CN110070624B - Urban geomorphology feature identification method based on VR combined with eye movement tracking - Google Patents
Urban geomorphology feature identification method based on VR combined with eye movement tracking Download PDFInfo
- Publication number
- CN110070624B CN110070624B CN201910342548.7A CN201910342548A CN110070624B CN 110070624 B CN110070624 B CN 110070624B CN 201910342548 A CN201910342548 A CN 201910342548A CN 110070624 B CN110070624 B CN 110070624B
- Authority
- CN
- China
- Prior art keywords
- geomorphic
- feature
- city
- local
- geomorphology
- 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
- 238000000034 method Methods 0.000 title claims abstract description 55
- 230000004424 eye movement Effects 0.000 title claims abstract description 26
- 230000008447 perception Effects 0.000 claims abstract description 47
- 238000005516 engineering process Methods 0.000 claims abstract description 13
- 238000004458 analytical method Methods 0.000 claims abstract description 12
- 238000007405 data analysis Methods 0.000 claims abstract description 4
- 230000000007 visual effect Effects 0.000 claims description 25
- 238000011156 evaluation Methods 0.000 claims description 16
- 238000011161 development Methods 0.000 claims description 15
- 210000001508 eye Anatomy 0.000 claims description 14
- 238000013439 planning Methods 0.000 claims description 11
- 238000005259 measurement Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 8
- 239000002245 particle Substances 0.000 claims description 6
- 238000010586 diagram Methods 0.000 claims description 5
- 238000002474 experimental method Methods 0.000 claims description 4
- 230000004927 fusion Effects 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000009825 accumulation Methods 0.000 claims description 3
- 230000006978 adaptation Effects 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 239000000178 monomer Substances 0.000 claims description 3
- 238000009877 rendering Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 230000003044 adaptive effect Effects 0.000 claims 1
- 230000019771 cognition Effects 0.000 abstract description 3
- 238000013440 design planning Methods 0.000 abstract description 3
- 238000005065 mining Methods 0.000 abstract description 3
- 238000013461 design Methods 0.000 description 17
- 238000011160 research Methods 0.000 description 7
- 230000015572 biosynthetic process Effects 0.000 description 4
- 239000011449 brick Substances 0.000 description 3
- 210000005252 bulbus oculi Anatomy 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 238000012937 correction Methods 0.000 description 2
- 238000007654 immersion Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 241001465382 Physalis alkekengi Species 0.000 description 1
- 230000003139 buffering effect Effects 0.000 description 1
- 238000009960 carding Methods 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000005034 decoration Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000000465 moulding Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000009469 supplementation Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G02—OPTICS
- G02B—OPTICAL ELEMENTS, SYSTEMS OR APPARATUS
- G02B27/00—Optical systems or apparatus not provided for by any of the groups G02B1/00 - G02B26/00, G02B30/00
- G02B27/01—Head-up displays
- G02B27/017—Head mounted
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/05—Geographic models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T19/00—Manipulating 3D models or images for computer graphics
- G06T19/006—Mixed reality
-
- G—PHYSICS
- G02—OPTICS
- G02B—OPTICAL ELEMENTS, SYSTEMS OR APPARATUS
- G02B27/00—Optical systems or apparatus not provided for by any of the groups G02B1/00 - G02B26/00, G02B30/00
- G02B27/01—Head-up displays
- G02B27/017—Head mounted
- G02B2027/0178—Eyeglass type
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Optics & Photonics (AREA)
- Data Mining & Analysis (AREA)
- Remote Sensing (AREA)
- Processing Or Creating Images (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A city feature recognition method based on VR combined eye movement tracking relates to city design planning. Establishing a local city geomorphic feature element case library; constructing a virtual reality VR city geomorphology scene which not only restores the real street geomorphology, but also has geomorphology component coding information; performing depth vision analysis on the sample by utilizing VR and eye movement tracking technologies; carrying out big data analysis on the sample, and identifying the weight relation and classification of the feature elements; and comprehensively evaluating the current situation of the geomorphic elements in each level of protection area based on the classification and weight relation of the street geomorphic feature elements acquired by the typical geomorphic area, and specifically proposing a dynamic control suggestion to each local level of geomorphic protection area when the situation of a certain type of geomorphic element deviates from a reference value according to the actual protection requirement of the geomorphic area. The method is a new method for mining and developing the urban landscape from perception of cities and cognition of cities by utilizing a digital technology.
Description
Technical Field
The invention relates to city design planning, in particular to a city feature identification method based on VR combined eye tracking.
Background
Under the current large background of popularizing urban culture, in order to highlight the feature of urban region and appearance, many cities usually renovate and restore old cities or historical blocks with certain urban region culture representatives, so that local residents and foreign tourists can enjoy the fun brought by the fusion of rich urban local culture and modern life. City geomorphology discernment is the important basis of developing city geomorphology protection and moulding work, and scientific, system and accurate city geomorphology discernment need be with people's basis as the center, knows the perception of different culture background crowds to city geomorphology from many first visual angles, finds out the law of different culture crowds to building geomorphology characteristic perception, and then scientifically collocates the geomorphology key element of different grade type proportions and carries out system construction and protection in specific city geomorphology planning district. Meanwhile, the rapid development of the current VR and eye tracking technologies provides a new opportunity for city space simulation and interaction research, the two technologies can be combined and applied to quickly, comprehensively and accurately know the visual and psychological perception of the experiencer on city features, and a wide development space can be provided for city feature identification and protection.
The identification explanation of the building features in the existing urban planning theory is only limited to the discussion of the basic principle, the traditional feature protection design is excessively dependent on the subjective judgment of planners, and a human-oriented technical operation method for accurately identifying the urban features is lacked. In the aspect of urban space and appearance research, in the research of the Wangjian and the like (Wangjian, Gaoyuan, Humingxing, Nanjing old city space form optimization [ J ] based on high-rise building management and control, urban planning, 2005, 1: 45-51), GIS technology is utilized to carry out systematic carding and optimization on urban building space forms, but only hierarchical evaluation and brief theoretical explanation are carried out on Nanjing old city landscape node parts, and the specific building appearance is not deeply researched. In practical operation, most of the current urban space vision research is calculation control of sight lines and vision fields in urban space, and no specific identification basis and method are provided for building feature weight from depth vision data of human eyeball motion. At present, a few research papers related to architectural features exist in China, for example, the psychophysics and the spatial perception theory are introduced into Zhou Yu and the like (Zhou Yu, Zhangkun, Yunsinan. quantitative research on street interface psychology cognition, architecture report, 2012, S2: 126-. However, the following problems still remain: firstly, the method can only judge the outline change condition of the street interface and cannot judge the specific building geomorphologic elements; secondly, the paper is subjected to visual analysis through an ideal model, the city appearance is ignored as an organic whole, the street interface contour is separately extracted for research, and the practical problem cannot be completely solved only from the angle of the interface contour change coefficient; and thirdly, the experimental scene is simulated by watching screen projection by wearing traditional stereoscopic glasses, so that real immersion is lacked, the experimental method adopts single questionnaire data, the mining of deep eye movement visual data of people is zero, and the method is simple and crude and has no practicability.
Disclosure of Invention
The invention aims to overcome the defects in the prior art, and provides a city geomorphic feature identification method based on VR combined eye tracking, which is used for identifying city geomorphic elements in city planning design, accurately identifying the weight relationship of the city geomorphic elements by means of establishing a city in-place building geomorphic case library, theoretical analysis, experimental data acquisition, data formula analysis, actual correction and the like, dynamically balancing the control proportion of various geomorphic elements in a city geomorphology control area by taking the numerical value of element classification clusters as a reference, and scientifically and systematically guiding the city geomorphology planning design and protection.
The invention comprises the following steps:
1) establishing a local city geomorphic feature element case library;
in step 1), the specific method for establishing the local city geomorphic feature element case library may be: the method comprises the steps of capturing local city geomorphology network Interest Point (Point of Interest) big data according to an automatic network crawler program WebSpider, integrating local city planning and opinions of local cities in a most representative geomorphology zone determined by experts in the building field, selecting a historical culture block with most representative geomorphology in the local cities, screening and classifying local city geomorphology characteristics, and establishing a local city geomorphology characteristic element case library.
2) Constructing a virtual reality VR city geomorphology scene which not only restores the real street geomorphology, but also has geomorphology component coding information;
in step 2), the specific method for constructing the virtual reality VR city landscape scene which not only restores the real street landscape but also has accurate coding information may be: firstly, importing point cloud measurement data of an unmanned aerial vehicle aerial tilt measurement, a handheld ground GPS attitude camera measurement and a vehicle-mounted ground laser radar into three-dimensional real scene modeling software to perform space-ground integrated real scene rendering modeling, and realizing organic fusion of multi-source real data; then, the live-action model is subjected to singleization and coding treatment, a local city geomorphologic feature element case library is established according to the step 1), and the city geomorphologic scene interface mesh model is replaced by a BIM model or a 3dmax model with monomer component information; finally, coding the geomorphic element components in the generated three-dimensional model one by one, importing the geomorphic element components into an Unreal Engine4 virtual Engine, and constructing a virtual reality VR city scene with three-dimensional coding geomorphic element information; the three-dimensional live-action modeling software comprises ContextCapture, PIX4D MAPPER, PHOTOSCAN, Photomesh and the like;
3) performing depth vision analysis on the sample by utilizing VR and eye movement tracking technologies;
in step 3), the specific method for performing depth visual analysis on the sample by using VR and eye tracking technology may be: implanting an infrared eye movement tracking aGlass module in the immersive VR helmet, fusing the VR helmet space posture and the eye movement data by using a Unreal-aGlass plug-in program, in the aspect of visual attention data acquisition, the relationship between horizontal and vertical visual angles of human eyes and visual definition change is simulated, the eyes are regarded as a point light source, whereas the line of sight is seen as a cone of light emitted therefrom, the cone having a higher energy of the middle light particle than the light particle at the edges, when the cone-shaped light rays irradiate the geomorphic element model component with the space coding information, through the accumulation of energy values, an intuitive three-dimensional visual attention thermodynamic diagram can be intelligently generated on the surface of the geomorphic element model, and when the energy value is 3 times higher than the average value, the method is characterized in that the method indicates that the feature element is focused, and indicates that the feature element is focused generally when the energy value is 1-3 times of the average value.
When sample data is obtained, a certain number of samples are randomly selected to perform VR eyeball motion tracking adaptation and VR environment adaptability experience; and filling in a personal basic information table for later-stage crowd sample data classification, and definitely introducing the task of VR experience: searching local most representative feature elements; then, urban landscape immersive VR experience is carried out, the duration is uniformly controlled to be 2-3 min, the rule and abnormal special conditions of eye movement and body movement of an experiencer are observed in real time through the monitoring end, the field experience of the experiencer is recorded by the wide-angle camera, the experimental process is reviewed and checked after the experiment, experimental sample data is corrected and supplemented in time, and the accuracy of depth vision perception data is improved.
4) Carrying out big data analysis on the sample, and identifying the weight relation and classification of the feature elements;
in step 4), the specific method for analyzing the big data of the sample, and identifying the weight relationship and classification of the feature elements may be: taking human-oriented as a center, finding out similarities and differences of attention features of different people by using eye movement data and space behavior data; through the questionnaire, the experimenter's familiarity with the local culture is known and the experimenter is divided into several categories, such as: local resident groups, groups with knowledge about local culture and external groups without knowledge about local culture (see figure 3, group samples) accurately find out basic feature elements, preliminary feature elements, clusters for improving the feature elements and the original feature elements of the local city and the weight relationship of various feature elements according to the difference of attention of each group to the feature elements; the clusters of the features are as follows:
(1) the basic feature element cluster is a feature concerned by all sample crowds, namely: local resident population, population with understanding on local culture and population without understanding on local culture pay attention to the feature of common appearance;
(2) the native physiognomy feature element cluster is a physiognomy feature concerned by local resident groups;
(3) the method comprises the steps of improving a geomorphic feature element cluster, wherein the geomorphic feature element cluster is a geomorphic feature concerned by people with understanding on local culture;
(4) the initial feature element cluster is a feature concerned by the foreign people who do not understand the text.
5) And comprehensively evaluating the current situation of the geomorphic elements in each level of protection area based on the classification and weight relation of the street geomorphic feature elements acquired by the typical geomorphic area, and specifically proposing a dynamic control suggestion to each local level of geomorphic protection area when the situation of a certain type of geomorphic element deviates from a reference value according to the actual protection requirement of the geomorphic area.
The evaluation method for the comprehensive evaluation perception value of the wind and appearance in each stage of the wind and appearance protection area comprises the following steps: the method comprises the steps of firstly constructing typical VR digital city scenes of all levels of the wind and appearance areas, selecting a certain amount of samples to perform perception evaluation on the wind and appearance current situations of all levels of the protection areas, indicating that the wind and appearance development condition is normal when the comprehensive perception value of the wind and appearance is within a reasonable range, indicating that the wind and appearance condition is good when the comprehensive perception value of the wind and appearance is greater than an upper limit value, indicating that the wind and appearance condition is not good when the comprehensive perception value of the wind and appearance is less than a lower limit value, comparing the scoring conditions of various wind and appearance elements in detail, finding out the wind and appearance problems in time and.
The reference range of the comprehensive evaluation perception value y of the geomorphic model is as follows:
in the feature protection core area y is an element (0.8 to 1.0)
In the geomorphic protection buffer area y is an element (0.6 to 0.8)
In the geomorphic protection coordination development area y epsilon (0.4 to 0.6)
The specific calculation method of the geomorphic comprehensive perception value y is as follows:
y＝b0+∑bxnwkz
in the formula (I), the compound is shown in the specification,
b0,b1,...,bx: a weight factor for each feature element, wherein x is (0,1,2,3,4, … …)
n0,n1,...,nw: attention from different groups of people, w ═ 0,1,2,3,4, … …)
k0,k1,...,kzThe contribution of different types of features, wherein z is (0,1,2,3,4, … …).
The dynamic control suggestion framework proposed by each level of the geomorphic protection area is as follows: in all the landscape protected areas, in order to promote the formation of the overall landscape of the city, the application of basic landscape elements is emphasized, the elements are local landscape elements which are accepted by people, and only a large number of elements are repeatedly adopted, the uniform background of the city landscape can be established, so that the formation of the overall image of the city landscape is promoted; control of original nature factors is emphasized in the geomorphic core area; control of the enhanced features is emphasized in the feature buffer area, and preliminary features are emphasized in the feature coordination development area.
The invention relates to a new method for mining and developing city features by using digital technology from city perception and city cognition. The method comprises the steps of disclosing the internal relation between depth visual data of different cultural crowds and urban landscapes through quantitative visual analysis of eye movement tracking data of different crowds in a VR urban environment, establishing a depth recognition mechanism of urban street landscapes, finding out the law of perception of the buildings and the landscapes of the different cultural crowds by utilizing big data, finding out classification and weight relation of each landscaped element, and scientifically matching the landscaped elements with different types and proportions in all levels of the urban landscaped planning and control area to carry out system control. The method emphasizes the human-oriented aspect, attaches importance to the embodiment of local culture in the city geomorphology design, and satisfies the objective and scientific recognition and protection of the city geomorphology characteristics. The method can effectively reduce the excessive dependence on subjective judgment of designers, avoid the simplification and one-sidedness of the city geomorphology design, ensure the foundation of geomorphology management protection in the city design, carry out specific calculation and design protection by combining with the actual functional area of the city, ensure the scientization and systematization of the city geomorphology design and promote the application of the leading edge digital technology in the city design field.
Drawings
Fig. 1 is a flow chart of three-dimensional eye movement data acquisition and integration.
Fig. 2 is a schematic diagram of the VR combining with the eye movement to simulate the human eye vision perception.
FIG. 3 is a diagram of the relationship between crowd samples and feature element identification and feature protection topology. In fig. 3, n1, n2, n3 … …: people with different cultural backgrounds; i 0: basic feature elements, i1, i2, i3 … …: different feature classification elements; a: and B, a geomorphic protection core area: and C, a landscape protection buffer area: and (5) coordinating and developing the region of the appearance.
Fig. 4 is a detail analysis of the feature element attention of the hong kong road and street lane.
FIG. 5 is a classification and weight analysis of hong Kong street lane feature perception by different cultural background people.
Fig. 6 is a planning drawing of each level of landscape protection areas of Zhangzhou ancient city.
Detailed Description
The following examples will further illustrate the present invention with reference to the accompanying drawings.
The embodiment of the invention comprises the following steps:
1) the method for establishing the local city geomorphic feature element case library comprises the following specific steps: the method comprises the steps of capturing local city geomorphology network Interest Point (Point of Interest) big data according to an automatic network crawler program WebSpider, integrating local city planning and opinions of local cities in a most representative geomorphology zone determined by experts in the building field, selecting a historical culture block with most representative geomorphology in the local cities, screening and classifying local city geomorphology characteristics, and establishing a local city geomorphology characteristic element case library.
2) The method comprises the following steps of constructing a virtual reality VR city geomorphology scene which not only restores real street geomorphology, but also has accurate coding information, and specifically comprises the following steps: firstly, importing three-dimensional real scene modeling software (such as ContextCapture, PIX4D MAPPER, PHOTOSCAN, Photomesh and the like) through unmanned aerial vehicle aviation inclination measurement, handheld ground GPS attitude camera measurement and vehicle-mounted ground laser radar point cloud measurement data to perform space-ground integrated real scene rendering modeling so as to realize organic fusion of multi-source real data; and finally, coding the geomorphic element components in the generated three-dimensional model one by one, importing the geomorphic element components into a non Engine4 virtual Engine, and constructing a virtual reality VR city scene with three-dimensional coding geomorphic element information.
3) The method for carrying out depth visual analysis on the sample by utilizing VR and eye movement tracking technology comprises the following specific steps: implanting a high-sensitivity infrared eye movement tracking aGlass module in an immersion VR helmet, fusing VR helmet space attitude and eye movement data by utilizing an Unreal-aGlass plug-in program (as shown in figure 1), simulating the relation between human eye horizontal and vertical visual angles and visual definition change on visual attention data acquisition, regarding eyes as a point light source, regarding sight as conical light emitted from the point light source, wherein the energy of the middle light particle of the conical light is higher than that of the light particle at the edge (as shown in figure 2), when the conical light irradiates a geomorphic element model component with space coding information, intelligently generating intuitive three-dimensional visual attention heat on the model surface through the accumulation of energy value force diagrams, when the energy value is higher than the average value by 3 times, showing that the geomorphic element is focused, and when the energy value is 1-3 times, indicating that the feature is of general interest.
When sample data is obtained, a certain number of samples are randomly selected to perform VR eyeball motion tracking adaptation and VR environment adaptability experience; and filling in a personal basic information table for sample data classification in the later period, and definitely introducing the task of VR experience: searching local most representative feature elements; then, urban landscape immersive VR experience is carried out, the duration is uniformly controlled to be 2-3 min, the rule and abnormal special conditions of eye movement and body movement of an experiencer are observed in real time through the monitoring end, the field experience of the experiencer is recorded by the wide-angle camera, the experimental process is reviewed and checked after the experiment, experimental sample data is corrected and supplemented in time, and the accuracy of depth vision perception data is improved.
4) Carrying out big data analysis on the sample, and identifying the weight relation and classification of the feature elements of the geomorphic model, wherein the specific method comprises the following steps: taking human-oriented as a center, finding out similarities and differences of attention features of different people by using eye movement data and space behavior data; through the questionnaire, the experimenter's familiarity with the local culture is known and the experimenter is divided into several categories, such as: local resident population, the crowd who has the understanding to local culture, the external crowd who does not have the knowledge to local culture (see figure 3, crowd sample), according to the difference of each crowd to the attention degree of geomorphic characteristic element, accurately find out the geomorphic basic element of local city, preliminary element, promote the cluster of element and original genuine element from this to and the weight relation of all kinds of geomorphic characteristic elements. Referring to fig. 3, the clusters of the feature elements are as follows:
(1) the basic feature element cluster is a feature type concerned by all sample crowds, namely: the local resident population, the population with understanding of the local culture and the population with understanding of the local culture pay attention to the feature of the common appearance;
(2) the native physiognomy feature element cluster is a physiognomy feature concerned by local resident groups;
(3) the method comprises the steps of improving a geomorphic feature element cluster, wherein the geomorphic feature element cluster is a geomorphic feature concerned by people with understanding on local culture;
(4) the preliminary clusters of features are features of interest to the foreign population that are not well understood herein.
5) And comprehensively evaluating the development conditions of various current situations of the geomorphic features in all levels of the protection areas by taking the classification and weight relation of the street geomorphic feature elements acquired by the typical geomorphic area as a reference, and specifically proposing a dynamic control suggestion to all levels of local geomorphic protection areas when the condition of a certain type of geomorphic feature elements deviates from the reference value according to the actual protection requirements of the geomorphic areas.
Referring to fig. 3, the method for evaluating the comprehensive evaluation perception value of the wind in each level of the wind protection area comprises the following steps: the method comprises the steps of firstly constructing typical VR digital city scenes of all levels of the wind and appearance areas, selecting a certain amount of samples to perform perception evaluation on the wind and appearance current situations of all levels of the protection areas, indicating that the wind and appearance development condition is normal when the comprehensive perception value of the wind and appearance is within a reasonable range, indicating that the wind and appearance condition is good when the comprehensive perception value of the wind and appearance is greater than an upper limit value, indicating that the wind and appearance condition is not good when the comprehensive perception value of the wind and appearance is less than a lower limit value, comparing the scoring conditions of various wind and appearance elements in detail, finding out the wind and appearance problems in time and.
The reference range of the comprehensive evaluation perception value y of the geomorphic model is as follows:
in the feature protection core area y is an element (0.8 to 1.0)
In the geomorphic protection buffer area y is an element (0.6 to 0.8)
In the geomorphic protection coordination development area y epsilon (0.4 to 0.6)
The specific calculation method of the geomorphic comprehensive perception value y is as follows:
y＝b0+∑bxnwkzin the formula, b0,b1,...,bx: a weight factor for each feature element, wherein x is (0,1,2,3,4, … …)
n0,n1...nw: attention from different groups of people, w ═ 0,1,2,3,4, … …)
k0,k1...kzThe contribution of different types of features, wherein z is (0,1,2,3,4, … …).
The dynamic control suggestion framework proposed by each level of the geomorphic protection area is as follows: in all the landscape protected areas, in order to promote the formation of the overall landscape of the city, the application of basic landscape elements is emphasized, the elements are local landscape elements which are accepted by people, and only a large number of elements are repeatedly adopted, the uniform background of the city landscape can be established, so that the formation of the overall image of the city landscape is promoted; control of original nature factors is emphasized in the geomorphic core area; control of the enhanced features is emphasized in the feature buffer area, and preliminary features are emphasized in the feature coordination development area.
Specific examples are given below. In this embodiment, taking zhangzhou ancient city as an example, identifying street landscape characteristics of ancient city and hierarchical protection control of landscape area are performed, and the specific process is as follows:
the first step is as follows: and (3) combining network crawler data and expert questionnaire opinions, selecting Zhangzhou ancient city hong Kong road segments as typical representative cases of local city geomorphology characteristics, and bringing typical Minnan street geomorphology elements into a case library.
The second step is that: and performing air-ground integrated real-scene modeling on the hong Kong road segments, then performing model lightweight and monomer processing, and constructing a VR hong Kong road scene with accurate element object coding information.
The third step: and randomly selecting 150 persons as samples to perform hong Kong road VR experience, and acquiring depth visual data.
To visually express the attention situation, the background is unified to gray. Black represents an important concern, such as: the geomorphic elements such as red bricks, lanterns, posts, brackets, advertisements and the like are focused. Dark grey represents general attention: such as: elements such as eaves, windows, and furniture have received general attention. Post-experience timely verification and correction of experience data, and dictation supplementation such as: spatial scale, material texture, element proportion, etc. (see fig. 4).
The fourth step: and identifying cluster classification and weight relation of the feature elements of the appearance of the hong Kong road according to eye tracking data and spatial behavior data of different Minnan cultural background crowds (as shown in figure 5).
(1) In the basic style element library, one can see: such elements as bricks, column corridors, and memorial archways are identified. This is a common concern, the most obvious type of feature.
(2) In the original genuine element library, elements such as characteristic doors and windows, cornices, space dimensions, material textures, element proportions and the like are identified, which are local people familiar with local culture and concerned about the feature elements.
(3) In the promotion of the geomorphic element library, some cultural elements such as couplets, advertisements and the like are identified, which are geomorphic elements concerned by people with certain understanding of local culture.
(4) In the preliminary feature library, it is seen that some nostalgic life small objects are identified, which is a general feature type that is of interest to ordinary foreign tourists.
The fifth step: and (4) evaluating a three-level landscape protection area of Zhangzhou ancient city and providing a dynamic protection control suggestion.
The line A is a ancient city core geomorphology protection area, the line B is an outer ancient city geomorphology buffering protection area, and the line C is an ancient city geomorphology coordinated development protection area (as shown in figure 6). In the physiognomy protection of Zhangzhou ancient city, the current situation three-level physiognomy protection area is dynamically and respectively subjected to perception evaluation by taking typical physiognomy characteristic recognition classification and weight relation of a core area hong Kong road as a reference, existing problems are found, and the optimal various physiognomy element combination and collocation suggestions provided for different levels of physiognomy protection areas guide the building physiognomy protection design and control (the current situation and the dynamic protection control suggestions of each level of street physiognomy area are shown in a table 1).
TABLE 1
Carry out the perception evaluation to ancient city geomorphology core protection district, the current situation geomorphology perception value y of surveying core area is 0.9, in standard control range (0.8 ~ 1.0), the whole protection situation of the core area geomorphology in reflection ancient city is good, see from the aspect subentry element perception score condition, except that preliminary geomorphology element numerical value is on the low side, all the other items are all at reasonable numerical range interval, so only need strengthen the preliminary guiding of one-level geomorphology element can.
Carry out the perception evaluation to ancient city geomorphic buffer protection district, the current situation geomorphic perception value y that records the buffer is 0.62, is close to the lower limit (0.6 ~ 0.8) of minimum standard value scope, and the whole protection situation of reflection ancient city buffer geomorphic is normal, and from the aspect subelement perception score condition, native geomorphic element is on the low side with promotion geomorphic element numerical value. Therefore, the control of original features is properly enhanced, the key design and construction of the key parts of the building with high visual attention are suggested, the features, materials and construction methods of building components are suggested to be consistent with those of the traditional building in southern Fujian, and the protection work is hoped to be carried out by the traditional craftsmen; meanwhile, the guiding of elements for improving the appearance is emphasized, and the elements such as couplets, advertisements, culture decoration and the like are utilized for improving the culture atmosphere of the street. If the calculation can be carried out according to the protection suggestion, the comprehensive perception value of the controlled geomorphic can reach 0.75, and the geomorphic buffer protection can reach a good level.
The method comprises the steps of carrying out perception evaluation on an ancient city geomorphic coordination development area, wherein the current geomorphic perception value y of the measured coordination development area is 0.38 and is lower than the lower limit (0.4-0.6) of the lowest standard value range, reflecting the poor integral protection condition of the geomorphic of the ancient city buffer area, and from the perception score condition of geomorphic subelements, the basic geomorphic elements and the preliminary geomorphic element perception value are lower. Therefore, it is proposed to increase the specific weight of basic features, such as the use of bricks, gallery and brackets; meanwhile, the adoption of primary physiognomic elements is emphasized, for example, some nostalgic scenes and small articles are used for setting off nostalgic ancient city atmosphere. If the calculation can be carried out according to the protection suggestion, the comprehensive perception value of the controlled geomorphic can reach 0.51, and the geomorphic coordinated development protection reaches a normal level.
The invention belongs to the technical field of urban design planning, and relates to an urban geomorphic feature identification and protection method based on VR combined eye movement tracking technology. The method comprises the steps of disclosing the internal relation between depth visual data of different cultural crowds and urban landscapes through quantitative visual analysis of eye-tracking data of different crowds in a VR urban environment, establishing a depth recognition mechanism of urban street landscapes feature, finding out the law of perception of the cultural crowds to building landscapes by utilizing big data, finding out classification and weight relation of each landscapes element, and scientifically matching the landscapes elements with different types and proportions in all levels of urban landscapes planning and control areas to carry out system control and guidance of the landscapes. The invention relates to a new method for perceiving and perceiving cities and excavating and developing city geomorphology, which emphasizes the human-oriented aspect, attaches importance to the embodiment of local culture in city geomorphology design and meets the requirement of objectively and scientifically recognizing and protecting city geomorphology characteristics. The method can effectively reduce the excessive dependence on subjective judgment of designers, avoid the simplification and one-sidedness of the city geomorphology design, ensure the foundation of geomorphology management protection in the city design, carry out specific calculation and design protection by combining with the actual functional area of the city, ensure the scientization and systematization of the city geomorphology design and promote the application of the leading edge digital technology in the city design field.
Claims (6)
1. A method for identifying urban features based on VR combined with eye movement tracking is characterized by comprising the following steps:
1) establishing a local city geomorphic feature element case library;
2) constructing a virtual reality VR city geomorphology scene which not only restores the real street geomorphology, but also has geomorphology component coding information;
3) the method for carrying out depth visual analysis on the sample by utilizing VR and eye movement tracking technology comprises the following specific steps: implanting an infrared eye movement tracking aGlass module in the immersive VR helmet, fusing the VR helmet space posture and the eye movement data by using a Unreal-aGlass plug-in program, in the aspect of visual attention data acquisition, the relationship between horizontal and vertical visual angles of human eyes and visual definition change is simulated, the eyes are regarded as a point light source, whereas the line of sight is seen as a cone of light emitted therefrom, the cone having a higher energy of the middle light particle than the light particle at the edges, when the cone light irradiates the geomorphic element model component with the space coding information, through the accumulation of energy values, an intuitive three-dimensional visual attention thermodynamic diagram is intelligently generated on the surface of the geomorphic element model, when the energy value is 3 times higher than the average value, the feature element is focused, and when the energy value is 1-3 times higher than the average value, the feature element is focused generally;
4) carrying out big data analysis on the sample, and identifying the weight relation and classification of the feature elements of the geomorphic model, wherein the specific method comprises the following steps: taking human-oriented as a center, finding out similarities and differences of attention features of different people by using eye movement data and space behavior data; through the questionnaire, the different familiarity of experimenters to local culture is known, and the experimental population is divided into a plurality of categories: the method comprises the following steps that local resident groups, groups with knowledge about local culture and external groups without knowledge about the local culture find out basic feature elements, preliminary feature elements, clusters for improving the feature elements and the original feature elements of local cities and the weight relationship of various feature elements according to the difference of attention degrees of the groups to the feature elements; the clusters of the features are as follows:
(1) the basic feature element cluster is a feature concerned by all sample crowds, namely: local resident population, population with understanding on local culture and population without understanding on local culture pay attention to the feature of common appearance;
(2) the native physiognomy feature element cluster is a physiognomy feature concerned by local resident groups;
(3) the method comprises the steps of improving a geomorphic feature element cluster, wherein the geomorphic feature element cluster is a geomorphic feature concerned by people with understanding on local culture;
(4) the initial feature cluster is the feature concerned by the foreign people who do not understand the text;
5) and comprehensively evaluating the current situation of the geomorphology in each level of protection area based on the classification and weight relation of the street geomorphology feature elements acquired by the typical geomorphology area.
2. The VR-based eye tracking-based urban feature recognition method as claimed in claim 1, wherein in step 1), the specific method for establishing the local urban feature element case library is as follows: the method comprises the steps of capturing local city geomorphology network interest point big data according to an automatic network crawler program WebSpider, integrating local city planning and opinions of most representative geomorphology areas of local cities, which are identified by experts in the building field, selecting one historical culture block of the most representative geomorphology representative of the local cities, screening and classifying local city geomorphology characteristics, and establishing a local city geomorphology characteristic element case base.
3. The method for city feature recognition based on VR combined with eye tracking as claimed in claim 1, wherein in step 2), the specific method for constructing a virtual reality VR city feature scene which not only restores real street landscape but also has precise coding information is as follows: firstly, importing point cloud measurement data of an unmanned aerial vehicle aerial tilt measurement, a handheld ground GPS attitude camera measurement and a vehicle-mounted ground laser radar into three-dimensional real scene modeling software to perform space-ground integrated real scene rendering modeling, and realizing organic fusion of multi-source real data; then, the live-action model is subjected to singleization and coding treatment, a local city geomorphologic feature element case library is established according to the step 1), and the city geomorphologic scene interface mesh model is replaced by a BIM model or a 3dmax model with monomer component information; finally, coding the geomorphic element components in the generated three-dimensional model one by one, importing the geomorphic element components into an UnrealEngine4 virtual engine, and constructing a virtual reality VR city scene with three-dimensional coding geomorphic element information; the three-dimensional live-action modeling software comprises ContextCapture, PIX4D MAPPER, PHOTOSCAN and Photomesh.
4. The method according to claim 1, wherein in step 3), when acquiring sample data, a certain number of samples are selected randomly to perform VR eye movement tracking adaptation and VR environment adaptive experience; and filling in a personal basic information table for later-stage crowd sample data classification, and definitely introducing the task of VR experience: searching local most representative feature elements; then, urban landscape immersive VR experience is carried out, the duration is uniformly controlled to be 2-3 min, the rule and abnormal special conditions of eye movement and body movement of an experiencer are observed in real time through the monitoring end, the field experience of the experiencer is recorded by the wide-angle camera, the experimental process is reviewed and checked after the experiment, experimental sample data is corrected and supplemented in time, and the accuracy of depth vision perception data is improved.
5. The method according to claim 1, wherein in step 5), the method for comprehensively evaluating the present features in each protection area based on the classification and weight relationship of the street and road features acquired from the typical features is as follows: according to the actual protection requirements of the geomorphic region, when the situation of a certain type of geomorphic element deviates from a reference value, a dynamic control suggestion is put forward for each local geomorphic protection region.
6. The method for city feature recognition based on VR-eye tracking as claimed in claim 1, wherein in step 5), the evaluation method for comprehensive evaluation perception value of each level of feature protection area is as follows: firstly, constructing typical VR digital city scenes of all levels of geomorphic characteristic elements, selecting a certain amount of samples to perform perception evaluation on the current situation of all levels of geomorphic protection areas, when the comprehensive geomorphic perception value is in a reasonable range, indicating that the geomorphic development condition is normal, when the comprehensive geomorphic perception value is greater than an upper limit value, indicating that the geomorphic situation is good, when the comprehensive geomorphic perception value is less than a lower limit value, indicating that the geomorphic situation is not good, comparing the scoring conditions of all types of geomorphic elements, finding out geomorphic problems in time, and proposing a pertinent suggestion; the reference range of the comprehensive evaluation perception value y of the geomorphic model is as follows:
in the feature protection core area y is an element (0.8 to 1.0)
In the geomorphic protection buffer area y is an element (0.6 to 0.8)
In the geomorphic protection coordination development area y epsilon (0.4 to 0.6)
The specific calculation method of the geomorphic comprehensive perception value y is as follows:
y＝b0+∑bxnwkz
in the formula, b0,b1,...,bx: a weight factor for each feature element, wherein x is (0,1,2,3,4, … …)
n0,n1,...,nw: attention from different groups of people, w ═ 0,1,2,3,4, … …)
k0,k1,...,kzThe contribution of different types of features, wherein z is (0,1,2,3,4, … …).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910342548.7A CN110070624B (en) | 2019-04-26 | 2019-04-26 | Urban geomorphology feature identification method based on VR combined with eye movement tracking |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910342548.7A CN110070624B (en) | 2019-04-26 | 2019-04-26 | Urban geomorphology feature identification method based on VR combined with eye movement tracking |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110070624A CN110070624A (en) | 2019-07-30 |
| CN110070624B true CN110070624B (en) | 2020-05-08 |
Family
ID=67369079
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910342548.7A Active CN110070624B (en) | 2019-04-26 | 2019-04-26 | Urban geomorphology feature identification method based on VR combined with eye movement tracking |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110070624B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111932680B (en) * | 2020-06-16 | 2022-06-28 | 厦门大学 | Urban geomorphic element identification method and system based on VR (virtual reality) depth visual perception |
| CN111836012B (en) * | 2020-06-28 | 2022-05-13 | 航天图景（北京）科技有限公司 | Video fusion and video linkage method based on three-dimensional scene and electronic equipment |
| CN111707239B (en) * | 2020-07-09 | 2021-08-17 | 厦门大学 | Method for realizing village historical building protection range detection based on oblique photography |
| CN112507799B (en) * | 2020-11-13 | 2023-11-24 | 幻蝎科技(武汉)有限公司 | Image recognition method based on eye movement fixation point guidance, MR glasses and medium |
| CN114863093B (en) * | 2022-05-30 | 2024-05-31 | 厦门大学 | Neural network training method based on eye movement technology and building design method and system |
| CN116822798B (en) * | 2023-07-06 | 2024-03-29 | 北京大学 | Regional locality measurement method for urban and rural feature modeling |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103258143A (en) * | 2013-06-05 | 2013-08-21 | 天津大学城市规划设计研究院 | Evaluation method for implementation effect of city scape planning |
| CN103810509A (en) * | 2012-11-08 | 2014-05-21 | 无锡津天阳激光电子有限公司 | Method and device of traveling Internet of Things |
| CN106066702A (en) * | 2016-08-03 | 2016-11-02 | 温州大学 | A kind of culture space analogy method based on Multimedia Digitalization technology |
| CN108762502A (en) * | 2018-05-24 | 2018-11-06 | 山东师范大学 | A kind of virtual reality crowd emulation mode and system based on eye movement tracking |
| CN108763407A (en) * | 2018-05-23 | 2018-11-06 | 王亮 | The virtual reality experience system that a kind of natural landscape and custom culture are combined |
| US10147232B2 (en) * | 2012-08-30 | 2018-12-04 | Atheer, Inc. | Method and apparatus for selectively presenting content |
| CN109582140A (en) * | 2018-11-23 | 2019-04-05 | 哈尔滨工业大学 | A kind of architecture indoor pathfinding element vision significance assessment system and method based on virtual reality and eye movement tracking |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3353630B1 (en) * | 2015-09-24 | 2021-05-26 | Tobii AB | Eye-tracking enabled wearable devices |
| CN106055102A (en) * | 2016-05-30 | 2016-10-26 | 北京奇艺世纪科技有限公司 | Virtual reality equipment control method and apparatus |
| CN105974808A (en) * | 2016-06-30 | 2016-09-28 | 宇龙计算机通信科技(深圳)有限公司 | Control method and control device based on virtual reality equipment and virtual reality equipment |
| CN108182583A (en) * | 2017-12-23 | 2018-06-19 | 成都正光恒电子科技有限责任公司 | A kind of tourism Internet of things system and device |
-
2019
- 2019-04-26 CN CN201910342548.7A patent/CN110070624B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10147232B2 (en) * | 2012-08-30 | 2018-12-04 | Atheer, Inc. | Method and apparatus for selectively presenting content |
| CN103810509A (en) * | 2012-11-08 | 2014-05-21 | 无锡津天阳激光电子有限公司 | Method and device of traveling Internet of Things |
| CN103258143A (en) * | 2013-06-05 | 2013-08-21 | 天津大学城市规划设计研究院 | Evaluation method for implementation effect of city scape planning |
| CN106066702A (en) * | 2016-08-03 | 2016-11-02 | 温州大学 | A kind of culture space analogy method based on Multimedia Digitalization technology |
| CN108763407A (en) * | 2018-05-23 | 2018-11-06 | 王亮 | The virtual reality experience system that a kind of natural landscape and custom culture are combined |
| CN108762502A (en) * | 2018-05-24 | 2018-11-06 | 山东师范大学 | A kind of virtual reality crowd emulation mode and system based on eye movement tracking |
| CN109582140A (en) * | 2018-11-23 | 2019-04-05 | 哈尔滨工业大学 | A kind of architecture indoor pathfinding element vision significance assessment system and method based on virtual reality and eye movement tracking |
Non-Patent Citations (1)
| Title |
|---|
| BIM+VR与建筑设计思维交互的耦合度评价及应用建议——以高校建筑设计教学为例;张若曦等;《生态城市与绿色建筑》;20180215;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110070624A (en) | 2019-07-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110070624B (en) | Urban geomorphology feature identification method based on VR combined with eye movement tracking | |
| He et al. | Urban neighbourhood environment assessment based on street view image processing: A review of research trends | |
| CN106228162B (en) | A kind of quick object identification method of mobile robot based on deep learning | |
| CN100533486C (en) | Digital city full-automatic generating method | |
| Zhang et al. | Panoramic visual perception and identification of architectural cityscape elements in a virtual-reality environment | |
| CN105989198A (en) | BIM-based (building information modeling based) road parametric auto-modeling method and system | |
| CN110080549B (en) | Protection decision-making method for wooden frame ancient architecture in architecture cultural heritage | |
| CN105139445A (en) | Scenario reconstruction method and apparatus | |
| CN103679655A (en) | LiDAR point cloud filter method based on gradient and area growth | |
| CN110032804B (en) | Engineering information system based on combination of BIM, MR and 3DP technologies | |
| CN114331031B (en) | Building traditional feature recognition and evaluation method and system | |
| CN116090065B (en) | Digital twinning-based smart city greening design method and device | |
| CN104484494A (en) | Structure computerizing automatic load transmission method based on building information model (BIM) | |
| CN102693285A (en) | Method for matching and retrieving three-dimensional building models based on shape recognition | |
| CN101364311A (en) | Fast and automatically modeling method in large-scale city simulation | |
| Huber et al. | Fusion of LIDAR data and aerial imagery for automatic reconstruction of building surfaces | |
| CN107368921A (en) | Track traffic scheme comparison method based on 3DGIS+BIM technologies | |
| CN117974912A (en) | Urban planning live-action three-dimensional simulation system | |
| CN107944089A (en) | A kind of plot limit for height analysis system and its analysis method for regarding corridor because of the present circumstance | |
| CN111932680B (en) | Urban geomorphic element identification method and system based on VR (virtual reality) depth visual perception | |
| KR101077588B1 (en) | Management system for obstacles airport using LIDAR | |
| CN110975215B (en) | Method, system and device for establishing transformer substation fire protection virtual training system | |
| CN111461772A (en) | Video advertisement integration system and method based on generation countermeasure network | |
| Xie | Digitized visual transformation of grotto art using deep learning and virtual reality technology | |
| Wang et al. | Quantitative Analysis Method of the Organizational Characteristics and Typical Types of Landscape Spatial Sequences Applied with a 3D Point Cloud Model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20190730 Assignee: CONDUCTORVR (XIAMEN) TECHNOLOGY CO.,LTD. Assignor: XIAMEN University Contract record no.: X2023350000043 Denomination of invention: A Method of Urban Feature Recognition Based on VR and Eye Movement Tracking Granted publication date: 20200508 License type: Common License Record date: 20230306 |