CN103440655A - Crossing bridge and offshore ship joint detection method in onboard remote sensing image - Google Patents
Crossing bridge and offshore ship joint detection method in onboard remote sensing image Download PDFInfo
- Publication number
- CN103440655A CN103440655A CN201310379302XA CN201310379302A CN103440655A CN 103440655 A CN103440655 A CN 103440655A CN 201310379302X A CN201310379302X A CN 201310379302XA CN 201310379302 A CN201310379302 A CN 201310379302A CN 103440655 A CN103440655 A CN 103440655A
- Authority
- CN
- China
- Prior art keywords
- water body
- image
- area
- target
- remote sensing
- 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
Images
Abstract
The invention relates to a crossing bridge and offshore ship joint detection method in an onboard remote sensing image. The crossing bridge and offshore ship joint detection method comprises the steps of firstly, carrying out otsu self-adaptation threshold segmentation on the onboard remote sensing image, then sequentially carrying out morphology closed operation and morphology open operation on a segmentation result image, obtaining a water body district image, then carrying out binaryzation operation on the water body district image, obtaining a water body district binary image, separating target candidate districts and water body background districts, calculating the area average value of the target candidate districts, checking whether the water body background districts exist around the target candidate district or not, if the value of the area of one target candidate area is larger than the average value and is surrounded by the water body background districts, determining that the target is an offshore ship, and if the value of the area of one target candidate district is smaller than the average value and only two opposite sides of the target candidate district are the water body background districts, determining that the target is a crossing bridge. The crossing bridge and offshore ship joint detection method is high in calculating efficiency, real-time processing can be easily carried out on an onboard computer, and the detection false alarm rate is low.
Description
Technical field
The invention belongs to technical field of remote sensing image processing, relate to crossing bridge and offshore naval vessel associated detecting method in a kind of aerial remote sensing image.
Background technology
The remote sensing image data obtained from airborne remote-sensing flatform, fast detecting goes out the strategic targets such as bridge, naval vessel, obtains the accurate location of target and for information about, is the important foundation of carrying out the target precision strike.The most technology is mainly paid close attention to the remote sensing image data obtained from empty day remote-sensing flatform and is detected the targets such as bridge, naval vessel, as Chinese Patent Application No. 201210077407.5, put down in writing " the marine Ship Detection in a kind of remote sensing image ", at first carry out the detection of suspected target according to local contrast information, then utilize space pyramid Matching Model to extract spatial context information deletion background interference, obtain the naval vessel testing result.Chinese Patent Application No. 200810232213.1, put down in writing a kind of " detection method for on-water bridge target in remote sensing image ", design different templates and carried out feature extraction, the bridge sorter obtained by training carries out identification and classification and obtains initial testing result, obtains final result after noise eliminating.These technology are directly faced is the mass data of scene image significantly, adopts the feature of calculation of complex to be detected its calculation cost to target inevitable high, is difficult to meet the requirement of practicality.Our application background is to carry out the detection on bridge and naval vessel from airborne remote sensing images, needs emphasis to consider the limited computational resource of airborne computer, have the ability of real-time processing.
Summary of the invention
The technical matters solved
For fear of the deficiencies in the prior art part, the present invention proposes crossing bridge and offshore naval vessel associated detecting method in a kind of aerial remote sensing image.
Technical scheme
Crossing bridge and offshore naval vessel associated detecting method in a kind of aerial remote sensing image is characterized in that step is as follows:
Step 1: at first the aerial remote sensing image is carried out to adaptive threshold between maximum kind and cut apart, then the segmentation result image is first carried out to closing operation of mathematical morphology and carries out again the morphology opening operation and obtain water body and background segment image on every side, according to water body and on every side the background segment image intercept and obtain the water body area image from airborne remote sensing images;
Step 2: using the gray-scale value peaked 1/2 of water body area image as threshold value, the water body area image is carried out to the binaryzation operation, obtain water body zone bianry image, the zone that in the bianry image of water body zone, the pixel gray-scale value is 255 is object candidate area, and the zone that in the bianry image of water body zone, the pixel gray-scale value is 0 is the water body background area;
Step 3: calculate the area average of object candidate area, the object candidate area area is greater than to this mean value, Preliminary detection is Bridge object, and the Preliminary detection that is less than this mean value is Ship Target;
Step 4: the Preliminary detection target in rectangle, whether the test-target surrounding exists the water body background area.If the target surrounding is the water body background area, this target is the offshore naval vessel, if the target surrounding only has relative both sides, is the water body background area, and this target is crossing bridge.
Beneficial effect
Crossing bridge and offshore naval vessel associated detecting method in a kind of aerial remote sensing image that the present invention proposes, at first the aerial remote sensing image being carried out to adaptive threshold between maximum kind cuts apart, then the segmentation result image first being carried out to closing operation of mathematical morphology carries out the morphology opening operation again and obtains the water body area image, then the water body area image is carried out to the binaryzation operation, obtain water body zone bianry image, separate object candidate area and water body background area, whether area average the test-target candidate region surrounding of calculating object candidate area exist the water body background area, if the object candidate area area is greater than mean value and surrounding is the water body background area, this target is the offshore naval vessel, if the object candidate area area is less than mean value and surrounding, to only have relative both sides be the water body background area, this target is crossing bridge.
The present invention compared with prior art, the present invention does not adopt the various features of calculation of complex to carry out the detection of realize target, but rely on gray feature difference by water body and background, target and water body are separated on every side, and the image pixel gray-scale value is a kind of feature of very easily obtaining, and realized the joint-detection on crossing bridge and offshore naval vessel according to the distribution situation of water body background area around target.The technology of the present invention counting yield is high, be easy to process in real time on airborne computer, detects false alarm rate low.
The accompanying drawing explanation
Fig. 1 is realization flow figure of the present invention;
Fig. 2 is the aerial remote sensing image;
Fig. 3 carries out between maximum kind to Fig. 2 the figure as a result that adaptive threshold is cut apart;
Fig. 4 carries out water body after morphology operations and background segment image on every side to Fig. 3;
Fig. 5 intercepts the water body area image obtained from Fig. 2 according to Fig. 4;
Fig. 6 is the water body zone bianry image after Fig. 5 carries out the binaryzation operation;
Fig. 7 is detected figure as a result.
Embodiment
Now in conjunction with the embodiments, the invention will be further described for accompanying drawing:
For the hardware environment of implementing, be: Intel Duo 2 double-core 2.93G computing machines, 2.0GB internal memory, 512M video card, the software environment of operation is: Matlab R2012a, Windows XP.We have realized with Matlab software the method that the present invention proposes.Aerial remote sensing image size is 938*562.
The present invention specifically is implemented as follows:
Step 1: the aerial remote sensing image in Fig. 2 is carried out to adaptive threshold between maximum kind and cut apart, obtain segmentation result Fig. 3, then to Fig. 3 first carry out closing operation of mathematical morphology carry out again the morphology opening operation obtain water body and on every side the background segment image be Fig. 4, intercepting from airborne remote sensing images according to Fig. 4 and obtaining the water body area image is Fig. 5;
Step 2: using the water body area image gray-scale value peaked 1/2 in Fig. 5 as threshold value, the water body area image is carried out to the binaryzation operation, obtaining water body zone bianry image is Fig. 6, the zone that in the bianry image of water body zone, the pixel gray-scale value is 255 is object candidate area, and the zone that in the bianry image of water body zone, the pixel gray-scale value is 0 is the water body background area;
Step 3: calculate the area average of object candidate area, the object candidate area area is greater than to this mean value, Preliminary detection is Bridge object, and the Preliminary detection that is less than this mean value is Ship Target;
Step 4: set up the Preliminary detection target in abutting connection with rectangle, this center that is the Preliminary detection target in abutting connection with rectangular centre, the length that length and width are the Preliminary detection target and width 1.5 times, and changing in abutting connection with test-target surrounding in rectangle whether have the water body background area.If the target surrounding is the water body background area, this target is the offshore naval vessel, if the target surrounding only has relative both sides, is the water body background area, and this target is crossing bridge, and testing result as shown in Figure 7.
Claims (2)
1. crossing bridge and offshore naval vessel associated detecting method in an aerial remote sensing image is characterized in that step is as follows:
Step 1: at first the aerial remote sensing image is carried out to adaptive threshold between maximum kind and cut apart, then the segmentation result image is first carried out to closing operation of mathematical morphology and carries out again the morphology opening operation and obtain water body and background segment image on every side, according to water body and on every side the background segment image intercept and obtain the water body area image from airborne remote sensing images;
Step 2: using the gray-scale value peaked 1/2 of water body area image as threshold value, the water body area image is carried out to the binaryzation operation, obtain water body zone bianry image, the zone that in the bianry image of water body zone, the pixel gray-scale value is 255 is object candidate area, and the zone that in the bianry image of water body zone, the pixel gray-scale value is 0 is the water body background area;
Step 3: calculate the area average of object candidate area, the object candidate area area is greater than to this mean value, Preliminary detection is Bridge object, and the Preliminary detection that is less than this mean value is Ship Target;
Step 4: the Preliminary detection target in rectangle, whether the test-target surrounding exists the water body background area.If the target surrounding is the water body background area, this target is the offshore naval vessel, if the target surrounding only has relative both sides, is the water body background area, and this target is crossing bridge.
2. crossing bridge and offshore naval vessel associated detecting method in the aerial remote sensing image according to claim 1, it is characterized in that: described Preliminary detection target in abutting connection with rectangle, be: take the center of Preliminary detection target is the center in abutting connection with rectangle, the length that is the Preliminary detection target in abutting connection with length and the width of rectangle and 1.5 times of width.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310379302XA CN103440655A (en) | 2013-08-27 | 2013-08-27 | Crossing bridge and offshore ship joint detection method in onboard remote sensing image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310379302XA CN103440655A (en) | 2013-08-27 | 2013-08-27 | Crossing bridge and offshore ship joint detection method in onboard remote sensing image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103440655A true CN103440655A (en) | 2013-12-11 |
Family
ID=49694348
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310379302XA Pending CN103440655A (en) | 2013-08-27 | 2013-08-27 | Crossing bridge and offshore ship joint detection method in onboard remote sensing image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103440655A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106372599A (en) * | 2016-08-30 | 2017-02-01 | 水利部水土保持监测中心 | Method and system for extracting silt arrester in water and soil retaining period |
| CN107677726A (en) * | 2017-09-29 | 2018-02-09 | 佛山科学技术学院 | A kind of real-time capture and analysis method of film breakdown phenomenon |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004302572A (en) * | 2003-03-28 | 2004-10-28 | Mitsubishi Space Software Kk | High luminance reflector image processing system, ship image processing system, method for processing image of high luminance reflector, computer readable recording medium recorded with program, and program |
| JP2006120006A (en) * | 2004-10-22 | 2006-05-11 | Nissan Motor Co Ltd | Eye opening/closing determination system |
| CN101634706A (en) * | 2009-08-19 | 2010-01-27 | 西安电子科技大学 | Method for automatically detecting bridge target in high-resolution SAR images |
| CN101976437A (en) * | 2010-09-29 | 2011-02-16 | 中国资源卫星应用中心 | High-resolution remote sensing image variation detection method based on self-adaptive threshold division |
| CN103020975A (en) * | 2012-12-29 | 2013-04-03 | 北方工业大学 | Wharf and ship segmentation method combining multi-source remote sensing image characteristics |
-
2013
