CN103473455B - Method for determining disease mode of ancient stone cave temple wall painting based on visual analysis - Google Patents
Method for determining disease mode of ancient stone cave temple wall painting based on visual analysis Download PDFInfo
- Publication number
- CN103473455B CN103473455B CN201310415112.9A CN201310415112A CN103473455B CN 103473455 B CN103473455 B CN 103473455B CN 201310415112 A CN201310415112 A CN 201310415112A CN 103473455 B CN103473455 B CN 103473455B
- Authority
- CN
- China
- Prior art keywords
- grottoes
- disease
- cave temple
- histogram
- layer
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a method for determining a disease mode of ancient stone cave temple wall paintings based on visual analysis. The method includes that a foundation database of stone cave temple caverns is established, the database contains location information and construction dynasty of the caverns, disease information and general survey time, and all disease information is high-dimensional feature vectors. The location information of a certain stone cave temple is read from the foundation database of the stone cave temple caverns. And then by the aid of a multilayered circular ring, the disease information of each layer of caverns of the stone cave temple under a same general survey time is at intervals distributed in the circular ring covered by a sector area in a same rotation direction with a bar graph form for simulating the effect of a heritage site panorama so as to discover the disease mode of the whole stone cave temple. By the aid of the method, work efficiency of related personnel in the field of culture heritage can be improved, and a solid foundation is established for cultural heritage protection.
Description
Technical field
The present invention relates to a kind of visual analysis and interaction technique means of adopting and realize Cave Temple mural painting Disease Analysis system in ancient times, particularly relate to a kind of based on visual analysis ancient times Cave Temple mural painting disease mode defining method.
Background technology
Cultural heritage is the treasure that history leaves people for, in today of globalization, for the protection of traditional culture, becomes a large focal spot of countries in the world government and concern among the people gradually.Cave Temple mural painting is as world cultural heritage, and the Mo kao grotto at Dunhuang of such as China is famous because of mural painting exquisite in its grottoes.But the degenerate problem that the mural painting of these preciousnesses is caused by human damage and physical environment, they may be the results of the many factors impacts such as physics, chemistry, biology, comprise the factors such as unaccelerated aging, environmental degradation and mankind's activity.Therefore, mural painting presents different diseases, it can be divided into crack, come off, fade, bleb, plays first, crisp alkali, hollowing and go mouldy according to phenomenon.Therefore mural painting is preserved and the degeneration that these historical and cultural heritages are caused from physical environment and human damage are very important.
Visual analysis is a new technology grown up in recent years, and being the product of information visualization and the development of scientific visualization field, is that people understand and annotate important means and the approach of large-scale complex situation.It mainly carries out analysis ratiocination decision-making by means of interactive user interface to complex data object, integrate information from magnanimity and dynamic data, obtains the understanding of the more deep layer to complex information.Information Visualization Technology is on the basis of present information processing platform, according to the needs of user to information, suitable visual symbol is utilized to represent the relation of various information and information inside and outside, make people more convenient, carry out with information source alternately rapidly, find to hide all kinds of knowledge in the information, carry out more effective interchange.Computing machine for information visuallization show be combined with the observation and analysis of people, define efficiently visual analysis method with solving a various difficult problem.
Nowadays, people have done a large amount of work, on the one hand, for mural painting disease for the protection of cultural heritage, the artificial census report that they do is relative with historical relic data comprehensively, for mural painting distress mechanism as crisp alkali, go mouldy, come off, the depth analysis of precipice body deformability; To the research of inorganic salts crystallization and humiture relation; Slowing down and controlling research organic pigments degrade; To pigment composition and property analysis; Humiture microclimate, desert subenvironment, visitor are to the research of mural painting harm influence; The light sensitive Journal of Sex Research of mural painting, also once launched international co-operation and carried out omnibearing protection project for specific Cave Temple mural painting.Each protection project is independently launched, although meticulous, its job information automaticity of the first is low, lacks effective codes and standards, and it two is that the protected mode of fighting separately is difficult to find potential rule and risk by large-scale data.On the other hand, they develop the method for a series of collection, analysis, visual and modeling cultural heritage information.As the virtual reality technology in visual or 3D reconstruction technique; Based on the general visualization system of GIS; CAD mapping etc.But these methods are not be exclusively used in cultural heritage protection, are not also exclusively used in the method for analysis and visual mural painting disease even at present.
