JP2003288581A - Water area extraction processing method, water area extraction processing apparatus, water area extraction processing program, and recording medium for the program - Google Patents
Water area extraction processing method, water area extraction processing apparatus, water area extraction processing program, and recording medium for the programInfo
- Publication number
- JP2003288581A JP2003288581A JP2002091092A JP2002091092A JP2003288581A JP 2003288581 A JP2003288581 A JP 2003288581A JP 2002091092 A JP2002091092 A JP 2002091092A JP 2002091092 A JP2002091092 A JP 2002091092A JP 2003288581 A JP2003288581 A JP 2003288581A
- Authority
- JP
- Japan
- Prior art keywords
- image
- water area
- extraction processing
- area extraction
- water
- 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
Landscapes
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
(57)【要約】
【課題】 衛星写真画像や航空写真画像などから水領域
を自動抽出する際に,マルチスペクトル特徴にもとづい
て安定して水領域を抽出することができるようにする。
【解決手段】 判定値算出処理22では,可視光の赤色
領域の波長をもつ電磁波をとらえたR画像20と近赤外
領域の電磁波をとらえたNIR画像21とを入力し,画
像中の対応する各点において,例えば「NIR画像の輝
度値/R画像の輝度値」というような判定値を算出す
る。水領域判定処理23では,算出された判定値が一定
値以下である場合に,その点を水領域と判定する。この
処理を画像中の各点について繰り返す。
(57) [Summary] [PROBLEMS] To automatically extract a water area based on multispectral features when automatically extracting a water area from a satellite photograph image, an aerial photograph image, or the like. In a determination value calculation process, an R image capturing an electromagnetic wave having a wavelength in a red region of visible light and an NIR image capturing an electromagnetic wave in a near-infrared region are input, and a corresponding image in the image is input. At each point, a determination value such as “luminance value of NIR image / luminance value of R image” is calculated. In the water area determination process 23, when the calculated determination value is equal to or less than a certain value, the point is determined as a water area. This process is repeated for each point in the image.
Description
【0001】[0001]
【発明の属する技術分野】本発明は,画像の中からマル
チスペクトル情報にもとづき水領域を自動的に抽出する
水領域抽出処理方法,水領域抽出処理装置,水領域抽出
処理プログラムおよびそのプログラムの記録媒体に関す
るものである。BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a water region extraction processing method, a water region extraction processing device, a water region extraction processing program, and a program recording the program for automatically extracting a water region from an image based on multispectral information. It concerns media.
【0002】[0002]
【従来の技術】地表を撮影した画像における海,湖,川
などの水領域抽出は,衛星写真や航空写真を用いたリモ
ートセンシングの分野で重要であるが,従来は画像と該
当地域の地図とを照合して水領域を抽出する手法を用い
たり,人手を用いたりしていた。2. Description of the Related Art Extraction of water regions such as oceans, lakes and rivers from images of the surface of the earth is important in the field of remote sensing using satellite photographs and aerial photographs. They used a method of extracting water regions by collating with, or using human hands.
【0003】[0003]
【発明が解決しようとする課題】しかし,この種の従来
の方法は,写真撮影時期と地図作成時期とが異なる場合
があるといった問題や,人手を用いることによりコスト
がかかるという問題がある。However, the conventional method of this kind has a problem that the photographing time may be different from the map making time, and it may be costly to use manpower.
【0004】本発明は,上記従来手法の問題点の解決を
図り,衛星写真や航空写真で一般的である近赤外領域の
電磁波をとらえた画像(NIR画像という)と,可視光
の赤色領域の波長をもつ電磁波をとらえた画像(R画像
という)とを用いることで,安定した水領域抽出を可能
にすることを目的とする。The present invention is intended to solve the problems of the above-mentioned conventional methods, and an image capturing an electromagnetic wave in the near infrared region (referred to as NIR image), which is generally used in satellite photography and aerial photography, and a red region of visible light. The object is to enable stable water region extraction by using an image (referred to as an R image) that captures an electromagnetic wave having a wavelength of.
【0005】[0005]
【課題を解決するための手段】本発明は,水の反射率が
可視赤色の領域と近赤外の領域とで大きく異なるといっ
た分光反射率特性に着目し,地表を撮影した画像から水
領域を抽出することを特徴とする。実現手段としては,
以下の方法を用いる。
1.可視光の赤色領域の波長をもつ電磁波をとらえた画
像(R画像)と近赤外領域の電磁波をとらえた画像(N
IR画像)の対応する各点において,
“NIR画像の輝度値/R画像の輝度値”
を計算する。
2.得られた値が一定値以下である場合,該点を水領域
と判定する。The present invention focuses on the spectral reflectance characteristic that the reflectance of water is greatly different between the visible red region and the near infrared region, and the water region is extracted from the image of the ground surface. It is characterized by extracting. As a means of realization,
The following method is used. 1. An image capturing an electromagnetic wave having a wavelength in the red region of visible light (R image) and an image capturing an electromagnetic wave in the near infrared region (N image)
At each corresponding point of the (IR image), "luminance value of NIR image / luminance value of R image" is calculated. 2. If the obtained value is less than a certain value, the point is determined to be a water region.
【0006】以上により,マルチスペクトル特徴にもと
づく安定した水領域の抽出が可能となる。As described above, it is possible to stably extract the water region based on the multi-spectral feature.
【0007】[0007]
【発明の実施の形態】以下,本発明の実施の形態を,図
を用いて詳細に説明する。BEST MODE FOR CARRYING OUT THE INVENTION Embodiments of the present invention will be described in detail below with reference to the drawings.
【0008】図1に,本実施の形態による水領域抽出処
理装置の構成例を示す。図中,1はCPUおよびメモリ
などからなる水領域抽出処理装置,10は可視光の赤色
領域の波長をもつ電磁波をとらえた画像(R画像)を記
憶するR画像記憶部,11は近赤外領域の電磁波をとら
えた画像(NIR画像)を記憶するNIR画像記憶部,
12はR画像とNIR画像とから各画素ごとにそれが水
領域であるか否かを判定するための値を計算する判定値
算出処理部,13は判定値算出処理部12が算出した判
定値にもとづいて水領域であるか否かを判定する水領域
判定処理部,14は水領域判定処理部13の出力である
水領域情報である。FIG. 1 shows a configuration example of a water region extraction processing device according to this embodiment. In the figure, 1 is a water region extraction processing device including a CPU and a memory, 10 is an R image storage unit that stores an image (R image) that captures an electromagnetic wave having a wavelength in the red region of visible light, and 11 is a near infrared ray. An NIR image storage unit that stores an image (NIR image) obtained by capturing electromagnetic waves in a region,
12 is a determination value calculation processing unit that calculates a value for determining whether each pixel is a water region from the R image and the NIR image, and 13 is a determination value calculated by the determination value calculation processing unit 12. The water area determination processing unit 14 for determining whether or not the water area is the water area is water area information output from the water area determination processing unit 13.
【0009】図2に,図1に示す水領域抽出処理装置1
の処理の流れを示す。入力となるR画像20は,可視光
の赤色領域の波長をもつ電磁波をとらえた画像であり,
NIR画像21は,近赤外領域の電磁波をとらえた画像
である。例えば衛星写真画像や航空写真画像等を用いた
リモートセンシングでは,植物の被覆状況を求めるため
にこの2種類の画像が良く用いられる。FIG. 2 shows a water area extraction processing apparatus 1 shown in FIG.
The flow of processing is shown. The input R image 20 is an image that captures an electromagnetic wave having a wavelength in the red region of visible light,
The NIR image 21 is an image that captures electromagnetic waves in the near infrared region. For example, in remote sensing using satellite photographic images or aerial photographic images, these two types of images are often used in order to determine the coverage of plants.
【0010】判定値算出処理22は,図1に示す判定値
算出処理部12が行う処理であり,ここではR画像20
とNIR画像21とを用い,水領域であるか否かを判定
するための判定値を算出する。はじめにアフィン変換な
どで,2枚の画像の位置合わせが必要となる場合も考え
られる。位置合わせが終了したら,対応する各点におい
て,判定値Xとして,
X=(NIR画像における輝度値)/(R画像における
輝度値)
を計算する。The judgment value calculation process 22 is a process performed by the judgment value calculation processing unit 12 shown in FIG.
And the NIR image 21 are used to calculate a determination value for determining whether or not the region is the water region. First, it may be necessary to align two images due to affine transformation. When the alignment is completed, X = (luminance value in NIR image) / (luminance value in R image) is calculated as the determination value X at each corresponding point.
【0011】水の反射率は,可視光の赤色領域と近赤外
領域とで大きく異なり,近赤外領域での反射率は可視光
赤色領域の反射率よりたいへん小さい。したがって,水
領域では判定値Xは小さな値をとる。The reflectance of water greatly differs between the red region of visible light and the near infrared region, and the reflectance in the near infrared region is much smaller than the reflectance of the visible light red region. Therefore, the judgment value X takes a small value in the water region.
【0012】水領域判定処理23は,水領域判定処理部
13が行う処理である。水領域判定処理23では,Xの
値が一定値以下である場合に,該点を水領域であると判
定する。この一定値は,照明条件やカメラ特性によって
大きく値が変動するが,例えば,
NIR/R<0.7
の場合に,その画素を水領域と判定する。The water area determination processing 23 is processing performed by the water area determination processing unit 13. In the water area determination processing 23, when the value of X is equal to or less than a certain value, the point is determined to be the water area. Although the value of this constant value varies greatly depending on the illumination conditions and the camera characteristics, for example, when NIR / R <0.7, the pixel is determined to be the water region.
【0013】また,上記判定値X以外にも,例えばNI
R画像21の輝度値とR画像20の輝度値との差を判定
尺度としたり,
Y=(NIR画像における輝度値−R画像における輝度
値)/(NIR画像における輝度値+R画像における輝
度値)
により算出されるYの値などを判定尺度とする方法も考
えられる。In addition to the judgment value X, for example, NI
The difference between the brightness value of the R image 21 and the brightness value of the R image 20 is used as a criterion, and Y = (brightness value in NIR image−brightness value in R image) / (brightness value in NIR image + brightness value in R image) It is also possible to use a method such as a value of Y calculated by
【0014】終了判定処理24は,処理を終わらせるか
否かを判定する処理であり,ここでは全画素について水
領域判定処理23が行われたか否かを判定する。まだ未
処理である画素が存在する場合には,判定値算出処理2
2に再度戻り,未処理部分について同様に処理を行う。The end determination process 24 is a process for determining whether or not to end the process, and here it is determined whether or not the water region determination process 23 has been performed for all pixels. If there are still unprocessed pixels, the judgment value calculation process 2
Returning to step 2 again, the same processing is performed on the unprocessed portion.
【0015】以上の水領域抽出処理装置1が行う処理
は,コンピュータとソフトウェアプログラムとによって
実現することができ,そのプログラムは,コンピュータ
が読み取り可能な可搬媒体メモリ,半導体メモリ,ハー
ドディスク等の適当な記録媒体に格納して,そこから読
み出すことによりコンピュータに実行させることができ
る。また,そのプログラムは通信回線を経由して他のコ
ンピュータからダウンロードすることができ,それをイ
ンストールして実行させることもできる。The processing performed by the water area extraction processing apparatus 1 described above can be realized by a computer and a software program, and the program is an appropriate computer-readable portable medium memory, semiconductor memory, hard disk, or the like. It can be executed by a computer by storing it in a recording medium and reading it from there. Further, the program can be downloaded from another computer via a communication line, and can be installed and executed.
【0016】[0016]
【発明の効果】以上説明したように,本発明は,水の分
光反射率特性,すなわち水の反射率は可視光赤色領域と
近赤外領域とで大きく異なるという特徴に着目した水領
域抽出を行う。このため,衛星写真画像や航空写真画像
で一般的なNIR画像とR画像を用いることで安定した
水領域抽出が可能となる。As described above, according to the present invention, the water region extraction is performed by focusing on the spectral reflectance characteristic of water, that is, the reflectance of water is largely different between the visible light red region and the near infrared region. To do. For this reason, stable water region extraction is possible by using general NIR images and R images in satellite photographic images and aerial photographic images.
【図1】本実施の形態による水領域抽出処理装置の構成
例を示す図である。FIG. 1 is a diagram showing a configuration example of a water region extraction processing device according to the present embodiment.
【図2】水領域抽出処理装置の処理の流れを示す図であ
る。FIG. 2 is a diagram showing a processing flow of a water region extraction processing device.
1 水領域抽出処理装置 10 R画像記憶部 11 NIR画像記憶部 12 判定値算出処理部 13 水領域判定処理部 14 水領域情報 1 Water area extraction processing device 10 R image storage unit 11 NIR image storage unit 12 Judgment value calculation processing unit 13 Water area determination processing unit 14 Water area information
フロントページの続き (72)発明者 伊藤 直己 東京都千代田区大手町二丁目3番1号 日 本電信電話株式会社内 (72)発明者 塩 昭夫 東京都千代田区大手町二丁目3番1号 日 本電信電話株式会社内 Fターム(参考) 5B057 AA14 BA02 BA08 BA30 DA08 DA12 DB02 DB09 DC22 DC32 DC36 5L096 AA06 BA18 CA04 FA14 GA08 JA22 Continued front page (72) Inventor Naoki Ito 2-3-1, Otemachi, Chiyoda-ku, Tokyo Inside Telegraph and Telephone Corporation (72) Inventor Akio Shio 2-3-1, Otemachi, Chiyoda-ku, Tokyo Inside Telegraph and Telephone Corporation F-term (reference) 5B057 AA14 BA02 BA08 BA30 DA08 DA12 DB02 DB09 DC22 DC32 DC36 5L096 AA06 BA18 CA04 FA14 GA08 JA22
Claims (5)
スペクトル情報にもとづき水領域を抽出する方法におい
て,可視光の赤色領域の波長をもつ電磁波をとらえた第
1の画像を取得し記憶する過程と,近赤外領域の電磁波
をとらえた第2の画像を取得し記憶する過程と,前記第
1および第2の画像中の対応する各点において第1の画
像の輝度値と第2の画像の輝度値とから算出される値に
もとづき該点が水領域か否かを判定する過程とを有する
ことを特徴とする水領域抽出処理方法。1. A method of extracting a water region based on multi-spectral information from an image by a computer, acquiring and storing a first image of an electromagnetic wave having a wavelength in the red region of visible light, and A process of acquiring and storing a second image capturing electromagnetic waves in the infrared region, and a luminance value of the first image and a luminance value of the second image at corresponding points in the first and second images. And a step of determining whether or not the point is a water area based on a value calculated from the water area extraction processing method.
おいて,前記水領域か否かを判定する過程では,前記第
1および第2の画像中の対応する各点において第2の画
像の輝度値を第1の画像の輝度値により除算し,除算に
より得られた値にもとづき該点が水領域であるか否かを
判定することを特徴とする水領域抽出処理方法。2. The water area extraction processing method according to claim 1, wherein in the process of determining whether or not the water area is included, the second image of the second image is obtained at each corresponding point in the first and second images. A water area extraction processing method, characterized in that the brightness value is divided by the brightness value of the first image, and whether or not the point is a water area is determined based on the value obtained by the division.
スペクトル情報にもとづき水領域を抽出する装置におい
て,可視光の赤色領域の波長をもつ電磁波をとらえた第
1の画像を取得し記憶する手段と,近赤外領域の電磁波
をとらえた第2の画像を取得し記憶する手段と,前記第
1および第2の画像中の対応する各点において第1の画
像の輝度値と第2の画像の輝度値とから算出される値に
もとづき該点が水領域か否かを判定する手段とを備える
ことを特徴とする水領域抽出処理装置。3. A device for extracting a water region based on multi-spectral information from an image by a computer, means for acquiring and storing a first image capturing an electromagnetic wave having a wavelength in the red region of visible light, and a means for storing the first image. Means for acquiring and storing a second image capturing electromagnetic waves in the infrared region, and luminance values of the first image and luminance values of the second image at corresponding points in the first and second images And a means for determining whether or not the point is a water area based on a value calculated from the water area extraction processing apparatus.
抽出処理方法を,コンピュータに実行させるための水領
域抽出処理プログラム。4. A water area extraction processing program for causing a computer to execute the water area extraction processing method according to claim 1 or 2.
抽出処理方法を,コンピュータに実行させるためのプロ
グラムを記録したことを特徴とする水領域抽出処理プロ
グラムの記録媒体。5. A recording medium for a water area extraction processing program, wherein a program for causing a computer to execute the water area extraction processing method according to claim 1 or 2 is recorded.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2002091092A JP2003288581A (en) | 2002-03-28 | 2002-03-28 | Water area extraction processing method, water area extraction processing apparatus, water area extraction processing program, and recording medium for the program |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2002091092A JP2003288581A (en) | 2002-03-28 | 2002-03-28 | Water area extraction processing method, water area extraction processing apparatus, water area extraction processing program, and recording medium for the program |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| JP2003288581A true JP2003288581A (en) | 2003-10-10 |
Family
ID=29236264
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP2002091092A Pending JP2003288581A (en) | 2002-03-28 | 2002-03-28 | Water area extraction processing method, water area extraction processing apparatus, water area extraction processing program, and recording medium for the program |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JP2003288581A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008250185A (en) * | 2007-03-30 | 2008-10-16 | Hamanasu Information:Kk | Pseudo near-infrared image formation method and soil moisture measurement method |
| WO2011129409A1 (en) * | 2010-04-14 | 2011-10-20 | Necシステムテクノロジー株式会社 | Precision improving device for three dimensional topographical data, precision improving method for three dimensional topographical data and recording medium |
| WO2019193702A1 (en) * | 2018-04-05 | 2019-10-10 | 日本電気株式会社 | Image processing device, image processing method, and recording medium having image processing program stored thereon |
| CN110334656A (en) * | 2019-07-08 | 2019-10-15 | 中国人民解放军战略支援部队信息工程大学 | Method and device for extracting water bodies from multi-source remote sensing images based on source probability weighting |
| CN111982031A (en) * | 2020-08-24 | 2020-11-24 | 江苏科技大学 | Water surface area measuring method based on unmanned aerial vehicle vision |
-
2002
- 2002-03-28 JP JP2002091092A patent/JP2003288581A/en active Pending
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008250185A (en) * | 2007-03-30 | 2008-10-16 | Hamanasu Information:Kk | Pseudo near-infrared image formation method and soil moisture measurement method |
| WO2011129409A1 (en) * | 2010-04-14 | 2011-10-20 | Necシステムテクノロジー株式会社 | Precision improving device for three dimensional topographical data, precision improving method for three dimensional topographical data and recording medium |
| JP2011221930A (en) * | 2010-04-14 | 2011-11-04 | Nec System Technologies Ltd | Three-dimensional topographic data accuracy-improving device, three-dimensional topographic data accuracy improving-method and program |
| CN102884565A (en) * | 2010-04-14 | 2013-01-16 | Nec软件系统科技有限公司 | Precision improving device for three dimensional topographical data, precision improving method for three dimensional topographical data and recording medium |
| US8897547B2 (en) | 2010-04-14 | 2014-11-25 | Nec Solution Innovators, Ltd. | Precision improving device for three dimensional topographical data, precision improving method for three dimensional topographical data and recording medium |
| WO2019193702A1 (en) * | 2018-04-05 | 2019-10-10 | 日本電気株式会社 | Image processing device, image processing method, and recording medium having image processing program stored thereon |
| JPWO2019193702A1 (en) * | 2018-04-05 | 2021-02-12 | 日本電気株式会社 | Image processing device, image processing method, and image processing program |
| US11373314B2 (en) | 2018-04-05 | 2022-06-28 | Nec Corporation | Land mask image generation for ocean surface and land surface |
| CN110334656A (en) * | 2019-07-08 | 2019-10-15 | 中国人民解放军战略支援部队信息工程大学 | Method and device for extracting water bodies from multi-source remote sensing images based on source probability weighting |
| CN110334656B (en) * | 2019-07-08 | 2021-09-21 | 中国人民解放军战略支援部队信息工程大学 | Multi-source remote sensing image water body extraction method and device based on information source probability weighting |
| CN111982031A (en) * | 2020-08-24 | 2020-11-24 | 江苏科技大学 | Water surface area measuring method based on unmanned aerial vehicle vision |
| CN111982031B (en) * | 2020-08-24 | 2021-12-31 | 衡阳市大雁地理信息有限公司 | Water surface area measuring method based on unmanned aerial vehicle vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP2102815B1 (en) | Method of sharpening using panchromatic pixels | |
| US6985631B2 (en) | Systems and methods for automatically detecting a corner in a digitally captured image | |
| JP5291084B2 (en) | Edge mapping incorporating panchromatic pixels | |
| Asha et al. | Auto removal of bright spot from images captured against flashing light source | |
| CN101595494B (en) | Robust feature extraction for color and grayscale images | |
| JP4712487B2 (en) | Image processing method and apparatus, digital camera apparatus, and recording medium recording image processing program | |
| RU2631765C1 (en) | Method and system of correcting perspective distortions in images occupying double-page spread | |
| CN104683767B (en) | Penetrating Fog image generating method and device | |
| US20080240601A1 (en) | Edge mapping using panchromatic pixels | |
| JP2009207118A (en) | Image shooting apparatus and blur correction method | |
| US7609846B2 (en) | Matching of digital images to acquisition devices | |
| US20060013486A1 (en) | Identification of acquisition devices from digital images | |
| US9843782B2 (en) | Interpolation device, storage medium, and method with multi-band color filter and noise reduced reference image | |
| CN119540050B (en) | Image stitching processing method and device | |
| CN115035281A (en) | A Fast Infrared Panoramic Image Stitching Method | |
| JP2007074578A (en) | Image processing apparatus, photographing apparatus, and program | |
| US20150186373A1 (en) | Method for sorting a group of images of a database and method for color correcting an image, corresponding devices, computer program and non-transitory computer readable medium | |
| JP2003288581A (en) | Water area extraction processing method, water area extraction processing apparatus, water area extraction processing program, and recording medium for the program | |
| US20100079582A1 (en) | Method and System for Capturing and Using Automatic Focus Information | |
| JP6068896B2 (en) | Image processing apparatus and program | |
| US12493939B2 (en) | Method and a device for reducing a dynamic range of an image | |
| JP2003288593A (en) | Urban area extraction processing method, urban area extraction processing apparatus, urban area extraction processing program, and recording medium for the program | |
| JP2003288592A (en) | Urban area extraction processing method, urban area extraction processing apparatus, urban area extraction processing program, and recording medium for the program |