CN106649607A - Remote sensing image online target recognition and monitoring method and system based on vector mask - Google Patents
Remote sensing image online target recognition and monitoring method and system based on vector mask Download PDFInfo
- Publication number
- CN106649607A CN106649607A CN201611069209.9A CN201611069209A CN106649607A CN 106649607 A CN106649607 A CN 106649607A CN 201611069209 A CN201611069209 A CN 201611069209A CN 106649607 A CN106649607 A CN 106649607A
- Authority
- CN
- China
- Prior art keywords
- file
- vector
- remote sensing
- mask
- monitoring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 49
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000012545 processing Methods 0.000 claims abstract description 47
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 10
- 230000006698 induction Effects 0.000 claims 1
- 238000004364 calculation method Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
- 239000003643 water by type Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/56—Information retrieval; Database structures therefor; File system structures therefor of still image data having vectorial format
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention discloses a remote sensing image online target recognition and monitoring method and system based on a vector mask. An existing reference image base map is subjected to vector marking, and coordinates and serial numbers of all vector blocks are stored; when an airborne or satellite-borne remote sensing system operates, a corresponding vector file is selected according to a shot region and converted into a binary or many-valued mask image; online target recognition and monitoring are carried out on a shot image according to the mask. According to the method and system, the processing range of an algorithm is greatly narrowed through the mask, the target recognition and monitoring efficiency is greatly improved, and calculation resources of the airborne or satellite-borne remote sensing system are effectively utilized.
Description
Technical field
The present invention relates to computer vision and area of pattern recognition, and in particular to a kind of remote sensing images based on vector mask
Online target identification and monitoring method and system.
Background technology
The resolution ratio more and more higher of remote sensing images, data volume is big, details is complicated, causes the calculation of Motion parameters and monitoring
Method complexity is high.Under the conditions of the military war or calamity emergency process in future etc. is many, need on remote sensing platform in real time
The target of some specific regions is identified and monitoring.But the image processing system carried on remote sensing platform is (hereinafter referred to as
Remote sensing platform processing system), whether memory space, or calculating speed is all difficult to meet online real-time processing, typically all
Beam back earth station's processing system to be analyzed.
The content of the invention
In order to solve the problems referred to above of the prior art, the present invention proposes a kind of remote sensing images based on vector mask and exists
Line target recognizes and monitoring method and system that the efficiency that remote sensing images are processed online is greatly improved, and effectively utilizes calculate money
Source, realizes real-time online identification and monitoring in remote sensing platform processing system.
The online target identification of remote sensing images based on vector mask and monitoring method of the present invention, including build vector file
Two parts in storehouse and real time on-line monitoring;
Build vector file storehouse:
The multiple regions for needing monitoring are carried out respectively image taking by step A1 using remote sensor, and captured image is passed
Earth station's processing system is sent to, base map image data base is built;
Step A2, vector mark is carried out using earth station's processing system to the image in base map image data base, is drawn many
The polygon of individual closing, and plus numbering, generate vector file;
Step A3, vector file is sent in the memory of remote sensing platform processing system and is stored, and builds vector file storehouse;
Real time on-line monitoring:
Step B1, using remote sensor the image of specific region is shot, and is input to remote sensing platform processing system;
Step B2, chooses the vector file comprising the specific region in the vector file storehouse that step A3 builds;
Step B3, by the vector file selected by step B2 rasterizing process is carried out, and is generated corresponding with the specific region
Mask file;
Step B4, according to the mask file that the image and step B3 that photograph in step B1 are generated, to the specific region
Interior target is identified and monitoring.
Preferably, vector file described in step A2 includes the geographical coordinate on each closed polygon summit, and respectively closing is more
The numbering of side shape.
Preferably, it is that vector file is converted into raster file that rasterizing described in step B3 is processed.
Preferably, internal point broadcast algorithm or scan-line algorithm are adopted in step B3 during rasterizing.
Preferably, mask file described in step B3 is two-value or many-valued mask file.
Preferably, if the image that photographs of regional extent step B1 that the mask file in step B3 after rasterizing is related to
During a subset of scope, then online target identification and the scope of monitoring are region involved by mask file.
Preferably, the space of the image that the spatial resolution of the mask file generated in step B3 is photographed with step B1
Resolution ratio is identical.
Preferably, target identification is carried out in step B4 with during monitoring, hunting zone is reduced according to mask information.
Preferably, described remote sensor is airborne or space remote sensing device.
The online target identification of remote sensing images based on vector mask and monitoring system of the present invention, including remote sensing platform process
System, earth station's processing system, the remote sensing platform processing system is carried out with earth station's processing system by wireless signal
Data transfer, it is characterised in that
Earth station's processing system includes that base map image data base, vector file signal generating unit, ground signal transmitting-receiving are single
Unit;The base map image data base includes the image in multiple regions of the needs monitoring that remote sensor shoots;Vector file generates single
Unit is configured to carry out vector mark to the image in base map image data base, draws the polygon of multiple closings, and plus numbering,
Generate vector file;Ground signal Transmit-Receive Unit is configured to receive the base map figure that remote sensor shoots from remote sensing platform processing system
Picture, the vector file generated by vector file signal generating unit is sent to remote sensing platform processing system;
The remote sensing platform processing system include vector file storehouse, remote sensing images receiving unit, mask file generating unit,
Target identification and monitoring unit, remote sensing platform signal transmitting and receiving unit;Remote sensing platform signal transmitting and receiving unit is configured to receive ground letter
The vector file that number Transmit-Receive Unit sends;Vector file storehouse includes the vector file received by remote sensing platform signal transmitting and receiving unit;
Remote sensing images receiving unit is configured to receive the image of the specific region that remote sensor shoots;Mask file generating unit be configured to from
The vector file comprising the specific region is chosen in vector file storehouse and rasterizing process is carried out, is generated and the specific region
Corresponding mask file;Target identification is configured to the image of the specific region that foundation remote sensor shoots and covers with monitoring unit
Film file generating unit generate mask file corresponding with the specific region, the target in specific region is identified with
Monitoring.
Base map image labeling vector file is generated two-value or many-valued grating image mask, according to the mask pair by the present invention
The image that remote sensor is obtained in real time carries out region screening, significantly reduces the hunting zone of target identification and monitoring algorithm, improves
Treatment effeciency, realizes the online target monitoring in real time of remote sensing platform processing system.Due to vector file very little, occupancy it is distant
Sense platform processes system memory space is also less.
Description of the drawings
Fig. 1 is the schematic flow sheet of the present embodiment;
Fig. 2 is the vector mark schematic diagram of step A2 in the present embodiment;
Fig. 3 is the specific region image shot in the present embodiment;
Fig. 4 is to process the grid mask used during Fig. 3.
Fig. 5 is the online target identification of remote sensing images and monitoring system schematic diagram in the present embodiment based on vector mask.
Specific embodiment
With reference to the accompanying drawings describing the preferred embodiment of the present invention.It will be apparent to a skilled person that this
A little embodiments are used only for explaining the know-why of the present invention, it is not intended that limit the scope of the invention.
The online target identification of remote sensing images based on vector mask and monitoring method of the present invention, as shown in figure 1, including structure
Build two parts in vector file storehouse and real time on-line monitoring;
Build vector file storehouse:
The multiple regions for needing monitoring are carried out respectively image taking by step A1 using remote sensor, and captured image is passed
Earth station's processing system is sent to, base map image data base is built;
Step A2, as shown in Fig. 2 carrying out vector mark to the image in base map image data base using earth station's processing system
Note, draws the polygon of multiple closings, and plus numbering, generates vector file;
Step A3, vector file is sent in the memory of remote sensing platform processing system and is stored, and builds vector file storehouse;
Remote sensing platform processing system in the present embodiment employs embedded chip;
Real time on-line monitoring:
Step B1, using remote sensor the image of specific region is shot, and is input to remote sensing platform processing system;The present embodiment
In the image that photographs it is as shown in Figure 3;
Step B2, chooses the vector file comprising the specific region in the vector file storehouse that step A3 builds;
Step B3, by the vector file selected by step B2 rasterizing process is carried out, and is generated corresponding with the specific region
Mask file;The two-value mask file generated in the present embodiment is as shown in Figure 4;
Step B4, according to the mask file that the image and step B3 that photograph in step B1 are generated, to the specific region
Interior target is identified and monitoring.
Image in the present embodiment in base map image data base described in step A1 is undressed remote sensing image.Can be with
For the remote sensing images that same remote sensor shoots, it is also possible to which phases shoot including different remote sensors, different, different spaces are differentiated
Rate, covering earth surface typical feature type, multiple geographic areas high-quality remote sensing image that may be present.Base map image
The source of remote sensing images has no effect on the enforcement of technical solution of the present invention and the realization of technique effect in database.
As shown in Fig. 2 step A2 carries out vector mark with ArcGIS softwares in the present embodiment, for land, water during mark
Domain depicts the polygon of several closings, and imparts different numberings.Vector mark can also other be commercial by QGIS etc.
Or GIS software of increasing income is completed, also can be completed by additive method.
The vector file includes the geographical coordinate on each closed polygon summit, and the numbering of each closed polygon.Wherein
Numbering is self-defining according to demand, and such as 0 represents that marine site, 1 represent that meadow, 2 represent airport.
The vector file takes memory space very little, and the memory space shared by each vector file is only tens to hundreds of
KB。
It is that vector file is converted into raster file that rasterizing described in step B3 is processed in the present embodiment.
Employ scan-line algorithm in the present embodiment in step B3 during rasterizing, can also using internal point broadcast algorithm or
Other can realize the algorithm of the function.
Mask file described in step B3 is two-value or many-valued mask file in the present embodiment.
What if regional extent step B1 that the mask file in the present embodiment in step B3 after rasterizing is related to was photographed
During a subset of image range, then online target identification and the scope of monitoring are region involved by mask file.
The image that the spatial resolution of the mask file in the present embodiment generated in step B3 is photographed with step B1
Spatial resolution is identical.
Target identification is carried out in the present embodiment in step B4 with during monitoring, hunting zone is contracted according to mask information
Subtract.
Remote sensor in the present embodiment is airborne or space remote sensing device, or other types sensoring.
When the present invention is identified based on mask, by mask information the process range of algorithm is drastically reduce the area.For example
When recognizing naval vessel, only need to be labeled as being monitored naval vessel in the range of waters in mask, mask is labeled as the region on land
Then need not be monitored.
A kind of online target identification of remote sensing images based on vector mask and monitoring system of the present invention, as shown in figure 5, bag
Remote sensing platform processing system, earth station's processing system are included, the remote sensing platform processing system is logical with earth station's processing system
Cross wireless signal to carry out data transmission.
Earth station's processing system includes that base map image data base, vector file signal generating unit, ground signal transmitting-receiving are single
Unit;The base map image data base includes the image in multiple regions of the needs monitoring that remote sensor shoots;Vector file generates single
Unit is configured to carry out vector mark to the image in base map image data base, draws the polygon of multiple closings, and plus numbering,
Generate vector file;Ground signal Transmit-Receive Unit is configured to receive the base map figure that remote sensor shoots from remote sensing platform processing system
Picture, the vector file generated by vector file signal generating unit is sent to remote sensing platform processing system.
The remote sensing platform processing system include vector file storehouse, remote sensing images receiving unit, mask file generating unit,
Target identification and monitoring unit, remote sensing platform signal transmitting and receiving unit;Remote sensing platform signal transmitting and receiving unit is configured to receive ground letter
The vector file that number Transmit-Receive Unit sends;Vector file storehouse includes the vector file received by remote sensing platform signal transmitting and receiving unit;
Remote sensing images receiving unit is configured to receive the image of the specific region that remote sensor shoots;Mask file generating unit be configured to from
The vector file comprising the specific region is chosen in vector file storehouse and rasterizing process is carried out, is generated and the specific region
Corresponding mask file;Target identification is configured to the image of the specific region that foundation remote sensor shoots and covers with monitoring unit
Film file generating unit generate mask file corresponding with the specific region, the target in specific region is identified with
Monitoring.
The present invention is using the big memory space of earth station's processing system and the advantage of high operational capability, it would be desirable to take larger
The base map image data base of memory space is stored in earth station's processing system, and the work of vector mark is also in earth station's processing system
Complete in system;The memory space for being sent to the vector file occupancy of remote sensing platform processing system is less, is reduced using vector mask
Search space so that target identification is improved with the real-time of monitoring, and reduces to remote sensing platform processing system
The requirement of energy, so as to reduce cost of implementation.
Those skilled in the art should be able to recognize that, with reference to the side of each example of the embodiments described herein description
Method step, unit, module, can with electronic hardware, computer software or the two be implemented in combination in, in order to clearly demonstrate
The interchangeability of electronic hardware and software, in the above description according to function generally describe each example composition and
Step.These functions are performed with electronic hardware or software mode actually, the application-specific and design depending on technical scheme
Constraints.Those skilled in the art can use different methods to the described function of realization to each specific application,
But this realization is it is not considered that beyond the scope of this invention.
So far, technical scheme is described already in connection with preferred embodiment shown in the drawings, but, this area
Technical staff is it is easily understood that protection scope of the present invention is expressly not limited to these specific embodiments.Without departing from this
On the premise of the principle of invention, those skilled in the art can make the change or replacement of equivalent to correlation technique feature, these
Technical scheme after changing or replacing it is fallen within protection scope of the present invention.
Claims (10)
1. a kind of online target identification of remote sensing images based on vector mask and monitoring method, it is characterised in that including building arrow
Two parts of amount library and real time on-line monitoring;
Build vector file storehouse:
The multiple regions for needing monitoring are carried out respectively image taking by step A1 using remote sensor, and captured image is sent to
Earth station's processing system, builds base map image data base;
Step A2, vector mark is carried out using earth station's processing system to the image in base map image data base, draws multiple envelopes
The polygon for closing, and plus numbering, generate vector file;
Step A3, vector file is sent in the memory of remote sensing platform processing system and is stored, and builds vector file storehouse;
Real time on-line monitoring:
Step B1, using remote sensor the image of specific region is shot, and is input to remote sensing platform processing system;
Step B2, chooses the vector file comprising the specific region in the vector file storehouse that step A3 builds;
Step B3, by the vector file selected by step B2 rasterizing process is carried out, and generates cover corresponding with the specific region
Film file;
Step B4, according to the mask file that the image and step B3 that photograph in step B1 are generated, in the specific region
Target is identified and monitoring.
2. method according to claim 1, it is characterised in that vector file described in step A2 includes each closed polygon
The geographical coordinate on summit, and the numbering of each closed polygon.
3. method according to claim 1, it is characterised in that the process of rasterizing described in step B3 is to turn vector file
Change raster file into.
4. method according to claim 3, it is characterised in that in step B3 during rasterizing using internal point broadcast algorithm or
Scan-line algorithm.
5. method according to claim 1, it is characterised in that mask file described in step B3 is two-value or many-valued mask
File.
6. method according to claim 1, it is characterised in that the region that the mask file in step B3 after rasterizing is related to
If during a subset of the image range that scope step B1 is photographed, then online target identification and the scope of monitoring are mask text
Region involved by part.
7. method according to claim 1, it is characterised in that the spatial resolution of the mask file generated in step B3
It is identical with the spatial resolution of the image that step B1 is photographed.
8. method according to claim 1, it is characterised in that carry out in step B4 target identification with during monitoring, according to covering
Film information is reduced to hunting zone.
9. the method according to any one of claim 1~8, it is characterised in that described remote sensor is airborne or spaceborne distant
Induction device.
10. a kind of online target identification of remote sensing images based on vector mask and monitoring system, including remote sensing platform processing system,
Earth station's processing system, the remote sensing platform processing system carries out data biography with earth station's processing system by wireless signal
It is defeated, it is characterised in that
Earth station's processing system includes base map image data base, vector file signal generating unit, ground signal Transmit-Receive Unit;Institute
State the image in multiple regions of the needs monitoring that base map image data base shoots including remote sensor;Vector file signal generating unit is configured
It is that vector mark is carried out to the image in base map image data base, draws the polygon of multiple closings, and plus numbering, generates arrow
Amount file;Ground signal Transmit-Receive Unit is configured to receive the base map image that remote sensor shoots, Xiang Yao from remote sensing platform processing system
Sense platform processes system sends the vector file generated by vector file signal generating unit;
The remote sensing platform processing system includes vector file storehouse, remote sensing images receiving unit, mask file generating unit, target
Identification and monitoring unit, remote sensing platform signal transmitting and receiving unit;Remote sensing platform signal transmitting and receiving unit is configured to receive ground signal receipts
The vector file that bill unit sends;Vector file storehouse includes the vector file received by remote sensing platform signal transmitting and receiving unit;Remote sensing
Image receiving unit is configured to receive the image of the specific region that remote sensor shoots;Mask file generating unit is configured to from vector
The vector file comprising the specific region is chosen in library and rasterizing process is carried out, is generated corresponding with the specific region
Mask file;Target identification is configured to according to the image and mask text of the specific region of remote sensor shooting with monitoring unit
The mask file corresponding with the specific region that part signal generating unit is generated, is identified and prison to the target in specific region
Survey.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611069209.9A CN106649607B (en) | 2016-11-28 | 2016-11-28 | Remote sensing image on-line target identification and monitoring method and system based on vector mask |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611069209.9A CN106649607B (en) | 2016-11-28 | 2016-11-28 | Remote sensing image on-line target identification and monitoring method and system based on vector mask |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106649607A true CN106649607A (en) | 2017-05-10 |
CN106649607B CN106649607B (en) | 2020-01-03 |
Family
ID=58813057
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611069209.9A Active CN106649607B (en) | 2016-11-28 | 2016-11-28 | Remote sensing image on-line target identification and monitoring method and system based on vector mask |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106649607B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108053409A (en) * | 2017-12-11 | 2018-05-18 | 中南大学 | Automatic construction method and system for remote sensing image segmentation reference library |
CN109359208A (en) * | 2018-09-13 | 2019-02-19 | 郑津 | A kind of distributed method and system of precisely lossless mark image instance |
CN112399196A (en) * | 2019-08-16 | 2021-02-23 | 阿里巴巴集团控股有限公司 | Image processing method and device |
CN114637876A (en) * | 2022-05-19 | 2022-06-17 | 中国电子科技集团公司第五十四研究所 | Large-scene unmanned aerial vehicle image rapid positioning method based on vector map feature expression |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6839454B1 (en) * | 1999-09-30 | 2005-01-04 | Biodiscovery, Inc. | System and method for automatically identifying sub-grids in a microarray |
CN101308544A (en) * | 2008-07-11 | 2008-11-19 | 中国科学院地理科学与资源研究所 | Spatial heterogeneity mode recognition method and layering method based on grids |
CN102033898A (en) * | 2010-09-27 | 2011-04-27 | 华东师范大学 | Extraction method for local cloud cover information metadata of moderate resolution imaging spectral image |
CN102314696A (en) * | 2011-07-13 | 2012-01-11 | 北京华迪宏图信息技术有限公司 | Vectorization method for raster data of remote sensing images |
CN104794336A (en) * | 2015-04-17 | 2015-07-22 | 武汉大学 | Farmland straw resource spacial distribution estimation method |
CN105279223A (en) * | 2015-10-20 | 2016-01-27 | 西南林业大学 | Computer automatic interpretation method for remote sensing image |
-
2016
- 2016-11-28 CN CN201611069209.9A patent/CN106649607B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6839454B1 (en) * | 1999-09-30 | 2005-01-04 | Biodiscovery, Inc. | System and method for automatically identifying sub-grids in a microarray |
CN101308544A (en) * | 2008-07-11 | 2008-11-19 | 中国科学院地理科学与资源研究所 | Spatial heterogeneity mode recognition method and layering method based on grids |
CN102033898A (en) * | 2010-09-27 | 2011-04-27 | 华东师范大学 | Extraction method for local cloud cover information metadata of moderate resolution imaging spectral image |
CN102314696A (en) * | 2011-07-13 | 2012-01-11 | 北京华迪宏图信息技术有限公司 | Vectorization method for raster data of remote sensing images |
CN104794336A (en) * | 2015-04-17 | 2015-07-22 | 武汉大学 | Farmland straw resource spacial distribution estimation method |
CN105279223A (en) * | 2015-10-20 | 2016-01-27 | 西南林业大学 | Computer automatic interpretation method for remote sensing image |
Non-Patent Citations (1)
Title |
---|
王彦情 等: "光学遥感图像舰船目标检测与识别综述", 《自动化学报》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108053409A (en) * | 2017-12-11 | 2018-05-18 | 中南大学 | Automatic construction method and system for remote sensing image segmentation reference library |
CN108053409B (en) * | 2017-12-11 | 2022-05-13 | 中南大学 | Automatic construction method and system for remote sensing image segmentation reference library |
CN109359208A (en) * | 2018-09-13 | 2019-02-19 | 郑津 | A kind of distributed method and system of precisely lossless mark image instance |
CN109359208B (en) * | 2018-09-13 | 2021-06-08 | 郑津 | Distributed method and system for accurately and losslessly labeling image instances |
CN112399196A (en) * | 2019-08-16 | 2021-02-23 | 阿里巴巴集团控股有限公司 | Image processing method and device |
CN114637876A (en) * | 2022-05-19 | 2022-06-17 | 中国电子科技集团公司第五十四研究所 | Large-scene unmanned aerial vehicle image rapid positioning method based on vector map feature expression |
Also Published As
Publication number | Publication date |
---|---|
CN106649607B (en) | 2020-01-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6976270B2 (en) | Remote determination of the amount stored in a container in a geographic area | |
EP3349147B1 (en) | System for monitoring marine vessels using a satellite network with determination at a terrestrial station of a rendezvous between the vessels which pass within a threshold distance using the satellite data. | |
Nassar et al. | A deep CNN-based framework for enhanced aerial imagery registration with applications to UAV geolocalization | |
CN108491837B (en) | Anti-attack method for improving license plate attack robustness | |
US11151734B2 (en) | Method and system for generating synthetic point cloud data using a generative model | |
US11556745B2 (en) | System and method for ordered representation and feature extraction for point clouds obtained by detection and ranging sensor | |
CN109816695A (en) | Target detection and tracking method for infrared small unmanned aerial vehicle under complex background | |
CN106649607A (en) | Remote sensing image online target recognition and monitoring method and system based on vector mask | |
CN109255286A (en) | A kind of quick detection recognition method of unmanned plane optics based on YOLO deep learning network frame | |
Ruban et al. | Method for determining elements of urban infrastructure objects based on the results from air monitoring | |
Du et al. | FA‐YOLO: An Improved YOLO Model for Infrared Occlusion Object Detection under Confusing Background | |
Yu et al. | Aircraft target detection using multimodal satellite-based data | |
Jiang et al. | Remote sensing object detection based on convolution and Swin transformer | |
CN107463944A (en) | A kind of road information extracting method using multidate High Resolution SAR Images | |
Jethani et al. | Surveillance system for monitoring social distance | |
CN114862952B (en) | Unmanned aerial vehicle detection and defense method and system | |
CN104615987B (en) | A kind of the wreckage of an plane intelligent identification Method and system based on error-duration model neutral net | |
Amabdiyil et al. | Marine vessel detection comparing GPRS and satellite images for security applications | |
Yadav et al. | Detection and Identification of Camouflaged Targets using Hyperspectral and LiDAR data. | |
Xiao et al. | A Shadow Capture Deep Neural Network for Underwater Forward‐Looking Sonar Image Detection | |
CN107895152B (en) | On-orbit cloud seam rapid detection method | |
CN114972140B (en) | Sea surface infrared and visible light image fusion method based on target segmentation | |
Silva Filho et al. | UAV visual autolocalizaton based on automatic landmark recognition | |
Downes | Lunar orbiter state estimation using neural network-based crater detection | |
Wu et al. | Precise UAV MMW-Vision Positioning: A Modal-Oriented Self-Tuning Fusion Framework |
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 |