Although carried out many investigation and research work at present, and will more and more store in a database about mural painting generaI investigation and Monitoring Data, but due to following reason, the analysis of disease, visual, to understand be very challenging, the first, the complex partial of disease depends on the complicacy of the structure of mural painting itself; The second, due to the diversity of data acquisition mode and description, data are isomery, multidimensional, multiple attribute; 3rd, the degradation mechanism of mural painting disease is very complicated, because most of disease is the result of many factors combined action; 4th, major part mural painting experienced by very long history before they are found, therefore the time that is monitored and record is relatively short, thus is limited for the information of studying disease and data, particularly about forming process and machine-processed in data be considerably less; 5th, disease has different features, is usually divided into stability disease and active type disease.
Summary of the invention
For above-mentioned deficiency of the prior art with by mural painting disease data visualization institute facing challenges, the invention provides a kind of based on visual analysis ancient times Cave Temple mural painting disease mode defining method, visual analysis technology is applied to the research aspect of traditional mural painting disease, it is the instrument of a set of analysis and hypothesis verification, be used for finding the disease mode of mural painting with this, the disease mode of mural painting can be analyzed efficiently, comprise the space distribution and temporal evolution pattern etc. of disease.
In order to solve the problems of the technologies described above, the present invention a kind of based on visual analysis ancient times Cave Temple mural painting disease mode defining method, comprise the following steps:
Step one, set up Cave Temple grottoes basic database, this database comprises the positional information of grottoes and builds the dynasty, and described positional information comprises the coordinate of grottoes number and grottoes; Also comprise in database through repeatedly generally investigating the defect information and generaI investigation time that obtain, described defect information comprises the order of severity of disease species, disease number and disease; All defect information are the proper vector of octuple;
Step 2, from above-mentioned Cave Temple grottoes basic database, read the positional information of a certain Cave Temple, make one group of concentric circles, the number of the circle that this concentric circles comprises is 2 times of this Cave Temple grottoes number of plies; From concentrically ringed outermost layer circle, ground floor and the round-formed annulus of the second layer, third layer and the 4th layer of round-formed annulus, the rest may be inferred, be formed with the donut identical with the grottoes number of plies, and the thickness of annulus is identical, each annulus in described donut except outermost layer is divided into multiple sector, and described sector refers to: on an annulus, two arcs that same central angle is corresponding and two figures surrounded along the line segment of radial direction through these two arc two ends; The defect information of this Cave Temple each layer grottoes under the same generaI investigation time is all distributed in the annulus that sector covers according to same sense of rotation compartment of terrain with the form of histogram; Wherein, the central angle being distributed with the sector of histogram is identical, and the central angle of the sector of non-distribution histogram is identical; Described histogram has the different color lump of many deciles, and each color lump represents hollowing respectively, comes off, crack, bleb, go mouldy, insect pest, play first and crisp alkali Damage Types;
Step 3, the similarity of two grottoes is determined by the geometric distance calculating every two grottoes Disease Characters vectors, according to the result of calculation definite threshold of similarity, line is done by between the histogram of representative two grottoes higher than threshold value, and adopt optimization bundle algorithm to be bundled by line, the central point not being distributed with the region of histogram is in each layer placed in reference mark by described optimization bundle algorithm, and outer field reference mark is under the jurisdiction of the reference mark of nexine successively, outer field grottoes are under the jurisdiction of the reference mark of nexine successively, and line is iterated be bundled into its reference mark,
Step 4, optionally show with the Damage Types information represented by bar graph form according to user's request, analyze and find disease mode, for determining that the recovery scenario of this Cave Temple mural painting lays the foundation.
Compared with prior art, the invention has the beneficial effects as follows:
Compared to existing already present Cave Temple mural painting disease research mode, advantage of the present invention is the use of this technology of rising of visual analysis and well solves pinpointing the problems of disease mode.Non-visualization technique is in the past compared; the present invention has more intuitive advantage; allow and use researchist of the present invention to wait discovery Cave Temple mural painting disease mode more clearly; utilize the inventive method can improve the work efficiency of cultural heritage field related personnel, for solid foundation is established in cultural heritage protection.
Accompanying drawing explanation
Fig. 1 (a) is multilayer annulus layout;
Fig. 1 (b) is the histogram representing a grottoes Damage Types information;
Fig. 1 (c) is the reference mark that the bundle algorithm optimized is arranged;
Fig. 1 (d) is the overall design finding mural painting disease mode;
Fig. 2 is the ThemeRiver finding disease temporal evolution pattern;
Fig. 3 is disease Symbiotic Model result figure;
Fig. 4 (a) is the disease mode result figure in northern cool period;
Fig. 4 (b) is the disease mode result figure of the Sui Dynasty;
The disease mode result figure in Fig. 4 (c) Shi Sheng Tang period;
Fig. 5 (a) is the space clustering model results figure of crisp alkali disease mode;
Fig. 5 (b) is the space clustering model results figure of bleb disease mode.
Embodiment
Below in conjunction with embodiment, the present invention is described in further detail.
The present invention a kind of based on visual analysis ancient times Cave Temple mural painting disease mode defining method, comprise the following steps:
Step one, set up Cave Temple grottoes basic database:
First carry out the pre-service of annual census data, comprise text and view data.Text data comprises the grottoes number of record, generaI investigation time, disease position, and Damage Types and other detailed description; View data comprises the photo of disease and disease is carried out to the picture of manual mark, and these image datas have reacted the order of severity and the distribution of disease on wall of disease to a certain extent.The data of these non-structural are octuples, polynary with isomery, and data set is very large, and there is redundancy to a great extent, they directly can not carry out information retrieval and analysis.Therefore, first we have employed the data extraction software of a robotization by non-structured data structured, then adopts the artificial mode evaluated to quantize the order of severity of disease.
Structurized database comprises the positional information of grottoes and builds the dynasty, and described positional information comprises the coordinate of grottoes number and grottoes; Also comprise in database through repeatedly generally investigating the defect information and generaI investigation time that obtain, described defect information comprises the order of severity of disease species, disease number and disease; All defect information are the proper vector of octuple;
Step 2, because the panorama sketch of a Cave Temple is the simplest method that can present Cave Temple global state, but it is too narrow oversize, and can not expand.In addition, because the complicacy of disease distribution and the order of severity causes structurized data set very large, be difficult to find disease mode by simple graphic analyses.Therefore, the present invention devises the layout of a multilayer annulus, and the effect of simulation Heritage area panorama sketch, to find the disease mode of whole Cave Temple rank.Inventor reads the positional information of a certain Cave Temple from above-mentioned Cave Temple grottoes basic database, makes one group of concentric circles, and the number of the circle that this concentric circles comprises is 2 times of this Cave Temple grottoes number of plies; From concentrically ringed outermost layer circle, ground floor and the round-formed annulus of the second layer, third layer and the 4th layer of round-formed annulus, the rest may be inferred, be formed with the donut identical with the grottoes number of plies, and the thickness of annulus is identical, each annulus in described donut except outermost layer is divided into multiple sector, as shown in Fig. 1 (a); Described sector refers to: on an annulus, two arcs that same central angle is corresponding and two figures surrounded along the line segment of radial direction through these two arc two ends; By the defect information of this Cave Temple each layer grottoes under the same generaI investigation time with the form of histogram (as Fig. 1 (b)) all according to same sense of rotation compartment of terrain be distributed to sector in the annulus that covers; Wherein, the central angle being distributed with the sector of histogram is identical, and the central angle of the sector of non-distribution histogram is identical; Because every layer has a large amount of grottoes, the screen space therefore distributing to the histogram of each grottoes in every one deck annulus is very limited.And each grottoes have multiple diseases type, in order to represent the defect information of grottoes, described histogram is divided into different color lumps more, each color lump represents a kind of Damage Types, color lump represents hollowing respectively, comes off, crack, bleb, goes mouldy, insect pest, plays first and crisp alkali Damage Types herein, by histogram to sector arrange be by near center to cylindrical place successively according to hollowing, come off, crack, bleb, go mouldy, insect pest, being disposed in order of first and crisp alkali.In the present invention, user can regulate the number of the thickness of annulus, the number of sector and histogram color lump dynamically, but ensure that the thickness of every layer of annulus is equal, the area that the sector being distributed with histogram in every layer of annulus covers is identical, the area that the sector not being distributed with histogram covers is identical, and the number of each histogram color lump is identical.By this strategy, each grottoes maintain its relative position, and the layout of multilayer annulus adds screen utilization rate simultaneously.
Step 3, determined the similarity of two grottoes by the geometric distance calculating every two grottoes Disease Characters vectors, according to the result of calculation of similarity and the demand definite threshold of user, do line by between the histogram of representative two grottoes higher than threshold value.But when the threshold value that user is arranged is lower, a large amount of lines can be produced, cause line very disorderly and unsystematic, and the histogram of internal layer may be capped.Therefore inventor adopts and optimizes bundle algorithm and bundled by line, the central point not being distributed with the region of histogram is in each layer placed in reference mark by described optimization bundle algorithm, and outer field reference mark is under the jurisdiction of the reference mark of nexine successively, outer field grottoes are under the jurisdiction of the reference mark of nexine successively, and line is iterated be bundled into its reference mark.As Fig. 1 (c) P
n+1reference mark be P
n, Q
n+1reference mark be Q
n, and in figure, the reference mark of line is from P
0to P
3with from Q
0to Q
3.Adopt such strategy, line can be bundled into different sectors and annulus, so that user better finds the trend of line, thus obtain the trend of similarity between grottoes.This reason also reserving space just and histogram compartment of terrain is placed on sector between annulus and annulus.
And conveniently user observes the more detailed defect information of each grottoes, when mouse floats on some histograms, the plane outspread drawing of the craft mark disease of corresponding grottoes can be presented, can by the disease details on scaling operational observations wall; Also can present the ThemeRiver of these grottoes, ThemeRiver is mainly used to the time-evolution observing disease, and its horizontal axis plots time, each river represents a kind of disease, and the width in river is determined by the disease number of each year simultaneously.As shown in Figure 2, each label wherein 1., 2., 3., 4. a kind of Damage Types number of the Regional Representative at place differentiation in time, the various diseases evolution in time of grottoes can be found clearly by ThemeRiver technical user
Step 4, optionally show with the Damage Types information represented by bar graph form according to user's request, analyze and find disease mode, for determining that the recovery scenario of this Cave Temple mural painting lays the foundation.
Confirm the present invention further below by research material and there is its science, accuracy and reproducibility.The Cave Temple in following instance is three-decker, and bottom to top layer grottoes with outer to internal layer annulus be one to one.
The Symbiotic Model of embodiment 1, disease:
The donut figure of reaction grottoes mural painting Damage Types information is drawn according to the inventive method step, and therefrom optionally show crack and hollowing two kinds of Damage Types information of the existence of this grottoes mural painting, as shown in Figure 3, can clearly draw through observation: most of grottoes have crack and hollowing disease, its Oxford gray and grayish histogram represent crack and hollowing respectively, and they occupy most of area of annulus.And hollowing and cracking almost occurs simultaneously, therefore we can think that crack and hollowing are symbiosis, namely can there is another kind of disease while a kind of disease exists.Result consulting domain expert according to the observation, they make an affirmation to this result, and make an explanation to this symbiosis: because these two kinds of diseases all have relation with the stability of grottoes building structure, As time goes on hollowing can be converted into crack.That is, under the prerequisite not having domain knowledge, our method is used also can to find the Symbiotic Model of disease.
The disease mode that embodiment 2, dynasty are relevant
Draw the donut figure of reaction grottoes mural painting Damage Types information according to the inventive method step, and therefrom optionally show the grottoes of different times construction.As shown in Fig. 4 (a), in north, cool period builds together and has made 8 grottoes, is built in third layer for wherein 7, is built in the second layer for 1, and as can be seen from the distribution situation of disease color in figure, the mural painting disease major part of the grottoes in this dynasty is crack, hollowing, rise first, come off.As shown in Fig. 4 (b), build together in the Sui Dynasty and made 90 grottoes, most of grottoes are positioned at the second layer and third layer, only have 5 grottoes at bottom.In 5 grottoes of the most bottom, there are 4 to there is crisp alkali disease evil (80%); In 64 grottoes in middle layer, there are 9 to there is crisp alkali disease evil (14%); In 21 grottoes of most top layer, there are 4 there is crisp alkali disease evil (19%).As shown in Fig. 4 (c), build together period made 96 grottoes in Sheng Tang, it is the period that construction grottoes number is maximum.In 62 grottoes of bottom, there are 47 grottoes to there is crisp alkali disease evil (75.8%); In 24 grottoes in middle layer, there are 3 grottoes to there is crisp alkali disease evil (12.5%); In 10 grottoes of most top layer, there are 4 there is crisp alkali disease evil (40%).Through these statistics, we find that the frequency that crisp alkali occurs at bottom is the highest, are and then top layers, and the frequency occurred in middle layer is minimum; And most of grottoes are built in the Sui Dynasty and Sheng Tang period.Result consulting domain expert according to the observation, they make an affirmation to this result, and give an explaination: because crisp alkali disease evil and moisture have relation, and bottom is close to ground, more high-risely can be subject to rain water mitigation again, the frequency therefore occurred in middle layer at soda acid is minimum.Also just because of this, the grottoes major part set up in early days is distributed in the second layer and these reasonable geographic position of third layer.And the economic dispatch various aspects in Yin Shengtang period are more flourishing, so the grottoes number built is also relatively many.
The disease Clustering in embodiment 3, space
Draw the donut figure of reaction grottoes mural painting Damage Types information according to the inventive method step, we select each class disease to show separately to check their distribution pattern, wherein have two kinds to present cluster phenomenon in 8 kinds of diseases.Histogram as Fig. 5 (a) Dark grey represents crisp alkali major part and is distributed in outermost layer, and histogram as grayish in Fig. 5 (b) represents bleb major part and is distributed in outermost layer.We guess that these two kinds of diseases seem and there is relation on ground, according to this phenomenon consulting domain expert, they make an affirmation to this result and give an explaination, because these two kinds of diseases are caused by soluble salt and moisture, more subaerial grottoes moisture is more, therefore the possibility causing two kinds of diseases is higher, this means that the position of crisp alkali and bleb generation is closer to ground.
The time-evolution pattern of embodiment 4, disease
As time goes by, disease can present several development model, can with the increase of another kind of defect phenomenon while certain defect phenomenon reduces.Therefore the relation between disease has obviously time trend, but the development of disease is a process slowly, is not easy to follow the trail of, thus is difficult to the time-evolution pattern finding disease.Therefore, we utilize ThemeRiver technology to present increase and the minimizing pattern of all diseases of 10 years in more intuitive mode, as shown in Figure 2.When the river of the most shallow (label 1.) of grey reduces, more shallow (label 4.) river of grey increases, and (label 3.) river that grey is the darkest simultaneously also increases.Present in this visual mode the process being evolved into another disease from a kind of disease, what represent in this example is be converted to crack by hollowing and come off.According to this result, we inquire about the original tracking report file of grottoes, really there is this temporal evolution pattern in report.
Above embodiment merely illustrates wherein several disease mode, user can according to different demands, show that the donut figure of reaction grottoes mural painting Damage Types information and ThemeRiver technology show different defect information, to find more disease mode according to the inventive method step.
Although invention has been described for composition graphs above; but the present invention is not limited to above-mentioned embodiment; above-mentioned embodiment is only schematic; instead of it is restrictive; those of ordinary skill in the art is under enlightenment of the present invention; when not departing from present inventive concept, can also make a lot of distortion, these all belong within protection of the present invention.
Claims (1)
1. based on visual analysis ancient times Cave Temple mural painting disease mode a defining method, comprise the following steps:
Step one, set up Cave Temple grottoes basic database, this database comprises the positional information of grottoes and builds the dynasty, and described positional information comprises the coordinate of grottoes number and grottoes; Also comprise in database through repeatedly generally investigating the defect information and generaI investigation time that obtain, described defect information comprises the order of severity of disease species, disease number and disease; All defect information are the proper vector of octuple, comprise hollowing, come off, crack, bleb, go mouldy, insect pest, rise first and crisp alkali Damage Types;
Step 2, from above-mentioned Cave Temple grottoes basic database, read the positional information of a certain Cave Temple, make one group of concentric circles, the number of the circle that this concentric circles comprises is 2 times of this Cave Temple grottoes number of plies; From concentrically ringed outermost layer circle, ground floor and the round-formed annulus of the second layer, third layer and the 4th layer of round-formed annulus, the rest may be inferred, be formed with the donut identical with the grottoes number of plies, and the thickness of annulus is identical, each annulus in described donut except outermost layer is divided into multiple sector, and described sector refers to: on an annulus, two arcs that same central angle is corresponding and two figures surrounded along the line segment of radial direction through these two arc two ends; The defect information of this Cave Temple each layer grottoes under the same generaI investigation time is all distributed in the annulus that sector covers according to same sense of rotation compartment of terrain with the form of histogram; Wherein, the central angle being distributed with the sector of histogram is identical, and the central angle of the sector of non-distribution histogram is identical; Described histogram has the different color lump of many deciles, and each color lump represents hollowing respectively, comes off, crack, bleb, go mouldy, insect pest, play first and crisp alkali Damage Types;
Step 3, the similarity of two grottoes is determined by the geometric distance calculating every two grottoes Disease Characters vectors, according to the result of calculation definite threshold of similarity, line is done by between the histogram of representative two grottoes higher than threshold value, and adopt optimization bundle algorithm to be bundled by line, the central point not being distributed with the region of histogram is in each layer placed in reference mark by described optimization bundle algorithm, and outer field reference mark is under the jurisdiction of the reference mark of nexine successively, outer field grottoes are under the jurisdiction of the reference mark of nexine successively, and line is bundled into its reference mark iteratively,
Step 4, optionally show with the Damage Types information represented by bar graph form according to user's request, analyze and find disease mode, for determining that the recovery scenario of this Cave Temple mural painting lays the foundation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310415112.9A CN103473455B (en) | 2013-09-12 | 2013-09-12 | Method for determining disease mode of ancient stone cave temple wall painting based on visual analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310415112.9A CN103473455B (en) | 2013-09-12 | 2013-09-12 | Method for determining disease mode of ancient stone cave temple wall painting based on visual analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103473455A CN103473455A (en) | 2013-12-25 |
| CN103473455B true CN103473455B (en) | 2015-03-04 |
Family
ID=49798302
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310415112.9A Active CN103473455B (en) | 2013-09-12 | 2013-09-12 | Method for determining disease mode of ancient stone cave temple wall painting based on visual analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103473455B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107481204A (en) * | 2017-08-15 | 2017-12-15 | 西安建筑科技大学 | A kind of ancient wall based on compressed sensing plays onychonosus and does harm to digital restorative procedure and intelligent terminal system |
| CN108446017B (en) * | 2018-02-12 | 2021-04-23 | 天津大学 | MR (magnetic resonance) glasses-based ancient mural disease visual analysis method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004279317A (en) * | 2003-03-18 | 2004-10-07 | Sumitomo Chem Co Ltd | Painting management system |
| CN102299911A (en) * | 2011-06-22 | 2011-12-28 | 天津大学 | DDos attack detection method based on concentric axis multidimensional data visualization model |
| CN102305769A (en) * | 2011-06-09 | 2012-01-04 | 天津大学 | Multispectral sectional drawing method applied to Chinese ancient painting repair |
| CN102609924A (en) * | 2012-03-12 | 2012-07-25 | 敦煌研究院 | Digital high-fidelity image collecting and processing method of stone cave temple wall paintings |
-
2013
- 2013-09-12 CN CN201310415112.9A patent/CN103473455B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004279317A (en) * | 2003-03-18 | 2004-10-07 | Sumitomo Chem Co Ltd | Painting management system |
| CN102305769A (en) * | 2011-06-09 | 2012-01-04 | 天津大学 | Multispectral sectional drawing method applied to Chinese ancient painting repair |
| CN102299911A (en) * | 2011-06-22 | 2011-12-28 | 天津大学 | DDos attack detection method based on concentric axis multidimensional data visualization model |
| CN102609924A (en) * | 2012-03-12 | 2012-07-25 | 敦煌研究院 | Digital high-fidelity image collecting and processing method of stone cave temple wall paintings |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103473455A (en) | 2013-12-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Modica et al. | Comparison and assessment of different object-based classifications using machine learning algorithms and UAVs multispectral imagery: A case study in a citrus orchard and an onion crop | |
| Stereńczak et al. | Influence of selected habitat and stand factors on bark beetle Ips typographus (L.) outbreak in the Białowieża Forest | |
| Goodbody et al. | Digital aerial photogrammetry for assessing cumulative spruce budworm defoliation and enhancing forest inventories at a landscape-level | |
| Packalen et al. | Predicting the spatial pattern of trees by airborne laser scanning | |
| Sun et al. | Counting trees in a subtropical mega city using the instance segmentation method | |
| Li et al. | Human fingerprint on structural density of forests globally | |
| CN115456490B (en) | Fishery resource data analysis method and system based on geographic information | |
| Melati | The use of remote sensing data to monitor land use systems and forest variables of the tropical rainforest landscape under transformation in Jambi Province, Sumatra, Indonesia | |
| Zheng et al. | Coconut trees detection on the tenarunga using high-resolution satellite images and deep learning | |
| Wang et al. | Simulating large-scale urban land-use patterns and dynamics using the U-Net deep learning architecture | |
| CN106780586A (en) | A kind of solar energy potential evaluation method based on ground laser point cloud | |
| CN103473455B (en) | Method for determining disease mode of ancient stone cave temple wall painting based on visual analysis | |
| CN113989657B (en) | Cultivated land range change detection method and device based on invariable information sample screening | |
| Penmetcha et al. | Computer vision-based algae removal planner for multi-robot teams | |
| Ventura et al. | Individual tree detection in large-scale urban environments using high-resolution multispectral imagery | |
| Rudge et al. | Developing landscape-scale forest restoration targets that embrace spatial pattern | |
| CN101887522A (en) | Method for extracting remote sensing image road based on multipoint simultaneous and rapid advance | |
| Sun et al. | Mapping China’s coastal aquaculture ponds expansion with sentinel-2 images during 2017–2021 | |
| Groom et al. | Historical maps machine learning helps us over the map vectorisation crux | |
| Jakab et al. | Detection of Plastic Greenhouses Using High Resolution Rgb Remote Sensing Data and Convolutional Neural Network | |
| Zhang et al. | Identification of parasite-host habitats in Anxiang county, Hunan Province, China based on multi-temporal China-Brazil earth resources satellite (CBERS) images | |
| Nobles | Dwelling on the edge of the Neolithic: Investigating human behaviour through the spatial analysis of Corded Ware settlement material in the Dutch coastal wetlands (2900-2300 calBc) | |
| Hamylton et al. | Observations of dugongs at Aldabra Atoll, western Indian Ocean: lagoon habitat mapping and spatial analysis of sighting records | |
| Riggins et al. | Per-segment aboveground forest biomass estimation using LIDAR-derived height percentile statistics | |
| CN114241299A (en) | Method and system for detecting garbage density of block chain water area based on genetic algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |