CN102855494A - Method and device for extracting water body of satellite remote sensing image - Google Patents
Method and device for extracting water body of satellite remote sensing image Download PDFInfo
- Publication number
- CN102855494A CN102855494A CN2012102974930A CN201210297493A CN102855494A CN 102855494 A CN102855494 A CN 102855494A CN 2012102974930 A CN2012102974930 A CN 2012102974930A CN 201210297493 A CN201210297493 A CN 201210297493A CN 102855494 A CN102855494 A CN 102855494A
- Authority
- CN
- China
- Prior art keywords
- water body
- sensing image
- water
- satellite remote
- information
- 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
Images
Abstract
The embodiment of the invention provides a method and a device for extracting a water body of a satellite remote sensing image. The method for extracting the water body of the satellite remote sensing image comprises the following steps: obtaining satellite remote sensing image data and utilizing a preset threshold in a preset decision-making tree to classify the water body information in the satellite remote sensing image data, thereby obtaining a water body extracting result after being classified. The device for extracting the water body of the satellite remote sensing image comprises an acquiring unit and a decision-making tree unit, wherein the acquiring unit is used for acquiring the satellite remote sensing image data, and the decision-making tree unit is used for utilizing the preset threshold in the preset decision-making tree to classify the water body information in the satellite remote sensing image data, thereby obtaining the water body extracting result after being classified. The method and device provided by the embodiment of the invention have the technical effect that the water body extraction precision of the satellite remote sensing image is increased.
Description
Technical field
The present invention relates to decipher and the classification of remote sensing image, relate in particular to a kind of water body extracting method and device of satellite remote-sensing image.
Background technology
The decipher of satellite remote-sensing image and classification are one of key areas of remote sensing technology research, and it is the important means of quick, Obtaining Accurate sensor information but is the process of a complexity.The development of remote Sensing Interpretation technology lags behind the development of remote sensor, at present, utilize the method for mathematical statistics and artificial decipher combination consuming time, consumption power, inefficiency, its decipher precision are subject to decipher personnel level and on the impact of the factors such as regional geography environment understanding.What remote sensing image reacted is the geography information with dynamic change characterization complicated, multi-level, many key elements.Because the complicacy of object spectrum, occurring in nature exists a large amount of " the different spectrum of jljl " and the phenomenon of " same object different images ", with simple mathematics with gain knowledge to process and can not reach high-precision requirement.Therefore, comprehensive study, multi-level analytical approach are significant for the extraction accuracy and the efficient that improve sensor information.
Sorting technique is the core that the earth's surface covers drawing, substantially can be divided into supervised classification and unsupervised classification, have the ginseng classification and without the ginseng classification, firmly classification and soft (blur) classification or by the pixel classification with sub-pixel classification and pursue object classification.Cover the Latest Development of Classification in Remote Sensing Image method from the earth's surface, utilize at present the mathematical statistics method to be still in the predominant methods of carrying out the large scale Classification in Remote Sensing Image in conjunction with artificial decipher.Obvious this method has the algorithm maturation, takes full advantage of the man-machine interaction advantageous feature, use duration but also exist, Personnel Dependence to the participation interpretation analysis is strong, and repeatable low limitation is difficult to rapidly, obtains accurately, objectively large tracts of land earth's surface coverage information.
Classification of remote-sensing images has been made significant headway in the past few decades, is mainly reflected in following three aspects: development and the application of (1) senior sorting algorithm, for example: sub-pixel classification, by object classification with based on the knowledge classification algorithm.(2) use of multiple remote sensing features comprises spectral information, spatial information, multidate and multi-sensor data; (3) assorting process is quoted auxiliary data, comprises landform, soil, road and demographic data.Accuracy evaluation is most important in the Images Classification process.Precision evaluation based on error matrix is that the most frequently used method of pixel classification is pursued in assessment, and the fuzzy classification outcome evaluation is more and more tended to blur method.Uncertain and error propagation affects nicety of grading, plays an important role in image processing process.Weakest link in the identification processing procedure and reduction uncertainty can improve the classification degree of accuracy greatly.To become an important problem in the uncertain Image Classification Studies afterwards.
Spectral signature provides most important information for Images Classification.Along with the raising of spatial resolution, have to consider the impact that texture and background are brought.The remotely-sensed data type is different, and the sorting technique that adopts is also different.For example: IKONOS(U.S. Yi Kenuosi satellite) and how much of the high resolving power of SPOT 5HRG(French SPOT-No. 5 satellite), although have high spatial resolution, but when the sorting technique based on pixel spectrum was applied to Images Classification, the benefit that high spatial resolution brings can not compensate far away because having a strong impact on of bringing of the shadow problem that the wide spectrum change on landform and vegetation distributed architecture and the capped soil causes.In this case, the combination of spectral information and texture information can reduce this problem, and is better than far away by the pixel sorter by object or OO sorting algorithm.Yet, in, in the low spatial resolution data because the disappearance of spatial information, it is even more important that spectral information seems.Because mixed pixel can produce some problems in the image in different resolution between low-to-medium altitude, thereby can not process by the pixel sorter.Such as SMA(Sub-Miniature-A, the sub-pixel feature of the parts of images wireless aerial interface) or fuzzy membership information is applied in the Images Classification, and the combination of view data and auxiliary data has become the another kind of approach that improves image classification method.When multi-source data is applied in the sorting technique, no longer applicable such as the parametric classification algorithm of maximum likelihood method.In this case, demand providing a kind of technical scheme that improves the water body extraction accuracy of satellite remote-sensing image urgently.
Summary of the invention
The embodiment of the invention provides a kind of water body extracting method and device of satellite remote-sensing image, to improve the water body extraction accuracy of satellite remote-sensing image.
On the one hand, the embodiment of the invention provides a kind of water body extracting method of satellite remote-sensing image, and the water body extracting method of described satellite remote-sensing image comprises:
Obtain the satellite remote-sensing image data;
Utilize the setting threshold in the default decision tree, the Water-Body Information in the described satellite remote-sensing image data is classified, obtain sorted water body and extract the result.
Optionally, in an embodiment of the present invention, described water body extracts the result and comprises: clear water, contain the water of vegetation and contain the water of silt.
Optionally, in an embodiment of the present invention, the water body extracting method of described satellite remote-sensing image also comprises: described satellite remote-sensing image data are carried out characteristic exponent extract; Sample pixel value in the water body sample that utilization is chosen is carried out statistical study, determines nine spectral signature component threshold values in the setting threshold in the described default decision tree; Utilize described nine spectral signature component threshold values, the Water-Body Information in the described satellite remote-sensing image data is classified, obtain sorted water body and extract the result.
Optionally, in an embodiment of the present invention, described water body sample comprises: deep water, shallow water, fish pond, contain vegetation information water, contain the water of silt information; Described nine spectral signature component threshold values comprise the setting threshold of following information: brightness, green degree, humidity.
Optionally, in an embodiment of the present invention, the water body extracting method of described satellite remote-sensing image also comprises: calculate the grade information component by the SRTM altitude figures, the gradient in the setting threshold in the decision tree that obtains presetting is filtered threshold value; Utilizing described nine spectral signature component threshold values, Water-Body Information in the described satellite remote-sensing image data is classified, after obtaining sorted water body extraction result, utilize the described gradient to filter threshold value, the sorted described water body that obtains is extracted the result carry out gradient filtration, the water body that obtains after the gradient is filtered extracts the result.
On the other hand, the embodiment of the invention provides a kind of water body extraction element of satellite remote-sensing image, and the water body extraction element of described satellite remote-sensing image comprises:
Acquiring unit is used for obtaining the satellite remote-sensing image data;
For the setting threshold that utilizes default decision tree, classifying to the Water-Body Information in the described satellite remote-sensing image data in the decision tree unit, obtains sorted water body and extract the result.
Optionally, in an embodiment of the present invention, described water body extracts the result and comprises: clear water, contain the water of vegetation and contain the water of silt.
Optionally, in an embodiment of the present invention, the water body extraction element of described satellite remote-sensing image also comprises: the characteristic exponent extraction unit is used for that described satellite remote-sensing image data are carried out characteristic exponent and extracts; Sample pixel value in the water body sample that utilization is chosen is carried out statistical study, determines nine spectral signature component threshold values in the setting threshold in the described default decision tree; The decision tree unit is further used for utilizing described nine spectral signature component threshold values, and the Water-Body Information in the described satellite remote-sensing image data is classified, and obtains sorted water body and extracts the result.
Optionally, in an embodiment of the present invention, described water body sample comprises: deep water, shallow water, fish pond, contain vegetation information water, contain the water of silt information; Described nine spectral signature component threshold values comprise the setting threshold of following information: six wave bands of raw video, brightness, green degree, humidity.
Optionally, in an embodiment of the present invention, the water body extraction element of described satellite remote-sensing image also comprises: gradient computing unit, be used for calculating the grade information component by the SRTM altitude figures, the gradient in the setting threshold in the decision tree that obtains presetting is filtered threshold value; The decision tree unit, be further used for utilizing described nine spectral signature component threshold values, Water-Body Information in the described satellite remote-sensing image data is classified, after obtaining sorted water body extraction result, utilize the described gradient to filter threshold value, the sorted described water body that obtains is extracted the result carry out gradient filtration, the water body that obtains after the gradient is filtered extracts the result.
Technique scheme has following beneficial effect: obtain the satellite remote-sensing image data because adopt; Utilize the setting threshold in the default decision tree, Water-Body Information in the described satellite remote-sensing image data is classified, obtain the technological means that sorted water body extracts the result, so have following technique effect: the water body extraction accuracy that has improved satellite remote-sensing image.
Description of drawings
In order to be illustrated more clearly in the embodiment of the invention or technical scheme of the prior art, the below will do to introduce simply to the accompanying drawing of required use in embodiment or the description of the Prior Art, apparently, accompanying drawing in the following describes only is some embodiments of the present invention, for those of ordinary skills, under the prerequisite of not paying creative work, can also obtain according to these accompanying drawings other accompanying drawing.
Fig. 1 is the water body extracting method process flow diagram of a kind of satellite remote-sensing image of the embodiment of the invention;
Fig. 2 is the water body extraction element structural representation of a kind of satellite remote-sensing image of the embodiment of the invention;
Fig. 3 is the water body extraction element structural representation of the another kind of satellite remote-sensing image of the embodiment of the invention;
Fig. 4 is that application example SRTM of the present invention organizes synoptic diagram;
The effective water body extracting method process flow diagram that Fig. 5 provides for application example of the present invention;
Fig. 6 a is the synoptic diagram that application example satellite remote-sensing image of the present invention is the lake;
Fig. 6 b is that application example of the present invention carries out the result schematic diagram that water body extracts to the lake of Fig. 6 a;
Fig. 7 a is the synoptic diagram that application example satellite remote-sensing image of the present invention is the wetland lake;
Fig. 7 b is that application example of the present invention carries out the result schematic diagram that water body extracts to the wetland lake of Fig. 7 a;
Fig. 8 a is the synoptic diagram that application example satellite remote-sensing image of the present invention is the field water body;
Fig. 8 b is application example of the present invention carries out the water body extraction to the field water body of Fig. 8 a result schematic diagram;
Fig. 8 c is the amplification effect synoptic diagram of the local water body in the square frame of Fig. 8 a;
Fig. 8 d is the amplification effect synoptic diagram of the local water body in the square frame of Fig. 8 b.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the invention, the technical scheme in the embodiment of the invention is clearly and completely described, obviously, described embodiment only is the present invention's part embodiment, rather than whole embodiment.Based on the embodiment among the present invention, those of ordinary skills belong to the scope of protection of the invention not making the every other embodiment that obtains under the creative work prerequisite.
The embodiment of the invention can consider to select senior non-parametric classifier, neural network for example, and decision tree is based on evidential reasoning or Knowledge-Based Method.Along with the appearance of digital machine and the exploration that utilizes the intelligent relative process of computer mould personification, accelerated the development of " pattern-recognition " this data analysis technique.Decision tree is widely used at area of pattern recognition as a kind of data mining technology, and be incorporated in the remote sensing image processing, so, simulation expert visual interpretation, set up the expert system of remote sensing image interpretation, realize that the automatic interpretation of image becomes one of main trend of remote sensing image interpretation.
As shown in Figure 1, be the water body extracting method process flow diagram of a kind of satellite remote-sensing image of the embodiment of the invention, the water body extracting method of described satellite remote-sensing image comprises:
101, obtain the satellite remote-sensing image data;
102, utilize setting threshold in the default decision tree, the Water-Body Information in the described satellite remote-sensing image data is classified, obtain sorted water body and extract the result.
Optionally, described water body extracts the result and comprises: clear water, contain the water of vegetation and contain the water of silt.
Optionally, the water body extracting method of described satellite remote-sensing image also comprises: described satellite remote-sensing image data are carried out characteristic exponent extract; Sample pixel value in the water body sample that utilization is chosen is carried out statistical study, determines nine spectral signature component threshold values in the setting threshold in the described default decision tree; Utilize described nine spectral signature component threshold values, the Water-Body Information in the described satellite remote-sensing image data is classified, obtain sorted water body and extract the result.
Optionally, described water body sample comprises: deep water, shallow water, fish pond, contain vegetation information water, contain the water of silt information; Described nine spectral signature component threshold values comprise the setting threshold of following information: six wave bands of raw video, brightness, green degree, humidity.
Optionally, the water body extracting method of described satellite remote-sensing image also comprises: calculate the grade information component by the SRTM altitude figures, the gradient in the setting threshold in the decision tree that obtains presetting is filtered threshold value; Utilizing described nine spectral signature component threshold values, Water-Body Information in the described satellite remote-sensing image data is classified, after obtaining sorted water body extraction result, utilize the described gradient to filter threshold value, the sorted described water body that obtains is extracted the result carry out gradient filtration, the water body that obtains after the gradient is filtered extracts the result.
As shown in Figure 2, be the water body extraction element structural representation of a kind of satellite remote-sensing image of the embodiment of the invention, the water body extraction element of described satellite remote-sensing image comprises:
For the setting threshold that utilizes default decision tree, classifying to the Water-Body Information in the described satellite remote-sensing image data in decision tree unit 22, obtains sorted water body and extract the result.
Optionally, described water body extracts the result and comprises: clear water, contain the water of vegetation and contain the water of silt.
Optionally, as shown in Figure 3, water body extraction element structural representation for the another kind of satellite remote-sensing image of the embodiment of the invention, the water body extraction element of described satellite remote-sensing image is except comprising above-mentioned acquiring unit 21, decision tree unit 22, also comprise: characteristic exponent extraction unit 23 is used for that described satellite remote-sensing image data are carried out characteristic exponent and extracts; Sample pixel value in the water body sample that utilization is chosen is carried out statistical study, determines nine spectral signature component threshold values in the setting threshold in the described default decision tree; Decision tree unit 22 is further used for utilizing described nine spectral signature component threshold values, and the Water-Body Information in the described satellite remote-sensing image data is classified, and obtains sorted water body and extracts the result.Optionally, described water body sample comprises: deep water, shallow water, fish pond, contain vegetation information water, contain the water of silt information; Described nine spectral signature component threshold values comprise the setting threshold of following information: six wave bands of raw video, brightness, green degree, humidity.Optionally, the water body extraction element of described satellite remote-sensing image can also comprise: gradient computing unit 24, be used for calculating the grade information component by the SRTM altitude figures, and the gradient in the setting threshold in the decision tree that obtains presetting is filtered threshold value; Decision tree unit 22, be further used for utilizing described nine spectral signature component threshold values, Water-Body Information in the described satellite remote-sensing image data is classified, after obtaining sorted water body extraction result, utilize the described gradient to filter threshold value, the sorted described water body that obtains is extracted the result carry out gradient filtration, the water body that obtains after the gradient is filtered extracts the result.
Embodiment of the invention said method or device technique scheme have following beneficial effect: obtain the satellite remote-sensing image data because adopt; Utilize the setting threshold in the default decision tree, Water-Body Information in the described satellite remote-sensing image data is classified, obtain the technological means that sorted water body extracts the result, so have following technique effect: the water body extraction accuracy that has improved satellite remote-sensing image.
The thought that adopts many characteristics to merge in the described scheme of the following application example of the present invention is applied to characteristic exponent extraction, grade information etc. and provides the several data feature for decision tree classification.
The described method of application example of the present invention is mainly for the Landsat(Landsat) the satellite data proposition, use spatial resolution and be 90 meters SRTM(Shuttle Radar Topography Mission, by American Space General Administration (NASA) and State Bureau of Surveying and Mapping of Ministry of National Defence (NIMA) combined measurement) digital elevation model (DEM, Digital Elevation Model) data are converted to gradient feature, simultaneously the Landsat satellite data is carried out characteristic exponent and extract, for decision tree classification provides nine spectral signature components.
The Landsat of U.S. NASA (Landsat) plan has been launched 7 (the 6th abortive launch) since the 23 days July in 1972.Landsat1-4 all lost efficacy in succession at present, and Landsat 5 is still at the operation of exceeding the time limit (from emission on March 1st, 1984 so far).Landsat7 launched on April 15th, 1999.Therefore the Landsat series satellite data of using at present mainly is the TM(thematic mapper of Landsat5, the special topic imager) the ETM+(Enhanced Thematic Mapper of data and Landsat7, enhancement mode special topic imager) data, the band class information of two kinds of data is shown in following table 1 and table 2:
| Wave band | Wavelength coverage (μ m) | Resolution |
| 1 | 0.45～0.53 | 30 meters |
| 2 | 0.52～0.60 | 30 |
| 3 | 0.63～0.69 | 30 meters |
| 4 | 0.76～0.90 | 30 meters |
| 5 | 1.55～1.75 | 30 meters |
| 6 | 10.40～12.50 | 120〉rice |
| 7 | 2.08～2.35 | 30 meters |
Table 1TM data parameters
| Wave band | Wavelength coverage (μ m) | Ground resolution |
| 1 | 0.45～0.515 | 30 meters |
| 2 | 0.525～0.605 | 30 |
| 3 | 0.63～0.690 | 30 meters |
| 4 | 0.75～0.90 | 30 meters |
| 5 | 1.55～1.75 | 30 meters |
| 6 | 10.40～12.50 | 60 meters |
| 7 | 2.09～2.35 | 30 meters |
| 8 | 0.52～0.90 | 15 meters |
Table 2ETM+ data parameters
SRTM(Shuttle Radar Topography Mission), by American Space General Administration (NASA) and State Bureau of Surveying and Mapping of Ministry of National Defence (NIMA) combined measurement.On February 11st, 2000, carry the SRTM system on " striving " number space shuttle of U.S.'s emission, carried out altogether 222 hours 23 minutes data collection task, obtain north latitude 60 and spend to the radar image data of the total area above 1.19 hundred million square kilometres between south latitude 60 degree, cover the top of the earth more than 80%.About 9.8 terabytes of the data volume of the radar image of SRTM system acquisition are processed through the data more than 2 years, have made digital terrain elevation model (DEM), i.e. present SRTM landform product data.This data product began to publish in 2003, the many revisions of experience, and present data revision version is the V4.1 version.This version is by CIAT(CIAT) the SRTM terrain data that utilizes new interpolation algorithm to obtain, the method has better been filled up the data void holes of SRTM 90.
The Method of Data Organization of SRTM is: per 5 degree longitude and latitude grids are divided a file, and being divided into is 24 row (60 to 60 degree) and 72 row (180 to 180 degree).The file designation rule is srtm_XX_YY.zip, and XX represents columns (01-72), and YY represents line number (01-24).As shown in Figure 4, organize synoptic diagram for application example SRTM of the present invention:
As shown in Figure 5, be the effective water body extracting method process flow diagram that application example of the present invention provides, the step that comprises is as follows:
501, obtain LANDSAT TM/ETM+ image
Analyze the raw video data, according to the form of expression of water body reflectivity curve behind the atmospheric correction, water body is classified, generally can be divided into three types: clear water, contain the water of vegetation and contain the water of silt.
Data are prepared: at first the raw video data are carried out characteristic exponent and extract, nine kinds of spectral information sources are provided, comprising: six wave bands, brightness, green degree and the humidity information of raw video; Then calculate the grade information component by the SRTM altitude figures.
Choose the water body sample according to comprehensive typical principle, comprise deep water, shallow water, fish pond, contain vegetation information water, contain the water of silt information etc.
Sample pixel value is carried out statistical study, definite threshold.
It is as follows that water body is extracted in the implementation procedure of passing through decision tree in the experiment:
502, judge whether Band2〉Band5, in this way, then turn 503; Otherwise, turn 506;
The extraction of 503-505, clear water part, judge whether to satisfy impose a condition into:
Band2>Band5
Band2<delta_b2
TC3>delta_tc3
Band6<delta_b6
In the following formula, the separation condition of clear water and other water bodys be Second Wave segment value (Band2) greater than the value of the 5th wave band (Band5), then determine the threshold value of correlated components according to statistical information.Wherein TC3 is the three-component (humidity) after characteristic exponent is extracted, delta_b2, and delta_tc3, delta_b6 are artificial setting threshold, recommend respectively to be made as 3100 ,-100,600.
If satisfy above condition, then be clear water, then turn 513; Otherwise, turn 505, not clear water, be other, flow process finishes.
506-509, contain chlorophyllous water body and extract, judge whether to satisfy impose a condition into:
Band2<=Band5
Band4 is maximum
Band4<delta_b4
TC2<delta_tc2
TC3>delta_tc3
Band5<delta_b5
In the following formula, the second wave band (Band2) value is condition precedent less than the value of the 5th wave band (Band5), maximum the second Rule of judgment of Band4＜delta_b4 and Band4 secondly, and then determine the threshold value of correlated components according to statistical information.Wherein TC2 is the second component (green degree) after characteristic exponent is extracted, delta_b4, and delta_b5, delta_tc2, delta_tc3 are artificial setting threshold, recommend respectively to be made as: 500,500,200 ,-300.
If satisfy above condition, then for containing chlorophyllous water, then turn 513; Otherwise, turn 509, not to contain chlorophyllous water, be other, flow process finishes.
The water body that 510-512, sediment charge are high extracts, judge whether to satisfy impose a condition into:
Band2<=Band5
Band4＜delta_b4 (no)
Band4 maximum (no)
TC1<delta_tc1
TC2<delta_tc2
TC3>delta_tc3
In the following formula, Band4＜delta_b4 and Band4 are to the maximum when no, determine the threshold value of correlated components according to statistical information, wherein, TC1 is the first component (brightness) after characteristic exponent is extracted, delta_b4, delta_tc1, delta_tc2, delta_tc3 is artificial setting threshold, recommends respectively to be made as: 500,1400,300 ,-300.
If satisfy above condition, then be the high water of sediment charge, then turn 513; Otherwise, turn 512, not the high water of sediment charge, be other, flow process finishes.
513, the gradient is filtered, and uses the gradient to filter threshold value three kinds of water bodys that extract are filtered;
514, the gradient that keeps after obtaining the gradient and filtering is extracted the result less than 10 ° water body.
Shown in Fig. 6 a, the synoptic diagram for application example satellite remote-sensing image of the present invention is the lake shown in Fig. 6 b, carries out the result schematic diagram of water body extraction to the lake of Fig. 6 a for application example of the present invention.Fig. 6 a is the inland lake that TM image 543 band combinations show, Fig. 6 b is the lake effect of extracting by decision tree, can find out that whole lake is all extracted.Because area of lake is larger, water is darker, so be black display at remote sensing image, can think that water body in lake is clear water.
Shown in Fig. 7 a, the synoptic diagram for application example satellite remote-sensing image of the present invention is the wetland lake shown in Fig. 7 b, carries out the result schematic diagram of water body extraction to the wetland lake of Fig. 7 a for application example of the present invention.Fig. 7 a is the wetland lake that TM image 543 band combinations show, can see that by image water-outlet body presents green, illustrate that vegetation is more, namely chlorophyll content is a lot, Fig. 7 b is the design sketch by this wetland lake of decision tree extraction, and the water body part is all extracted basically.So utilize decision tree to extract the higher water body successful of chlorophyll content by setting threshold.
Shown in Fig. 8 a, the synoptic diagram for application example satellite remote-sensing image of the present invention is the field water body shown in Fig. 8 b, carries out the result schematic diagram of water body extraction to the field water body of Fig. 8 a for application example of the present invention.Fig. 8 c is the amplification effect synoptic diagram of the local water body in the square frame of Fig. 8 a.Fig. 8 d is the amplification effect synoptic diagram of the local water body in the square frame of Fig. 8 b.Fig. 8 a is the field water body that TM image 543 band combinations show, show in the way that water body is blue, because water body is more shallow, and the more cause of sediment charge, Fig. 8 b is the water body effect of extracting by decision tree, Fig. 8 c and Fig. 8 d are respectively the amplification effect of local water body, can see water-outlet body extraction clear-cut, successful.
The traditional decision-tree of application example of the present invention has been used nine characteristics of variables after the characteristic exponent extraction, for providing, the foundation of decision tree enriches effective attribute information, improve the extraction accuracy of water body by the setting to threshold value in a plurality of characteristic variables, the impact of shade has effectively been eliminated in the application of filtering by the gradient simultaneously, especially in the more situation of massif shade, effect is more obvious.But because the radiant correction data that provide are atmospheric envelope top reflectivity, rather than real Reflectivity for Growing Season, can't carry out real normalization to all data, above-mentioned threshold value can also be finely tuned for different images in concrete the application.
Application example of the present invention provides a kind of effective water body extracting method based on the Landsat satellite image.The method takes full advantage of the multiple auxiliary datas such as spectral information, grade information increases the data source that is beneficial to information extraction, the form of expression according to the water body reflectivity curve behind the atmospheric correction, and come setting threshold by the statistical study to sample pixel value, respectively various types of water bodys are extracted.Show that by experiment the method information extraction precision is high, the improvement of earth's surface information extracting method provides reference in the geographical national conditions monitoring project that can be about to carry out for China.
Those skilled in the art can also recognize the various illustrative components, blocks (illustrative logical block) that the embodiment of the invention is listed, the unit, and step can pass through electronic hardware, computer software, or both combinations realize.Be the clear replaceability (interchangeability) of showing hardware and software, above-mentioned various illustrative components (illustrative components), unit and step have been described their function generally.Such function is to realize depending on the designing requirement of specific application and whole system by hardware or software.Those skilled in the art can be for every kind of specific application, and can make ins all sorts of ways realizes described function, but this realization should not be understood to exceed the scope of embodiment of the invention protection.
Various illustrative logical block described in the embodiment of the invention, or the unit can pass through general processor, digital signal processor, special IC (ASIC), field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or the design of above-mentioned any combination realizes or operates described function.General processor can be microprocessor, and alternatively, this general processor also can be any traditional processor, controller, microcontroller or state machine.Processor also can realize by the combination of calculation element, for example digital signal processor and microprocessor, multi-microprocessor, Digital Signal Processor Core of one or more microprocessors associatings, or any other similarly configuration realize.
Method described in the embodiment of the invention or the step of algorithm can directly embed hardware, the software module of processor execution or the two combination.Software module can be stored in the storage medium of other arbitrary form in RAM storer, flash memory, ROM storer, eprom memory, eeprom memory, register, hard disk, moveable magnetic disc, CD-ROM or this area.Exemplarily, storage medium can be connected with processor so that processor can be from storage medium reading information, and can deposit write information to storage medium.Alternatively, storage medium can also be integrated in the processor.Processor and storage medium can be arranged among the ASIC, and ASIC can be arranged in the user terminal.Alternatively, processor and storage medium also can be arranged in the different parts in the user terminal.
In one or more exemplary designs, the described above-mentioned functions of the embodiment of the invention can realize in hardware, software, firmware or this three's combination in any.If realize in software, these functions can be stored on the medium with computer-readable, or are transmitted on the medium of computer-readable with one or more instructions or code form.The computer-readable medium comprises the computer storage medium and is convenient to so that allow computer program transfer to other local telecommunication media from a place.Storage medium can be the useable medium that any general or special computer can access.For example, such computer readable media can include but not limited to RAM, ROM, EEPROM, CD-ROM or other optical disc storage, disk storage or other magnetic storage device, or other anyly can be used for carrying or storage can be read by general or special computer or general or special processor the program code of form with instruction or data structure and other medium.In addition, any connection can suitably be defined as the computer-readable medium, for example, if software is by a concentric cable, fiber optic cables, twisted-pair feeder, Digital Subscriber Line (DSL) or also being comprised in the defined computer-readable medium with wireless way for transmittings such as infrared, wireless and microwave from a web-site, server or other remote resource.Described video disc (disk) and disk (disc) comprise Zip disk, radium-shine dish, CD, DVD, floppy disk and Blu-ray Disc, and disk is usually with the magnetic duplication data, and video disc carries out the optical reproduction data with laser usually.Above-mentioned combination also can be included in the computer-readable medium.
Above-described embodiment; purpose of the present invention, technical scheme and beneficial effect are further described; institute is understood that; the above only is the specific embodiment of the present invention; the protection domain that is not intended to limit the present invention; within the spirit and principles in the present invention all, any modification of making, be equal to replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (10)
1. the water body extracting method of a satellite remote-sensing image is characterized in that, the water body extracting method of described satellite remote-sensing image comprises:
Obtain the satellite remote-sensing image data;
Utilize the setting threshold in the default decision tree, the Water-Body Information in the described satellite remote-sensing image data is classified, obtain sorted water body and extract the result.
2. the water body extracting method of satellite remote-sensing image as claimed in claim 1 is characterized in that, described water body extracts the result and comprises: clear water, contain the water of vegetation and contain the water of silt.
3. the water body extracting method of satellite remote-sensing image as claimed in claim 2 is characterized in that the water body extracting method of described satellite remote-sensing image also comprises:
Described satellite remote-sensing image data are carried out characteristic exponent to be extracted;
Sample pixel value in the water body sample that utilization is chosen is carried out statistical study, determines nine spectral signature component threshold values in the setting threshold in the described default decision tree;
Utilize described nine spectral signature component threshold values, the Water-Body Information in the described satellite remote-sensing image data is classified, obtain sorted water body and extract the result.
4. the water body extracting method of satellite remote-sensing image as claimed in claim 3 is characterized in that described water body sample comprises: deep water, shallow water, fish pond, contain vegetation information water, contain the water of silt information; Described nine spectral signature component threshold values comprise the setting threshold of following information: six wave bands of raw video, brightness, green degree, humidity.
5. the water body extracting method of satellite remote-sensing image as claimed in claim 4 is characterized in that the water body extracting method of described satellite remote-sensing image also comprises:
Calculate the grade information component by the SRTM altitude figures, the gradient in the setting threshold in the decision tree that obtains presetting is filtered threshold value;
Utilizing described nine spectral signature component threshold values, Water-Body Information in the described satellite remote-sensing image data is classified, after obtaining sorted water body extraction result, utilize the described gradient to filter threshold value, the sorted described water body that obtains is extracted the result carry out gradient filtration, the water body that obtains after the gradient is filtered extracts the result.
6. the water body extraction element of a satellite remote-sensing image is characterized in that, the water body extraction element of described satellite remote-sensing image comprises:
Acquiring unit is used for obtaining the satellite remote-sensing image data;
For the setting threshold that utilizes default decision tree, classifying to the Water-Body Information in the described satellite remote-sensing image data in the decision tree unit, obtains sorted water body and extract the result.
7. the water body extraction element of satellite remote-sensing image as claimed in claim 6 is characterized in that, described water body extracts the result and comprises: clear water, contain the water of vegetation and contain the water of silt.
8. the water body extraction element of satellite remote-sensing image as claimed in claim 7 is characterized in that the water body extraction element of described satellite remote-sensing image also comprises:
The characteristic exponent extraction unit is used for that described satellite remote-sensing image data are carried out characteristic exponent and extracts; Sample pixel value in the water body sample that utilization is chosen is carried out statistical study, determines nine spectral signature component threshold values in the setting threshold in the described default decision tree;
The decision tree unit is further used for utilizing described nine spectral signature component threshold values, and the Water-Body Information in the described satellite remote-sensing image data is classified, and obtains sorted water body and extracts the result.
9. the water body extraction element of satellite remote-sensing image as claimed in claim 8 is characterized in that described water body sample comprises: deep water, shallow water, fish pond, contain vegetation information water, contain the water of silt information; Described nine spectral signature component threshold values comprise the setting threshold of following information: six wave bands of raw video, brightness, green degree, humidity.
10. the water body extraction element of satellite remote-sensing image as claimed in claim 9 is characterized in that the water body extraction element of described satellite remote-sensing image also comprises:
Gradient computing unit is used for calculating the grade information component by the SRTM altitude figures, and the gradient in the setting threshold in the decision tree that obtains presetting is filtered threshold value;
The decision tree unit, be further used for utilizing described nine spectral signature component threshold values, Water-Body Information in the described satellite remote-sensing image data is classified, after obtaining sorted water body extraction result, utilize the described gradient to filter threshold value, the sorted described water body that obtains is extracted the result carry out gradient filtration, the water body that obtains after the gradient is filtered extracts the result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210297493.0A CN102855494B (en) | 2012-08-20 | 2012-08-20 | A kind of Clean water withdraw method of satellite remote-sensing image and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210297493.0A CN102855494B (en) | 2012-08-20 | 2012-08-20 | A kind of Clean water withdraw method of satellite remote-sensing image and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102855494A true CN102855494A (en) | 2013-01-02 |
| CN102855494B CN102855494B (en) | 2015-08-12 |
Family
ID=47402070
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210297493.0A Active CN102855494B (en) | 2012-08-20 | 2012-08-20 | A kind of Clean water withdraw method of satellite remote-sensing image and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102855494B (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103761717A (en) * | 2014-01-26 | 2014-04-30 | 河海大学 | City water extraction method based on panchromatic remote sensing image |
| CN104318051A (en) * | 2014-09-15 | 2015-01-28 | 中国水利水电科学研究院 | Rule-based remote-sensing automatic extraction system and method of wide-range water body information |
| CN105184252A (en) * | 2015-08-31 | 2015-12-23 | 中国科学院遥感与数字地球研究所 | Water bloom identification method and device based on high-spatial-resolution image |
| CN105279519A (en) * | 2015-09-24 | 2016-01-27 | 四川航天系统工程研究所 | Remote sensing image water body extraction method and system based on cooperative training semi-supervised learning |
| CN105761286A (en) * | 2016-02-29 | 2016-07-13 | 环境保护部卫星环境应用中心 | Water color exception object extraction method and system based on multi-spectral remote sensing image |
| CN106599902A (en) * | 2016-11-04 | 2017-04-26 | 浙江大学 | Sugar crystal classification and recognition and crystallization quality control method based on image |
| CN107025467A (en) * | 2017-05-09 | 2017-08-08 | 环境保护部卫星环境应用中心 | A kind of method for building up and device of water body disaggregated model |
| CN107271367A (en) * | 2017-05-05 | 2017-10-20 | 北京师范大学 | A kind of identifying water boy method and device |
| CN108007899A (en) * | 2017-11-29 | 2018-05-08 | 南威软件股份有限公司 | A kind of spissatus shadow detection method based on TM images |
| CN109325973A (en) * | 2018-11-19 | 2019-02-12 | 珠江水利委员会珠江水利科学研究院 | A kind of city river network water body atmospheric correction method |
| CN109472304A (en) * | 2018-10-30 | 2019-03-15 | 厦门理工学院 | Tree species classification method, device and equipment based on SAR Yu optical remote sensing time series data |
| CN111199236A (en) * | 2020-01-06 | 2020-05-26 | 国家卫星气象中心(国家空间天气监测预警中心) | Method, equipment and medium for extracting water body in satellite image by using decision tree |
| CN113111816A (en) * | 2021-04-20 | 2021-07-13 | 中国水利水电科学研究院 | River landform unit classification and identification method |
| CN113203399A (en) * | 2021-04-16 | 2021-08-03 | 青岛地质工程勘察院(青岛地质勘查开发局) | Underground space resource quantity analysis method |
| US11226431B2 (en) | 2017-07-26 | 2022-01-18 | Xinjiang Goldwind Science & Technology Co., Ltd. | Method and device for filling invalid regions of terrain elevation model data |
| CN117523321A (en) * | 2024-01-03 | 2024-02-06 | 自然资源部第二海洋研究所 | Optical shallow water classification method based on passive remote sensing spectral image application neural network |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102054274A (en) * | 2010-12-01 | 2011-05-11 | 南京大学 | Method for full automatic extraction of water remote sensing information in coastal zone |
| CN102540169A (en) * | 2012-01-11 | 2012-07-04 | 武汉大学 | Quality evaluation method for water body mapping product based on remote sensing image |
-
2012
- 2012-08-20 CN CN201210297493.0A patent/CN102855494B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102054274A (en) * | 2010-12-01 | 2011-05-11 | 南京大学 | Method for full automatic extraction of water remote sensing information in coastal zone |
| CN102540169A (en) * | 2012-01-11 | 2012-07-04 | 武汉大学 | Quality evaluation method for water body mapping product based on remote sensing image |
Non-Patent Citations (1)
| Title |
|---|
| 邓劲松，等: "决策树方法从SPOT卫星影像中自动提取水体信息研究", 《浙江大学学报(农业与生命科学版)》, no. 302, 31 December 2005 (2005-12-31), pages 171 - 174 * |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103761717A (en) * | 2014-01-26 | 2014-04-30 | 河海大学 | City water extraction method based on panchromatic remote sensing image |
| CN104318051A (en) * | 2014-09-15 | 2015-01-28 | 中国水利水电科学研究院 | Rule-based remote-sensing automatic extraction system and method of wide-range water body information |
| CN104318051B (en) * | 2014-09-15 | 2017-06-16 | 中国水利水电科学研究院 | The rule-based remote sensing of Water-Body Information on a large scale automatic extracting system and method |
| CN105184252A (en) * | 2015-08-31 | 2015-12-23 | 中国科学院遥感与数字地球研究所 | Water bloom identification method and device based on high-spatial-resolution image |
| CN105184252B (en) * | 2015-08-31 | 2019-01-22 | 中国科学院遥感与数字地球研究所 | A kind of wawter bloom recognition methods and device based on high spatial resolution images |
| CN105279519B (en) * | 2015-09-24 | 2018-09-21 | 四川航天系统工程研究所 | Remote sensing image Clean water withdraw method and system based on coorinated training semi-supervised learning |
| CN105279519A (en) * | 2015-09-24 | 2016-01-27 | 四川航天系统工程研究所 | Remote sensing image water body extraction method and system based on cooperative training semi-supervised learning |
| CN105761286A (en) * | 2016-02-29 | 2016-07-13 | 环境保护部卫星环境应用中心 | Water color exception object extraction method and system based on multi-spectral remote sensing image |
| CN106599902A (en) * | 2016-11-04 | 2017-04-26 | 浙江大学 | Sugar crystal classification and recognition and crystallization quality control method based on image |
| CN106599902B (en) * | 2016-11-04 | 2019-09-24 | 浙江大学 | A kind of sugar crystal Classification and Identification and crystalline quality control method based on image |
| CN107271367A (en) * | 2017-05-05 | 2017-10-20 | 北京师范大学 | A kind of identifying water boy method and device |
| CN107025467A (en) * | 2017-05-09 | 2017-08-08 | 环境保护部卫星环境应用中心 | A kind of method for building up and device of water body disaggregated model |
| US11226431B2 (en) | 2017-07-26 | 2022-01-18 | Xinjiang Goldwind Science & Technology Co., Ltd. | Method and device for filling invalid regions of terrain elevation model data |
| CN108007899A (en) * | 2017-11-29 | 2018-05-08 | 南威软件股份有限公司 | A kind of spissatus shadow detection method based on TM images |
| CN109472304B (en) * | 2018-10-30 | 2021-04-16 | 厦门理工学院 | Tree species classification method, device and equipment based on SAR and optical remote sensing time sequence data |
| CN109472304A (en) * | 2018-10-30 | 2019-03-15 | 厦门理工学院 | Tree species classification method, device and equipment based on SAR Yu optical remote sensing time series data |
| CN109325973A (en) * | 2018-11-19 | 2019-02-12 | 珠江水利委员会珠江水利科学研究院 | A kind of city river network water body atmospheric correction method |
| CN109325973B (en) * | 2018-11-19 | 2020-11-24 | 珠江水利委员会珠江水利科学研究院 | Urban river network area water body atmosphere correction method |
| CN111199236A (en) * | 2020-01-06 | 2020-05-26 | 国家卫星气象中心(国家空间天气监测预警中心) | Method, equipment and medium for extracting water body in satellite image by using decision tree |
| CN113203399A (en) * | 2021-04-16 | 2021-08-03 | 青岛地质工程勘察院(青岛地质勘查开发局) | Underground space resource quantity analysis method |
| CN113111816A (en) * | 2021-04-20 | 2021-07-13 | 中国水利水电科学研究院 | River landform unit classification and identification method |
| CN113111816B (en) * | 2021-04-20 | 2021-09-28 | 中国水利水电科学研究院 | River landform unit classification and identification method |
| CN117523321A (en) * | 2024-01-03 | 2024-02-06 | 自然资源部第二海洋研究所 | Optical shallow water classification method based on passive remote sensing spectral image application neural network |
| CN117523321B (en) * | 2024-01-03 | 2024-04-09 | 自然资源部第二海洋研究所 | Optical shallow water classification method based on passive remote sensing spectral image application neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102855494B (en) | 2015-08-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102855494B (en) | A kind of Clean water withdraw method of satellite remote-sensing image and device | |
| Keshtkar et al. | Land-cover classification and analysis of change using machine-learning classifiers and multi-temporal remote sensing imagery | |
| Xia et al. | Automatic extraction of aquaculture ponds based on Google Earth Engine | |
| Aksoy et al. | Landslide identification and classification by object-based image analysis and fuzzy logic: An example from the Azdavay region (Kastamonu, Turkey) | |
| Eid et al. | Coastal wetland vegetation features and digital Change Detection Mapping based on remotely sensed imagery: El-Burullus Lake, Egypt | |
| Zhang et al. | GWL_FCS30: global 30 m wetland map with fine classification system using multi-sourced and time-series remote sensing imagery in 2020 | |
| Lemenkova | ISO Cluster classifier by ArcGIS for unsupervised classification of the Landsat TM image of Reykjavík | |
| Șerban et al. | Mapping thermokarst lakes and ponds across permafrost landscapes in the Headwater Area of Yellow River on northeastern Qinghai-Tibet Plateau | |
| Philippe et al. | Assessing Forest cover change and deforestation hot-spots in the north Kivu Province, DR-Congo using remote sensing and GIS | |
| Yang et al. | The spatial distribution and expansion of subsided wetlands induced by underground coal mining in eastern China | |
| Wang et al. | Object-based change detection for vegetation disturbance and recovery using Landsat time series | |
| Wang et al. | Crops planting structure and karst rocky desertification analysis by Sentinel-1 data | |
| Magee | Segmentation, object-oriented applications for remote sensing land cover and land use classification | |
| Omarzadeh et al. | Evaluation of changes in the Forest Environment in Guilan Province using a combination of Remote Sensing Data | |
| Tretyakov et al. | Features of interpretation of plant association of National Natural Park Slobozhanskiy using Landsat 8 satellite data | |
| Harshana et al. | The Implementation of the Mangrove Quality Index: A Way to Overcome Overestimation and Classification Concerns in Detecting Mangrove Forest Cover | |
| Bonini et al. | Semiautomatic inventory and geomorphological characterization of mass movements using high-resolution images and open-source software in the Ribeira de Iguape Valley, Brazil | |
| Coulibaly et al. | Mapping aboveground forest biomass from IKONOS satellite image and multi-source geospatial data using neural networks and a Kriging interpolation | |
| Elshorbagy et al. | Rice area inter annual variation through a remote sensing based mapping algorithm | |
| Akyol | Mapping and quantifying early tidal wetland evolution using remotely piloted aircraft system imagery and object-based image analysis | |
| delos Santos et al. | Assessment of Mangrove Colonization of Aquaculture Ponds Through Satellite Image Analysis: Implications for Mangrove Management | |
| CN115019184B (en) | Remote-sensing-image-based stony desertification degree automatic grading method and device | |
| Blasch | Multitemporal soil pattern analysis for organic matter estimation at croplands using multispectral satellite data | |
| Mukumbuta et al. | A comparison between three legacy soil maps of Zambia at national scale: The spatial patterns of legend units and their relation to soil properties | |
| Nanda et al. | SVM and OBIA based Comparative Analysis on LANDSAT Multi Temporal Data for Wetland Mapping |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |