CN101614822B - Method for testing road damage based on post-disaster high-resolution remote sensing image - Google Patents
Method for testing road damage based on post-disaster high-resolution remote sensing image Download PDFInfo
- Publication number
- CN101614822B CN101614822B CN2009100894200A CN200910089420A CN101614822B CN 101614822 B CN101614822 B CN 101614822B CN 2009100894200 A CN2009100894200 A CN 2009100894200A CN 200910089420 A CN200910089420 A CN 200910089420A CN 101614822 B CN101614822 B CN 101614822B
- Authority
- CN
- China
- Prior art keywords
- road
- damage
- image
- remote sensing
- post
- 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
Abstract
The invention discloses a method for testing road damage based on post-disaster high-resolution remote sensing image, which belongs to the technical field of road damage detection and evaluation. The method comprises the steps as follows: high-resolution remote sensing image of a damaged road is preprocessed, and spatial registration is carried out on the image data and the data in a GIS road database; then, by adopting the assistant of the information in the GIS road database, the road coverage area before the damage is extracted through analyzing the post-disaster high-resolution remote sensing image; simultaneously, the road coverage area after the damage in the high-resolution remote sensing image is extracted; and road damage information is obtained through comparing the road coverage areas before and after the damage. The method fully uses the GIS road database, realizes the object-level damage testing method by adopting the post-disaster high-resolution image only, improves the accuracy of the testing results, and reduces the level of manual intervention.
Description
Technical field
The invention relates to the detection technique of the road damage that disaster causes, be specifically related to a kind of method that detects road damage based on post-disaster high-resolution remote sensing image.
Background technology
Road is the important component part of traffic life line system.After major natural disasters take place, understand the road damage situation in disaster area quickly and accurately, make rational planning for rescue path and formulation road repairing plan, rescue has crucial meaning for calamity emergency.High-resolution remote sensing image can reflect face of land information comprehensively, apace, and therefore the influence that is not subjected to the restriction of time and region, not destroyed by the ground disaster, has the application prospect of wide model in the road damage that disaster causes detects and assesses.With regard to the method that high-resolution remote sensing image detects road damage, mainly undertaken by artificial decipher mode, can not satisfy the demand of road damage fast detecting and assessment far away.
At present, change detecting method is the artificial target damage of the remote sensing image used always a detection method, and its basic skills is to utilize damage that the forward and backward not dbjective state of phase simultaneously takes place, and is analyzed, thereby finds the damage variation range of target.Fig. 1 is the basic procedure of change detecting method, wherein, the abstraction hierarchy of objective expression in the temporal feature extraction step, be divided into pixel level, feature level and target level, adopt the detection method difference of these three kinds of objective expression modes as follows: the method that adopts the pixel level to detect is basic processing unit with the pixel, utilize not the remote sensing image of phase simultaneously, image geometry registration, radiant correction are required than higher, as image difference method, image ratioing technigue etc., there are a large amount of insignificant non-target interfere informations in the testing result.The method that adopts the feature level to detect is to utilize through abstract attribute and architectural feature to compare, and testing result has certain target semanteme, and more approaching real atural object changes, and by feature extraction, has reduced the requirement to image type, radiant correction.And the method that adopts target level to detect is to carry out on the base of recognition in that the target in the image is carried out, and testing result has the specific aim semanteme, can fully utilize the target various features and compare.Therefore, target level detection method versatility is the strongest, is fit to different data source and image types, and the damage that is fit to very much artificial target such as road, buildings detects.
Summary of the invention
The present invention is based on target level detection method of the prior art, a kind of post-disaster high-resolution remote sensing image and GIS transportation database of utilizing is provided, realize the method that road damage detects, improved the accuracy of testing result, reduced the degree of manual intervention.
Technical scheme of the present invention is:
A kind of method based on the detection of the high-resolution remote sensing image after calamity road damage, its step comprises:
1) post-disaster high-resolution remote sensing image to road carries out pre-service, and the data of this image and the data of GIS transportation database are carried out spatial registration;
2) utilize the information and the above-mentioned post-disaster high-resolution remote sensing image of GIS transportation database, extract the routes coverage before damage takes place;
3) utilize the information of GIS transportation database once more, obtain the routes coverage after damage in the described high-resolution remote sensing image takes place;
4), thereby obtain the damage information of road by relatively damaging the variation of forward and backward road covering space scope.
Pre-service in the described step 1) comprises: utilize gaussian filtering to remove image noise, and stretch, regulate the image greyscale contrast with histogram.
Described step 2) is specially: post-disaster high-resolution remote sensing image is carried out rim detection, further refinement image edge, on center line, width and the category of roads information basis of while road before the damage that the GIS transportation database provides, the road straight-line segment that guiding Hough change detection is not damaged, be connected the complete bilateral line of the road segment segment formation road of not damage then by Feature Grouping with the Ribbon-snake method, thereby obtain the coverage of pavement of road.
Described step 3) is specially: the post-disaster high-resolution image is cut apart, on the basis of cut zone, information according to the GIS transportation database, to extracted region gray scale, the shape facility in the center line of road nearby sphere, according to above-mentioned feature identification typical case road area, be seed points further, according to the spectrum between the imagery zone, geometric properties relation with typical road area, merge the zone that satisfies condition around the seed points, form the overlay area of damage back road.
Described step 4) is that utilizing superposes damages forward and backward road covering space scope, obtains damaging the space distribution information of road.
Compared with prior art, the invention has the beneficial effects as follows:
The present invention only utilizes the post-disaster high-resolution image, and information such as the road axis that provides at the GIS transportation database, width down auxiliary realized damaging the extraction of forward and backward road covering area range respectively, and then obtained the road information of damage.Owing to only utilize the image after the calamity, overcome the preceding incomplete problem of image data of calamity.By on the forward and backward road target base of recognition of damage, detecting, make inspection 0 survey the result and have clear and definite road semanteme, help further assessment and analyze; Make full use of the auxiliary image feature analysis of priori that transportation database provides, improved result's accuracy, reduced the degree of manual intervention.
Description of drawings
Fig. 1 is the basic procedure of the change detecting method of the artificial target damage of existing remote sensing image;
Fig. 2 is the ultimate principle figure of road damage detection method of the present invention;
Fig. 3 obtains the process flow diagram of the routes coverage before damage takes place for the present invention;
The process flow diagram of the coverage extraction of back road takes place in Fig. 4 for the present invention damages;
Fig. 5 is the shape facility synoptic diagram according to the definition of GIS road route.
Embodiment
2 couples of the present invention describe in further detail below in conjunction with accompanying drawing:
First step: the high-resolution remote sensing image after the road damage is carried out pre-service, specifically be, utilize gaussian filtering to remove image noise, stretch with histogram and regulate image greyscale contrast etc.; And, the data of pending image data and GIS transportation database are carried out spatial registration in order to utilize GIS road data guiding image processing.
Second step: the routes coverage before road damage takes place is extracted.In the high resolution image after calamity, not destroyed highway sideline has kept the morphological feature of road before the damage, and GIS basis road data provides the center line and the information such as width, category of roads of road before the damage simultaneously.Therefore, not destroyed highway sideline in can passing through detection and being connected image extracts the complete bilateral line of the preceding road of damage, and then obtains coverage.
Fig. 3 is based on the concrete steps of extracting before the damage of bilateral line.At first utilize the detection algorithm that embeds degree of belief that pending post-disaster high-resolution remote sensing image is carried out rim detection, further utilize Mathematical Morphology Method refinement image edge.On the basis of edge detection results, in the contiguous regional extent of center line of road that the GIS transportation database provides, according to information such as the direction of road, width, the road straight-line segment that guiding Hough change detection is not damaged.Then, the road that provides with the GIS transportation database is the priori target, utilize the geological information such as locus, direction, width of detection of straight lines section, the complete bilateral line that is connected the road segment segment formation road of not damage by Feature Grouping with the Ribbon-snake method, at last the bilateral line of road is converted to polygon, obtains the coverage of pavement of road.
Third step: the routes coverage after damage takes place is extracted.In the post-disaster high-resolution image, Sun Hui pavement of road does not have the provincial characteristics of homogeneous.Therefore, can extract the pavement of road overlay area after damage takes place according to the feature in zone in the image.
Fig. 4 is the basic step that the coverage extraction of back road takes place in damage.At first, pending post-disaster high-resolution image is cut apart, on the basis of cut zone, for the extracted region gray scale, the shape facility that are positioned at the center line of road nearby sphere that the GIS transportation database provides.According to these features, calculate the fuzzy membership of road, discern typical road area, be seed points further with typical road area, utilize the gray scale between the imagery zone, several how various features relation, the width, the directional information that provide according to the GIS transportation database generate constraint condition, by the method for zone merging, merge the zone that satisfies condition around the seed points, form the overlay area of damage back road.
Fig. 5 is the shape facility synoptic diagram according to the definition of GIS road route.The GIS road data provides the center line of every road, according to every road route Road
Ref, define reference frame respectively, be initial point with the road starting point, be respectively length direction coordinate axis and Width coordinate axis along road direction and vertical road direction, its length L
AExpression, width W
AExpression.These features comprise position (dis), length and width (L and W), banded degree (ribbonfit).The distance of regional centre distance library track route has been represented in the position.Length and width have been described the zone respectively along the codomain scope on the coordinate axis of road direction and vertical road direction.Length is defined as the projection at the reference road length direction, and its width is defined as the projection at the reference road Width.The band shape degree is used to describe the fitting degree of zone and belt-like zone, is defined as the ratio of the area of zone outsourcing belt-like zone minimum with it.
The 4th step: the damage of road distributes and extracts.The road covering space scope that the damage of being obtained is forward and backward superposes, and calculates the road scope before the damage that is positioned at but the zone of road scope after damage not, the space distribution that obtains to damage road.
More than by specific embodiment the method for utilizing high-resolution remote sensing image to detect road damage provided by the present invention has been described, those skilled in the art is to be understood that, in the scope that does not break away from essence of the present invention, can make certain deformation or modification to the present invention; Be not limited to disclosed content among the embodiment.
Claims (5)
1. one kind is detected the method for road damage based on post-disaster high-resolution remote sensing image, and its step comprises:
1) post-disaster high-resolution remote sensing image to road carries out pre-service, and the data of this image and the data of GIS transportation database are carried out spatial registration;
2) utilize the information of GIS transportation database, post-disaster high-resolution remote sensing image is analyzed, extract the routes coverage before damage takes place;
3) utilize the information of GIS transportation database once more, extract the routes coverage after damage in the above-mentioned high-resolution remote sensing image takes place;
4), thereby obtain the damage information of road by relatively damaging the variation of forward and backward road covering space scope.
2. the method for claim 1 is characterized in that, the pre-service in the described step 1) comprises: utilize gaussian filtering to remove image noise, and stretch, regulate the image greyscale contrast with histogram.
3. the method for claim 1, it is characterized in that, described step 2) is specially: post-disaster high-resolution remote sensing image is carried out rim detection, further refinement image edge, on center line, width and the category of roads information basis of while road before the damage that the GIS transportation database provides, the road straight-line segment that guiding Hough change detection is not damaged, be connected the complete bilateral line of the road segment segment formation road of not damage then by Feature Grouping with the Ribbon-snake method, thereby obtain the coverage of the pavement of road before damage takes place.
4. as claim 1 or 3 described methods, it is characterized in that, described step 3) is specially: the post-disaster high-resolution image is cut apart, on the basis of cut zone, information according to the GIS transportation database, to extracted region gray scale, the shape facility in the center line of road nearby sphere, according to above-mentioned feature identification typical case road area, be seed points further with typical road area, according to the spectrum between the imagery zone, geometric properties relation, merge the zone that satisfies condition around the seed points, form the overlay area of damage back road.
5. the method for claim 1 is characterized in that, described step 4) is that utilizing superposes damages forward and backward road covering space scope, obtains damaging the space distribution information of road.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2009100894200A CN101614822B (en) | 2009-07-17 | 2009-07-17 | Method for testing road damage based on post-disaster high-resolution remote sensing image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2009100894200A CN101614822B (en) | 2009-07-17 | 2009-07-17 | Method for testing road damage based on post-disaster high-resolution remote sensing image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101614822A CN101614822A (en) | 2009-12-30 |
| CN101614822B true CN101614822B (en) | 2011-07-27 |
Family
ID=41494566
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2009100894200A Active CN101614822B (en) | 2009-07-17 | 2009-07-17 | Method for testing road damage based on post-disaster high-resolution remote sensing image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101614822B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101982831A (en) * | 2010-11-23 | 2011-03-02 | 中国科学院对地观测与数字地球科学中心 | Road quick extraction system |
| CN102409599B (en) * | 2011-09-22 | 2013-09-04 | 中国科学院深圳先进技术研究院 | Road surface detection method and system |
| CN103729853B (en) * | 2014-01-15 | 2016-06-08 | 武汉大学 | High score remote sensing image building under three-dimension GIS auxiliary damages detection method |
| CN105913361A (en) * | 2016-04-08 | 2016-08-31 | 民政部国家减灾中心 | Flood disaster assessment system and method |
| CN109300072B (en) * | 2018-09-07 | 2022-09-23 | 北京大学 | Traffic infrastructure damage condition calculation method based on geographic grids |
| CN109376638B (en) * | 2018-10-15 | 2022-03-04 | 西安建筑科技大学 | Text-to-ground rate calculation method based on remote sensing image and geographic information system |
| CN109785307B (en) * | 2019-01-09 | 2020-08-07 | 武汉大学 | Unmanned aerial vehicle image road damage assessment method based on vector guidance |
| CN109828999A (en) * | 2019-01-24 | 2019-05-31 | 厦门大学 | Road service system detection recognition method after calamity based on the cross-domain city big data of multi-source |
| CN111160199B (en) * | 2019-12-23 | 2022-09-13 | 云南省交通规划设计研究院有限公司 | Highway disaster information detection method based on high-resolution remote sensing image |
| CN117113160B (en) * | 2023-10-25 | 2024-02-02 | 北京大学深圳研究生院 | Post-disaster recovery condition monitoring method and device, computer equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1721877A (en) * | 2004-07-15 | 2006-01-18 | 牛铮 | Land application variety detection based on historical maps or drawings |
| CN1790052A (en) * | 2005-12-19 | 2006-06-21 | 武汉大学 | Area feature variation detection method based on remote sensing image and GIS data |
| TW200629183A (en) * | 2005-02-15 | 2006-08-16 | Univ Nat Pingtung Sci & Tech | Real-time mobile debris-flow disaster prevention and alert system |
| JP2007011582A (en) * | 2005-06-29 | 2007-01-18 | Information & Science Techno-System Co Ltd | Flood forecasting system |
| CN101126812A (en) * | 2007-09-27 | 2008-02-20 | 武汉大学 | High resolution ratio remote-sensing image division and classification and variety detection integration method |
-
2009
- 2009-07-17 CN CN2009100894200A patent/CN101614822B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1721877A (en) * | 2004-07-15 | 2006-01-18 | 牛铮 | Land application variety detection based on historical maps or drawings |
| TW200629183A (en) * | 2005-02-15 | 2006-08-16 | Univ Nat Pingtung Sci & Tech | Real-time mobile debris-flow disaster prevention and alert system |
| JP2007011582A (en) * | 2005-06-29 | 2007-01-18 | Information & Science Techno-System Co Ltd | Flood forecasting system |
| CN1790052A (en) * | 2005-12-19 | 2006-06-21 | 武汉大学 | Area feature variation detection method based on remote sensing image and GIS data |
| CN101126812A (en) * | 2007-09-27 | 2008-02-20 | 武汉大学 | High resolution ratio remote-sensing image division and classification and variety detection integration method |
Non-Patent Citations (1)
| Title |
|---|
| 任玉环等.汶川地震道路震害高分辨率遥感信息提取方法探讨.《遥感技术与应用》.2009,第24卷(第01期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101614822A (en) | 2009-12-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101614822B (en) | Method for testing road damage based on post-disaster high-resolution remote sensing image | |
| Yang et al. | 3D local feature BKD to extract road information from mobile laser scanning point clouds | |
| Weidner et al. | Classification methods for point clouds in rock slope monitoring: A novel machine learning approach and comparative analysis | |
| US9196048B2 (en) | Autonomous pavement condition assessment | |
| CN102930540B (en) | Method and system for detecting contour of urban building | |
| Díaz-Vilariño et al. | Automatic classification of urban pavements using mobile LiDAR data and roughness descriptors | |
| Gargoum et al. | A literature synthesis of LiDAR applications in transportation: Feature extraction and geometric assessments of highways | |
| Gao et al. | Detection and segmentation of cement concrete pavement pothole based on image processing technology | |
| CN106842231A (en) | A kind of road edge identification and tracking | |
| CN105203552A (en) | 360-degree tread image detecting system and method | |
| KR101219767B1 (en) | Method for Field Survey of Digital Mapping Road Layers Using Vehicle Mobile Mapping System | |
| Guo et al. | Automatic reconstruction of road surface features by using terrestrial mobile lidar | |
| CN106951879A (en) | Multiple features fusion vehicle checking method based on camera and millimetre-wave radar | |
| US10275916B2 (en) | Display method of road property and display device of road property | |
| CN107958183A (en) | A kind of city road network information automation extraction method of high-resolution remote sensing image | |
| Puente et al. | Automatic detection of road tunnel luminaires using a mobile LiDAR system | |
| CN110197173B (en) | Road edge detection method based on binocular vision | |
| CN103020605A (en) | Bridge identification method based on decision-making layer fusion | |
| KR20150109633A (en) | Position recognition apparatus and method of mobile object | |
| CN104504718A (en) | High-definition aerial remote sensing data automatic road extraction method | |
| CN103310199A (en) | Vehicle model identification method based on high-resolution remote sensing data | |
| Ma et al. | Automatic road damage detection using high-resolution satellite images and road maps | |
| Chen et al. | A feasibility study on use of generic mobile laser scanning system for detecting asphalt pavement cracks | |
| Wang et al. | Automatic estimation of road slopes and superelevations using point clouds | |
| US10514254B2 (en) | Road surface property acquiring method and road surface property acquiring device |
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 |