CN104239885A - Earthquake disaster damage degree evaluation method based on unmanned aerial vehicle aerial photos - Google Patents

Earthquake disaster damage degree evaluation method based on unmanned aerial vehicle aerial photos Download PDF

Info

Publication number
CN104239885A
CN104239885A CN201410454210.8A CN201410454210A CN104239885A CN 104239885 A CN104239885 A CN 104239885A CN 201410454210 A CN201410454210 A CN 201410454210A CN 104239885 A CN104239885 A CN 104239885A
Authority
CN
China
Prior art keywords
image
region
earthquake disaster
sigma
glcm
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.)
Granted
Application number
CN201410454210.8A
Other languages
Chinese (zh)
Other versions
CN104239885B (en
Inventor
刘皓挺
王巍
王学锋
于文鹏
王军龙
蓝天
马建立
何哲玺
宋伟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Aerospace Times Electronics Corp
Beijing Aerospace Control Instrument Institute
Original Assignee
China Aerospace Times Electronics Corp
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China Aerospace Times Electronics Corp filed Critical China Aerospace Times Electronics Corp
Priority to CN201410454210.8A priority Critical patent/CN104239885B/en
Publication of CN104239885A publication Critical patent/CN104239885A/en
Application granted granted Critical
Publication of CN104239885B publication Critical patent/CN104239885B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • 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
    • G06V10/54—Extraction of image or video features relating to texture

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Astronomy & Astrophysics (AREA)
  • Remote Sensing (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

Provided is an earthquake disaster damage degree evaluation method based on unmanned aerial vehicle aerial photos. An unmanned aerial vehicle is adopted to carry out hovering and image collection over an earthquake disaster area, earthquake disaster area image area-of-interest marking and selecting are respectively carried out on seven kinds of typical surface features, namely, houses, roads, bridges, dams, mountains, riverways and vegetation, according to an artificial interactive method, the gray level co-occurrence matrix textural features, the Tamura textural features, the Gabor ripplet textural features and the straight line and circle features of the selected area are selectively calculated, and finally the earthquake disaster surface feature damage degree is evaluated through a support vector machine classifier. The method is suitable for carrying out early information collection and evaluation in the happening area of earthquakes and secondary disasters caused by the earthquakes.

Description

A kind of earthquake disaster damage degree appraisal procedure of taking photo by plane based on unmanned plane
Technical field
The present invention relates to a kind of earthquake disaster damage degree appraisal procedure of taking photo by plane based on unmanned plane.
Background technology
China's area is vast in territory, and mountain range rises and falls, and in length and breadth, geologic condition is comparatively complicated in river.Due to reasons such as climate effect, geologic condition differences, many areas are subject to the infringement of earthquake and secondary disaster thereof throughout the year.The area such as Qinghai, Yunnan, western Sichuan, SOUTH OF GANSU as China be located in Alps-Himalaya seismic zone the place of process, repeatedly there is the earthquake of more than 4.5 grades in recent years, caused larger casualties and economic loss.Under normal circumstances, when earthquake disaster occurs, the most frequently used mode is the assessment adopting the earthquake magnitude of seismograph collection different earthquake sampled point and degree of splitting index to carry out disaster loss grade, and the advantage of this method is measurement result authority, highly versatile; But it is comparatively abstract, fuzzy that shortcoming is measurement result, not even not accurately, the degree that is damaged in a concrete disaster area cannot be described clearly.Definition as traditional earthquake destructiveness is divided into weak shock (earthquake magnitude is less than 3 grades), felt earthquake (earthquake magnitude is more than or equal to 3 grades, is less than 4.5 grades), middle macroseism (earthquake magnitude is greater than 4.5 grades, is less than 6 grades), macroseism (earthquake magnitude is greater than 6 grades), Giant Bullous (earthquake magnitude is greater than 8 grades) etc. according to the size of earthquake magnitude, the information that this kind of evaluation index provides for the rescue personnel of non-geology specialty when carrying out seismic disaster relief is comparatively fuzzy, the damaged condition that earthquake causes earth's surface building and structure cannot be judged, and due to seismograph sampled point limited amount, certain distance is all had apart from different earthquake disaster area, the geology characteristic of each department, construction quality is all not identical, the earthquake actual destruction of causing and the situation of injuring are also not exclusively corresponding with These parameters, therefore often the real disaster-stricken situation information in reflection concrete earthquake areas is difficult to, and then be also difficult to the emergency degree judging seismic disaster relief.
Along with the development of scientific and technological level, in Disaster Assessment technological means, adopt remote sensing or Aerial Images to carry out the information of disaster scenarios it and assessment has data feature directly perceived, believable, be widely used in domestic all kinds of disaster alarm and rescue task in recent years.Chinese patent " remote sensing earthquake damage information extraction and method for digging based on pixel " (domestic patent publication No. CN101788685A) proposes a kind of method adopting remote Sensing Image Analysis, automatically region of variation is found by spectrum variation, principal component fusion, adopt dual threshold algorithm of region growing to split region of variation again, the mode explained finally by artificial visual extracts Earthquake damage information; Chinese patent " a kind of disaster situation obtaining system " (domestic patent publication No. CN201672918U) proposes the method adopting unmanned plane carry video camera, digital camera, forward looking infrared image collecting device, gather disaster-stricken image, with auxiliary disaster assistance and post-disaster reconstruction; Chinese patent " a kind of disaster monitoring electronics delineation system of taking photo by plane based on unmanned plane " (domestic patent publication No. CN102419171A) proposes to adopt a kind of ground delineation system to adopt the mode of writing pencil to mark to the information that unmanned plane is passed back.But, by being not difficult to find out the analysis of above-mentioned patent: the problem using remotely-sensed data to carry out disaster loss grade assessment is the acquisition of remotely-sensed data and editor's analytical cycle is longer, cost is higher, issue and the acquisition of data can only be provided by specific channel and authoritative department; And the acquisition of high-altitude Aerial Images needs to adopt medium-sized or large-scale aircraft to perform aerial mission, be not easy to carrying and use of rescue group.
Summary of the invention
Technical matters to be solved by this invention is, proposes the earthquake disaster damage degree appraisal procedure of taking photo by plane based on unmanned plane that a kind of cost is low, can realize the quick collection to the disaster-stricken situation in earthquake-stricken area and assessment.
The present invention includes following technical scheme:
1, based on the earthquake disaster damage degree appraisal procedure that unmanned plane is taken photo by plane, it is characterized in that performing step is as follows:
(1) set up typical earthquake disaster image feature data collection, described typical earthquake disaster image feature data collection comprises the earthquake disaster image feature data collection of house, road, bridge, dykes and dams, massif, river course and vegetation;
To multiple earthquake disaster images of acquisition of taking photo by plane based on unmanned plane in the past, determine that the image-region in house obtains the image-region more than 200 houses by the mode of user's hand labeled, the image-region in each house determined is calculated to the characteristics of image in house, and the house damage degree that the image-region providing each house is corresponding, thus obtain the earthquake disaster image feature data collection in house;
To multiple earthquake disaster images of acquisition of taking photo by plane based on unmanned plane in the past, determine that the image-region of road obtains the image-region more than 200 roads by the mode of user's hand labeled, the image-region of each road determined is calculated to the characteristics of image of road, and the road damage degree that the image-region providing each road is corresponding, thus obtain the earthquake disaster image feature data collection of road;
To multiple earthquake disaster images of acquisition of taking photo by plane based on unmanned plane in the past, determine that the image-region of bridge obtains the image-region more than 200 bridges by the mode of user's hand labeled, the image-region of each bridge is calculated to the characteristics of image of bridge, and the bridge damage degree that the image-region providing each bridge is corresponding, thus obtain the earthquake disaster image feature data collection of bridge;
To multiple earthquake disaster images of acquisition of taking photo by plane based on unmanned plane in the past, determine that the image-region of dykes and dams obtains the image-region more than 200 dykes and dams by the mode of user's hand labeled, the image-region of each dykes and dams is calculated to the characteristics of image of dykes and dams, and the dykes and dams damage degree that the image-region providing each dykes and dams is corresponding, thus obtain the earthquake disaster image feature data collection of dykes and dams;
To multiple earthquake disaster images of acquisition of taking photo by plane based on unmanned plane in the past, determine that the image-region of massif obtains the image-region more than 200 massifs by the mode of user's hand labeled, the image-region of each massif is calculated to the characteristics of image of massif, and the massif damage degree that the image-region providing each massif is corresponding, thus obtain the earthquake disaster image feature data collection of massif;
To multiple earthquake disaster images of acquisition of taking photo by plane based on unmanned plane in the past, determine that the image-region in river course obtains the image-region more than 200 river courses by the mode of user's hand labeled, the image-region in each river course is calculated to the characteristics of image in river course, and the river course damage degree that the image-region providing each river course is corresponding, thus obtain the earthquake disaster image feature data collection in river course;
To multiple earthquake disaster images of acquisition of taking photo by plane based on unmanned plane in the past, determine that the image-region of vegetation obtains the image-region more than 200 vegetation by the mode of user's hand labeled, the image-region of each vegetation is calculated to the characteristics of image of vegetation, and the vegetation damage degree that the image-region providing each vegetation is corresponding, thus obtain the earthquake disaster image feature data collection of vegetation;
The characteristics of image in house comprises gray level co-occurrence matrixes angle second moment index GLCM aSM, gray level co-occurrence matrixes index of correlation GLCM cOR, gray level co-occurrence matrixes entropy index GLCM eNT, contrast index T in Tamura textural characteristics con, Gabor direction character index f gabor, utilize Hough transform to carry out the straight line number index H of straight-line detection lwith the round number index H utilizing Hough transform to carry out loop truss c;
The characteristics of image in road, bridge, dykes and dams and river course includes gray level co-occurrence matrixes angle second moment index GLCM aSM, gray level co-occurrence matrixes moment of inertia index GLCM cON, gray level co-occurrence matrixes entropy index GLCM eNT, gray level co-occurrence matrixes unfavourable balance square index GLCM iDM, contrast index T in Tamura textural characteristics con, Gabor direction character index f gaborwith the straight line number index H utilizing Hough transform to carry out straight-line detection l;
The characteristics of image of massif and vegetation includes gray level co-occurrence matrixes angle second moment index GLCM aSM, gray level co-occurrence matrixes moment of inertia index GLCM cON, gray level co-occurrence matrixes unfavourable balance square index GLCM iDM, contrast index T in Tamura textural characteristics conwith Gabor direction character index f gabor;
(2) utilize house, road, bridge, dykes and dams, massif, the earthquake disaster image feature data training of river course and vegetation practices respective support vector machine classifier;
(3) take photo by plane based on unmanned plane and obtain new earthquake disaster image;
(4) for house, road, bridge, dykes and dams, massif, river course, vegetation 7 quasi-representative atural object, corresponding image-region is determined respectively by the mode of user's hand labeled to the new earthquake disaster image obtained, calculate characteristics of image corresponding to every quasi-representative atural object according to the image-region determined, finally corresponding according to every quasi-representative atural object characteristics of image adopts the sorter of corresponding support vector machine to carry out the assessment of all kinds of atural object damage degree.
The present invention compared with prior art beneficial effect is:
(1) the present invention devises a kind of earthquake disaster damage degree appraisal procedure adopting unmanned plane to take image, directly assess according to the damage degree being carried out earthquake and secondary disaster thereof by damage degree of earth's surface culture and Images of Natural Scenery, have the disaster-stricken situation in disaster area is described accurately, feature intuitively.
(2) the damage degree appraisal procedure designed by the present invention, adopts the image gathered in earthquake disaster in the past to carry out extraction and the calculating of the aspect of model, achieves accumulation of knowledge and reuse, have higher assessment reliability and accuracy.
(3) the disaster damage degree appraisal procedure designed by the present invention, unmanned aerial vehicle platform near the ground is adopted to carry out the collection of view data, and adopt damage degree assessment software to carry out the process of view data, there is the advantage that system is easy to use, flexible, cost is low, intelligence degree is high, be suitable for equipping recovery force on a large scale.
(4) the present invention's gray level co-occurrence matrixes image texture characteristic, Tamura textural characteristics, Gabor wavelet textural characteristics, straight line and circular image feature of adopting when carrying out the assessment of atural object damage degree, close to the visual perception of human visual system, the damage degree of earthquake to atural object can be described preferably, there is the advantage calculating simple, explicit physical meaning that is that calculate etc.
Accompanying drawing explanation
Fig. 1 is method calculation flow chart of the present invention;
Fig. 2 is UAS operating diagram of the present invention.
Embodiment
As shown in Figure 1, the inventive method based on evaluating system comprise many rotor wing unmanned aerial vehicles subsystem, unmanned plane during flying ground control and output display subsystem composition, wherein:
Many rotor wing unmanned aerial vehicles subsystem is made up of many rotor wing unmanned aerial vehicles, two-freedom rotary motion camera, GPS locating module, on-air radio data transceiver terminal; Many rotor wing unmanned aerial vehicles are installed two-freedom rotary motion camera, GPS locating module and on-air radio data transceiver terminal; Many rotor wing unmanned aerial vehicles are the unmanned plane during flying device of 4 rotors, 6 rotors or 8 rotors, and many rotor wing unmanned aerial vehicles adopt powered battery, and the non-stop flight time is not less than 30 minutes, and flying height is not less than 15 meters; Two-freedom rotary motion camera can realize the rotation of pitching-5 ° ~ 185 °, driftage 0 ° ~ 300 ° of angular ranges; GPS locating module is for obtaining the current spatial coordinated information of unmanned plane; On-air radio data transceiver terminal is for receiving the flight steering order that unmanned plane during flying ground controls and output display subsystem sends, and the unmanned plane during flying ground image that the camera of many rotor wing unmanned aerial vehicles is taken being sent it back ground controls and output display subsystem;
Unmanned plane during flying ground controls and output display subsystem is made up of terrestrial wireless data transceiver terminal and portable computer; Terrestrial wireless data transceiver terminal is used for and many rotor wing unmanned aerial vehicles carry out data communication, controls, monitors the normal flight of many rotor wing unmanned aerial vehicles; Portable computer is used for the picture of the many rotor wing unmanned aerial vehicle shootings of output display, portable computer utilizes the sorter of typical earthquake disaster image feature data set pair support vector machine to train, and adopt the sorter of support vector machine to carry out the estimation of the damaged degree of ruining of interactively, the duty of the many rotor wing unmanned aerial vehicles of simultaneous real-time monitoring according to the image of shooting.
The present invention adopts the wireless network transmissions agreement of IEEE 802.11G, and according to the compressed format of MPEG4, the image taken by many rotor wing unmanned aerial vehicles camera controls to unmanned plane during flying ground and output display subsystem returns.Two-freedom rotary motion camera is Visible Light Camera.
As shown in Figure 2, the performing step of earthquake disaster damage degree appraisal procedure of taking photo by plane based on unmanned plane of the present invention is as follows:
(1) set up typical earthquake disaster image feature data collection, described typical earthquake disaster image feature data collection comprises the earthquake disaster image feature data collection of house, road, bridge, dykes and dams, massif, river course and vegetation:
To multiple earthquake disaster images of acquisition of taking photo by plane based on unmanned plane in the past, determine that the image-region in house obtains the image-region more than 200 houses by the mode of user's hand labeled, the image-region in each house determined is calculated to the characteristics of image in house, and the house damage degree that the image-region providing each house is corresponding, thus obtain the earthquake disaster image feature data collection in house;
To multiple earthquake disaster images of acquisition of taking photo by plane based on unmanned plane in the past, determine that the image-region of road obtains the image-region more than 200 roads by the mode of user's hand labeled, the image-region of each road determined is calculated to the characteristics of image of road, and the road damage degree that the image-region providing each road is corresponding, thus obtain the earthquake disaster image feature data collection of road;
To multiple earthquake disaster images of acquisition of taking photo by plane based on unmanned plane in the past, determine that the image-region of bridge obtains the image-region more than 200 bridges by the mode of user's hand labeled, the image-region of each bridge is calculated to the characteristics of image of bridge, and the bridge damage degree that the image-region providing each bridge is corresponding, thus obtain the earthquake disaster image feature data collection of bridge;
To multiple earthquake disaster images of acquisition of taking photo by plane based on unmanned plane in the past, determine that the image-region of dykes and dams obtains the image-region more than 200 dykes and dams by the mode of user's hand labeled, the image-region of each dykes and dams is calculated to the characteristics of image of dykes and dams, and the dykes and dams damage degree that the image-region providing each dykes and dams is corresponding, thus obtain the earthquake disaster image feature data collection of dykes and dams;
To multiple earthquake disaster images of acquisition of taking photo by plane based on unmanned plane in the past, determine that the image-region of massif obtains the image-region more than 200 massifs by the mode of user's hand labeled, the image-region of each massif is calculated to the characteristics of image of massif, and the massif damage degree that the image-region providing each massif is corresponding, thus obtain the earthquake disaster image feature data collection of massif;
To multiple earthquake disaster images of acquisition of taking photo by plane based on unmanned plane in the past, determine that the image-region in river course obtains the image-region more than 200 river courses by the mode of user's hand labeled, the image-region in each river course is calculated to the characteristics of image in river course, and the river course damage degree that the image-region providing each river course is corresponding, thus obtain the earthquake disaster image feature data collection in river course;
To multiple earthquake disaster images of acquisition of taking photo by plane based on unmanned plane in the past, determine that the image-region of vegetation obtains the image-region more than 200 vegetation by the mode of user's hand labeled, the image-region of each vegetation is calculated to the characteristics of image of vegetation, and the vegetation damage degree that the image-region providing each vegetation is corresponding, thus obtain the earthquake disaster image feature data collection of vegetation.
For above-mentioned 7 quasi-representative image category, the mode of user's hand labeled is as follows:
For road, bridge, dykes and dams and river course, determine that the method for corresponding image-region is as follows by the mode of user's hand labeled: adopt the mode of straight line and Drawing of Curve to mark road, bridge, the edge placement in dykes and dams and river course, then to extract between straight line and/or curve image-region as the image-region determined; For house, determined that by the mode of user's hand labeled the method for the image-region in house is as follows: adopt the manual position of drawing a circle to approve out house of quadrilateral, then extract the image-region of quadrilateral inside as the image-region determined; For massif and vegetation, determine that the method for corresponding image-region is as follows by the mode of user's hand labeled: adopt the manual region of drawing a circle to approve out massif and vegetation of polygon, then extract the image-region of polygonal internal as the image-region determined.
Each characteristics of image of the present invention is defined as follows:
I) gray level co-occurrence matrixes angle second moment GLCM aSM, this index characterization metric of image texture intensity profile degree of uniformity and texture fineness, its calculating formula is such as formula shown in (1):
GLCM ASM = Σ i Σ j p ( i , j ) 2 - - - ( 1 )
Wherein, the gray level co-occurrence matrixes that p (i, j) is piece image, coordinate (i, j) represents image location information.
Ii) gray level co-occurrence matrixes moment of inertia GLCM cON, this index characterization metric of the sharpness of image texture and the depth of texture, its calculating formula is such as formula shown in (2):
GLCM CON = Σ i Σ j ( i - j ) 2 p ( i , j ) - - - ( 2 )
Iii) gray level co-occurrence matrixes is correlated with GLCM cOR, this index characterization metric of texture similar area directivity size, its calculating formula is such as formula shown in (3):
GLCM COR = Σ i Σ j ( ij ) p ( i , j ) - μ x GLCM μ y GLCM σ x GLCM σ y GLCM - - - ( 3 )
Wherein, be respectively p x ( i ) = Σ k p ( i , k ) , ( i = 1,2 , . . . , N g ) With average and mean square deviation, N gfor the maximal value of single pixel grayscale.
Iv) gray level co-occurrence matrixes entropy GLCM eNT, the complexity of this index characterization gradation of image distribution or mixed and disorderly degree, its calculating formula is such as formula shown in (4):
GLCM ENT = - Σ i Σ j p ( i , j ) log [ p ( i , j ) ] - - - ( 4 )
V) gray level co-occurrence matrixes unfavourable balance square GLCM iDM, the degree of uniformity of this index characterization image texture, its calculating formula is such as formula shown in (5):
GLCM IDM = Σ i Σ j 1 1 + ( i - j ) 2 p ( i , j ) - - - ( 5 )
Vi) the contrast T in Tamura textural characteristics con, the intensity of this index characterization variation of image grayscale, its calculating formula is such as formula shown in (6) and (7):
T con = σ α 4 1 / 4 - - - ( 6 )
α 4 = μ 4 σ 4 - - - ( 7 )
Wherein μ 4be the fourth central distance of image patch, σ is the mean square deviation of the image-region determined, α 4for intermediate variable.When actual computation, first the rectangular window region of fixed size in the image-region determined is got, i.e. image patch, and adopt this rectangular window area coverage image to determine region according to order from top to bottom, from left to right, and carry out image fourth central apart from the calculating with mean square deviation.
Vii) Gabor direction character f gabor: if g (x, y) represents Gabor function, using g (x, y) as generating function, by carrying out yardstick expansion and rotational transform to g (x, y), can obtain one group of self similarity wave filter g mn(x, y), Gabor wavelet conversion may be defined as formula (12), and corresponding textural characteristics can be calculated as formula (13) and (14).Gabor wavelet proper vector may be defined as formula (15).
g ( x , y ) = 1 2 π σ x σ y exp [ - 1 2 ( x 2 σ x 2 + y 2 σ y 2 ) + 2 πjWx ] - - - ( 8 )
g mn(x,y)＝a -mg(x′,y′) (9)
x′＝a -m(xcosθ+ysinθ) (10)
y′＝a -m(-xsinθ+ycosθ) (11)
W mn ( x , y ) = ∫ ∫ I ( x , y ) g mn * ( x - x 1 , y - y 1 ) d x 1 d y 1 - - - ( 12 )
μ mn＝∫∫|W mn(x,y)|dxdy (13)
σ mn = ∫ ∫ [ | W mn ( x , y ) | - μ mn ] 2 dxdy - - - ( 14 )
Wherein, g (x, y) represents Two-Dimensional Gabor Wavelets basis function, and W is Gaussian function multiple modulation frequency, σ x, σ yfor the mean square deviation of variable x and y; g mn(x, y) is self similarity wave filter, a -mscale factor, a>1, x ', y ' is the result of calculation after converting x, y, m and n is integer, represents corresponding yardstick and direction, m ∈ [0, M-1], M are all dimension, n ∈ [0, K-1], θ=n π K, K are all direction numbers, subscript " * " represents conjugate complex number, x 1, y 1represent Gabor wavelet integral transformation side-play amount, I (x, y) represents the image-region selected out, W mnthe result that (x, y) converts for Gabor wavelet, μ mn, σ mnfor average and the mean square deviation feature of Gabor wavelet.
Viii), in the artificial structure taken photo by plane at unmanned plane, than being easier to the edge occurring buildings rule, as the fundamental element such as straight line, circle, Hough transform technology therefore can be adopted to realize the straight line number H of straight-line detection lwith the round number H of loop truss cfeature interpretation calculate.With other line compared with loop truss technology, the detection technique of Hough transform has the advantages that calculated amount is little, calculating accuracy is high.
By above-mentioned calculated disaster characteristic composition typical earthquake disaster image feature data collection, and according to earthquake disaster expertise, the grade destroyed according to disaster carries out the mark of disaster damage degree.A kind of typical earthquake disaster image feature data collection sample is as shown in 1 table.Damage degree concept proposed by the invention, mainly describes from the angle of graphical analysis the destructiveness that house, road, bridge, massif etc. suffer when suffering earthquake or its secondary disaster affects.This index should build with evaluated ground artificial the construction quality of natural scene or geologic structure relevant, therefore have and more specifically, more intuitively describe effect accurately than indexs such as earthquake magnitude, degree of splitting.Such as, place A and the place B in somewhere simultaneously shake, and the earthquake magnitude that seismograph records is similarly 6.0 grades; But the geologic structure on A ground is comparatively firm, culture's quality is better, and when generation 6.0 grades of earthquakes, the damage that earth's surface suffers is not very serious, the casualties caused is naturally less, and it is little that the image result of taking photo by plane is that earth's surface culture and natural scene damage degree; And B ground is located in mountain region along the river, earth's surface culture is second-rate, and there occurs serious earth's surface when generation 6.0 grades of earthquakes caves in, and culture all damages, and casualties is serious, and it is huge that the result of taking photo by plane is that culture and natural scene damage degree.The definition of damage degree defines according to the artificial experience of seismological expert and rescue expert the destructiveness that atural object causes according to earthquake.Be enumerated a kind of 5 grades of appraisal procedures of building construction damage degree in table 2, the damage degree define method of other 6 type atural object is similar with it.When the damage degree assessment of reality, need seismological expert and rescue expert to observe a large amount of historical earthquake and to take photo by plane data, according to the content of definition in table 2, carry out differentiation and the marking of atural object damage degree according to subjective judgement.Therefore, by the definition of image damage degree, can image and the different Disaster degree in quantitative description two places, for follow-up rescue work provides guidance.
Table 1 earthquake disaster damage degree evaluate image characteristic data set sample
Table 2 house damage degree define method
Sequence number Damage situation describes Grade
1 Surface structures generation crackle, but do not cave in One-level
2 Surface structures generation severe crack, but do not cave in Secondary
3 Surface structures generating portion is caved in, but major structural damage occurs Three grades
4 Surface structures caves in, but structure is for gross distortion occurs Level Four
5 Surface structures caves in completely, and comminuted destruction occurs in building structure Pyatyi
When occur landslide secondary disaster, rubble flow secondary disaster, surface collapse, sedimentation and cracking seismic secondary disaster time, the training data obtained when account form and above-mentioned generation earthquake disaster and monitoring data completely the same; And the destructiveness caused ground due to all kinds of disaster is different, the span difference to some extent of corresponding each feature, therefore can realize the differentiation to all kinds of disaster by said method.
(2) typical earthquake disaster image feature data collection training classifier is adopted.
According to the data set accumulated in above-mentioned steps (1), carry out the training of SVM classifier.SVM classifier is the mathematical tool of the Corpus--based Method theories of learning, compared with other sorter instrument, SVM is more suitable for the data solving small sample, non-linear, high-dimensional, local minimum problem, and the present invention is comparatively applicable to solving disaster damage degree classification problem herein by attempting various sorter determination SVM classifier.In the implementation of training, need training 7 sorters altogether, be respectively the image analysis result of house, road, bridge, dykes and dams, massif, river course, vegetation damage situation, the indicator combination mode of graphical analysis can see the content in table 1.The training data of each sorter is the various combination (see table 1) of image texture and edge feature, the evaluation grade (see table 2) of the comprehensive degree of damage of the monitoring data of sorter each disaster that to be seismological expert provide according to professional knowledge.The sample size of each SVM classifier training data should be greater than 200 groups of data (positive and negative sample number is respectively greater than 100), and the classification precision of prediction of final each SVM classifier should be greater than 95%.Once sorter has been trained, then the output of this sorter has been then the description to earthquake and secondary disaster damage degree thereof.
(3) take photo by plane based on unmanned plane and obtain new earthquake disaster image
The many rotor wing unmanned aerial vehicles of remote control carry out flying or hovering in overhead, disaster area, in the process of flight, the camera of carry in unmanned plane lower end carries out captured in real-time to the ground in disaster area, among the internal memory result of shooting being stored in system, and according to demand by the wireless network transmissions agreement of the data acquisition IEEE 802.11G taken photo by plane and according to the compressed format of MPEG4 send back in real time ground unmanned plane during flying ground control and output display subsystem among, obtain new earthquake disaster image.
(4) assessment of damage degree is carried out
To the new earthquake disaster image obtained, corresponding image-region is determined for house, road, bridge, dykes and dams, massif, river course, vegetation 7 quasi-representative atural object respectively by the mode of user's hand labeled, calculate characteristics of image corresponding to every quasi-representative atural object according to the image-region determined, finally corresponding according to every quasi-representative atural object characteristics of image adopts the sorter of corresponding support vector machine to carry out the assessment of damage degree.
The inventive method is comparatively suitable for earthquake and secondary landslide, rubble flow, surface collapse, sedimentation occurring and carries out early stage disaster information during cracking disaster to collect and assess.
The unspecified part of the present invention belongs to general knowledge as well known to those skilled in the art.

Claims (8)

1., based on the earthquake disaster damage degree appraisal procedure that unmanned plane is taken photo by plane, it is characterized in that performing step is as follows:
(1) set up typical earthquake disaster image feature data collection, described typical earthquake disaster image feature data collection comprises the earthquake disaster image feature data collection of house, road, bridge, dykes and dams, massif, river course and vegetation;
To multiple earthquake disaster images of acquisition of taking photo by plane based on unmanned plane in the past, determine that the image-region in house obtains the image-region more than 200 houses by the mode of user's hand labeled, the image-region in each house determined is calculated to the characteristics of image in house, and the house damage degree that the image-region providing each house is corresponding, thus obtain the earthquake disaster image feature data collection in house;
To multiple earthquake disaster images of acquisition of taking photo by plane based on unmanned plane in the past, determine that the image-region of road obtains the image-region more than 200 roads by the mode of user's hand labeled, the image-region of each road determined is calculated to the characteristics of image of road, and the road damage degree that the image-region providing each road is corresponding, thus obtain the earthquake disaster image feature data collection of road;
To multiple earthquake disaster images of acquisition of taking photo by plane based on unmanned plane in the past, determine that the image-region of bridge obtains the image-region more than 200 bridges by the mode of user's hand labeled, the image-region of each bridge is calculated to the characteristics of image of bridge, and the bridge damage degree that the image-region providing each bridge is corresponding, thus obtain the earthquake disaster image feature data collection of bridge;
To multiple earthquake disaster images of acquisition of taking photo by plane based on unmanned plane in the past, determine that the image-region of dykes and dams obtains the image-region more than 200 dykes and dams by the mode of user's hand labeled, the image-region of each dykes and dams is calculated to the characteristics of image of dykes and dams, and the dykes and dams damage degree that the image-region providing each dykes and dams is corresponding, thus obtain the earthquake disaster image feature data collection of dykes and dams;
To multiple earthquake disaster images of acquisition of taking photo by plane based on unmanned plane in the past, determine that the image-region of massif obtains the image-region more than 200 massifs by the mode of user's hand labeled, the image-region of each massif is calculated to the characteristics of image of massif, and the massif damage degree that the image-region providing each massif is corresponding, thus obtain the earthquake disaster image feature data collection of massif;
To multiple earthquake disaster images of acquisition of taking photo by plane based on unmanned plane in the past, determine that the image-region in river course obtains the image-region more than 200 river courses by the mode of user's hand labeled, the image-region in each river course is calculated to the characteristics of image in river course, and the river course damage degree that the image-region providing each river course is corresponding, thus obtain the earthquake disaster image feature data collection in river course;
To multiple earthquake disaster images of acquisition of taking photo by plane based on unmanned plane in the past, determine that the image-region of vegetation obtains the image-region more than 200 vegetation by the mode of user's hand labeled, the image-region of each vegetation is calculated to the characteristics of image of vegetation, and the vegetation damage degree that the image-region providing each vegetation is corresponding, thus obtain the earthquake disaster image feature data collection of vegetation;
The characteristics of image in house comprises gray level co-occurrence matrixes angle second moment index GLCM aSM, gray level co-occurrence matrixes index of correlation GLCM cOR, gray level co-occurrence matrixes entropy index GLCM eNT, contrast index T in Tamura textural characteristics con, Gabor direction character index f gabor, utilize Hough transform to carry out the straight line number index H of straight-line detection lwith the round number index H utilizing Hough transform to carry out loop truss c;
The characteristics of image in road, bridge, dykes and dams and river course includes gray level co-occurrence matrixes angle second moment index GLCM aSM, gray level co-occurrence matrixes moment of inertia index GLCM cON, gray level co-occurrence matrixes entropy index GLCM eNT, gray level co-occurrence matrixes unfavourable balance square index GLCM iDM, contrast index T in Tamura textural characteristics con, Gabor direction character index f gaborwith the straight line number index H utilizing Hough transform to carry out straight-line detection l;
The characteristics of image of massif and vegetation includes gray level co-occurrence matrixes angle second moment index GLCM aSM, gray level co-occurrence matrixes moment of inertia index GLCM cON, gray level co-occurrence matrixes unfavourable balance square index GLCM iDM, contrast index T in Tamura textural characteristics conwith Gabor direction character index f gabor;
(2) utilize house, road, bridge, dykes and dams, massif, the earthquake disaster image feature data training of river course and vegetation practices respective support vector machine classifier;
(3) take photo by plane based on unmanned plane and obtain new earthquake disaster image;
(4) for house, road, bridge, dykes and dams, massif, river course, vegetation 7 quasi-representative atural object, corresponding image-region is determined respectively by the mode of user's hand labeled to the new earthquake disaster image obtained, calculate characteristics of image corresponding to every quasi-representative atural object according to the image-region determined, finally corresponding according to every quasi-representative atural object characteristics of image adopts the sorter of corresponding support vector machine to carry out the assessment of every quasi-representative atural object damage degree.
2. a kind of earthquake disaster damage degree appraisal procedure of taking photo by plane based on unmanned plane according to claim 1, is characterized in that: described earthquake disaster comprises earthquake and secondary disaster thereof, and secondary disaster comprises landslide, rubble flow, surface collapse, sedimentation and cracking.
3. a kind of earthquake disaster damage degree appraisal procedure of taking photo by plane based on unmanned plane according to claim 1, it is characterized in that: for road, bridge, dykes and dams and river course, determine that the method for corresponding image-region is as follows by the mode of user's hand labeled: adopt the mode of straight line or Drawing of Curve to mark road, bridge, the edge placement in dykes and dams and river course, then extract two straight lines, two curves or the image-region between straight line and a curve are as the image-region determined.
4. a kind of earthquake disaster damage degree appraisal procedure of taking photo by plane based on unmanned plane according to claim 1, it is characterized in that: for house, determined that by the mode of user's hand labeled the method for the image-region in house is as follows: adopt the manual position of drawing a circle to approve out house of quadrilateral, then extract the image-region of quadrilateral inside as the image-region determined.
5. a kind of earthquake disaster damage degree appraisal procedure of taking photo by plane based on unmanned plane according to claim 1, it is characterized in that: for massif and vegetation, determine that the method for corresponding image-region is as follows by the mode of user's hand labeled: adopt the manual region of drawing a circle to approve out massif and vegetation of polygon, then extract the image-region of polygonal internal as the image-region determined.
6. a kind of earthquake disaster damage degree appraisal procedure of taking photo by plane based on unmanned plane according to claim 1, is characterized in that:
GLCM ASM = Σ i Σ j p ( i , j ) 2
GLCM CON = Σ i Σ j ( i - j ) 2 p ( i , j )
GLCM COR = Σ i Σ j ( ij ) p ( i , j ) - μ x GLCM μ y GLCM σ x GLCM σ y GLCM
GLCM ENT = - Σ i Σ j p ( i , j ) log [ p ( i , j ) ]
GLCM IDM = Σ i Σ j 1 1 + ( i - j ) 2 p ( i , j )
Wherein, the gray level co-occurrence matrixes of image-region of p (i, j) for determining, coordinate (i, j) represents the positional information of the image-region determined, be respectively p x ( i ) = Σ k p ( i , k ) With average and mean square deviation, i=1,2 ..., N g, j=1,2 ..., N g, N gfor the maximal value of single pixel grayscale.
7. a kind of earthquake disaster damage degree appraisal procedure of taking photo by plane based on unmanned plane according to claim 1, is characterized in that:
T con = σ α 4 1 / 4
α 4 = μ 4 σ 4
Wherein μ 4be the fourth central square of image patch, σ is the mean square deviation of the image-region determined, α 4for intermediate variable.
8. a kind of earthquake disaster damage degree appraisal procedure of taking photo by plane based on unmanned plane according to claim 1, is characterized in that: Gabor direction character index f gaborcomputing formula as follows:
g ( x , y ) = 1 2 π σ x σ y exp [ - 1 2 ( x 2 σ x 2 + y 2 σ y 2 ) + 2 πjWx ]
g mn(x,y)＝a -mg(x′,y′)
x′＝a -m(xcosθ+ysinθ)
y′＝a -m(-xsinθ+ycosθ)
W mn ( x , y ) = ∫ ∫ I ( x , y ) g mn * ( x - x 1 , y - y 1 ) d x 1 d y 1
μ mn＝∫∫|W mn(x,y)|dxdy
σ mn = ∫ ∫ [ | W mn ( x , y ) | - μ mn ] 2 dxdy
Wherein, g (x, y) represents Two-Dimensional Gabor Wavelets basis function, and W is Gaussian function multiple modulation frequency, σ x, σ yfor the mean square deviation of variable x and y; g mn(x, y) is self similarity wave filter, a -mscale factor, a>1, x ', y ' is the result of calculation after converting x, y, m and n is integer, represents corresponding yardstick and direction, m ∈ [0, M-1], M are all dimension, n ∈ [0, K-1], θ=n π/K, K are all direction numbers, subscript " * " represents conjugate complex number, x 1, y 1represent Gabor wavelet integral transformation side-play amount, I (x, y) represents the image intensity of (x, y) position, W mnthe result that (x, y) converts for Gabor wavelet, μ mn, σ mnfor average and the mean square deviation feature of Gabor wavelet.
CN201410454210.8A 2014-09-05 2014-09-05 A kind of earthquake disaster damage degree appraisal procedure based on unmanned plane Active CN104239885B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201410454210.8A CN104239885B (en) 2014-09-05 2014-09-05 A kind of earthquake disaster damage degree appraisal procedure based on unmanned plane

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201410454210.8A CN104239885B (en) 2014-09-05 2014-09-05 A kind of earthquake disaster damage degree appraisal procedure based on unmanned plane

Publications (2)

Publication Number Publication Date
CN104239885A true CN104239885A (en) 2014-12-24
CN104239885B CN104239885B (en) 2017-11-28

Family

ID=52227909

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201410454210.8A Active CN104239885B (en) 2014-09-05 2014-09-05 A kind of earthquake disaster damage degree appraisal procedure based on unmanned plane

Country Status (1)

Country Link
CN (1) CN104239885B (en)

Cited By (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104915495A (en) * 2015-06-05 2015-09-16 中国科学院水利部成都山地灾害与环境研究所 Mudslide disaster situation assessment method and application
CN105096315A (en) * 2015-06-19 2015-11-25 西安电子科技大学 Method for segmenting heterogeneous super-pixel SAR (Synthetic Aperture Radar) image based on Gamma distribution
CN106295699A (en) * 2016-08-11 2017-01-04 北京师范大学 A kind of earthquake Damage assessment method and apparatus based on high-definition remote sensing data
CN106462819A (en) * 2016-04-05 2017-02-22 盛玉伟 Real estate quality detection method and system
CN106969751A (en) * 2017-03-13 2017-07-21 西安科技大学 A kind of method of the coal mining subsidence amount monitoring calculation based on unmanned aerial vehicle remote sensing
CN107665078A (en) * 2016-07-28 2018-02-06 卡西欧计算机株式会社 Display control unit, display control method and storage medium
CN108154067A (en) * 2016-12-02 2018-06-12 航天星图科技（北京）有限公司 A kind of mud-rock flow area monitoring method
CN108304809A (en) * 2018-02-06 2018-07-20 清华大学 The damaged appraisal procedure of near real-time based on aerial images after shake
CN109145812A (en) * 2018-08-20 2019-01-04 贵州宜行智通科技有限公司 Squatter building monitoring method and device
CN109544579A (en) * 2018-11-01 2019-03-29 上海理工大学 A method of damage building is assessed after carrying out calamity using unmanned plane
CN111126184A (en) * 2019-12-09 2020-05-08 武汉大学 Post-earthquake building damage detection method based on unmanned aerial vehicle video
CN111339826A (en) * 2020-05-06 2020-06-26 山西大学 Landslide unmanned aerial vehicle linear sensor network frame detection system
CN111988397A (en) * 2020-08-19 2020-11-24 航天欧华信息技术有限公司 Earthquake-proof disaster-reduction disaster-relief method and system based on edge calculation
CN112381060A (en) * 2020-12-04 2021-02-19 哈尔滨工业大学 Building earthquake damage level classification method based on deep learning
CN113283280A (en) * 2021-02-22 2021-08-20 西北工业大学 Ground target cloud model damage effect evaluation method based on visible light image processing
CN114547763A (en) * 2020-11-27 2022-05-27 北京理工大学 Aircraft command control computer system
CN114782826A (en) * 2022-06-20 2022-07-22 绵阳天仪空间科技有限公司 Safety monitoring system and method for post-disaster building
CN114927002A (en) * 2022-04-28 2022-08-19 浙江中裕通信技术有限公司 Road induction method and device for post-disaster rescue

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1828336A (en) * 2006-04-04 2006-09-06 张路平 Rapid estimation method for earthquake disaster damage based on GIS technology
CN101979961A (en) * 2010-05-18 2011-02-23 中国地震局地球物理研究所 Disaster condition acquisition system
CN103034870A (en) * 2012-12-14 2013-04-10 南京思创信息技术有限公司 Ship fast identification method based on features
CN103034863A (en) * 2012-12-24 2013-04-10 重庆市勘测院 Remote-sensing image road acquisition method combined with kernel Fisher and multi-scale extraction
CN103198333A (en) * 2013-04-15 2013-07-10 中国科学院电子学研究所 Automatic semantic labeling method of high resolution remote sensing image
CN103426158A (en) * 2012-05-17 2013-12-04 中国科学院电子学研究所 Method for detecting two-time-phase remote sensing image change
US8625890B1 (en) * 2011-10-17 2014-01-07 Google Inc. Stylizing geographic features in photographic images based on image content
CN103699903A (en) * 2013-12-24 2014-04-02 中国科学院深圳先进技术研究院 City roof green area calculation method and system based on image identification
CN103761740A (en) * 2014-01-23 2014-04-30 武汉大学 Construction damage assessment method based on single post-earthquake POLSAR image

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1828336A (en) * 2006-04-04 2006-09-06 张路平 Rapid estimation method for earthquake disaster damage based on GIS technology
CN101979961A (en) * 2010-05-18 2011-02-23 中国地震局地球物理研究所 Disaster condition acquisition system
US8625890B1 (en) * 2011-10-17 2014-01-07 Google Inc. Stylizing geographic features in photographic images based on image content
CN103426158A (en) * 2012-05-17 2013-12-04 中国科学院电子学研究所 Method for detecting two-time-phase remote sensing image change
CN103034870A (en) * 2012-12-14 2013-04-10 南京思创信息技术有限公司 Ship fast identification method based on features
CN103034863A (en) * 2012-12-24 2013-04-10 重庆市勘测院 Remote-sensing image road acquisition method combined with kernel Fisher and multi-scale extraction
CN103198333A (en) * 2013-04-15 2013-07-10 中国科学院电子学研究所 Automatic semantic labeling method of high resolution remote sensing image
CN103699903A (en) * 2013-12-24 2014-04-02 中国科学院深圳先进技术研究院 City roof green area calculation method and system based on image identification
CN103761740A (en) * 2014-01-23 2014-04-30 武汉大学 Construction damage assessment method based on single post-earthquake POLSAR image

Cited By (29)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104915495A (en) * 2015-06-05 2015-09-16 中国科学院水利部成都山地灾害与环境研究所 Mudslide disaster situation assessment method and application
CN104915495B (en) * 2015-06-05 2017-09-05 中国科学院水利部成都山地灾害与环境研究所 A kind of Debris-flow Hazards appraisal procedure and application
CN105096315A (en) * 2015-06-19 2015-11-25 西安电子科技大学 Method for segmenting heterogeneous super-pixel SAR (Synthetic Aperture Radar) image based on Gamma distribution
CN105096315B (en) * 2015-06-19 2018-03-06 西安电子科技大学 Heterogeneous super-pixel SAR image segmentation method based on Gamma distributions
CN106462819A (en) * 2016-04-05 2017-02-22 盛玉伟 Real estate quality detection method and system
WO2017173563A1 (en) * 2016-04-05 2017-10-12 盛玉伟 Method and system for detecting real estate quality
CN107665078A (en) * 2016-07-28 2018-02-06 卡西欧计算机株式会社 Display control unit, display control method and storage medium
CN107665078B (en) * 2016-07-28 2022-01-04 卡西欧计算机株式会社 Display control device, display control method, and storage medium
CN106295699A (en) * 2016-08-11 2017-01-04 北京师范大学 A kind of earthquake Damage assessment method and apparatus based on high-definition remote sensing data
CN108154067A (en) * 2016-12-02 2018-06-12 航天星图科技（北京）有限公司 A kind of mud-rock flow area monitoring method
CN106969751A (en) * 2017-03-13 2017-07-21 西安科技大学 A kind of method of the coal mining subsidence amount monitoring calculation based on unmanned aerial vehicle remote sensing
CN106969751B (en) * 2017-03-13 2017-11-14 西安科技大学 A kind of method of the coal mining subsidence amount monitoring calculation based on unmanned aerial vehicle remote sensing
CN108304809B (en) * 2018-02-06 2020-03-27 清华大学 Near real-time earthquake damage assessment method based on post-earthquake aerial image
CN108304809A (en) * 2018-02-06 2018-07-20 清华大学 The damaged appraisal procedure of near real-time based on aerial images after shake
CN109145812A (en) * 2018-08-20 2019-01-04 贵州宜行智通科技有限公司 Squatter building monitoring method and device
CN109544579A (en) * 2018-11-01 2019-03-29 上海理工大学 A method of damage building is assessed after carrying out calamity using unmanned plane
CN111126184A (en) * 2019-12-09 2020-05-08 武汉大学 Post-earthquake building damage detection method based on unmanned aerial vehicle video
CN111126184B (en) * 2019-12-09 2022-04-12 武汉大学 Post-earthquake building damage detection method based on unmanned aerial vehicle video
CN111339826A (en) * 2020-05-06 2020-06-26 山西大学 Landslide unmanned aerial vehicle linear sensor network frame detection system
CN111339826B (en) * 2020-05-06 2023-05-02 山西大学 Landslide unmanned aerial vehicle linear sensor network frame detecting system
CN111988397A (en) * 2020-08-19 2020-11-24 航天欧华信息技术有限公司 Earthquake-proof disaster-reduction disaster-relief method and system based on edge calculation
CN111988397B (en) * 2020-08-19 2023-03-31 航天欧华信息技术有限公司 Earthquake-proof disaster-reduction disaster-relief method and system based on edge calculation
CN114547763A (en) * 2020-11-27 2022-05-27 北京理工大学 Aircraft command control computer system
CN112381060A (en) * 2020-12-04 2021-02-19 哈尔滨工业大学 Building earthquake damage level classification method based on deep learning
CN113283280A (en) * 2021-02-22 2021-08-20 西北工业大学 Ground target cloud model damage effect evaluation method based on visible light image processing
CN113283280B (en) * 2021-02-22 2023-05-02 西北工业大学 Ground target cloud model damage effect evaluation method based on visible light image processing
CN114927002A (en) * 2022-04-28 2022-08-19 浙江中裕通信技术有限公司 Road induction method and device for post-disaster rescue
CN114927002B (en) * 2022-04-28 2023-03-14 浙江中裕通信技术有限公司 Road induction method and equipment for post-disaster rescue
CN114782826A (en) * 2022-06-20 2022-07-22 绵阳天仪空间科技有限公司 Safety monitoring system and method for post-disaster building

Also Published As

Publication number Publication date
CN104239885B (en) 2017-11-28

Similar Documents

Publication Publication Date Title
CN104239885A (en) Earthquake disaster damage degree evaluation method based on unmanned aerial vehicle aerial photos
Solazzo et al. Mapping and measuring aeolian sand dunes with photogrammetry and LiDAR from unmanned aerial vehicles (UAV) and multispectral satellite imagery on the Paria Plateau, AZ, USA
CN104881865B (en) Forest pest and disease monitoring method for early warning and its system based on unmanned plane graphical analysis
Koutsias et al. Logistic regression modelling of multitemporal Thematic Mapper data for burned area mapping
Ling et al. Object-based sub-pixel mapping of buildings incorporating the prior shape information from remotely sensed imagery
Abd et al. Maximum likelihood for land-use/land-cover mapping and change detection using Landsat satellite images: A case study “South of Johor”
CN104616093A (en) Earthquake disaster rescue command and dispatch system and method
CN108459318A (en) Potential landslide EARLY RECOGNITION method based on remote sensing technology
Gupta et al. Analysis of impervious land-cover expansion using remote sensing and GIS: A case study of Sylhet sadar upazila
CN111932591B (en) Method and system for remote sensing intelligent extraction of typical geological disasters
CN103413151A (en) Hyperspectral image classification method based on image regular low-rank expression dimensionality reduction
CN107341492A (en) A kind of Karst Rocky Desertification information extracting method
Clark Small unmanned aerial systems comparative analysis for the application to coastal erosion monitoring
CN114048944A (en) Estimation method for people to be evacuated and houses to be damaged under rainstorm induced geological disaster
Singh et al. Detection of 2011 Sikkim earthquake-induced landslides using neuro-fuzzy classifier and digital elevation model
Karl et al. A technique for estimating rangeland canopy-gap size distributions from high-resolution digital imagery
Dai et al. Assessment of karst rocky desertification from the local to regional scale based on unmanned aerial vehicle images: A case‐study of Shilin County, Yunnan Province, China
Comert et al. Rapid mapping of forested landslide from ultra-high resolution unmanned aerial vehicle data
Sui et al. Processing of multitemporal data and change detection
Rose et al. Challenges and lessons from a wetland LiDAR project: a case study of the Okefenokee Swamp, Georgia, USA
CN114239379A (en) Transmission line geological disaster analysis method and system based on deformation detection
Wikantika et al. Quick assessment on identification of damaged building and land‐use changes in the post‐tsunami disaster with a quick‐look image of IKONOS and Quickbird (A case study in Meulaboh City, Aceh)
CN112097743A (en) Building earthquake-resistant characteristic analysis method based on unmanned aerial vehicle technology
Li et al. “3S” Technologies and Application for Dynamic Monitoring Soil and Water Loss in the Yangtze River Basin, China
Li et al. Study on road damage assessment based on RS and GIS

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant