CN104637063A - Method for detecting oil film edge in synthetic aperture radar ocean oil overflow image - Google Patents
Method for detecting oil film edge in synthetic aperture radar ocean oil overflow image Download PDFInfo
- Publication number
- CN104637063A CN104637063A CN201510084955.4A CN201510084955A CN104637063A CN 104637063 A CN104637063 A CN 104637063A CN 201510084955 A CN201510084955 A CN 201510084955A CN 104637063 A CN104637063 A CN 104637063A
- Authority
- CN
- China
- Prior art keywords
- image
- edge
- gray
- value
- threshold value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a method for detecting the oil film edge in a synthetic aperture radar ocean oil overflow image. The method comprises the following steps that an original image is preprocessed; a gray value histogram is made through counting the gray values of each point in a grayscale image, and the minimum value between the two wave peaks is used as the threshold value; the gray value of a single point in the image is extracted and is compared with the obtained threshold value, a binary image is obtained, and the threshold value segmentation is realized; the obtained binary image is subjected to edge extraction, the edge of the binary image is extracted by a Canny algorithm, and the edge is the oil film edge of the oil overflow image. The method has the advantages that the noise interference can be effectively inhibited, and in addition, the oil film boundary can be more completely extracted.
Description
Art
The invention belongs to digital image processing techniques, relate to a kind of method detecting oil film edge.
Background technology
Utilization is continually developed along with petroleum resources, following one by one ocean water body oil pollution problem is on the rise, and in various marine pollution, no matter oil pollution is at occurrence frequency, Distribution Breadth, or all rank first in the extent of injury, oneself causes serious harm to the productive life of people.Therefore, obtain Algorithms for Oil Slick information in time, can protect the marine environment, reduce and salvage cost, significant to global ecological environment.Threshold segmentation and rim detection are the gordian techniquies in Digital Image Processing, and how segmentation and detection algorithm reach the target that precision is high, integrality is high, speed is fast, strong interference immunity becomes people's pursuit.Marine oil film edge detection method can be good the interference that causes of solution noise and can be complete the border extracting oil spilling oil film, there is good prospect.
Summary of the invention
The object of this invention is to provide a kind of method detecting oil film edge in synthetic-aperture radar marine oil spill image.Threshold segmentation combines with rim detection by the present invention, realizes the extraction at oil film edge, effectively inhibits the interference of noise, and comparatively complete extracts Oil Boundary.Technical scheme is as follows:
In synthetic-aperture radar marine oil spill image, detect the method at oil film edge, method is as follows:
1) Technologies Against Synthetic Aperture Radar marine oil spill image carries out pre-service, and the first step is gaussian filtering, then carries out mean filter on this basis, obtains pretreated image;
2) for pretreated image, make grey value histograms by the gray-scale value of each point in statistics gray-scale map, select two peak-to-peak minimum value of ripple as threshold value;
3) extract the gray-scale value of a point in image and contrast with the threshold value obtained, black is shown in the point that gray-scale value is greater than threshold value image after treatment, be shown as white in the point that gray-scale value is less than threshold value image after treatment, thus obtain a bianry image, realize Threshold segmentation;
4) carry out edge extracting to the bianry image obtained, use Canny algorithm to extract the edge of bianry image, this edge is exactly the oil film edge of oil spilling image.
The noise of SAR image is a serious problem, and when directly carrying out edge detection process to SAR original image, noise can cause obtaining desirable result.The algorithm combined with rim detection by Threshold segmentation can remove the impact of noise by threshold method, thus can obtain clearly when carrying out rim detection further, continuous print, complete image boundary, takes full advantage of the advantage of two kinds of methods.Through experimental result contrast verification, the method with directly carry out compared with rim detection, improving accuracy of detection to image, complete, continuous print edge can be obtained.The present invention can be applied in marine oil spill monitoring effectively, has Detection job high, the advantage that continuous edge is complete.
Accompanying drawing explanation
Fig. 1 is the original image of SAR marine oil spill image;
Fig. 2 is the image that original image obtains after pre-service;
The grey level histogram that Fig. 3 uses when being and extracting by threshold value;
Fig. 4 carries out Threshold segmentation to pretreated image to be converted into bianry image;
Fig. 5 carries out to bianry image the result that Canny rim detection extracts the edge of bianry image;
Fig. 6 is the result directly using Canny rim detection original image to obtain.
Embodiment
Below in conjunction with accompanying drawing, the present invention will be described.
Fig. 1 is the original image of SAR marine oil spill image.The method of oil film edge extracting of the present invention is mainly divided into four steps: Image semantic classification, and threshold value obtains, Threshold segmentation and rim detection.Concrete steps are as follows:
1) Image semantic classification: Technologies Against Synthetic Aperture Radar marine oil spill image carries out pre-service, the first step is gaussian filtering, then carries out mean filter on this basis, after pre-service as shown in Figure 2.
2) threshold value obtains: make grey value histograms by the gray-scale value of each point in statistics gray-scale map, see Fig. 3, select two peak-to-peak minimum value of ripple as threshold value, the present embodiment selects 62 as threshold value.
3) Threshold segmentation: extract the gray-scale value of a point in image and contrast with the threshold value obtained, black is shown in the point that gray-scale value is greater than threshold value image after treatment, white is shown as in the point that gray-scale value is less than threshold value image after treatment, thus obtain a bianry image, as shown in Figure 4, Threshold segmentation is realized.
4) rim detection: carry out edge extracting to the bianry image obtained, use Canny algorithm to extract the edge of bianry image, this edge is exactly the oil film edge of oil spilling image, as shown in Figure 5.
Fig. 6 is the result directly using Canny rim detection original image to obtain.
Claims (1)
1. in synthetic-aperture radar marine oil spill image, detect the method at oil film edge, method is as follows:
1) Technologies Against Synthetic Aperture Radar marine oil spill image carries out pre-service, and the first step is gaussian filtering, then carries out mean filter on this basis, obtains pretreated image;
2) for pretreated image, make grey value histograms by the gray-scale value of each point in statistics gray-scale map, select two peak-to-peak minimum value of ripple as threshold value;
3) extract the gray-scale value of a point in image and contrast with the threshold value obtained, black is shown in the point that gray-scale value is greater than threshold value image after treatment, be shown as white in the point that gray-scale value is less than threshold value image after treatment, thus obtain a bianry image, realize Threshold segmentation;
4) carry out edge extracting to the bianry image obtained, use Canny algorithm to extract the edge of bianry image, this edge is exactly the oil film edge of oil spilling image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510084955.4A CN104637063A (en) | 2015-02-16 | 2015-02-16 | Method for detecting oil film edge in synthetic aperture radar ocean oil overflow image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510084955.4A CN104637063A (en) | 2015-02-16 | 2015-02-16 | Method for detecting oil film edge in synthetic aperture radar ocean oil overflow image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104637063A true CN104637063A (en) | 2015-05-20 |
Family
ID=53215769
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510084955.4A Pending CN104637063A (en) | 2015-02-16 | 2015-02-16 | Method for detecting oil film edge in synthetic aperture radar ocean oil overflow image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104637063A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113436218A (en) * | 2021-07-28 | 2021-09-24 | 西安电子科技大学 | SAR image edge detection method based on Gaussian filtering and mean filtering |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030132946A1 (en) * | 2002-01-11 | 2003-07-17 | Applied Materials, Inc. | System and method for edge ehnancement of images |
| CN101571915A (en) * | 2009-06-16 | 2009-11-04 | 大连海事大学 | Method for identifying oil spill of SAR image based on characteristic value |
| CN102609709A (en) * | 2012-02-03 | 2012-07-25 | 清华大学 | Sea surface oil spilling segmentation method based on polarized SAR (synthetic aperture radar) data fusion |
| CN103971370A (en) * | 2014-05-15 | 2014-08-06 | 中国科学院遥感与数字地球研究所 | Intelligent ocean oil spill detection method for remote sensing large image |
-
2015
- 2015-02-16 CN CN201510084955.4A patent/CN104637063A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030132946A1 (en) * | 2002-01-11 | 2003-07-17 | Applied Materials, Inc. | System and method for edge ehnancement of images |
| CN101571915A (en) * | 2009-06-16 | 2009-11-04 | 大连海事大学 | Method for identifying oil spill of SAR image based on characteristic value |
| CN102609709A (en) * | 2012-02-03 | 2012-07-25 | 清华大学 | Sea surface oil spilling segmentation method based on polarized SAR (synthetic aperture radar) data fusion |
| CN103971370A (en) * | 2014-05-15 | 2014-08-06 | 中国科学院遥感与数字地球研究所 | Intelligent ocean oil spill detection method for remote sensing large image |
Non-Patent Citations (2)
| Title |
|---|
| 胡冠华: "基于合成孔径雷达海洋溢油图像的油膜提取和边缘检测", 《万方数据》 * |
| 薛浩洁,种劲松: "基于反对称二进小波的SAR图像海洋表面油膜检测方法", 《电子与信息学报》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113436218A (en) * | 2021-07-28 | 2021-09-24 | 西安电子科技大学 | SAR image edge detection method based on Gaussian filtering and mean filtering |
| CN113436218B (en) * | 2021-07-28 | 2023-02-10 | 西安电子科技大学 | SAR image edge detection method based on Gaussian filtering and mean filtering |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Gatos et al. | Improved document image binarization by using a combination of multiple binarization techniques and adapted edge information | |
| Farahmand et al. | Document image noises and removal methods | |
| CN106709426B (en) | Ship target detection method based on infrared remote sensing image | |
| CN103778627B (en) | A kind of marine site based on SAR image oil spilling detection method | |
| CN104361336A (en) | Character recognition method for underwater video images | |
| Bakshi et al. | Real-time iris segmentation based on image morphology | |
| CN106780486A (en) | A kind of Surface Defects in Steel Plate image extraction method | |
| CN103745468A (en) | Significant object detecting method based on graph structure and boundary apriority | |
| CN105488787A (en) | Geometric active contour model-based coastline detection method for remote sensing image | |
| CN102629318A (en) | Fingerprint image segmentation method based on support vector machine | |
| CN102663700A (en) | Segmentation method for adhering grain binary image | |
| Rabee et al. | License plate detection and recognition in complex scenes using mathematical morphology and support vector machines | |
| CN105447489A (en) | Character and background adhesion noise elimination method for image OCR system | |
| Yang et al. | A fast adaptive binarization method for complex scene images | |
| CN104637063A (en) | Method for detecting oil film edge in synthetic aperture radar ocean oil overflow image | |
| Ren et al. | Effective SAR sea ice image segmentation and touch floe separation using a combined multi-stage approach | |
| CN103207997A (en) | Kernel density estimation-based license plate character segmentation method | |
| Liu | An improved image enhancement algorithm based on fuzzy set | |
| Gatos et al. | Efficient binarization of historical and degraded document images | |
| CN103577808A (en) | Frogman recognition method | |
| Song et al. | Road detection algorithm of integrating region and edge information | |
| Biao et al. | Segmentation and recognition of bridges in high resolution SAR images | |
| Xiong et al. | Research on an Edge Detection Algorithm of Remote Sensing Image Based on Wavelet Enhancement and Morphology. | |
| Wang et al. | An intelligent coastline interpretation of several types of seacoasts from TM/ETM+ images based on rules | |
| Papavassiliou et al. | A Morphology Based Approach for Binarization of Handwritten Documents |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150520 |