CN104486585B - A kind of city magnanimity monitor video management method and system based on GIS - Google Patents
A kind of city magnanimity monitor video management method and system based on GIS Download PDFInfo
- Publication number
- CN104486585B CN104486585B CN201410795276.3A CN201410795276A CN104486585B CN 104486585 B CN104486585 B CN 104486585B CN 201410795276 A CN201410795276 A CN 201410795276A CN 104486585 B CN104486585 B CN 104486585B
- Authority
- CN
- China
- Prior art keywords
- monitoring data
- video monitoring
- video
- key frame
- data
- 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
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention provides a kind of city magnanimity monitor video management method and system based on GIS, by the space-time position for obtaining the video monitoring data, semantic attribute, vector characteristic and key frame, and by the space-time position, key frame, semantic attribute and vector characteristic are uniformly stored in generalized information system, the video monitoring data is managed with the GIS integrated management systems frame by frame, carry out being based on the space-time position, key frame, the condition query of semantic attribute and vector characteristic positions with search, so as to which massive video data management is converted into based on positioning key frame images, it is semantic, the GIS integrated management of vector quantization, at utmost reduce data volume, improve managerial ability and efficiency.
Description
Technical field
The present invention relates to GIS-Geographic Information System (GIS), more particularly to a kind of city magnanimity monitor video management based on GIS
Method and system.
Background technology
City mass video monitoring data lacks storage, management, processing, analytical model and the ability of efficient optimization.Magnanimity
Video data can not be fully utilized, and lack effective integration shared platform, lack globalization, integrated management inquiry mechanism etc..
Conventional video data is managed using file mode, it is difficult to data processing is carried out frame by frame, result is collected,
Overall expression, because video data lacks space coordinates and attribute information, can not effectively be managed by Database Systems.
, it is necessary to by magnanimity, uncalibrated visual servo video on the premise of current data acquisition capability is far longer than storage disposal ability
Information carries out resolution process, effectively reduces data volume, improves information added value.
GIS has the unified management of multiple types data with integrating disposal ability, is that the ideal of massive video optimum management is put down
Platform.
Number of patent application 201310443078.6 provides one kind and geographical location information is added in video file and is established
The method of index;Number of patent application 201310675740.0 provides a kind of based on video surveillance network positioning and method for tracing;
Number of patent application 201410115063.1 provides a kind of video semanteme and retrieves the camera system and method synchronous with compression;Patent
Application number 201310695141.5 provides a kind of video abstraction generating method based on GIS, and the application is exactly with above-mentioned patent
Based on, with reference to generalized information system, it is further provided a kind of system for managing video.
The content of the invention
This patent provides a kind of city magnanimity monitor video management method based on GIS, by city video monitoring number
According to coordinatograph, semantization, summaryization, vectorized process is carried out, video information is converted into its key frame and its dependent coordinate, mesh
The set of mark, vector, attribute data, is uniformly stored in generalized information system.
To achieve the above object, the present invention uses following technical proposals:
A kind of city magnanimity monitor video management method based on GIS, comprises the steps:
Obtain video monitoring data;
Obtain the space-time position of the video monitoring data;
The key frame of the video monitoring data is extracted, and positions the key frame;
Obtain the semantic attribute of the video monitoring data key frame;
Obtain the vector characteristic of the video monitoring data key frame;By the space-time position of the video monitoring data, close
Key frame, semantic attribute and vector characteristic are uniformly stored in generalized information system, obtain GIS integrated management systems;
The video monitoring data is managed with the GIS integrated management systems frame by frame, carried out based on the space-time position, pass
The condition query of key frame, semantic attribute and vector characteristic positions with search.
In certain embodiments, also comprise the steps:
The GIS integrated management systems carry out images match, semantics recognition and vector superposed to the data of the key frame.
In certain embodiments, wherein, the space-time position of the monitoring data is obtained, is comprised the steps:
Geographical location information is added in the video monitoring data and establishes index;
The video monitoring data is positioned and followed the trail of.
In certain embodiments, wherein, geographical location information is added in the video monitoring data and establishes index, is wrapped
Include following step:
Obtain the geographical location information data of the video monitoring data collection point;
The geographical location information data is inserted in the file header reserved field of the video monitoring data;
Using the geographical location information data as index, establish based on locus inquiry, cluster and association analysis
Video file data storehouse.
In certain embodiments, wherein, the video monitoring data is positioned and followed the trail of, is comprised the steps:
Obtain the geographical coordinate of the monitoring device of the video monitoring data;
Centered on each video monitoring equipment, according to monitoring range, the space coordinates of video surveillance network are established;
Selection characteristic point is surveyed and drawn, and obtains the geographical coordinate of characteristic point, and character pair point is in video monitoring equipment
Pixel value in imaging array;
Using above-mentioned characteristic point as control point, projective transformation and Coordinate Conversion are carried out, makes other ground image surfaces in imaging array
Vegetarian refreshments has corresponding geographic coordinate values;
When target appears in monitoring range, by obtaining target place pixel point coordinates, and combining environmental periphery relation,
Converse the geographical coordinate of target;
By transferring the geographical coordinate of target different frame in video surveillance network, the motion track of target is formed.
In certain embodiments, wherein, the key frame of the video monitoring data is extracted, and positions the key frame, wrapped
Include following step:
By extracting the key frame of the video monitoring data based on shot boundary or based on being regarded described in motion analysis extraction
The key frame of frequency monitoring data or the key frame that the video monitoring data is extracted based on Video clustering;
The key frame is positioned by raster data management.
In certain embodiments, wherein, the semantic attribute of the video monitoring data is obtained, is comprised the steps:
Including personal settings with applying two stages, wherein:
The personal settings include:Select the set of specific objective;Establish the video features of the video monitoring data
Semantic base;Sample training is carried out to Sample video under offline environment, to obtain training parameter collection;Training parameter is configured at
In grader;
The application includes:Video is obtained, starts to compress;Key frame is extracted in the compressed domain;In the key-frame extraction
Moving Objects;Semantic feature is extracted in key frame or Moving Objects;Read the training parameter collection in grader;By the language of extraction
Adopted feature is matched with training parameter collection, obtains the index of video semanteme.
In certain embodiments, wherein, the vector characteristic of the video monitoring data is obtained, is comprised the steps:
Obtain the geographical coordinate of target in the video monitoring data;
The pixel coordinate of target in the video monitoring data key frame and geographical coordinate are corresponded;
By carrying out rim detection to the target in the video monitoring data frame by frame, the pixel of its Edge Feature Points is obtained
Coordinate;
The pixel coordinate of the target, geographical coordinate, shooting time and frame number recorded in tables of data;
By being superimposed frame by frame, one group of vector current tables of data changed over time is formed, former video monitoring data is converted into
【Pixel coordinate+longitude and latitude+shooting time】Set of coordinate values, be stored in GIS in, formed and the continuous videos of destination object plucked
Will.
In certain embodiments, also include the video monitoring before the key frame of the video monitoring data is extracted
Data carry out the step of concentration.
In addition, present invention also offers a kind of city magnanimity monitor video management system based on GIS, including:
Data acquisition module, for obtaining video monitoring data;
Position acquisition module, for obtaining the space-time position of the video monitoring data;
Key frame locating module, for extracting the key frame of the video monitoring data, and position the key frame;
Semantic acquisition module, for obtaining the semantic attribute of the video monitoring data;
Vector acquisition module, for obtaining the vector characteristic of the video monitoring data;Data memory module, for by institute
Space-time position, key frame, semantic attribute and the vector characteristic for stating video monitoring data are uniformly stored in generalized information system, obtain GIS
Integrated management system, the GIS integrated management systems manage the video monitoring data frame by frame, carry out being based on the space-time
Put, the condition query of key frame, semantic attribute and vector characteristic positions with search.
City magnanimity monitor video management method and system provided by the invention based on GIS, by obtaining the video
Space-time position, semantic attribute, vector characteristic and the key frame of monitoring data, and by the space-time position, key frame, semantic attribute
And vector characteristic is uniformly stored in generalized information system, the video monitoring data is managed with the GIS integrated management systems frame by frame,
Carry out condition query based on the space-time position, key frame, semantic attribute and vector characteristic to position with search, so as to by magnanimity
Video data management be converted into based on positioning key frame images, semanteme, vector quantization GIS integrated management, at utmost reduce
Data volume, improve managerial ability and efficiency.
Brief description of the drawings
Fig. 1 is the step flow chart of the city magnanimity monitor video management method provided by the invention based on GIS.
Fig. 2 is to obtain the video monitoring in the city magnanimity monitor video management method provided by the invention based on GIS
The step flow chart of the space-time position of data.
Fig. 3 is the schematic diagram of the raster data management framework in GIS software provided by the invention.
Fig. 4 is to obtain the video monitoring in the city magnanimity monitor video management method provided by the invention based on GIS
The step flow chart of the semantic attribute of data.
Fig. 5 is to obtain the video monitoring in the city magnanimity monitor video management method provided by the invention based on GIS
The step flow chart of the vector characteristic of data.
Fig. 6 is the structural representation of the system for managing video provided by the invention based on GIS.
Embodiment
In order that the purpose of the present invention, technical scheme and beneficial effect are more clearly understood, below in conjunction with accompanying drawing and implementation
Example, the present invention will be described in further detail.It should be appreciated that specific embodiment described herein is only explaining this hair
It is bright, it is not intended to limit the present invention.
Referring to Fig. 1, flowed for the step of city magnanimity monitor video management method 100 provided by the invention based on GIS
Cheng Tu, comprise the steps:
Step S110:Obtain video monitoring data;
In the present embodiment, above-mentioned video monitoring data is city mass video monitoring data.
Step S120:Obtain the space-time position of the video monitoring data;
Referring to Fig. 2, wherein, in step S120, the space-time position for obtaining the video monitoring data comprises the steps:
Step S121:Geographical location information is added in the video monitoring data and establishes index;
Step S122:The video monitoring data is positioned and followed the trail of.
Wherein, in step S121, geographical location information is added in the video monitoring data and establishes index, including under
State step:
Step S121a:Obtain the geographical location information data of the video monitoring data collection point;
Step S121b:The geographical location information data is inserted to the file header reserved field of the video monitoring data
In;
Step S121c:Using the geographical location information data as index, establish based on locus inquiry, cluster and
The video file data storehouse of association analysis.
Wherein, in step S122, the video monitoring data is positioned and followed the trail of, is comprised the steps:
Step S122a:Obtain the geographical coordinate of the monitoring device of the video monitoring data;
Step S122b:Centered on each video monitoring equipment, according to monitoring range, the space of video surveillance network is established
Coordinate system;
Step S122c:Selection characteristic point is surveyed and drawn, and obtains the geographical coordinate of characteristic point, and character pair point is in video
Pixel value in the imaging array of monitoring device;
Step S122d:Using above-mentioned characteristic point as control point, projective transformation and Coordinate Conversion are carried out, is made in imaging array
Other ground pixels have corresponding geographic coordinate values;
Step S122e:When target appears in monitoring range, by obtaining target place pixel point coordinates, and coupling collar
Border periphery relation, converse the geographical coordinate of target;
Step S122f:By transferring the geographical coordinate of target different frame in video surveillance network, the movement of target is formed
Track.
Step S130:The key frame of the video monitoring data is extracted, and positions the key frame;
Wherein, in step S130, the key frame of the video monitoring data is extracted, and positions the key frame, including under
State step:
By extracting the key frame of the video monitoring data based on shot boundary or based on being regarded described in motion analysis extraction
The key frame of frequency monitoring data or the key frame that the video monitoring data is extracted based on Video clustering.Preferably, institute is being extracted
The step of also including the video monitoring data carrying out concentration before stating the key frame of video monitoring data.
The key frame is positioned by raster data management.It is appreciated that raster data management processing is GIS major functions
One of, grating image is made up of pixel, each pixel binary representation.
Referring to Fig. 3, grating image is carried out piecemeal classification processing by GIS, database is restored again into, raster dataset physics is deposited
Storage carries out tissue using the multiple index mechanism of " pyramidal layer-wave band-data block ", and the key frame is determined so as to complete
Position.
Step S140:Obtain the semantic attribute of the video monitoring data;
Referring to Fig. 4, wherein, step S140:The semantic attribute of the video monitoring data is obtained, is comprised the steps:
Step S141:Personal settings:
Wherein, in step S141, the personal settings include:
Step S141a:Select the set of specific objective;
Step S141b:Establish the video features semantic base of the video monitoring data;
Step S141c:Sample training is carried out to Sample video under offline environment, to obtain training parameter collection;
Step S141d:Training parameter is configured in grader;
Step S142:The application includes:
Step S142a:Video is obtained, starts to compress;
Step S142b:Key frame is extracted in the compressed domain;
Step S142c:In the key-frame extraction Moving Objects;
Step S142d:Semantic feature is extracted in key frame or Moving Objects;
Step S142e:Read the training parameter collection in grader;
Step S142f:The semantic feature of extraction is matched with training parameter collection, obtains the index of video semanteme.
Step S150:Obtain the vector characteristic of the video monitoring data;
Referring to Fig. 5, wherein, in step S150, obtain the vector characteristic of the video monitoring data, including following steps
Suddenly:
Step S151:Obtain the geographical coordinate of target in the video monitoring data;
Step S152:The pixel coordinate of target in the video monitoring data key frame and geographical coordinate are corresponded;
Step S153:By carrying out rim detection to the target in the video monitoring data frame by frame, its edge spy is obtained
Levy the pixel coordinate of point;
Step S154:The pixel coordinate of the target, geographical coordinate, shooting time and frame number recorded in tables of data;
Step S155:By being superimposed frame by frame, one group of vector current tables of data changed over time is formed, by former video monitoring number
According to being converted into【Pixel coordinate+longitude and latitude+shooting time】Set of coordinate values, be stored in GIS in, formed to the continuous of destination object
Video frequency abstract.
Step S160:The space-time position of the video monitoring data, key frame, semantic attribute and vector characteristic are uniformly deposited
It is stored in generalized information system, obtains GIS integrated management systems;
Step S170:The video monitoring data is managed with the GIS integrated management systems frame by frame, when carrying out being based on described
Empty position, key frame, semantic attribute and the condition query of vector characteristic and search position.
Referring again to Fig. 1, the city magnanimity monitor video management method provided by the invention based on GIS also includes following steps
Suddenly:
Step S180:The GIS integrated management systems data of the key frame are carried out images match, semantics recognition and
It is vector superposed.
In addition, referring to Fig. 6, be a kind of system for managing video 100 based on GIS provided by the invention, including:
Data acquisition module 110, for obtaining video monitoring data;
Position acquisition module 120, for obtaining the space-time position of the video monitoring data;
Key frame locating module 130, for extracting the key frame of the video monitoring data, and position the key frame;
Semantic acquisition module 140, for obtaining the semantic attribute of the video monitoring data;
Vector acquisition module 150, for obtaining the vector characteristic of the video monitoring data;
Data memory module 160, for by the space-time position of the video monitoring data, key frame, semantic attribute and arrow
Measure feature is uniformly stored in generalized information system, obtains GIS integrated management systems, and the GIS integrated management systems manage described frame by frame
Video monitoring data, carry out the condition query based on the space-time position, key frame, semantic attribute and vector characteristic and determine with search
Position.
It is appreciated that also having video analysis function in the GIS integrated management systems, realize and enter for key frame data
Row images match, semantics recognition, vector superposed etc. operate.
City magnanimity monitor video management method and system provided by the invention based on GIS, by obtaining the video
Space-time position, semantic attribute, vector characteristic and the key frame of monitoring data, and by the space-time position, key frame, semantic attribute
And vector characteristic is uniformly stored in generalized information system, the video monitoring data is managed with the GIS integrated management systems frame by frame,
Carry out condition query based on the space-time position, key frame, semantic attribute and vector characteristic to position with search, so as to by magnanimity
Video data management be converted into based on positioning key frame images, semanteme, vector quantization GIS integrated management, at utmost reduce
Data volume, improve managerial ability and efficiency.
It should be noted that:In the various embodiments described above, the description of each embodiment is all given priority to, and is not had in each embodiment
The part being described in detail, the detailed description of specification full text is referred to, here is omitted.
Described above is only the preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
Member, under the premise without departing from the principles of the invention, can also make some improvements and modifications, these improvements and modifications also should be regarded as
Protection scope of the present invention.
Claims (7)
1. a kind of city magnanimity monitor video management method based on GIS, it is characterised in that comprise the steps:
Obtain video monitoring data;
Obtain the space-time position of the video monitoring data;
The key frame of the video monitoring data is extracted, and positions the key frame;
Obtain the semantic attribute of the video monitoring data key frame;
Obtain the vector characteristic of the video monitoring data key frame;
The space-time position of the video monitoring data, key frame, semantic attribute and vector characteristic are uniformly stored in generalized information system
In, obtain GIS integrated management systems;
The video monitoring data is managed with the GIS integrated management systems frame by frame, carried out based on the space-time position, key
The condition query of frame, semantic attribute and vector characteristic positions with search;
Wherein, the space-time position of the monitoring data is obtained, is comprised the steps:
Geographical location information is added in the video monitoring data and establishes index;
The video monitoring data is positioned and followed the trail of;
Wherein, the video monitoring data is positioned and followed the trail of, comprised the steps:
Obtain the geographical coordinate of the monitoring device of the video monitoring data;
Centered on each video monitoring equipment, according to monitoring range, the space coordinates of video surveillance network are established;
Selection characteristic point is surveyed and drawn, and obtains the geographical coordinate of characteristic point, and character pair point is in the imaging of video monitoring equipment
Pixel value in matrix;
Using above-mentioned characteristic point as control point, projective transformation and Coordinate Conversion are carried out, makes other ground pixels in imaging array
With corresponding geographic coordinate values;
When target appears in monitoring range, by obtaining target place pixel point coordinates, and combining environmental periphery relation, conversion
Go out the geographical coordinate of target;
By transferring the geographical coordinate of target different frame in video surveillance network, the motion track of target is formed.
2. the city magnanimity monitor video management method based on GIS as claimed in claim 1, it is characterised in that under also including
State step:
The GIS integrated management systems carry out images match, semantics recognition and vector superposed to the data of the key frame.
3. the city magnanimity monitor video management method based on GIS as claimed in claim 1, it is characterised in that wherein, in institute
State and geographical location information is added in video monitoring data and establishes index, comprise the steps:
Obtain the geographical location information data of the video monitoring data collection point;
The geographical location information data is inserted in the file header reserved field of the video monitoring data;
Using the geographical location information data as index, the video based on locus inquiry, cluster and association analysis is established
Document data bank.
4. the city magnanimity monitor video management method based on GIS as claimed in claim 1, it is characterised in that wherein, extract
The key frame of the video monitoring data, and the key frame is positioned, comprise the steps:
Supervised by extracting the key frame of the video monitoring data based on shot boundary or extracting the video based on motion analysis
Control the key frame of data or the key frame of the video monitoring data is extracted based on Video clustering;
The key frame is positioned by raster data management.
5. the city magnanimity monitor video management method based on GIS as claimed in claim 1, it is characterised in that wherein, obtain
The semantic attribute of the video monitoring data key frame, comprises the steps:
Including personal settings with applying two stages, wherein:
The personal settings include:Select the set of specific objective;The video features for establishing the video monitoring data are semantic
Storehouse;Sample training is carried out to Sample video under offline environment, to obtain training parameter collection;Training parameter is configured at classification
In device;
The application includes:Video is obtained, starts to compress;Key frame is extracted in the compressed domain;Moved in the key-frame extraction
Object;Semantic feature is extracted in key frame or Moving Objects;Read the training parameter collection in grader;The semanteme of extraction is special
Sign is matched with training parameter collection, obtains the index of video semanteme.
6. the city magnanimity monitor video management method based on GIS as claimed in claim 1, it is characterised in that wherein, obtain
The vector characteristic of the video monitoring data key frame, comprises the steps:
Obtain the geographical coordinate of target in the video monitoring data;
The pixel coordinate of target in the video monitoring data key frame and geographical coordinate are corresponded;
By carrying out rim detection to the target in the video monitoring data frame by frame, the pixel for obtaining its Edge Feature Points is sat
Mark;
The pixel coordinate of the target, geographical coordinate, shooting time and frame number recorded in tables of data;
By being superimposed frame by frame, one group of vector current tables of data changed over time is formed, former video monitoring data is converted into pixel
The set of coordinate values of coordinate and longitude and latitude and shooting time, it is stored in GIS, forms the continuous videos summary to destination object.
7. the city magnanimity monitor video management method based on GIS as described in claim 1 or 4, it is characterised in that extracting
The step of also including the video monitoring data carrying out concentration before the key frame of the video monitoring data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410795276.3A CN104486585B (en) | 2014-12-18 | 2014-12-18 | A kind of city magnanimity monitor video management method and system based on GIS |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410795276.3A CN104486585B (en) | 2014-12-18 | 2014-12-18 | A kind of city magnanimity monitor video management method and system based on GIS |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104486585A CN104486585A (en) | 2015-04-01 |
CN104486585B true CN104486585B (en) | 2018-01-05 |
Family
ID=52761084
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410795276.3A Active CN104486585B (en) | 2014-12-18 | 2014-12-18 | A kind of city magnanimity monitor video management method and system based on GIS |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104486585B (en) |
Families Citing this family (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106156199B (en) * | 2015-04-22 | 2022-04-08 | 清华大学 | Video monitoring image storage and retrieval method |
CN104867161B (en) * | 2015-05-14 | 2018-03-23 | 国家电网公司 | A kind of method for processing video frequency and device |
CN105205880B (en) * | 2015-07-17 | 2018-03-16 | 广东好帮手电子科技股份有限公司 | A kind of method and its system based on geographical position retrieval data |
CN105933655A (en) * | 2016-05-13 | 2016-09-07 | 深圳先进技术研究院 | Video and WIFI mixed positioning method and system |
CN106027957A (en) * | 2016-05-13 | 2016-10-12 | 深圳先进技术研究院 | Video positioning and publishing system |
CN106027959A (en) * | 2016-05-13 | 2016-10-12 | 深圳先进技术研究院 | Video recognizing-tracking-positioning system based on position linear fitting |
CN115329029B (en) * | 2022-10-14 | 2023-02-28 | 北京邮电大学 | Mobile terminal-oriented complex condition geographic information query method, device and medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1144434A (en) * | 1994-07-29 | 1997-03-05 | Dva公司 | Video decompression |
CN1633092A (en) * | 2004-11-25 | 2005-06-29 | 武汉大学 | Distributed GIS space information integration apparatus and method based on mobile Agent and GML |
CN102609517A (en) * | 2012-02-09 | 2012-07-25 | 武汉大学 | Method and system for online vector map comprehensive services |
-
2014
- 2014-12-18 CN CN201410795276.3A patent/CN104486585B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1144434A (en) * | 1994-07-29 | 1997-03-05 | Dva公司 | Video decompression |
CN1633092A (en) * | 2004-11-25 | 2005-06-29 | 武汉大学 | Distributed GIS space information integration apparatus and method based on mobile Agent and GML |
CN102609517A (en) * | 2012-02-09 | 2012-07-25 | 武汉大学 | Method and system for online vector map comprehensive services |
Also Published As
Publication number | Publication date |
---|---|
CN104486585A (en) | 2015-04-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104486585B (en) | A kind of city magnanimity monitor video management method and system based on GIS | |
Zhong et al. | Fully convolutional networks for building and road extraction: Preliminary results | |
US10997788B2 (en) | Context-aware tagging for augmented reality environments | |
CN107133325B (en) | Internet photo geographic space positioning method based on street view map | |
CN103984710B (en) | Video interactive querying method and system based on mass data | |
US10043097B2 (en) | Image abstraction system | |
CN102959946B (en) | The technology of view data is expanded based on relevant 3D cloud data | |
Hu et al. | GeoAI at ACM SIGSPATIAL: progress, challenges, and future directions | |
Liu et al. | Research on automatic garbage detection system based on deep learning and narrowband internet of things | |
CN104484814B (en) | A kind of advertising method and system based on video map | |
Daly et al. | Mining and Classifying Image Posts on Social Media to Analyse Fires. | |
CN103426165A (en) | Precise registration method of ground laser-point clouds and unmanned aerial vehicle image reconstruction point clouds | |
CN107103615A (en) | A kind of monitor video target lock-on tracing system and track lock method | |
CN101470730B (en) | Image repetition detection method based on spectrum characteristics analysis | |
CN103905824A (en) | Video semantic retrieval and compression synchronization camera system and method | |
Werner et al. | DeepMoVIPS: Visual indoor positioning using transfer learning | |
CN104520848A (en) | Searching for events by attendants | |
Kalantar et al. | Smart counting–oil palm tree inventory with UAV | |
Hoffmann et al. | Using social media images for building function classification | |
CN106530331A (en) | Video monitoring system and method | |
CN111507416A (en) | Smoking behavior real-time detection method based on deep learning | |
KR102388777B1 (en) | System for providing adjacent building pre-survey service usign 360 degree virtual reality camera | |
Kim et al. | TVDP: Translational visual data platform for smart cities | |
KR20220027000A (en) | Method and device for extracting spatial relationship of geographic location points | |
CN116843867A (en) | Augmented reality virtual-real fusion method, electronic device and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |