CN106408027A - Method and system for extracting image of logistics warehouse behind storage yard at port - Google Patents
Method and system for extracting image of logistics warehouse behind storage yard at port Download PDFInfo
- Publication number
- CN106408027A CN106408027A CN201610847354.9A CN201610847354A CN106408027A CN 106408027 A CN106408027 A CN 106408027A CN 201610847354 A CN201610847354 A CN 201610847354A CN 106408027 A CN106408027 A CN 106408027A
- Authority
- CN
- China
- Prior art keywords
- image
- classification
- extraction
- stockyard
- feature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- 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
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- 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)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a method and a system for extracting an image of logistics warehouses behind a storage yard at a port. The method has the advantages of accurate image extraction and high processing efficiency on the basis of data features and features of the logistics warehouses the behind storage yard at the port. The method comprises the steps of: (1) adopting a lee sigma edge extraction algorithm for a band of a remote sensing image, wherein the lee sigma edge extraction algorithm uses a specific edge filter for creating two independent edge images from an original image, and the two independent edge images are respectively a bright edge image and a dark edge image; (2) subjecting the bright edge image, the dark edge image and the remote sensing image to multi-scale segmentation, so as to obtain image objects; (3), classifying objects with large blue band specific values in the obtained image objects into a category A, and using brightness average value features for removing out the objects with low brightness average values in the category A; (4), and using a normalized difference vegetation index NDVI feature for removing out the objects less than a specified threshold value in the category A, so as to obtain a category of the warehouses with blue roofs. The invention further provides a system for extracting the image of logistics warehouses behind the storage yard at the port.
Description
Technical field
The present invention relates to the technical field of image procossing, the stockyard rear logistics warehouse figure at more particularly, to a kind of extraction harbour
The method of picture, and extract the system of the stockyard rear logistics warehouse image at harbour.
Background technology
Harbour, as seaborne important component part, is increasingly subject to people's attention, and becomes traffic programme
A crucial research direction.And the planning construction at harbour, need to obtain various atural objects and its position at harbour.Square object behind stockyard
Stream warehouse is a kind of important atural object at harbour, and the extraction of stockyard rear logistics warehouse is a very important project, is worth throwing
Enter substantial amounts of research and development strength.
But, there is presently no the extraction that special method is directed to stockyard rear logistics warehouse.Existing method is being extracted
With during monitoring, the not feature of the stockyard rear logistics warehouse at the feature according to data and harbour, therefore image zooming-out are forbidden
Really, treatment effeciency is low.
Content of the invention
For overcoming the defect of prior art, the technical problem to be solved in the present invention there is provided a kind of stockyard at extraction harbour
The method of rear logistics warehouse image, it carries according to the feature of the feature of data and the stockyard rear logistics warehouse at harbour, image
Take accurately, treatment effeciency is high.
The technical scheme is that：The method of the stockyard rear logistics warehouse image at this extraction harbour, the method bag
Include following steps：
(1) lee sigma Boundary extracting algorithm is used to a wave band of remote sensing image, this algorithm uses one specifically
Boundary filter, creates two independent edge images from raw video：One bright limb image and a dark limb image；
(2) described bright limb image and dark limb image are participated in multi-scale division together with remote sensing image, obtain image
Object；
(3) in the imaged object obtaining, the larger object of blue band ratio is categorized as classification A；Special using luminance mean value
Levy relatively low the picking out away of luminance mean value in A classification；
(4) using normalization difference vegetation index NDVI feature, the object being less than specified threshold in A classification is picked out, thus
Obtain the warehouse classification on blue roof.
Present invention stockyard rear logistics warehouse to be extracted shows as blue roof, red roof, white room in image
The difference tone such as top, Lycoperdon polymorphum Vitt roof, the present invention is directed to the warehouse atural object on blue roof, according to its feature using blue band ratio,
Luminance mean value, NDVI feature realize the extraction in above-mentioned warehouse, therefore the stockyard rear at the feature according to data for the present invention and harbour
The feature of logistics warehouse, accurately, treatment effeciency is high for image zooming-out.
Additionally provide a kind of system of the stockyard rear logistics warehouse image at extraction harbour, this system includes：lee sigma
Boundary extracting algorithm module, its configuration carrys out a wave band to remote sensing image and uses lee sigma Boundary extracting algorithm, this algorithm
Using a specific boundary filter, create two independent edge images from raw video：One bright limb image and
One dark limb image；Multi-scale division algoritic module, its configuration comes described bright limb image and dark limb image and remote sensing
Image participates in multi-scale division together, obtains imaged object；
First sort module, its configuration comes in the imaged object obtaining, and the larger object of blue band ratio is categorized as class
Other A；Using luminance mean value feature relatively low the picking out away of luminance mean value in A classification；
Second sort module, its configuration comes specified being less than in A classification using normalization difference vegetation index NDVI feature
The object of threshold value is picked out, thus obtaining the warehouse classification on blue roof.
Brief description
The flow chart that Fig. 1 show the method for the stockyard rear logistics warehouse image at the extraction harbour according to the present invention.
Specific embodiment
As shown in figure 1, the method for the stockyard rear logistics warehouse image at this extraction harbour, the method includes following step
Suddenly：
(1) lee sigma Boundary extracting algorithm is used to a wave band of remote sensing image, this algorithm uses one specifically
Boundary filter, creates two independent edge images from raw video：One bright limb image and a dark limb image；
(2) described bright limb image and dark limb image are participated in multi-scale division together with remote sensing image, obtain image
Object；
(3) in the imaged object obtaining, the larger object of blue band ratio is categorized as classification A；Special using luminance mean value
Levy relatively low the picking out away of luminance mean value in A classification；
(4) using normalization difference vegetation index NDVI feature, the object being less than specified threshold in A classification is picked out, thus
Obtain the warehouse classification on blue roof.
Present invention stockyard rear logistics warehouse to be extracted shows as blue roof, red roof, white room in image
The difference tone such as top, Lycoperdon polymorphum Vitt roof, the present invention is directed to the warehouse atural object on blue roof, according to its feature using blue band ratio,
Luminance mean value, NDVI feature realize the extraction in above-mentioned warehouse, therefore the stockyard rear at the feature according to data for the present invention and harbour
The feature of logistics warehouse, accurately, treatment effeciency is high for image zooming-out.
In the imaged object obtaining, the larger object of blue band ratio is categorized as specific classification A.Due in image
The brightness that warehouse is showed is higher, therefore can be using luminance mean value feature relatively low the picking out away of luminance mean value in A classification.
In addition, the NDVI value of blue object is higher, using its feature, the object being less than certain threshold value in A classification is picked out, thus obtaining indigo plant
The warehouse classification on color roof.
In addition, the method also includes step (5), in the imaged object obtaining, the larger object classification of red band ratio
For classification B, thus obtaining the warehouse classification on red roof.
In addition, the method also includes step (6), after oil tank classification extraction finishes, using rectangle fitting feature and brightness
Characteristics of mean extracts white rectangle warehouse.Finish because oil tank classification is extracted, the remaining object having high luminance values
Including atural objects such as warehouse, Perioperative cardiac events, but warehouse roof typically assumes rectangular shape, therefore equal using rectangle fitting feature and brightness
Value tag extracts white rectangle warehouse.
In addition, in described step (6), rectangle fitting feature is that an imaged object has the square of similar size and ratio with it
The fitting degree of shape, 0 expression not matching, the 1 complete matching of expression.The calculating of this feature is built upon an image pair with selection
On the basis of having rectangle of the same area.The ratio of rectangle is also equal to the length of imaged object and the ratio of width.?
The area of the imaged object outside rectangle is compared with the area do not filled by imaged object in rectangle.Rectangle fitting feature
Calculated according to formula (1)
Span is [0,1] (1)
Wherein, ρv(x, y) is the Elliptical distance of a pixel (x, y).
In addition, it is intended that threshold value is 0.1 in described step (4).
Further, ArcGIS product line provides the user a telescopic, comprehensive GIS platform.
ArcObjects contains substantial amounts of programmable component, from fine-grained object (for example single geometric object) to coarseness
Object (map object for example interacting with the existing ArcMap document) face that is related to is extremely wide, and these objects are integrated with for developer comprehensively
GIS function.The ArcGIS product that each is built up using ArcObjects provides an application and development for developer
Container, including desktop GIS (ArcGIS Desktop), Embedded GIS (ArcGIS Engine) and service GIS (ArcGIS
Server).
The conventional business datum containing GIS space (mainly currently a popular ArcGIS data form) is carrying out data
When safeguarding editor (mainly additions and deletions change and look into), two ways is mainly had to carry out the unified management control of space and attribute data at present
System：
First, GIS-Geographic Information System (Geographic Information System or Geo-Information
System, GIS) it is sometimes referred to as " GeoscienceInformation System ".It is one kind specifically highly important space information system.It is
Under computer hardware and software system is supported, to relevant geographical point in earth top layer all or in part (inclusion atmosphere) space
Cloth data is acquired, stores, managing, computing, the technological system analyzed, be shown and described.
2nd, so-called MIS (management information system -- MANAGEMENT INFORMATION SYSTEM) system, refers mainly to
It is by the system of routine matter operation.This system is mainly used in managing the record needing, and carries out correlation to record data
Process, the information of process is informed gerentocratic a set of NMS in time.
During exploitation website, if related service and the design work of interface are carried out with traditional MIS development scheme,
Due to not adding to the particularity of GIS data to consider in design, often the same of MIS assembly can called during exploitation is realized
When call GIS assembly, the operation for same target often will detach the control of affair mechanism simultaneously.Final data is made
Become unpredictable hidden danger.
Therefore, present invention also offers method based on the stockyard rear logistics warehouse image extracting harbour a kind of compatible
The space of ArcGIS and the unified control method of attribute data, it includes data base's aspect, data access aspect, front end presentation layer
Face；
In data base's aspect, for the entity possessing spatial data, while increasing Custom Space classification, increase word
The WKT field of symbol type, this field is as the redundancy of the WKT form of Custom Space classification field；Wound for data message
Build, by writing storing process when the record execution comprising WKT field creates, execution WKT is same with self-defined categorical data
Step work；For editing and updating operation, by writing storing process, renewal is synchronized to self-defined classification data field；For
Deletion action, is deleted from functional by data base；For inquiry operation, it is divided into space querying, attribute query, space to belong to
Property mixing inquiry three kinds of forms, the wherein condition query of attribute query Yes-No space field；
In data access aspect, database manipulation is carried out by primary SQL or ORM mode；
Show aspect in front end, the character string that the figure that user is drawn is converted to WKT form is delivered to data base.
The method unified database designs, and considers GIS and MIS data storage, to become under the premise of necessarily required
Ripe traditional mode carries out data base's design work, therefore, it is possible to avoid GIS phenomenon detached with MIS design data；This
Bright unified database accesses and operation mechanism, and compatible popular SQL and ORM accesses mode of operation, therefore supports the data such as affairs
Place has characteristic；The present invention, while carrying out service data manipulating, can carry out related service event in modes such as business event
Triggering, therefore strengthens GIS business operation business complexity, and flexibility ratio is high；The present invention is on stream it is only necessary to common
MIS developer can carry out the generalized information systems of mode such as GIS and MIS＆GIS mixing under less GIS professional knowledge background
Exploitation, system framework no GIS assembly and version rely on；Data product produced by the present invention is compatible with ArcGIS software product,
Therefore the work such as data edits maintenance again, service is issued can be carried out by ArcGIS software.
It will appreciated by the skilled person that it is permissible for realizing all or part of step in above-described embodiment method
Instruct related hardware to complete by program, described program can be stored in a computer read/write memory medium,
Upon execution, including each step of above-described embodiment method, and described storage medium can be this program：ROM/RAM, magnetic
Dish, CD, storage card etc..Therefore, corresponding with the method for the present invention, the present invention also includes a kind of heap at extraction harbour simultaneously
The system of field rear logistics warehouse image, this system is generally represented in the form of the functional module corresponding with each step of method.
Using the system of the method, this system includes：
Lee sigma Boundary extracting algorithm module, its configuration carrys out a wave band to remote sensing image and uses lee sigma side
Edge extraction algorithm, this algorithm uses a specific boundary filter, creates two independent edge images from raw video：
One bright limb image and a dark limb image；Multi-scale division algoritic module, its configuration come described bright limb image with
Dark limb image participates in multi-scale division together with remote sensing image, obtains imaged object；
First sort module, its configuration comes in the imaged object obtaining, and the larger object of blue band ratio is categorized as class
Other A；Using luminance mean value feature relatively low the picking out away of luminance mean value in A classification；
Second sort module, its configuration comes specified being less than in A classification using normalization difference vegetation index NDVI feature
The object of threshold value is picked out, thus obtaining the warehouse classification on blue roof.
In addition, this system also includes the 3rd sort module, its configuration comes in the imaged object obtaining, and red band ratio is relatively
Big object is categorized as classification B, thus obtaining the warehouse classification on red roof.
In addition, this system also includes the 4th sort module, its configuration, after oil tank classification extraction finishes, intends using rectangle
Close feature and go out white rectangle warehouse with luminance mean value feature extraction.
In addition, in described 4th sort module, rectangle fitting feature is that an imaged object has similar size and ratio with it
The fitting degree of the rectangle of example, rectangle fitting feature calculates according to formula (1)
Span is [0,1] (1)
Wherein, ρv(x, y) is the Elliptical distance of a pixel (x, y).
In addition, it is intended that threshold value is 0.1 in described second sort module.
Additionally provide a kind of sky of the compatibility ArcGIS of system based on the stockyard rear logistics warehouse image extracting harbour
Between and attribute data unified control system, this system includes：
Data base, it configures and to be directed to the entity possessing spatial data, while increasing Custom Space classification, increases
The WKT field of character types, this field is as the redundancy of the WKT form of Custom Space classification field；For data message
Create, by writing storing process when the record execution comprising WKT field creates, execute WKT and self-defined categorical data
Synchronous working；For editing and updating operation, by writing storing process, renewal is synchronized to self-defined classification data field；Pin
To deletion action, deleted from functional by data base；For inquiry operation, it is divided into space querying, attribute query, space
Attribute mixing three kinds of forms of inquiry, the wherein condition query of attribute query Yes-No space field；
Data access module, its configuration carries out database manipulation by primary SQL or ORM mode；
Front end display module, the character string that the figure that user is drawn by its configuration is converted to WKT form is delivered to data
Storehouse.
The above, be only presently preferred embodiments of the present invention, and not the present invention is made with any pro forma restriction, every according to
Any simple modification, equivalent variations and modification above example made according to the technical spirit of the present invention, all still belongs to the present invention
The protection domain of technical scheme.
Claims (10)
1. a kind of stockyard rear logistics warehouse image at extraction harbour method it is characterised in that：The method comprises the following steps：
(1) lee sigma Boundary extracting algorithm is used to a wave band of remote sensing image, this algorithm uses a specific edge
Wave filter, creates two independent edge images from raw video：One bright limb image and a dark limb image；
(2) described bright limb image and dark limb image are participated in multi-scale division together with remote sensing image, obtain imaged object；
(3) in the imaged object obtaining, the larger object of blue band ratio is categorized as classification A；Using luminance mean value feature A
Relatively low the picking out away of luminance mean value in classification；
(4) using normalization difference vegetation index NDVI feature, the object being less than specified threshold in A classification is picked out, thus obtaining
The warehouse classification on blue roof.
2. the stockyard rear logistics warehouse image at extraction harbour according to claim 1 method it is characterised in that：The party
Method also includes step (5), and in the imaged object obtaining, the larger object of red band ratio is categorized as classification B, thus obtaining red
The warehouse classification on color roof.
3. the stockyard rear logistics warehouse image at extraction harbour according to claim 2 method it is characterised in that：The party
Method also includes step (6), after oil tank classification extraction finishes, goes out white using rectangle fitting feature and luminance mean value feature extraction
Rectangle warehouse.
4. the stockyard rear logistics warehouse image at extraction harbour according to claim 3 method it is characterised in that：Described
In step (6), rectangle fitting feature is that an imaged object has the fitting degree of the rectangle of similar size and ratio, rectangle with it
Fit characteristic calculates according to formula (1)Span is [0,1] (1)
Wherein, ρv(x, y) is the Elliptical distance of a pixel (x, y).
5. the stockyard rear logistics warehouse image at extraction harbour according to claim 1 method it is characterised in that：Described
It is intended that threshold value is 0.1 in step (4).
6. a kind of stockyard rear logistics warehouse image at extraction harbour system it is characterised in that：This system includes：
Lee sigma Boundary extracting algorithm module, its configuration is carried using lee sigma edge to a wave band of remote sensing image
Take algorithm, this algorithm uses a specific boundary filter, create two independent edge images from raw video：One
Bright limb image and a dark limb image；Multi-scale division algoritic module, its configuration comes described bright limb image and dark side
Edge image participates in multi-scale division together with remote sensing image, obtains imaged object；
First sort module, its configuration comes in the imaged object obtaining, and the larger object of blue band ratio is categorized as classification A；
Using luminance mean value feature relatively low the picking out away of luminance mean value in A classification；
Second sort module, its configuration come using normalization difference vegetation index NDVI feature in A classification be less than specified threshold
Object pick out, thus obtaining the warehouse classification on blue roof.
7. the stockyard rear logistics warehouse image at extraction harbour according to claim 6 system it is characterised in that：This is
System also includes the 3rd sort module, and its configuration comes in the imaged object obtaining, and the larger object of red band ratio is categorized as class
Other B, thus obtain the warehouse classification on red roof.
8. the stockyard rear logistics warehouse image at extraction harbour according to claim 7 system it is characterised in that：This is
System also includes the 4th sort module, and its configuration comes after oil tank classification extraction finishes, using rectangle fitting feature and luminance mean value
Feature extraction goes out white rectangle warehouse.
9. the stockyard rear logistics warehouse image at extraction harbour according to claim 8 system it is characterised in that：Described
In 4th sort module, rectangle fitting feature is that an imaged object has the matching journey of the rectangle of similar size and ratio with it
Degree, rectangle fitting feature calculates according to formula (1)
Span is [0,1] (1)
Wherein, ρv(x, y) is the Elliptical distance of a pixel (x, y).
10. the system of the stockyard rear logistics warehouse image based on extraction harbour according to claim 1, its feature exists
In：It is intended that threshold value is 0.1 in described second sort module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610847354.9A CN106408027A (en) | 2016-09-23 | 2016-09-23 | Method and system for extracting image of logistics warehouse behind storage yard at port |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610847354.9A CN106408027A (en) | 2016-09-23 | 2016-09-23 | Method and system for extracting image of logistics warehouse behind storage yard at port |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106408027A true CN106408027A (en) | 2017-02-15 |
Family
ID=57997505
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610847354.9A Pending CN106408027A (en) | 2016-09-23 | 2016-09-23 | Method and system for extracting image of logistics warehouse behind storage yard at port |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106408027A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108629289A (en) * | 2018-04-11 | 2018-10-09 | 千寻位置网络有限公司 | The recognition methods in farmland and system, applied to the unmanned plane of agricultural |
| US10325152B1 (en) | 2017-12-04 | 2019-06-18 | Transport Planning and Research Institute Ministry of Transport | Method of extracting warehouse in port from hierarchically screened remote sensing image |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030081833A1 (en) * | 2001-04-23 | 2003-05-01 | National Aeronautics And Space Administration | Method for implementation of recursive hierarchical segmentation on parallel computers |
| CN102663394A (en) * | 2012-03-02 | 2012-09-12 | 北京航空航天大学 | Method of identifying large and medium-sized objects based on multi-source remote sensing image fusion |
-
2016
- 2016-09-23 CN CN201610847354.9A patent/CN106408027A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030081833A1 (en) * | 2001-04-23 | 2003-05-01 | National Aeronautics And Space Administration | Method for implementation of recursive hierarchical segmentation on parallel computers |
| CN102663394A (en) * | 2012-03-02 | 2012-09-12 | 北京航空航天大学 | Method of identifying large and medium-sized objects based on multi-source remote sensing image fusion |
Non-Patent Citations (2)
| Title |
|---|
| 刘文静: "资源三号卫星影像解译样本及特征知识库构建研究", 《中国优秀硕士学位论文全文数据库——基础科学辑》 * |
| 甘甜: "基于高分辨率遥感影像数据的建筑物震害信息分类提取研究", 《中国优秀硕士学位论文全文数据库——基础科学辑》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10325152B1 (en) | 2017-12-04 | 2019-06-18 | Transport Planning and Research Institute Ministry of Transport | Method of extracting warehouse in port from hierarchically screened remote sensing image |
| CN108629289A (en) * | 2018-04-11 | 2018-10-09 | 千寻位置网络有限公司 | The recognition methods in farmland and system, applied to the unmanned plane of agricultural |
| CN108629289B (en) * | 2018-04-11 | 2021-07-30 | 千寻位置网络有限公司 | Farmland identification method and system and agricultural unmanned aerial vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11176443B1 (en) | Application control and text detection from application screen images | |
| CN106407940A (en) | Port water area image extraction method and system | |
| CN108537146B (en) | Print form and handwriting mixed text line extraction system | |
| JP4139615B2 (en) | Event clustering of images using foreground / background segmentation | |
| Fauqueur et al. | Region-based image retrieval: Fast coarse segmentation and fine color description | |
| US8527519B2 (en) | Query system for a hybrid voxel and feature database | |
| Cao et al. | Automatic change detection in high-resolution remote-sensing images by means of level set evolution and support vector machine classification | |
| US20140245121A1 (en) | Creating and Switching a View of a Collection Including Image Data and Symbolic Data | |
| CN105849685A (en) | Editing options for image regions | |
| CN102194123A (en) | Method and device for defining table template | |
| CN105718555A (en) | Hierarchical semantic description based image retrieving method | |
| CN104166695A (en) | Subdivision, query and dynamic display method oriented to remote sensing data content | |
| Lang et al. | Combined object-based classification and manual interpretation–synergies for a quantitative assessment of parcels and biotopes | |
| CN110119460A (en) | Image search method, device and electronic equipment | |
| Huang et al. | Detecting shadows in high-resolution remote-sensing images of urban areas using spectral and spatial features | |
| Zhang et al. | A multiple feature fully convolutional network for road extraction from high-resolution remote sensing image over mountainous areas | |
| CN106408027A (en) | Method and system for extracting image of logistics warehouse behind storage yard at port | |
| US11869127B2 (en) | Image manipulation method and apparatus | |
| CN106407941A (en) | Method and system for monitoring port sea reclamation based on object-oriented image analysis | |
| CN106407938A (en) | Method and system for extracting specific ground object of port by utilizing remote sensing image | |
| US7755646B2 (en) | Image management through lexical representations | |
| CN113012220A (en) | Fruit counting method and device and electronic equipment | |
| Argialas et al. | Change detection of buildings in suburban areas from high resolution satellite data developed through object based image analysis | |
| CN106408572A (en) | Method and system for monitoring container storage yard at port by utilizing remote sensing image | |
| CN106485726A (en) | A kind of extracting method of Ore stockpile image at harbour and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170215 |