CN107862280A - A kind of storm surge disaster appraisal procedure based on unmanned aerial vehicle remote sensing images - Google Patents
A kind of storm surge disaster appraisal procedure based on unmanned aerial vehicle remote sensing images Download PDFInfo
- Publication number
- CN107862280A CN107862280A CN201711074644.5A CN201711074644A CN107862280A CN 107862280 A CN107862280 A CN 107862280A CN 201711074644 A CN201711074644 A CN 201711074644A CN 107862280 A CN107862280 A CN 107862280A
- Authority
- CN
- China
- Prior art keywords
- fishing
- calamity
- row
- remote sensing
- damage
- 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
- 238000000034 method Methods 0.000 title claims abstract description 45
- HUTDUHSNJYTCAR-UHFFFAOYSA-N ancymidol Chemical compound C1=CC(OC)=CC=C1C(O)(C=1C=NC=NC=1)C1CC1 HUTDUHSNJYTCAR-UHFFFAOYSA-N 0.000 claims abstract description 13
- 230000008859 change Effects 0.000 claims abstract description 5
- 238000012549 training Methods 0.000 claims description 14
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 13
- 238000001514 detection method Methods 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 3
- 210000004744 fore-foot Anatomy 0.000 claims description 3
- 238000011835 investigation Methods 0.000 abstract description 5
- 230000032683 aging Effects 0.000 abstract description 4
- 238000010606 normalization Methods 0.000 abstract description 2
- 238000000605 extraction Methods 0.000 description 8
- 238000011156 evaluation Methods 0.000 description 7
- 230000004927 fusion Effects 0.000 description 7
- 238000012544 monitoring process Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 239000000463 material Substances 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000002310 reflectometry Methods 0.000 description 4
- 239000013535 sea water Substances 0.000 description 4
- 230000003595 spectral effect Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 238000012937 correction Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000007500 overflow downdraw method Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 201000004569 Blindness Diseases 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 239000003653 coastal water Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000000368 destabilizing effect Effects 0.000 description 1
- 230000001066 destructive effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000001771 impaired effect Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- VMXUWOKSQNHOCA-UKTHLTGXSA-N ranitidine Chemical compound [O-][N+](=O)\C=C(/NC)NCCSCC1=CC=C(CN(C)C)O1 VMXUWOKSQNHOCA-UKTHLTGXSA-N 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
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
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/80—Geometric correction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- 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
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
-
- 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
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20212—Image combination
- G06T2207/20216—Image averaging
-
- 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
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
-
- 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
- G06T2207/30181—Earth observation
- G06T2207/30192—Weather; Meteorology
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to a kind of storm surge disaster appraisal procedure based on unmanned aerial vehicle remote sensing images, including：S1：Fishing row's remote sensing image after remote sensing image and calamity is arranged in fishing before the calamity of fishing row culture zone is obtained using unmanned plane；S2：Listed and indexed based on fishing and survey index threshold using fishing row's area before histogram Two-peak method acquisition calamity；Meanwhile using arest neighbors image matching method, remote sensing image is arranged into fishing after calamity and matched with fishing row remote sensing image before calamity, obtains fishing row's area after calamity；S3：Obtain disaster-stricken front and rear fishing row area change value；S4：Obtain fishing row's space wastage rate；S5：Default fishing row damage rate is chosen according to the Storm events grade of this storm tide, obtains the ratio of loss late and damage rate；S6：Obtain fishing and arrange disaster-stricken damaged area.Compared with prior art, the present invention had both improved the ageing of the condition of a disaster assessment, had ensured science, the normalization of investigation and assessment again, and can be using unmanned plane striograph as subsequent examination foundation.
Description
Technical field
The present invention relates to the field of preventing and reducing natural disasters, Disaster Assessment field, and unmanned aerial vehicle remote sensing images are based on more particularly, to one kind
Storm surge disaster appraisal procedure.
Background technology
China's Oceanic disasters loss accounts for the 10% of whole natural calamity total losses, and storm surge disaster is Oceanic disasters
First of.Effectively evaluate storm surge disaster to lose to caused by coastal culture zone, positive can enter for casualty loss situation
Row relief and compensation work, the assessment of storm surge disaster loss can simply be divided into two kinds：When the Pre-Evaluation of disaster, that is,
Predictability before disaster occurs assesses (risk assessment)；Second, the monitoring after disaster occurs is assessed, i.e., disaster occurs
Its general loss is estimated rapidly by live factual survey measuring and calculating afterwards.The accuracy that both assess is different, has different meanings
Justice and purposes.
After storm surge disaster occurs, ocean administrative departments at different levels all positive tissues implement disaster relief related work, ensure the victims of the disaster
Basic living, to greatest extent reduce disaster caused by loss.It is reported that cause culture zone straight for storm surge disaster at present
Economic loss evaluation is connect mainly by way of field investigation, reporting and submitting higher level, ocean front office personnel combine personal
Experience, historical data statistics, material is reported to carry out analysis decision.Although work of preventing and reducing natural disasters achieves huge effect, with
New period development, existing Disaster Assessment mechanism is remained compared with actual demand in worth improved place.Specifically include with
Under several aspects：
First, need to go deep into coastal the know the real situation tune detailed to each fisherman, the progress of She Hai enterprises in storm surge disaster evaluation process
Look into, rescue procedure is complicated and needs to put into more manpower and materials, and needs to spend the more time to realize commenting for the condition of a disaster
Estimate, can not meet ocean with fisheries management department in operational rapid response to customer's need；
Second, not covered comprehensively to more be compensated or investigated, more reports during the process of the investigation be present, report, leak again
The scene of report, easily cause Disaster Assessment and the uneven behavior such as repeat or omit, Disaster Assessment work with it is very big it is random with it is blind
Mesh.
The inventive method mainly studies the coastal culture zone monitoring property appraisal procedure after storm surge disaster occurs, and mainly
Consider the direct losses of disaster, that is, assess culture zone material property loss caused by disaster.Purpose is disaster occurs
When caused by culture zone direct economic loss make quick estimation, to provide reference frame in time for Disaster relief countermeasure.
The content of the invention
It is an object of the present invention to overcome the above-mentioned drawbacks of the prior art and provide one kind is distant based on unmanned plane
Feel the storm surge disaster appraisal procedure of image, both improved the ageing of the condition of a disaster assessment, ensure science, the rule of investigation and assessment again
Plasticity, and can be using unmanned plane striograph as subsequent examination foundation.
The purpose of the present invention can be achieved through the following technical solutions：
A kind of storm surge disaster appraisal procedure based on unmanned aerial vehicle remote sensing images, comprises the following steps：
S1：Fishing row's remote sensing image after remote sensing image and calamity is arranged in fishing before the calamity of fishing row culture zone is obtained using unmanned plane；
S2：According to before calamity fishing row remote sensing image obtain fishing list and index survey index threshold, based on fishing list and index survey index threshold adopt
Area S is arranged by fishing before fishing row remote sensing image acquisition calamity before calamity with histogram Two-peak method1；
Meanwhile using arest neighbors image matching method, remote sensing image is arranged into fishing after calamity and arranges remote sensing image with fishing before calamity
Matched, obtain fishing row's area S after calamity2；
S3：Disaster-stricken front and rear fishing row area change value Δ S is obtained, meets below equation：Δ S=S1-S2；
S4：Obtain fishing row's space wastage rate LLoss, meet below equation：LLoss=Δ S/S1；
S5：Default fishing row's damage rate L is chosen according to the Storm events grade of this storm tideDamage, obtain loss late and damage
The ratio L of rate is ruined, meets below equation：L=LDamage/LLoss；
S6：Obtain fishing and arrange disaster-stricken damaged area SDamage, meet below equation：SDamageDisaster-stricken damage face is arranged in=L × Δ S, the fishing
Product SDamageAs storm surge disaster assessment result.
Fishing row's area S after the acquisition calamity2The step of be specially：
First, fishing before calamity is arranged into remote sensing image as training sample, according to 8 × 8 pixel size to training sample
Image is split, and arranges fishing in training sample region and background water area progress features training, the extraction row of setting out on a fishing voyage region
With background water area corresponding to fishing row's region decision result of fishing row's remote sensing image and store before feature and calamity；
Then, the fishing row of fishing row's remote sensing image after feature acquisition calamity corresponding to region and background water area is arranged based on fishing
Region decision result, using arest neighbors image matching method, region decision result is arranged in the fishing that fishing after calamity is arranged to remote sensing image
Characteristic point is matched with the characteristic point of fishing row's region decision result of fishing row remote sensing image before calamity, deletes fishing row's remote sensing after calamity
Region decision knot is arranged in the unmatched fishing of characteristic point in striograph with fishing row's region decision result of fishing row remote sensing image before calamity
The characteristic point of fruit；
Finally, after the characteristic point acquisition calamity of fishing row's region decision result that remote sensing image is arranged according to fishing after the calamity filtered out
Fishing row's area S2。
Fishing row's damage rate LDamageIt is impaired by fishing row in the Storm events grade classification and historical disaster situation of storm tide
Range statistics obtains, and reflects that the row's of setting out on a fishing voyage affected area accounts for the area ratio that disaster-stricken forefoot area is arranged in fishing.
Fishing row's damage rate LDamageValue criterion be specially：
If height of being surged before and after storm tide H ∈ (30,50] cm, then LDamage=0；
If height of being surged before and after storm tide H ∈ (50,100] cm, then LDamage=0.1；
If height of being surged before and after storm tide H ∈ (100,150] cm, then LDamage=0.5；
If height of being surged before and after storm tide H ∈ (150,200] cm, then LDamage=0.69；
If height of being surged before and after storm tide H ∈ (200,300] cm, then LDamage=0.85；
If height of being surged before and after storm tide H ＞ 300cm, LDamage=1.
The fishing list and index survey index threshold Q meet below equation：In formula,For sample area
The average value of detection index is arranged in fishing, and σ is that the variance of detection index is arranged in the fishing of sample area.
Compared with prior art, the present invention has advantages below：
1st, the present invention considers to obtain by the way of unmanned aerial vehicle remote sensing Landed Typhoon point in time before and after storm surge disaster attached
Near high resolution remote sensing image, by being analyzed and processed to remote sensing image, the casualty loss letter of coastal culture zone is studied in extraction
Cease and it is analyzed, and Monitoring Index threshold value Fast Extraction, histogram Two-peak method and arest neighbors are arranged by fishing
Image matching method, qualitative analysis and quantitative analysis are organically combined, fishing row damage caused by having carried out typhoon disaster
Analysis, the assessment of fishing row damaged area, effective technical support is provided for fisheries management caused by tentatively extrapolating typhoon.
2nd, the calculating of fishing row area passes through arest neighbors image matching method, arest neighbors image matching method after calamity in the present invention
Selected correctly compared to the principle brush that individually same characteristic features point compared with before calamity be present using fishing row after calamity with histogram Two-peak method
Characteristic point can obtain the higher result of precision.
3rd, fishing row affected area statistics in the Storm events grade classification and historical disaster situation of the invention for combining storm tide
Set fishing to arrange damage rate, and optimal fishing is chosen according to the Storm events grade of real-time storm tide and arranges damage rate, so as to improve fishing
The degree of accuracy that damaged area is assessed is arranged, reliable guarantee is provided to carry out entry evaluation after calamity.
4th, experiment of UAV remote sensing system due to have the advantages that response is rapid, landing is convenient, can low latitude operation, high resolution,
Have in storm surge disaster is investigated and is assessed ageing well；Disaster-stricken situation is objectively responded out by unmanned plane striograph,
Reduce randomness and blindness that storm surge disaster is assessed.
Brief description of the drawings
Fig. 1 is the inventive method flow chart.
Embodiment
The present invention is described in detail with specific embodiment below in conjunction with the accompanying drawings.The present embodiment is with technical solution of the present invention
Premised on implemented, give detailed embodiment and specific operating process, but protection scope of the present invention is not limited to
Following embodiments.
As shown in figure 1, a kind of storm surge disaster appraisal procedure based on unmanned aerial vehicle remote sensing images comprises the following steps：
S1：Fishing row's remote sensing image after remote sensing image and calamity is arranged in fishing before the calamity of fishing row culture zone is obtained using unmanned plane.
This method is monitored by unmanned aerial vehicle remote sensing on the coastal culture zone easily influenceed by storm tide, grasps cultivation in real time
Real-time change situation before area's calamity after calamity, the orthophotoquad obtained using unmanned plane, face is arranged for fishing after calamity before follow-up acquisition calamity
Product provides Data safeguard.Comprise the following steps that：
(1) image data obtains, processing and orthography generate
1) survey region selection and flight-line design
According to the situation of Landed Typhoon, marine site region near debarkation point is chosen as regional assessment its Disaster of Storm Surges of taking photo by plane
Evil loss, to ensure to take photo by plane, region hazard-affected body casualty loss situation is clearly readable, and this ground resolution of taking photo by plane should be better than 0.1m,
Therefore flight flying height is set as 500m, set endlap as 80%, sidelapping 65%.The design in course line is according to actual existing
Field is set, it is necessary to meet that the influence data in research marine site can be covered.
2) flying quality acquisition and image data quality examination
Aerial images acquisition is carried out in the case where being adapted to the weather condition of unmanned plane, for gaps and omissions, fuzzy image data
Benefit survey is carried out, the requirement until meeting orthography generation.
3) image data processing and orthography generation
1. image joint is realized based on SIFT (Scale-invariant feature transform) algorithm
By computer technology, what shot unmanned plane using SIFT algorithms several had a lap just penetrates remote sensing image
Carry out spatial match alignment, be then fused into a width do not have obvious aberration, without obvious splicing line wide viewing angle scene panorama
Figure.The essence of SIFT operators is the image in different scale space come tectonic scale spatial function using difference of Gaussian function
On the Local Extremum with directional information that detects extract the position and direction of characteristic point.By the feature of acquisition to
Amount carries out characteristic matching so as to realize image joint.
2. visual fusion
Image fusion technology is the lap progress relevant treatment in image, ensures that image in overlapping region put down by transition
It is sliding, without obvious splicing seams, undistorted phenomenon, no luminance difference, there is good visual effect.Due to unmanned plane shadow to be spliced
Seem that same sensor is got, therefore can be merged using Pixel-level directly to be melted to the view data of lap
Close, this fusion can retain enough raw video information, and the visual fusion precision obtained to same type of sensor is very high.Weighting
Average fusion is a kind of fusion method the most frequently used in Pixel-level fusion, and its pixel value to overlapping region is folded again after being weighted
Add average treatment, fusion speed is fast, simple, intuitive.The selection of weight coefficient is that average weighted fusion method is crucial, and selection is suitable
When weights, it is possible to achieve overlapping region seamlessly transits.
3. geometric correction
Due to the destabilizing factor of remotely sensed image so that remote sensing images have certain geometric distortion, by eliminating image
On coordinate of the pixel in image coordinate system and its coordinate difference in the frames of reference such as map coordinates system, establish image
Cell coordinate and its corresponding relation under specific projected coordinate system between corresponding ground object target coordinate.Sat using remote sensing image
Coordinate transformation relation between mark and geographical coordinates (standard map, control point data) realizes geometric correction, generates orthophotoquad.
S2：Entry evaluation damaged area, fishing row's area S before calamity is obtained respectively1With fishing row's area S after calamity2。
(1) fishing row's area S before calamity1Acquisition
1) recognition principle
For fishing row because being built using timber and plastic material, reflectivity is higher than the seawater of background.In red wave band, fishing row
The red wave band reflectivity in culture zone is apparently higher than background water body, and in green wave band, fishing row's green wave band reflectivity in culture zone is slightly above background
Water body.It is less obvious in blue wave band, fishing row culture zone and the difference of seawater background.Therefore, the reflection differences of different-waveband are utilized
Spectral index different and using different-waveband, culture zone can be arranged to fishing and extracted.Meanwhile fishing row has obvious geometry
Shape.The grid for showing as approximate regulation is arranged in fishing, therefore can be in the extraction side in seawater fishery area using the texture information of image
Face plays a role.At present, textural characteristics are as a kind of vision for reflecting homogeneity phenomenon in image independent of color or brightness
Feature, important information and their contacting with surrounding environment of object surface structure tissue line are contained, on ground
Target identification has given play to due effect.
2) sensitive band selection is built with characteristic index
By analyzing the spectral signature of each wave band of remote sensing image, find to be difficult to culture zone mesh based on single wave band image
Target automatically extracts, and strengthens Target scalar in this construction feature index with prominent.The basic thought that Ratio index proposes is more
In spectral band, analysis draws the most strong reflection wave band of research ground class and most weak reflected waveband, is further expanded by ratio computing
Gap greatly between the two so that Target scalar obtains the enhancing of maximum on image, and background atural object is then suppressed.Due to coastal waters
Red wave band is arranged in the fishing of cultivation and the difference in reflectivity of green wave band and surrounding seawater is obvious.The present invention chooses green wave band and red ripple
Section structure Ratio index formula.
3) fishing, which is listed and indexed, surveys index threshold Fast Extraction
1. fishing row's detection index I
I=Bred/Bgreen, BredFor the numerical value of red spectral band, BgreenFor the numerical value of green light band.
2. fishing, which is listed and indexed, surveys index threshold Q determinations
Threshold value Q determination：The selection of threshold value is the average I values plus-minus 2 in the sample area based on fishing row remote sensing image before calamity
Times variance determine.Specific operation process is：Red, green, blue colored synthesis image based on remote sensing image, visually selection
Fishing stock layout local area, is made region of interest, calculates I average values and variance yields corresponding to the region of interest, then threshold value Q selection is located at
Wherein,For I average value, σ is sample area variance.
4) damaged area entry evaluation
Based on fishing list and index survey index threshold use histogram Two-peak method, by before calamity fishing row remote sensing image obtain calamity before fishing row
Area S1。
To sum up, the present invention establishes fishing row's Monitoring Index, research fishing row's Monitoring Index threshold value Fast Extraction, and is directed to fishing
Row is mixed with the characteristic of 2 kinds of objects of water body and raft in itself, can quickly, accurately be obtained using histogram Two-peak method before obtaining calamity
Fishing row's area S1。
(2) fishing row's area S after calamity2Acquisition
Because fishing row's distribution after disaster-stricken is irregular, the extent of damage is different, compared to having obvious geometry before calamity
Fishing row's distribution.The identification relative difficult of fishing row area after calamity, for this phenomenon, this method makees fishing row remote sensing image before calamity
It is input to for training sample in system, and arranges fishing culture zone and background water body progress features training, is extracted two kinds of
Feature and judged result simultaneously store, and then color characteristic that fishing after the calamity of acquisition is arranged to remote sensing image uses arest neighbors image
Method of completing the square, image is matched, calculate fishing row's gross area after calamity.Step is specially：
First, fishing before calamity is arranged into remote sensing image as training sample, according to 8 × 8 pixel size to training sample
Image is split, and arranges fishing in training sample region and background water area progress features training, the extraction row of setting out on a fishing voyage region
With background water area corresponding to fishing row's region decision result of fishing row's remote sensing image and store before feature and calamity.
Then, the fishing row of fishing row's remote sensing image after feature acquisition calamity corresponding to region and background water area is arranged based on fishing
Region decision result, using arest neighbors image matching method, region decision result is arranged in the fishing that fishing after calamity is arranged to remote sensing image
Characteristic point is matched with the characteristic point of fishing row's region decision result of fishing row remote sensing image before calamity, deletes fishing row's remote sensing after calamity
Region decision knot is arranged in the unmatched fishing of characteristic point in striograph with fishing row's region decision result of fishing row remote sensing image before calamity
The characteristic point of fruit.
Finally, after the characteristic point acquisition calamity of fishing row's region decision result that remote sensing image is arranged according to fishing after the calamity filtered out
Fishing row's area S2。
S3：Disaster-stricken front and rear fishing row area change value Δ S is obtained, meets below equation：Δ S=S1-S2, wherein, S1Calculating
By threshold value Q judgements and histogram Two-peak method, processing speed is fast and precision is high, S2Calculating pass through arest neighbors images match side
Method, arest neighbors image matching method is compared individually has same characteristic features using fishing row after calamity with histogram Two-peak method compared with before calamity
The principle brush of point, which selects correct characteristic point, can obtain the higher result of precision.
S4：Obtain fishing row's space wastage rate LLoss, meet below equation：LLoss=Δ S/S1, loss late expression is due to platform
The area ratio that the fishing that the storm tide of wind influences to be submerged, wash away is arranged；
S5：Default fishing row's damage rate L is chosen according to the Storm events grade of this storm tideDamage, obtain loss late and damage
The ratio L of rate is ruined, meets below equation：L=LDamage/LLoss, that is to say, that thinking that typhoon is more serious, fishing row's loss late is bigger, its
The ratio of damage is also higher, and Storm events grade will influence the ratio of damage rate and loss late.
Wherein, fishing row's damage rate LDamageBy in the Storm events grade classification and historical disaster situation of storm tide fishing row by
Damage range statistics to obtain, and reflect that the row's of setting out on a fishing voyage affected area accounts for the area ratio that disaster-stricken forefoot area is arranged in fishing.
In the present embodiment, fishing row's damage rate LDamageValue criterion such as following table：
| Rank | Storm events grade name | Surge/cm | Damage rate is arranged in fishing |
| 0 | Light storm tide | 30~50 | 0 |
| 1 | Whirlies tide | 51~100 | 0.1 |
| 2 | General storm tide | 101~150 | 0.5 |
| 3 | Larger storm tide | 151~200 | 0.69 |
| 4 | Tempest tide | 201~300 | 0.85 |
| 5 | Especially big storm tide | 301~450 | 1 |
| 6 | Rare especially big storm tide | More than 451 | 1 |
S6：Obtain fishing and arrange disaster-stricken damaged area SDamage, meet below equation：SDamageDisaster-stricken damage face is arranged in=L × Δ S, the fishing
Product SDamageAs storm surge disaster assessment result.
Destructive analysis is arranged in fishing caused by by carrying out storm surge disaster, and damaged area is arranged in fishing caused by tentatively extrapolating typhoon
Ratio, disaster-stricken damaged area S is arranged so as to obtain the high fishing of precisionDamage, reliable guarantee is provided to carry out entry evaluation after calamity.
To sum up, the present invention realizes unmanned plane image processing flow, fishing row identification and damaged area entry evaluation whole flow process
Integration, wherein, by SIFT algorithms identification feature point so as to realize the superposition of striograph, using fishing list and index survey index threshold
It is preliminary that Fast Extraction, histogram Two-peak method and arest neighbors image matching method quickly and accurately carry out disaster to striograph
Assess, both improved the ageing of the condition of a disaster assessment, and ensured science, the normalization of investigation and assessment again, and can be by unmanned plane shadow
As foundation of the figure as subsequent examination.
Claims (5)
1. a kind of storm surge disaster appraisal procedure based on unmanned aerial vehicle remote sensing images, it is characterised in that comprise the following steps：
S1：Fishing row's remote sensing image after remote sensing image and calamity is arranged in fishing before the calamity of fishing row culture zone is obtained using unmanned plane；
S2：Listed and indexed according to fishing row remote sensing image acquisition fishing before calamity and survey index threshold, listed and indexed based on fishing and survey index threshold using straight
Square figure Two-peak method arranges area S by fishing before fishing row remote sensing image acquisition calamity before calamity1；
Meanwhile using arest neighbors image matching method, remote sensing image is arranged into fishing after calamity and carried out with fishing row remote sensing image before calamity
Matching, obtain fishing row's area S after calamity2；
S3：Disaster-stricken front and rear fishing row area change value Δ S is obtained, meets below equation：Δ S=S1-S2；
S4：Obtain fishing row's space wastage rate LLoss, meet below equation：LLoss=Δ S/S1；
S5：Default fishing row's damage rate L is chosen according to the Storm events grade of this storm tideDamage, obtain loss late and damage rate
Ratio L, meet below equation：L=LDamage/LLoss；
S6：Obtain fishing and arrange disaster-stricken damaged area SDamage, meet below equation：SDamageDisaster-stricken damaged area S is arranged in=L × Δ S, the fishingDamage
As storm surge disaster assessment result.
2. a kind of storm surge disaster appraisal procedure based on unmanned aerial vehicle remote sensing images according to claim 1, its feature exist
In fishing row's area S after the acquisition calamity2The step of be specially：
First, fishing before calamity is arranged into remote sensing image as training sample, according to 8 × 8 pixel size to the image of training sample
Split, and arrange fishing in training sample region and background water area progress features training, extract the row of setting out on a fishing voyage region and the back of the body
The fishing of fishing row remote sensing image is arranged region decision result and stored before feature corresponding to scape water area and calamity；
Then, the fishing row region of fishing row's remote sensing image after feature acquisition calamity corresponding to region and background water area is arranged based on fishing
Judged result, using arest neighbors image matching method, by the feature of fishing row's region decision result of fishing row remote sensing image after calamity
Point is matched with the characteristic point of fishing row's region decision result of fishing row remote sensing image before calamity, deletes fishing row's remote sensing image after calamity
Region decision result is arranged in the unmatched fishing of characteristic point in figure with fishing row's region decision result of fishing row remote sensing image before calamity
Characteristic point；
Finally, the characteristic point that fishing row's region decision result of remote sensing image is arranged according to fishing after the calamity filtered out obtains fishing row after calamity
Area S2。
3. a kind of storm surge disaster appraisal procedure based on unmanned aerial vehicle remote sensing images according to claim 1, its feature exist
In fishing row's damage rate LDamageAffected area is arranged by fishing in the Storm events grade classification and historical disaster situation of storm tide
Statistics obtains, and reflects that the row's of setting out on a fishing voyage affected area accounts for the area ratio that disaster-stricken forefoot area is arranged in fishing.
4. a kind of storm surge disaster appraisal procedure based on unmanned aerial vehicle remote sensing images according to claim 3, its feature exist
In fishing row's damage rate LDamageValue criterion be specially：
If height of being surged before and after storm tide H ∈ (30,50] cm, then LDamage=0；
If height of being surged before and after storm tide H ∈ (50,100] cm, then LDamage=0.1；
If height of being surged before and after storm tide H ∈ (100,150] cm, then LDamage=0.5；
If height of being surged before and after storm tide H ∈ (150,200] cm, then LDamage=0.69；
If height of being surged before and after storm tide H ∈ (200,300] cm, then LDamage=0.85；
If height of being surged before and after storm tide H ＞ 300cm, LDamage=1.
5. a kind of storm surge disaster appraisal procedure based on unmanned aerial vehicle remote sensing images according to claim 1, its feature exist
Listed and indexed in, the fishing and survey index threshold Q and meet below equation：In formula,Listed and indexed for the fishing of sample area
The average value of index is surveyed, σ is that the variance of detection index is arranged in the fishing of sample area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711074644.5A CN107862280A (en) | 2017-11-06 | 2017-11-06 | A kind of storm surge disaster appraisal procedure based on unmanned aerial vehicle remote sensing images |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711074644.5A CN107862280A (en) | 2017-11-06 | 2017-11-06 | A kind of storm surge disaster appraisal procedure based on unmanned aerial vehicle remote sensing images |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107862280A true CN107862280A (en) | 2018-03-30 |
Family
ID=61700795
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711074644.5A Pending CN107862280A (en) | 2017-11-06 | 2017-11-06 | A kind of storm surge disaster appraisal procedure based on unmanned aerial vehicle remote sensing images |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107862280A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110533544A (en) * | 2019-08-28 | 2019-12-03 | 中国科学院遥感与数字地球研究所 | Crops freeze evil setting loss Claims Resolution method and system |
| CN114092821A (en) * | 2022-01-21 | 2022-02-25 | 北京艾尔思时代科技有限公司 | Wheat lodging extraction method and system based on unmanned aerial vehicle image and self-adaptive threshold |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101964060A (en) * | 2010-06-24 | 2011-02-02 | 西安电子科技大学 | SAR variant target identification method based on local textural feature |
| CN102214298A (en) * | 2011-06-20 | 2011-10-12 | 复旦大学 | Method for detecting and identifying airport target by using remote sensing image based on selective visual attention mechanism |
| US20150302270A1 (en) * | 2012-08-07 | 2015-10-22 | Metaio Gmbh | A method of providing a feature descriptor for describing at least one feature of an object representation |
| CN106504189A (en) * | 2016-11-29 | 2017-03-15 | 福建四创软件有限公司 | A kind of ocean disaster area extracting method based on GIS |
-
2017
- 2017-11-06 CN CN201711074644.5A patent/CN107862280A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101964060A (en) * | 2010-06-24 | 2011-02-02 | 西安电子科技大学 | SAR variant target identification method based on local textural feature |
| CN102214298A (en) * | 2011-06-20 | 2011-10-12 | 复旦大学 | Method for detecting and identifying airport target by using remote sensing image based on selective visual attention mechanism |
| US20150302270A1 (en) * | 2012-08-07 | 2015-10-22 | Metaio Gmbh | A method of providing a feature descriptor for describing at least one feature of an object representation |
| CN106504189A (en) * | 2016-11-29 | 2017-03-15 | 福建四创软件有限公司 | A kind of ocean disaster area extracting method based on GIS |
Non-Patent Citations (4)
| Title |
|---|
| 卢业伟 等: "基于高分辨率影像的近海养殖区的一种自动提取方法", 《遥感技术与应用》 * |
| 杜春鹏 等: "一种结合拓扑信息和SIFT特征的多源遥感影像自动匹配方法", 《测绘通报》 * |
| 环境保护部卫星环境应用中心，中国环境监测总站: "《生态环境遥感监测技术》", 31 December 2013, 北京：中国环境科学出版社 * |
| 闫静 等: "基于无人机遥感技术的港湾养殖区监测", 《厦门大学学报（自然科学版）》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110533544A (en) * | 2019-08-28 | 2019-12-03 | 中国科学院遥感与数字地球研究所 | Crops freeze evil setting loss Claims Resolution method and system |
| CN114092821A (en) * | 2022-01-21 | 2022-02-25 | 北京艾尔思时代科技有限公司 | Wheat lodging extraction method and system based on unmanned aerial vehicle image and self-adaptive threshold |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bao et al. | Monitoring of beach litter by automatic interpretation of unmanned aerial vehicle images using the segmentation threshold method | |
| Su et al. | Textural and local spatial statistics for the object‐oriented classification of urban areas using high resolution imagery | |
| Nichol et al. | Urban vegetation monitoring in Hong Kong using high resolution multispectral images | |
| US20110200249A1 (en) | Surface detection in images based on spatial data | |
| CN109376600A (en) | Multi-spectrum remote sensing image comprehensive characteristics cloud detection method of optic and device | |
| Bonnet et al. | Comparison of UAS photogrammetric products for tree detection and characterization of coniferous stands | |
| Szantoi et al. | A tool for rapid post-hurricane urban tree debris estimates using high resolution aerial imagery | |
| Hou et al. | Extraction of remote sensing-based forest management units in tropical forests | |
| Kabiri et al. | Detecting coral bleaching, using QuickBird multi-temporal data: a feasibility study at Kish Island, the Persian Gulf | |
| CN107862280A (en) | A kind of storm surge disaster appraisal procedure based on unmanned aerial vehicle remote sensing images | |
| CN117115669B (en) | Object-level ground object sample self-adaptive generation method and system with double-condition quality constraint | |
| Shokirov et al. | Multi-platform LiDAR approach for detecting coarse woody debris in a landscape with varied ground cover | |
| Korpela et al. | The performance of a local maxima method for detecting individual tree tops in aerial photographs | |
| Coulter et al. | Time–space radiometric normalization of TM/ETM+ images for land cover change detection | |
| Zhang | Native vegetation classification using remote sensing techniques: A case study of dairy flat regrowth bush by using the AUT unmanned aerial vehicle | |
| Ilangakoon et al. | Estimating leaf area index by bayesian linear regression using terrestrial Lidar, LAI-2200 plant canopy analyzer, and landsat tm spectral indices | |
| Wang et al. | Multi-scale crown closure retrieval for moso bamboo forest using multi-source remotely sensed imagery based on geometric-optical and Erf-BP neural network models | |
| Tang et al. | A new method for extracting trees and buildings from sparse LiDAR data in urban areas | |
| Akinbiola et al. | Application of UAV photogrammetry for the assessment of forest structure and species network in the tropical forests of southern nigeria | |
| Walker et al. | Southeast Florida shallow-water habitat mapping & coral reef community characterization | |
| Martini et al. | Using object-based image analysis to detect laughing gull nests | |
| Pan et al. | Improved seeded region growing for detection of water bodies in aerial images | |
| Torsvik et al. | Detection of macroplastic on beaches using drones and object-based image analysis | |
| Chayhard et al. | Application of aerial photography with visible atmospherically resistant index by using unmanned aerial vehicles for seagrass bed classification in Kung Krabaen Bay, Thailand | |
| Asriningrum et al. | Platform Reef Lagoon Detection From Sentinel-2 In Panggang Island And Semakdaun Island |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 350001 unit 6, 4 building, 245 Xiu Shan Road, Xin Dian Town, Jinan District, Fuzhou, Fujian, 608 Applicant after: Four creation technology limited company Address before: 350012 unit 6, 4 building, 245 Xiu Shan Road, Xin Dian Town, Jinan District, Fuzhou, Fujian, 608 Applicant before: Fujian Strong Software Co., Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180330 |