command is transmitted to the object identification cloud system, and the command analysis module analyzes the command and transmits the analyzed command to the flight control system to control the unmanned aerial vehicle to track the target object;
s9: in the process of tracking the object by the unmanned aerial vehicle, if the proportion of the object in the shot image is more than 30%, the rotation is controlled; and if the ratio is less than 30%, the unmanned aerial vehicle is guided to fly close to the object, the ratio of 30% is kept, the image of the target object is continuously shot, then the image is transmitted to the object identification cloud system, and the image is analyzed and fed back to the ground station system for observation of an operator.
The second deep learning classification module comprises the following steps:
step 1, a deep learning classification module receives image data;
step 2, pretreatment, comprising the following steps:
separating an image area from a background, avoiding feature extraction in an area without effective information, accelerating the speed of subsequent processing and improving the accuracy of image feature extraction and matching;
enhancing the image, improving the image quality and recovering the original structure;
c, carrying out image binarization, and converting the image from a gray level image into a binary image;
d, thinning the image, and converting a clear but non-uniform binary image into a point-line image with the line width of only one pixel;
step 3, feature extraction, namely expressing the features which can fully express the uniqueness of the image in a numerical form, reserving real features and filtering out false features;
step 4, image classification, namely distributing the images to different image libraries in an accurate and consistent method;
step 5, matching images, and comparing the current image characteristics with the stored template image characteristics;
and 6, sending each object and the relative position of the image of the object to a category position extraction module.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (9)
1. The utility model provides an unmanned aerial vehicle high in clouds object identification tracker based on AI technique, a serial communication port, flight control system and the shooting system including ground station system, object identification cloud system and unmanned aerial vehicle end, wherein:
the shooting system is used for shooting and collecting images of objects in a shooting range;
the object identification cloud system receives image processing acquired by the unmanned aerial vehicle shooting and analyzes the category and position information of an object in the image processing;
the ground station system is used for receiving the image shot by the unmanned aerial vehicle and the object information identified by the object identification cloud system and then appointing the type of the object to be tracked;
and the flight control system receives an instruction sent by the ground station system and controls the unmanned aerial vehicle to track and shoot the object to be tracked.
2. The AI-technology-based unmanned aerial vehicle cloud object identification and tracking system of claim 1, wherein the camera system comprises a camera and a data transmission module, the camera is mounted on the unmanned aerial vehicle through a pan-tilt head, the camera collects images within a shooting range, and the collected images are transmitted to the flight control system through the data transmission module.
3. The AI-technology-based unmanned aerial vehicle cloud object identification and tracking system of claim 1, wherein the ground station system comprises a ground communication module, and a ground login verification module, a data processing module and an instruction input module electrically connected thereto, wherein the ground login verification module analyzes and identifies identity information input by an operator, and grants operation permission after successful authentication, the operator inputs an instruction of an object to be tracked through the instruction input module, the instruction is sent to the object identification cloud system through the ground communication module, meanwhile, the ground communication module transmits data acquired by the object identification cloud system to the data processing module, and the data processing module analyzes the data information and presents the data on a user interface for the operator to operate.
4. The AI-technology-based cloud object identification and tracking system for unmanned aerial vehicles according to claim 1, wherein the flight control system comprises a flight control communication module and a flight control login verification module, a flight control module and a pan-tilt control module electrically connected thereto, the flight control communication module exchanges data with a ground station system and a shooting system to realize communication with the ground station system and the shooting system, the flight control login verification module logs in an object identification cloud system through an unmanned aerial vehicle ID number and a private serial number, the flight control module and the pan-tilt control module acquire relative position information of an object to be tracked from the object identification cloud system, the flight control module controls the flight tracking direction of the unmanned aerial vehicle, and the pan-tilt control module controls the angle at which a pan-tilt connected with a camera and the unmanned aerial vehicle needs to deflect.
5. The AI technology-based unmanned aerial vehicle cloud object identification and tracking system of claim 1, wherein the object identification cloud system comprises a cloud communication module, a cloud login verification module, a command parsing module, and an object identification module, the cloud communication module performs data transmission with the flight control system and the ground station system, the cloud login verification module is electrically connected with the cloud communication module and identifies the login request of the ground station system and the flight control system transmitted from the cloud communication module, if the login request is legal, the ground station system or the flight control system is permitted to be added, after the login request is added, the command parsing module electrically connected with the cloud communication module analyzes and processes the data transmitted from the ground station system and the flight control system, then transmits the command of the ground station system to the flight control system, and transmits the image shot by the unmanned aerial vehicle to the object identification module for analysis and processing, the category of the object and the position information are identified.
6. The AI-technology-based unmanned aerial vehicle cloud object identification and tracking system of claim 5, wherein the object identification module comprises a command security check module, a deep learning classification module, a category position extraction module and a data distribution and subscription module, the command security check module checks a command loading condition sent from the ground station, the deep learning classification module performs operation classification on data in a video shot by the camera and selects each object and a relative position of an image where the object is located, the category extraction module transparently transmits the type of each object and the relative position of the image where the object is located to the data distribution and subscription module, and the data distribution and subscription module transmits the received data to the ground station system and the flight control system.
7. An unmanned aerial vehicle cloud object identification and tracking method based on AI technology is characterized by comprising the following steps:
s1: the ground station system and the flight control systems of the unmanned aerial vehicles log in the object identification cloud system through the verification of the cloud login verification module, and the ground station system is connected with the unmanned aerial vehicles in a control mode through the object statistics identification cloud system;
s2: inputting a control instruction for each unmanned aerial vehicle in an instruction input module of the ground station system;
s3: the flight control system receives the instruction of the ground station and then triggers a corresponding function to control the unmanned aerial vehicle to fly;
s4: in the flight process of the unmanned aerial vehicle, the camera continuously collects images in a shooting range, and the collected images are transmitted to a flight control system;
s5: after the object identification cloud system receives the image data transmitted by the flight control system, the object identification module performs analysis processing to identify the type of an object and extract position information, and then the result is transmitted to the ground station system and the flight control system through the cloud communication module;
s6: after a data processing module of the ground station system receives statistical data of the flight control system, the data processing module analyzes the statistical data and displays the statistical data on a user interface;
s7: an operator selects an object to be tracked according to the statistical result and inputs a tracking instruction through the instruction input module;
s8: the command is transmitted to the object identification cloud system, and the command analysis module analyzes the command and transmits the analyzed command to the flight control system to control the unmanned aerial vehicle to track the target object;
s9: in the process of tracking the object by the unmanned aerial vehicle, if the proportion of the object in the shot image is more than 30%, the rotation is controlled; and if the ratio is less than 30%, the unmanned aerial vehicle is guided to fly close to the object, the ratio of 30% is kept, the image of the target object is continuously shot, then the image is transmitted to the object identification cloud system, and the image is analyzed and fed back to the ground station system for observation of an operator.
8. The AI technology-based cloud object recognition and tracking method for unmanned aerial vehicles according to claim 7, wherein the processing of the image data by the object recognition module in step S5 is as follows:
the first step is as follows: the command and data safety inspection module inspects data sent from the ground station and module parameter loading conditions, and if the data are normal, the command is sent to the deep learning classification module;
the second step is that: the deep learning classification module is used for calculating and classifying object data in the image shot by the camera according to the trained parameters, selecting the relative positions of each object and the image where the object is located, and sending the relative positions to the classification position extraction module;
the third step: the category position extraction module transparently transmits the relative positions of each object and the image where the object is located, which are obtained in the deep learning classification module, to the data distribution and subscription module, then checks whether the object specified by the ground station is in the image, and if so, transmits the data to the data distribution module;
the fourth step: and the data distribution and subscription module sends the received data to the ground station and the flight control module.
9. The AI technology-based unmanned aerial vehicle cloud object identification and tracking method of claim 8, wherein the second deep learning classification module operation classification comprises the following steps:
step 1, a deep learning classification module receives image data;
step 2, pretreatment, comprising the following steps:
separating an image area from a background, avoiding feature extraction in an area without effective information, accelerating the speed of subsequent processing and improving the accuracy of image feature extraction and matching;
enhancing the image, improving the image quality and recovering the original structure;
c, carrying out image binarization, and converting the image from a gray level image into a binary image;
d, thinning the image, and converting a clear but non-uniform binary image into a point-line image with the line width of only one pixel;
step 3, feature extraction, namely expressing the features which can fully express the uniqueness of the image in a numerical form, reserving real features and filtering out false features;
step 4, image classification, namely distributing the images to different image libraries in an accurate and consistent method;
step 5, matching images, and comparing the current image characteristics with the stored template image characteristics;
and 6, sending each object and the relative position of the image of the object to a category position extraction module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910716631.6A CN112327935A (en) | 2019-08-05 | 2019-08-05 | AI technology-based unmanned aerial vehicle cloud object identification and tracking system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910716631.6A CN112327935A (en) | 2019-08-05 | 2019-08-05 | AI technology-based unmanned aerial vehicle cloud object identification and tracking system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112327935A true CN112327935A (en) | 2021-02-05 |
Family
ID=74319872
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910716631.6A Pending CN112327935A (en) | 2019-08-05 | 2019-08-05 | AI technology-based unmanned aerial vehicle cloud object identification and tracking system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112327935A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113553667A (en) * | 2021-08-12 | 2021-10-26 | 东北大学 | Airplane structural member design method based on deep learning |
| CN115834845A (en) * | 2023-02-24 | 2023-03-21 | 山东慧创信息科技有限公司 | Unmanned aerial vehicle land data identification system based on thing networking |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105554480A (en) * | 2016-03-01 | 2016-05-04 | 深圳市大疆创新科技有限公司 | Unmanned aerial vehicle image shooting control method and device, user device and unmanned aerial vehicle |
| CN107357314A (en) * | 2017-08-30 | 2017-11-17 | 上海拓攻机器人有限公司 | A kind of unmanned vehicle long-range control method and system |
| CN107463958A (en) * | 2017-08-04 | 2017-12-12 | 成都东谷利农农业科技有限公司 | Insect identifies method for early warning and system |
| CN107909600A (en) * | 2017-11-04 | 2018-04-13 | 南京奇蛙智能科技有限公司 | The unmanned plane real time kinematics target classification and detection method of a kind of view-based access control model |
| CN109376660A (en) * | 2018-10-26 | 2019-02-22 | 天宇经纬（北京）科技有限公司 | A kind of target monitoring method, apparatus and system |
| CN109814596A (en) * | 2019-02-02 | 2019-05-28 | 广州中科云图智能科技有限公司 | UAV Flight Control System based on mobile communication |
-
2019
- 2019-08-05 CN CN201910716631.6A patent/CN112327935A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105554480A (en) * | 2016-03-01 | 2016-05-04 | 深圳市大疆创新科技有限公司 | Unmanned aerial vehicle image shooting control method and device, user device and unmanned aerial vehicle |
| CN107463958A (en) * | 2017-08-04 | 2017-12-12 | 成都东谷利农农业科技有限公司 | Insect identifies method for early warning and system |
| CN107357314A (en) * | 2017-08-30 | 2017-11-17 | 上海拓攻机器人有限公司 | A kind of unmanned vehicle long-range control method and system |
| CN107909600A (en) * | 2017-11-04 | 2018-04-13 | 南京奇蛙智能科技有限公司 | The unmanned plane real time kinematics target classification and detection method of a kind of view-based access control model |
| CN109376660A (en) * | 2018-10-26 | 2019-02-22 | 天宇经纬（北京）科技有限公司 | A kind of target monitoring method, apparatus and system |
| CN109814596A (en) * | 2019-02-02 | 2019-05-28 | 广州中科云图智能科技有限公司 | UAV Flight Control System based on mobile communication |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113553667A (en) * | 2021-08-12 | 2021-10-26 | 东北大学 | Airplane structural member design method based on deep learning |
| CN113553667B (en) * | 2021-08-12 | 2023-10-27 | 东北大学 | Aircraft structural member design method based on deep learning |
| CN115834845A (en) * | 2023-02-24 | 2023-03-21 | 山东慧创信息科技有限公司 | Unmanned aerial vehicle land data identification system based on thing networking |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10452951B2 (en) | Active visual attention models for computer vision tasks | |
| CN111932588B (en) | Tracking method of airborne unmanned aerial vehicle multi-target tracking system based on deep learning | |
| Gaszczak et al. | Real-time people and vehicle detection from UAV imagery | |
| CN106412501B (en) | A kind of the construction safety behavior intelligent monitor system and its monitoring method of video | |
| CN103761514A (en) | System and method for achieving face recognition based on wide-angle gun camera and multiple dome cameras | |
| CN111679695B (en) | Unmanned aerial vehicle cruising and tracking system and method based on deep learning technology | |
| US20140085545A1 (en) | System and method for detection and tracking of moving objects | |
| CN104951775A (en) | Video technology based secure and smart recognition method for railway crossing protection zone | |
| CN109887040A (en) | The moving target actively perceive method and system of facing video monitoring | |
| KR101788225B1 (en) | Method and System for Recognition/Tracking Construction Equipment and Workers Using Construction-Site-Customized Image Processing | |
| CN108731587A (en) | A kind of the unmanned plane dynamic target tracking and localization method of view-based access control model | |
| CN111765974B (en) | Wild animal observation system and method based on miniature refrigeration thermal infrared imager | |
| CN110276286B (en) | Embedded panoramic video stitching system based on TX2 | |
| CN105810023B (en) | Airport undercarriage control automatic monitoring method | |
| CN112327935A (en) | AI technology-based unmanned aerial vehicle cloud object identification and tracking system and method | |
| CN112800918A (en) | Identity recognition method and device for illegal moving target | |
| CN114511592B (en) | Personnel track tracking method and system based on RGBD camera and BIM system | |
| CN116894936B (en) | Unmanned aerial vehicle vision-based marine target identification and positioning method and system | |
| CN112327893A (en) | AI (Artificial intelligence) technology-based unmanned aerial vehicle flight control front-end people counting system and method | |
| CN107885231A (en) | A kind of unmanned plane capturing method and system based on visible images identification | |
| CN113449566A (en) | Intelligent image tracking method and system for low-speed small target in human-in-loop | |
| CN112327936A (en) | AI technology-based unmanned aerial vehicle front-end object recognition and tracking system and method | |
| KR20230155432A (en) | Imaging device, tracking system and imaging method | |
| CN112327894A (en) | AI (Artificial intelligence) technology-based unmanned aerial vehicle cloud people counting system and method | |
| US10553022B2 (en) | Method of processing full motion video data for photogrammetric reconstruction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210205 |
|
| RJ01 | Rejection of invention patent application after publication |