- 2013-08-27 CN CN201310379302XA patent/CN103440655A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004302572A (en) * | 2003-03-28 | 2004-10-28 | Mitsubishi Space Software Kk | High luminance reflector image processing system, ship image processing system, method for processing image of high luminance reflector, computer readable recording medium recorded with program, and program |
| JP2006120006A (en) * | 2004-10-22 | 2006-05-11 | Nissan Motor Co Ltd | Eye opening/closing determination system |
| CN101634706A (en) * | 2009-08-19 | 2010-01-27 | 西安电子科技大学 | Method for automatically detecting bridge target in high-resolution SAR images |
| CN101976437A (en) * | 2010-09-29 | 2011-02-16 | 中国资源卫星应用中心 | High-resolution remote sensing image variation detection method based on self-adaptive threshold division |
| CN103020975A (en) * | 2012-12-29 | 2013-04-03 | 北方工业大学 | Wharf and ship segmentation method combining multi-source remote sensing image characteristics |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106372599A (en) * | 2016-08-30 | 2017-02-01 | 水利部水土保持监测中心 | Method and system for extracting silt arrester in water and soil retaining period |
| CN107677726A (en) * | 2017-09-29 | 2018-02-09 | 佛山科学技术学院 | A kind of real-time capture and analysis method of film breakdown phenomenon |
| CN107677726B (en) * | 2017-09-29 | 2021-05-04 | 佛山科学技术学院 | Real-time capturing and analyzing method for film breakdown phenomenon |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105574855B (en) | Infrared small target detection method under cloud background based on template convolution and false alarm rejection | |
| CN103400156B (en) | Based on the High Resolution SAR image Ship Detection of CFAR and rarefaction representation | |
| CN102496016B (en) | Infrared target detection method based on space-time cooperation framework | |
| CN104331886B (en) | Port region ship and warship detection method based on high resolution SAR image | |
| CN104050477A (en) | Infrared image vehicle detection method based on auxiliary road information and significance detection | |
| Xia et al. | A novel sea-land segmentation algorithm based on local binary patterns for ship detection | |
| CN104616006A (en) | Surveillance video oriented bearded face detection method | |
| CN114549933A (en) | Countermeasure sample generation method based on target detection model feature vector migration | |
| CN104766344A (en) | Vehicle detecting method based on moving edge extractor | |
| CN105512622A (en) | Visible remote-sensing image sea-land segmentation method based on image segmentation and supervised learning | |
| Yang et al. | HCNN-PSI: A hybrid CNN with partial semantic information for space target recognition | |
| CN104199009B (en) | A kind of radar image clutter suppression method based on time domain specification | |
| Xue et al. | Rethinking automatic ship wake detection: state-of-the-art CNN-based wake detection via optical images | |
| CN103577804A (en) | Abnormal human behavior identification method based on SIFT flow and hidden conditional random fields | |
| CN103440655A (en) | Crossing bridge and offshore ship joint detection method in onboard remote sensing image | |
| Si et al. | Maritime Ship Detection Method for Satellite Images Based on Multiscale Feature Fusion | |
| Zhang et al. | An improved lightweight yolo-fastest V2 for engineering vehicle recognition fusing location enhancement and adaptive label assignment | |
| Abad | Proposed image pre-processing techniques for face recognition using openCV | |
| Liu et al. | Obstacle recognition for ADAS using stereovision and snake models | |
| Zha et al. | SAR ship detection based on salience region extraction and multi-branch attention | |
| Yuanzi et al. | Transyolo: high-performance object detector for forward looking sonar images | |
| Tian et al. | A novel method of river detection for high resolution remote sensing image based on corner feature and SVM | |
| Huang et al. | The precise recognition of moving object in complex background | |
| TW201926248A (en) | Improved thermal image feature extraction method by increasing the weight of the human-shaped contour block to reduce the weight of the inner block of the human figure by analyzing the difference in thermal brightness of the inner region of the block | |
| Xu et al. | Crowd density estimation based on improved Harris & OPTICS Algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20131211 |