CN111539318B - Red ground object extraction method, device, storage medium and system - Google Patents
Red ground object extraction method, device, storage medium and system Download PDFInfo
- Publication number
- CN111539318B CN111539318B CN202010321128.3A CN202010321128A CN111539318B CN 111539318 B CN111539318 B CN 111539318B CN 202010321128 A CN202010321128 A CN 202010321128A CN 111539318 B CN111539318 B CN 111539318B
- Authority
- CN
- China
- Prior art keywords
- red
- image
- ground
- new
- extracting
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/176—Urban or other man-made structures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the field of remote sensing technology application, in particular to a method, a device, a storage medium and a system for extracting red surface features. The method comprises the steps of respectively collecting a ground object sample with a certain pixel number for each ground object in the ground surface reflection characteristic value image; fitting a reflection spectrum curve of a typical feature by using the pixel mean value of the feature sample; analyzing the difference of the reflection characteristic values of the red ground object and other color ground objects in the reflection spectrum curve, and constructing and extracting a new spectrum index of the red ground object according to the analysis result; and setting a threshold range for extracting the red ground objects according to the new spectral index, and extracting the red ground objects in the image to be detected through the threshold range. According to the method, the spectral index for effectively extracting the red ground objects is constructed through operation and positive and negative processing between key wave bands, and the red ground objects in the images can be detected and extracted more conveniently through a threshold value method; the method can effectively extract the red ground objects in the image, and has better detection effect and higher precision compared with a simple wave band threshold value method.
Description
Technical Field
The invention relates to the field of remote sensing technology application, in particular to a method, a device, a storage medium and a system for extracting red surface features.
Background
The remote sensing image recognition of the ground object is an important basis for monitoring regional environment change, the red ground object is a common ground object in the image (for example, a building with a red roof in a high-resolution urban image), the number of the red ground objects is large, the distribution is wide, and the red ground object is one of important targets for monitoring. Currently, a specific effective method for detecting only red ground objects is lacked. The red ground objects in the urban images can be detected and extracted to a certain extent by an image classification method, a band threshold method and a simple inter-spectrum operation threshold method, but the effects on speed and precision are poor. The classification method needs to determine the types of ground features, select training samples of different types of ground features, perform classification, perform non-red ground feature masking and other steps to finally obtain the red ground features in the images, and has the disadvantages of complex process, more time consumption and no convenience in extraction of single-color ground features; the wave band threshold value method and the simple spectrum operation threshold value method are easy to mistakenly extract the ground objects with high reflection in the red light wave band into red ground objects, the conventionally adopted threshold value method is low in precision, and the extraction result is not stable.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a red ground object extraction method, a red ground object extraction device, a red ground object extraction storage medium and a red ground object extraction system.
In order to achieve the above object, a first aspect of the present invention provides a red feature extraction method, including the following steps:
respectively collecting surface feature samples with certain pixel numbers for each surface feature in the surface reflection characteristic value image;
fitting a reflection spectrum curve of a typical feature by using the pixel mean value of the feature sample;
analyzing the difference of the reflection characteristic values of the red ground object and other color ground objects in the reflection spectrum curve, and constructing and extracting a new spectrum index of the red ground object according to the analysis result;
and setting a threshold range for extracting the red ground objects according to the new spectral index, and extracting the red ground objects in the image to be detected through the threshold range.
A second aspect of the present invention provides a red feature extraction apparatus, including a processor, an input device, an output device, and a memory, where the processor, the input device, the output device, and the memory are connected to each other, where the memory is used to store a computer program, and the computer program includes program instructions, and the processor is configured to call the program instructions to execute the method according to the first aspect of the present invention.
A third aspect of the invention proposes a computer-readable storage medium having stored thereon a computer program comprising program instructions which, when executed by a processor, cause the processor to carry out the method as described in the first aspect of the invention.
The fourth aspect of the invention provides a red ground object extraction system, which comprises a terminal device and a red ground object extraction device; the terminal device is in communication connection with the red feature extraction means, which performs the method as described in the first aspect of the invention.
The invention has the beneficial effects that:
(1) According to the method, through the sum and difference operation among key wave bands, the characteristic images are accumulated and subjected to positive and negative processing, the red ground feature information is enhanced in the new characteristics, the other color ground feature information is weakened, a new spectral index capable of effectively extracting the red ground features is created, and the red ground features in the images are favorably detected and extracted through a threshold method;
(2) The method can effectively extract the red ground objects in the image, and has the advantages of simple, convenient and quick detection process for the ground objects compared with a classification method, good detection effect and high precision compared with a simple wave band threshold value method.
Drawings
FIG. 1 is a flow chart of a red feature extraction method according to a first embodiment of the present invention;
FIG. 2 is a surface reflection eigenvalue image of a first embodiment of the present invention;
FIG. 3 is a reflection spectrum plot of a first embodiment of the present invention;
FIG. 4 is a graph of the new spectral index for the first embodiment of the present invention;
FIG. 5 is a diagram illustrating a result of detecting a red feature according to the first embodiment of the present invention;
FIG. 6 is a schematic view of a red soil feature extraction device according to a second embodiment of the present invention;
FIG. 7 is a block diagram of a red feature extraction system according to a fourth embodiment of the present invention.
Detailed Description
Specific embodiments of the present invention will be described in detail below, and it should be noted that the embodiments described herein are only for illustration and are not intended to limit the present invention. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. However, it will be apparent to one of ordinary skill in the art that: it is not necessary to employ these specific details to practice the present invention. In other instances, well-known circuits, software, or methods have not been described in detail so as not to obscure the present invention.
Throughout the specification, reference to "one embodiment," "an embodiment," "one example," or "an example" means: the particular features, structures, or characteristics described in connection with the embodiment or example are included in at least one embodiment of the invention. Thus, the appearances of the phrases "in one embodiment," "in an embodiment," "one example" or "an example" in various places throughout this specification are not necessarily all referring to the same embodiment or example. Furthermore, the particular features, structures, or characteristics may be combined in any suitable combination and/or sub-combination in one or more embodiments or examples. Further, those of ordinary skill in the art will appreciate that the illustrations provided herein are for illustrative purposes and are not necessarily drawn to scale.
Example one
Referring to fig. 1, a method for extracting red ground objects according to a first embodiment of the present invention includes the following steps:
s1: and preprocessing the image to be detected to obtain the earth surface reflection characteristic value image without atmospheric influence. In this embodiment, the image to be detected is an 8-band WorldView-2 image (see Table 1 for specific parameters); the image is guided into ENVI4.5 software for radiation calibration, fusion and atmospheric correction, and then a test area (the area is 2.45km2) is cut out, namely the earth surface reflection characteristic value image (see figure 2 specifically) after atmospheric influence can be removed, interference can be avoided as far as possible through the operation, and the detection precision can be effectively improved.
Table 1: worldView-2 image data parameters
S2: and respectively collecting a ground object sample with a certain pixel number for each ground object in the ground surface reflection characteristic value image. Specifically, samples with certain pixel numbers are respectively collected for a red roof, a white roof, a blue roof, a cyan roof, a gray ground feature roof, vegetation, shadows and the like in a WorldView-2 image.
S3: and fitting a reflection spectrum curve of a typical feature by using the pixel average value of the feature sample (see figure 3 in particular). It should be further noted that the fitting of the reflection spectrum curve by using the pixel mean value can adopt the prior art, and will not be described herein again.
S4: and analyzing the difference of the reflection characteristic values of the red ground object and other color ground objects in the reflection spectrum curve, and constructing and extracting a new spectrum index of the red ground object according to an analysis result. Specifically, the spectral reflectance characteristic value difference between the Red feature and the other color features is analyzed in the reflectance Spectrum curve, the Red feature information is enhanced and the other color features information is weakened by using the operation forms of the sum, difference, multiplication and the like of the characteristic wave bands, and a new spectral Index RGOSI (Red group Object spectral Index) which can extract the Red feature by a threshold method is constructed (see fig. 4 specifically).
It should be further explained that, when constructing a new spectral index for extracting red features, the following sub-steps are specifically included:
s41: and generating a new characteristic image I and a new characteristic image II for enhancing the red ground feature information and weakening the other color ground feature information according to the reflection spectrum curve.
In this embodiment, the new characteristic image i is a new characteristic image i, i.e., b4+ b5+ b6, which is generated by finding out, from fig. 3, bands in which the reflection characteristic value of the red feature is large (information is prominent) and the reflection characteristic values of most other features are not as large as the reflection characteristic value of the red feature, and adding these bands to fully enhance the red feature information and less enhance the other-color feature information.
In this embodiment, the new characteristic image ii is obtained by finding out a band that can significantly enhance the red feature information by subtracting two bands from each other, and can reduce or less enhance the other bands of the red feature information from fig. 3, and finding out bands satisfying the above conditions, and obtaining the new characteristic image ii, i.e., b4-b1, b4-b2, b4-b3, b5-b1, b5-b2, b5-b3, b5-b4, b6-b1, b6-b2, b6-b3, b6-b4, and b6-b5, through a difference operation.
S42: and generating a difference image for increasing the difference between the red ground object and other ground objects according to the reflection spectrum curve.
In this embodiment, the difference image is obtained by finding out some suitable wavebands from fig. 3, selecting 2 wavebands from the wavebands, obtaining a median of reflection feature values of the two wavebands, subtracting the median of the reflection feature value of the central waveband, so that a pixel value of the red feature and a pixel value of the other color feature in the image have a positive-negative difference, increasing a difference between the red feature and the other color feature, and performing a waveband operation to obtain a difference image, i.e., (b 1+ b 5)/2-b 3.
S43: and summing the new characteristic image I and the new characteristic image II, multiplying the sum by the difference image, and obtaining the new spectral index according to the operation result.
In this embodiment, all enhanced images obtained in S41 are added to comprehensively enhance red feature information, and then multiplied by the feature image obtained in S42 (the above calculations are performed by floating point type operation), the feature image of S42 is used to enhance the red feature positively, enhance the other color features negatively, increase the separability of the red feature and the other color features in the image, and construct a new spectral index RGOSI that can extract the red feature by the threshold method, that is, RGOSI = [2 × b ] 4 +4×b 5 +6×b 6 -3×(b 1 +b 2 +b 3 )]×[(b 1 +b 5 )/2-b 3 ]。
S5: and setting a threshold range for extracting the red ground objects according to the new spectral index, and extracting the red ground objects in the image to be detected through the threshold range. Specifically, the new spectral index is divided by 100000, and the reflectance spectrum curve is used to count the red feature sample in the new spectral index image to obtain an initial threshold, which can be combined with visual observation and adjustment of the threshold to finally obtain the most suitable RGOSI threshold range [19.337581, 528.890930] for extracting the red feature, and the red feature in the image is extracted by using the threshold range (see fig. 5 specifically).
Example two
Referring to fig. 6, a red feature extraction apparatus according to a second embodiment of the present invention includes an input device 41, a processor 42, a memory 43, and an output device 44, where the input device 41, the processor 42, the memory 43, and the output device 44 are connected to each other via a communication bus 40, where the memory 43 is used for storing a computer program, and the computer program includes program instructions, and the processor 42 is configured to call the program instructions to execute the steps of the red feature extraction method according to the first embodiment of the present invention.
It will be appreciated that in embodiments of the invention, memory 43 may include both read-only memory and random access memory, and provides instructions and data to processor 42. A portion of the memory 43 may also include non-volatile random access memory. For example, the memory 43 may also store information regarding the type of device.
The processor 42 is operative to run or execute an operating system, various software programs, and its own instruction set stored in the internal memory 43, and is operative to process data and instructions received from the touch input device or from other external input pathways to perform various functions.
The input device 41 may be a touch input device such as a numeric keypad or a mechanical keyboard; the output device 44 may include a display or the like.
EXAMPLE III
A computer-readable storage medium proposed by the third embodiment of the present invention stores a computer program including program instructions that, when executed by a processor, cause the processor to execute the red feature extraction method as described in the first embodiment of the present invention.
In particular, the computer-readable storage medium may include Cache (Cache), high-speed Random Access Memory (RAM), such as common double data rate synchronous dynamic random access memory (DDR SDRAM), and may also include non-volatile memory (NVRAM), such as one or more read-only memories (ROM), magnetic disk storage devices, flash memory (Flash) memory devices, or other non-volatile solid-state memory devices, such as compact disk (CD-ROM, DVD-ROM), floppy disks or data tapes, and so forth.
Example four
Referring to fig. 7, a red surface feature extraction system according to a fourth embodiment of the present invention includes a terminal device and a red surface feature extraction device; the terminal device is communicatively connected to the red surface feature extraction device, which may be the device according to embodiment 2 of the present invention, and will not be described herein for brevity.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail with reference to the foregoing embodiments, those skilled in the art will appreciate that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present invention, and they should be construed as being included in the following claims and description.
Claims (5)
1. A red ground object extraction method is characterized by comprising the following steps:
respectively collecting surface feature samples with certain pixel numbers for each surface feature in the surface reflection characteristic value image;
fitting a reflection spectrum curve of a typical feature by using the pixel mean value of the feature sample;
analyzing the difference of the reflection characteristic values of the red ground object and other color ground objects in the reflection spectrum curve, and constructing and extracting a new spectrum index of the red ground object according to the analysis result;
setting a threshold range for extracting the red ground objects according to the new spectral index, and extracting the red ground objects in the image to be detected through the threshold range;
the construction of the new spectral index for extracting the red ground objects specifically comprises the following steps:
generating a new characteristic image I and a new characteristic image II for enhancing the red ground feature information and weakening the other color ground feature information according to the reflection spectrum curve;
generating a difference image for increasing the difference between the red ground object and other ground objects according to the reflection spectrum curve;
summing the new characteristic image I and the new characteristic image II, multiplying the sum by the difference image, and obtaining the new spectrum index according to the operation result;
the generating of the new feature image i specifically includes:
finding out a wave band in which the reflection characteristic value of the red ground object is larger and the reflection characteristic values of other most ground objects are not more outstanding than the red ground object from the reflection spectrum curve;
summing the wave bands to obtain a new characteristic image I which fully enhances the red ground features and less enhances the information of other ground features;
the generating of the new feature image ii specifically includes:
finding out N groups of wave bands which can obviously enhance the red ground objects and weaken or slightly enhance other color ground object information from the reflection spectrum curve, wherein each group of wave bands of the N groups of wave bands comprises two different wave bands;
performing difference value operation on two different wave bands in each group of wave bands to obtain a new characteristic image II;
generating the difference image specifically includes:
selecting two wave bands from the reflection spectrum curve, and solving a median value of reflection characteristic values of the two wave bands;
performing difference operation on the median and the reflection characteristic value of the central wave band, and obtaining a difference image through the wave band operation;
the setting of the threshold range specifically includes:
dividing the new spectral index by 100000, and counting the red ground object sample in the new spectral index image by using a reflection spectral curve to obtain an initial threshold value;
and adjusting the initial threshold value to obtain the optimal threshold value range for extracting the red ground object.
2. The method for extracting red land features according to claim 1, further comprising:
and preprocessing the image to be detected to obtain the earth surface reflection characteristic value image after the atmospheric influence is removed, wherein the preprocessing comprises the steps of carrying out radiometric calibration, fusion and atmospheric correction on the image to be detected.
3. A red feature extraction apparatus, comprising a processor, an input device, an output device and a memory, the processor, the input device, the output device and the memory being interconnected, wherein the memory is configured to store a computer program comprising program instructions, and the processor is configured to invoke the program instructions to perform the method of any one of claims 1-2.
4. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program comprising program instructions that, when executed by a processor, cause the processor to perform the method according to any of claims 1-2.
5. A red surface feature extraction system is characterized by comprising terminal equipment and a red surface feature extraction device; the terminal device is in communication connection with the red feature extraction apparatus, which performs the method of any one of claims 1-2.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010321128.3A CN111539318B (en) | 2020-04-22 | 2020-04-22 | Red ground object extraction method, device, storage medium and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010321128.3A CN111539318B (en) | 2020-04-22 | 2020-04-22 | Red ground object extraction method, device, storage medium and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111539318A CN111539318A (en) | 2020-08-14 |
CN111539318B true CN111539318B (en) | 2023-04-07 |
Family
ID=71980016
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010321128.3A Active CN111539318B (en) | 2020-04-22 | 2020-04-22 | Red ground object extraction method, device, storage medium and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111539318B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112033914B (en) * | 2020-09-01 | 2021-04-20 | 深圳市数字城市工程研究中心 | Color steel tile factory building extraction method based on remote sensing image |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1837787A (en) * | 2006-04-19 | 2006-09-27 | 南京大学 | Non-destructive precise determination method for biophysical parameters of cotton |
WO2020015326A1 (en) * | 2018-07-19 | 2020-01-23 | 山东科技大学 | Remote sensing image cloud shadow detection method supported by earth surface type data |
CN110796113A (en) * | 2019-11-05 | 2020-02-14 | 洛阳师范学院 | City blue terrain detection method based on WorldView-2 image |
-
2020
- 2020-04-22 CN CN202010321128.3A patent/CN111539318B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1837787A (en) * | 2006-04-19 | 2006-09-27 | 南京大学 | Non-destructive precise determination method for biophysical parameters of cotton |
WO2020015326A1 (en) * | 2018-07-19 | 2020-01-23 | 山东科技大学 | Remote sensing image cloud shadow detection method supported by earth surface type data |
CN110796113A (en) * | 2019-11-05 | 2020-02-14 | 洛阳师范学院 | City blue terrain detection method based on WorldView-2 image |
Non-Patent Citations (2)
Title |
---|
潘方博 ; 杨淼 ; 胡乃勋 ; 毛鹏磊 ; 李长征 ; .一种利用TM/ETM+影像新型水体提取算法.科技经济导刊.2016,(05),全文. * |
王静,何挺,李玉环.基于高光谱遥感技术的土地质量信息挖掘研究.遥感学报.2005,(04),全文. * |
Also Published As
Publication number | Publication date |
---|---|
CN111539318A (en) | 2020-08-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110390267B (en) | Mountain landscape building extraction method and device based on high-resolution remote sensing image | |
CN111860336B (en) | High-resolution remote sensing image inclined ship target detection method based on position sensing | |
Su et al. | Textural and local spatial statistics for the object‐oriented classification of urban areas using high resolution imagery | |
CN105956557B (en) | A kind of sequential remote sensing image cloud covered areas domain automatic testing method of object-oriented | |
CN103226832B (en) | Based on the multi-spectrum remote sensing image change detecting method of spectral reflectivity mutation analysis | |
CN106407927A (en) | Salient visual method based on polarization imaging and applicable to underwater target detection | |
CN107507209B (en) | Printogram extraction method of polarized SAR image | |
CN111611965B (en) | Method for extracting land surface water body based on Sentinel-2 image | |
CN110334623B (en) | Method for extracting collapsing information based on Sentinel-2A satellite remote sensing image | |
WO2024217541A1 (en) | Remote-sensing image change detection method based on siamese network | |
CN111007013B (en) | Crop rotation fallow remote sensing monitoring method and device for northeast cold region | |
CN107421892A (en) | A kind of hyperspectral data processing method for water body information | |
CN106228130A (en) | Remote sensing image cloud detection method of optic based on fuzzy autoencoder network | |
CN111539318B (en) | Red ground object extraction method, device, storage medium and system | |
CN110032988A (en) | Uv raman spectroscopy system real-time noise-reducing Enhancement Method | |
CN107085851A (en) | A kind of method and device of extraction waters water front | |
CN115330703A (en) | Remote sensing image cloud and cloud shadow detection method based on context information fusion | |
CN108492288A (en) | The high score satellite image change detecting method of multiple dimensioned stratified sampling based on random forest | |
US7480052B1 (en) | Opaque cloud detection | |
CN114926826A (en) | Scene text detection system | |
CN105718924B (en) | High score satellite image cloud detection method of optic based on combination features and machine learning | |
CN109389063B (en) | Remote sensing image strip noise removing method based on wave band correlation | |
CN113837123A (en) | Mid-resolution remote sensing image offshore culture area extraction method based on spectral-spatial information combination | |
CN114049571A (en) | Method and device for extracting water body area of hyperspectral image and electronic equipment | |
CN112329791B (en) | Automatic extraction method for hyperspectral image water area |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |