CN110490089B - Image identification method of satellite receiving equipment - Google Patents
Image identification method of satellite receiving equipment Download PDFInfo
- Publication number
- CN110490089B CN110490089B CN201910688484.6A CN201910688484A CN110490089B CN 110490089 B CN110490089 B CN 110490089B CN 201910688484 A CN201910688484 A CN 201910688484A CN 110490089 B CN110490089 B CN 110490089B
- Authority
- CN
- China
- Prior art keywords
- satellite receiving
- receiving equipment
- image
- image recognition
- satellite
- 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
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/242—Aligning, centring, orientation detection or correction of the image by image rotation, e.g. by 90 degrees
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Image Processing (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention discloses an image recognition method of satellite receiving equipment, which comprises the steps of establishing a multi-direction satellite receiving equipment placing image recognition training library; reading the position and direction information of satellite receiving equipment in an image to be judged; according to the read position and direction information of the satellite receiving equipment, selecting a corresponding recognition model from a multi-direction satellite receiving equipment placing image recognition training library to compare and recognize the direction information of the satellite receiving equipment, and judging the placing validity; and (4) marking the identified image corresponding to the satellite receiving equipment placed legally by comparison, and storing the image into a satellite receiving equipment placed image identification training library. The image recognition technology of the satellite receiving equipment can be used for carrying out legality recognition on the placing state of the satellite receiving equipment in the image, an effective distinguishing mode is provided for legality use of the satellite receiving equipment, recognition accuracy is high, and operability is high.
Description
Technical Field
The invention relates to the field of satellite television equipment, in particular to an image identification method of satellite receiving equipment.
Background
The satellite receiver is a device capable of receiving satellite television programs, and provides great convenience for knowing external information in partial rural areas; in order to enhance management of satellite television broadcast terrestrial reception facilities and promote socialist mental civilization, regulations for satellite television broadcast terrestrial reception facility management are made.
However, at present, when investigating the validity of the satellite receiver, a manual discrimination mode is adopted to send workers under a relevant inspection department to perform the on-site inspection of visits, which consumes huge manpower and material resources; in many remote areas, due to the limitation of geographical conditions, the traffic inconvenience in mountainous areas is difficult to achieve manually, and comprehensive inspection cannot be performed; meanwhile, when the field inspection is carried out, the cooperation of residents in departments and even some potential safety hazards can be caused.
Disclosure of Invention
In view of the above-mentioned deficiencies in the prior art, the present invention provides an image recognition method for a satellite receiving device.
In order to achieve the purpose of the invention, the invention adopts the technical scheme that: the image recognition method of the satellite receiving equipment comprises the steps of establishing a multi-direction satellite receiving equipment placement image recognition training library; reading the position and direction information of satellite receiving equipment in an image to be judged; according to the read position and orientation information of the satellite receiving equipment, selecting a corresponding identification model from a multi-direction satellite receiving equipment placing image identification training library to compare and identify the orientation information of the satellite receiving equipment, and judging the placing validity; and (4) marking the identified image corresponding to the satellite receiving equipment placed legally by comparison, and storing the image into a satellite receiving equipment placed image identification training library.
Further, the multi-direction satellite receiving device placement image recognition training library is a 24-direction satellite receiving device placement image recognition training library.
Further, the 24 directions include the 12 directions of the horizontal plane and the 2 directions perpendicular to the horizontal plane.
Further, the horizontal 12 directions in the 24 directions are divided into 12 parts on the average by 360 degrees on the horizontal plane, and each direction is different by 30 degrees.
Further, the 2-direction perpendicular to the horizontal plane is a first direction at 65 degrees from the horizontal plane and a second direction at 90 degrees from the horizontal plane.
Further, when the image to be judged is collected, the lens is a lens with the focal length larger than 4 mm.
Furthermore, the satellite receiver has a unique corresponding set legal placing direction under each longitude and latitude position.
The invention has the beneficial effects that: the image recognition technology of the satellite receiving equipment can be used for legally recognizing the placing state of the satellite receiving equipment in an image, an effective distinguishing mode is provided for legally using the satellite receiving equipment, whether the satellite receiving equipment is legal or not can be judged by collecting the image, manpower and material resources are greatly saved, an image recognition training library is placed for the satellite receiving equipment by 24 for subsequent recognition, and the image recognition technology is high in operability and high in recognition accuracy.
Drawings
Fig. 1 schematically shows a distribution diagram of the image recognition technology of the satellite receiving device in the 12-way direction.
Fig. 2 schematically shows a vertical 2-way distribution of the image recognition technology of the satellite receiver.
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 embodiment is only one embodiment of the present invention, and not all 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.
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be described in further detail with reference to the accompanying drawings and specific embodiments.
Also, for the sake of simplicity, the technical common knowledge known to those skilled in the art is omitted in the following.
The image recognition technology of the satellite receiving equipment comprises the step of establishing a multi-direction satellite receiving equipment arrangement image recognition training library. The multi-direction satellite receiving equipment placement image recognition training library stores image information of a legally used satellite receiving equipment placement state at a certain longitude and latitude position; and an identification model can be established according to image data of legal placement state in the satellite receiving equipment placement image identification training library.
In specific implementation, the satellite receiver has a unique corresponding set legal placing direction under each longitude and latitude position; in actual operation, the legal placing state of the satellite receiving equipment under any longitude and latitude is integrated and analyzed, and the multi-direction satellite receiving equipment placing image recognition training library is set to be 24-direction satellite receiving equipment placing image recognition training libraries.
In the present application, referring to fig. 1 and fig. 2, fig. 1 schematically shows a horizontal 12-way distribution diagram of the image recognition technology of the satellite receiving device, and fig. 2 schematically shows a vertical 2-way distribution diagram of the image recognition technology of the satellite receiving device.
As shown in fig. 1 and fig. 2, specifically, the 24-direction comprises a horizontal plane 12-direction and a horizontal plane 2-direction vertical to the horizontal plane, the horizontal 12-direction in the 24-direction is divided into 12 parts on average by 360 degrees on the horizontal plane, and an included angle between two adjacent directions on the horizontal plane is 30 degrees; and the 2-direction vertical to the horizontal plane is a first direction at 65 degrees from the horizontal plane and a second direction at 90 degrees from the horizontal plane.
And then, reading the position and direction information of the satellite receiving equipment in the image to be judged, selecting a corresponding identification model from a multidirectional satellite receiving equipment placement image identification training library according to the read position information of the satellite receiving equipment, comparing and identifying the direction information of the satellite receiving equipment, and judging the validity of placement.
In a specific implementation, 24 models are identified corresponding to 24 models; specifically, when 24 image recognition models are placed in the satellite receiving device, the satellite receiving device is photographed in each direction and in a proper deviation range according to different longitude and latitude information by using a specific background, the number of photos at different angles is not less than 100, and after the photos in each direction are scratched, the satellite receiving device part of the photos is subjected to recognition training, namely, 24 recognition models are provided in total.
When the placing validity of the satellite receiving equipment in the image to be judged is judged, a corresponding recognition model in the 24 directions is selected to recognize the placing state of the satellite receiver according to the position information, namely the longitude and latitude information, if the placing direction of the satellite receiving equipment in the image to be judged is consistent with the set placing direction, the use is judged to be legal, and if the placing direction of the satellite receiving equipment in the image to be judged is not consistent with the set placing direction, the illegal use is judged.
And then, images which are identified and correspond to the satellite receiving equipment which is placed legally are marked by comparison, and are stored in a satellite receiving equipment placing image identification training library for later identification training. The image recognition technology of the satellite receiving equipment carries out legality recognition on the placing state of the satellite receiving equipment in the image, effective identification is provided for legality use of the satellite receiving equipment, recognition accuracy is high, and operability is strong.
In addition, in the present application, in order to make the shot image not have significant distortion, when the image to be determined is collected, the lens is selected as a lens with a focal length greater than 4mm, that is, the shooting opening angle of the lens is 75 degrees or less, the horizontal angle is between 52.5 and 90 degrees, the first horizontal angle is 52.5+ (90-52.5)/3 =65 degrees (the deviation range is 52.5 to 77.5 degrees of the horizontal plane), and the second horizontal center is 90 degrees (the deviation range is 77.5 to 102.5 degrees of the horizontal plane).
In actual operation, at present, when the use legality of the satellite receiver is investigated, workers under relevant inspection departments are dispatched to carry out on-site inspection for visiting, and a manual distinguishing mode is adopted, so that huge manpower and material resources are consumed; in many remote areas, due to the limitation of geographical conditions, the traffic inconvenience in mountainous areas is difficult to achieve manually, and comprehensive inspection cannot be performed; meanwhile, when the field inspection is carried out, the problems that residents in departments are not matched and even some potential safety hazards exist can also exist.
Therefore, this design can adopt unmanned aerial vehicle to carry out the image shooting, discerns the orientation of putting of satellite receiving equipment in the image again, and then judges the legality of its use, has greatly saved manpower and materials, and maneuverability is strong, facilitate promotion and application.
When the image is collected by the unmanned aerial vehicle, the unmanned aerial vehicle can be initialized, whether the storage space of the magnetic disk is sufficient or not is judged according to the area to be identified, and whether the required power consumption is sufficient or not is judged; if the unmanned aerial vehicle is sufficient, the unmanned aerial vehicle is initialized to be started to fly to the designated area to be identified, and if the unmanned aerial vehicle is insufficient, the unmanned aerial vehicle is reinitialized according to insufficient conditions.
After the initialization process of the unmanned aerial vehicle is completed, starting the unmanned aerial vehicle to fly to a specified area to be identified, starting photographing equipment carried on the unmanned aerial vehicle when the unmanned aerial vehicle reaches a specified position in the area to be identified, continuously photographing seamless photos of the area to be identified, acquiring position information of the area to be identified when the images are photographed, and packaging and uploading the position information and the image information acquired at the position to a central database; and meanwhile, when the unmanned aerial vehicle sails and shoots, the unmanned aerial vehicle can cruise and fly according to the shape of the Chinese character 'bow'.
Only receiving and sequentially identifying pictures shot by the unmanned aerial vehicle, identifying a plurality of pictures shot by the unmanned aerial vehicle, wherein the pictures contain satellite receiving equipment, identifying a certain object in the pictures in a common identifying mode, and screening the pictures containing the satellite receiving equipment by adopting a manual identifying mode; the image recognition technology or the image recognition software of the patent can also be adopted to recognize the picture containing the pattern of the satellite receiving equipment, so that the limitation is not specifically set, and the repeated description is not needed.
If the shot picture contains the satellite receiving equipment, the placing direction of the satellite receiving equipment in the shot picture is subsequently judged, if the shot picture does not contain the satellite receiving equipment, the satellite receiving equipment is directly stored in the local shot picture, and the identification process is continued until the last picture of the area to be identified shot by the unmanned aerial vehicle is identified.
When identifying whether the shot picture contains the satellite receiving equipment or not, judging the legality of the placing direction of the identified picture containing the satellite receiving equipment; specifically, a multi-direction satellite receiving device placement image recognition training library is established, the position and direction information of the satellite receiving device in the image to be determined is read, and according to the read position information of the satellite receiving device, a corresponding recognition model is selected from the multi-direction satellite receiving device placement image recognition training library to compare and recognize the direction information of the satellite receiving device, and the validity of placement of the satellite receiving device is determined.
Because the satellite receiver has a unique corresponding set placing direction under each longitude and latitude position, if the placing direction of the satellite receiver in the image to be judged is consistent with the placing directions of the 24 models in the identification library, the use is judged to be legal, and if the placing direction of the satellite receiver in the image to be judged is not matched with the 24 models in the identification library, the use is judged to be illegal; and the judging process is continued until the last picture which is shot by the unmanned aerial vehicle and contains the satellite receiving equipment in the area to be identified is judged.
And after the judgment is finished, storing the image information to be judged corresponding to the satellite receiver judged to be illegally used into the violation database, and sending the image information to be judged to the supervision department. And marking the image information to be distinguished corresponding to the satellite receiver which is judged to be legally used, and storing the image information to be distinguished into a satellite receiving equipment placing image recognition training library for later recognition training.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (6)
1. An image recognition method of a satellite receiving apparatus, comprising the steps of:
a. establishing a multi-direction satellite receiving equipment placement image recognition training library; the multi-direction satellite receiving equipment arrangement image recognition training library is a 24-direction satellite receiving equipment arrangement image recognition training library;
b. reading the position and direction information of satellite receiving equipment in an image to be judged;
c. according to the read position and direction information of the satellite receiving equipment, selecting a corresponding recognition model from a multi-direction satellite receiving equipment placing image recognition training library to compare and recognize the direction information of the satellite receiving equipment, and judging the placing validity;
d. and (4) marking the identified image corresponding to the satellite receiving equipment placed legally by comparison, and storing the image into a satellite receiving equipment placed image identification training library.
2. The image recognition method of a satellite receiving apparatus according to claim 1, characterized in that: the 24 directions include a 12 direction including a horizontal plane and a 2 direction perpendicular to the horizontal plane.
3. The image recognition method of a satellite receiving apparatus according to claim 1 or 2, characterized in that: the horizontal 12 directions in the 24 directions are divided into 12 parts on the average by 360 degrees on the horizontal plane, and each direction is different by 30 degrees.
4. The image recognition method of a satellite receiving apparatus according to claim 3, characterized in that: the 2-direction perpendicular to the horizontal plane is a first direction at 65 degrees from the horizontal plane and a second direction at 90 degrees from the horizontal plane.
5. The image recognition method of a satellite receiving apparatus according to claim 3, wherein: when an image to be judged is collected, the lens is a lens with the focal length larger than 4 mm.
6. The image recognition method of a satellite receiving apparatus according to claim 1, characterized in that: the satellite receiving equipment has a unique corresponding set legal placing direction under each longitude and latitude position.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910688484.6A CN110490089B (en) | 2019-07-29 | 2019-07-29 | Image identification method of satellite receiving equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910688484.6A CN110490089B (en) | 2019-07-29 | 2019-07-29 | Image identification method of satellite receiving equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110490089A CN110490089A (en) | 2019-11-22 |
CN110490089B true CN110490089B (en) | 2023-04-07 |
Family
ID=68548686
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910688484.6A Active CN110490089B (en) | 2019-07-29 | 2019-07-29 | Image identification method of satellite receiving equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110490089B (en) |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104035115A (en) * | 2014-06-06 | 2014-09-10 | 中国科学院光电研究院 | Vision-aided satellite navigation and positioning method, and positioning machine |
CN106331639A (en) * | 2016-08-31 | 2017-01-11 | 浙江宇视科技有限公司 | Method and apparatus of automatically determining position of camera |
CN106713822A (en) * | 2015-08-14 | 2017-05-24 | 杭州海康威视数字技术股份有限公司 | Video camera used for video monitoring and monitoring system |
CN109035629A (en) * | 2018-07-09 | 2018-12-18 | 深圳码隆科技有限公司 | A kind of shopping settlement method and device based on open automatic vending machine |
CN109445588A (en) * | 2018-10-23 | 2019-03-08 | 北京快乐认知科技有限公司 | Point based on image recognition tracer technique is read to give directions part click judging method |
CN109598241A (en) * | 2018-12-05 | 2019-04-09 | 武汉大学 | Satellite image marine vessel recognition methods based on Faster R-CNN |
CN109711285A (en) * | 2018-12-11 | 2019-05-03 | 百度在线网络技术(北京)有限公司 | Training, test method and the device of identification model |
CN109784309A (en) * | 2019-02-01 | 2019-05-21 | 上海智能交通有限公司 | A kind of advertisement board on highway identifying system and method based on in-vehicle camera |
CN109948523A (en) * | 2019-03-18 | 2019-06-28 | 中国汽车工程研究院股份有限公司 | A kind of object recognition methods and its application based on video Yu millimetre-wave radar data fusion |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2008042887A (en) * | 2006-07-14 | 2008-02-21 | Ricoh Co Ltd | Imaging device, imaging system, image data recording method, and program |
-
2019
- 2019-07-29 CN CN201910688484.6A patent/CN110490089B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104035115A (en) * | 2014-06-06 | 2014-09-10 | 中国科学院光电研究院 | Vision-aided satellite navigation and positioning method, and positioning machine |
CN106713822A (en) * | 2015-08-14 | 2017-05-24 | 杭州海康威视数字技术股份有限公司 | Video camera used for video monitoring and monitoring system |
CN106331639A (en) * | 2016-08-31 | 2017-01-11 | 浙江宇视科技有限公司 | Method and apparatus of automatically determining position of camera |
CN109035629A (en) * | 2018-07-09 | 2018-12-18 | 深圳码隆科技有限公司 | A kind of shopping settlement method and device based on open automatic vending machine |
CN109445588A (en) * | 2018-10-23 | 2019-03-08 | 北京快乐认知科技有限公司 | Point based on image recognition tracer technique is read to give directions part click judging method |
CN109598241A (en) * | 2018-12-05 | 2019-04-09 | 武汉大学 | Satellite image marine vessel recognition methods based on Faster R-CNN |
CN109711285A (en) * | 2018-12-11 | 2019-05-03 | 百度在线网络技术(北京)有限公司 | Training, test method and the device of identification model |
CN109784309A (en) * | 2019-02-01 | 2019-05-21 | 上海智能交通有限公司 | A kind of advertisement board on highway identifying system and method based on in-vehicle camera |
CN109948523A (en) * | 2019-03-18 | 2019-06-28 | 中国汽车工程研究院股份有限公司 | A kind of object recognition methods and its application based on video Yu millimetre-wave radar data fusion |
Non-Patent Citations (4)
Title |
---|
QuickBird卫星图像信息识别;林辉等;《中国图象图形学》;20051225(第12期);1504-1510 * |
Usability of mobile applications: literature review and rationale for a new usability model;R Harrison等;《Journal of Interaction Science》;20130507;第1卷(第1期);1-16 * |
基于状态估计的虚拟应答器捕获方法研究;刘江等;《铁道学报》;20181015(第10期);75-84 * |
基于霍夫森林的变电站开关设备检测及状态识别;邵剑雄等;《电力系统自动化》;20160610(第11期);121-126 * |
Also Published As
Publication number | Publication date |
---|---|
CN110490089A (en) | 2019-11-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110645986B (en) | Positioning method and device, terminal and storage medium | |
CN107944450B (en) | License plate recognition method and device | |
CN102110332B (en) | Book registering and managing device based on computer vision and radio frequency identification technology | |
CN105518704A (en) | Systems and methods for detecting and classifying objects in video captured using mobile devices | |
CA2779946A1 (en) | Method and system for reading and validating identity documents | |
CN109740479A (en) | A kind of vehicle recognition methods, device, equipment and readable storage medium storing program for executing again | |
CN106991821A (en) | Vehicles peccancy hand-held mobile terminal data collecting system | |
EP3033714A1 (en) | Image identification marker and method | |
CN107464446B (en) | Inspection method and device for vertical parking space parking information | |
CN110164139B (en) | System and method for detecting and identifying side parking | |
CN110427949A (en) | The method, apparatus of list verification calculates equipment and medium | |
CN113822247A (en) | Method and system for identifying illegal building based on aerial image | |
CN112487894B (en) | Automatic track traffic protection area inspection method and device based on artificial intelligence | |
CN112329881A (en) | License plate recognition model training method, license plate recognition method and device | |
Gunawan et al. | Design of automatic number plate recognition on android smartphone platform | |
CN111723656A (en) | Smoke detection method and device based on YOLO v3 and self-optimization | |
CN105069718B (en) | Self-service monitoring method and system for smart homeland real estate based on mobile Internet of things | |
CN112633114B (en) | Unmanned aerial vehicle inspection intelligent early warning method and device for building change event | |
CN110490089B (en) | Image identification method of satellite receiving equipment | |
CN116580026B (en) | Automatic optical detection method, equipment and storage medium for appearance defects of precision parts | |
CN115546221B (en) | Reinforcing steel bar counting method, device, equipment and storage medium | |
CN108573220B (en) | Road crack identification method based on group multi-source data | |
CN110430358B (en) | Use monitoring method for satellite receiver | |
CN114820748B (en) | Full-view-angle characteristic intelligent evidence obtaining method based on panoramic data | |
CN110569743A (en) | advertisement information recording method, storage medium and management system |
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 |