CN102054166A - Scene recognition technology used in outdoor augmented reality system - Google Patents

Abstract

The invention relates to the technical field of pattern recognition, in particular to a novel scene recognition technology used in an outdoor augmented reality system. The invention utilizes secondary spacial position information to restrain, so as to reduce the retrieval range of scene recognition at first, then provides two characteristics namely use texture and use profile to express the scene, and leads a categorizer with a simpler structure to evaluate posterior probability models of the two characteristics, so as to realize the scene recognition method based on visual sense. The scene recognition technology provided by the invention can meet the requirements of real-time performance and high recognition rate, and is suitable for application in outdoor augmented reality systems with larger range and more scenes.

Description

A kind of new scene Recognition technology that is used for outdoor augmented reality system

Technical field

The present invention relates to mode identification technology, particularly relate to a kind of new scene Recognition technology that is used for outdoor augmented reality system.

Background technology

Augmented reality technology (Augmented Reality-AR) is a kind of emerging computer utility and the human-computer interaction technology that produces along with the development of virtual reality technology.This technology merges the virtual environment that computing machine generates mutually with user's real scene on every side, makes the user be sure of that from sensory effects virtual environment is its ingredient of real scene on every side.

The range of application of early stage augmented reality system is confined to indoor or outdoor small-scale environments usually, and mostly research object is the simple scenario of single or less target.In recent years, along with constantly widen in its range of application of development and the field of augmented reality technology, the researchist begin gradually to pay close attention to how the augmented reality technology is applied to outdoor complicated on a large scale, target-rich environment, realized the multiple system that is applicable to different application.Mainly comprise as follows:

1, based on the .2006:1. of the city navigation system of augmented reality technology [referring to Murphy D Kahari M.Mara-sensor based augmented reality system for mobile imaging.the IEEE InternationalSymposium on Mixed and Augmented Reality 2006[C]].This type systematic is measured position and the orientation of user in the city by GPS and compass, and by showing that the place that each bar road is led to navigate for the user, simultaneity factor can also be measured user's gait of march.

2, museum guiding system [referring to Bruns E.Bimber O Brombach B.SubobjectDetection through Spatial Relationships on Mobile Phones.InternationalConference of Intelligent User Interfaces (IUI2009) [C] .2009.].This type systematic uses the positions of technological orientation visitor in the museum such as GPS or bluetooth, utilize compass determine the user towards or utilize vision technique identification user perceptual showpiece, better understand the showpiece of being visited by helping the user, make user's visit process become abundant, interesting to user's demonstration various information relevant with showpiece.

3, on a large scale ancient site guide to visitors and playback system [referring to Guo Junwei, Wang Yongtian, ChenJing, et al.Augmented Reality Registration Algorithm Applied in Reconstructionof Yuanmingyuan Archaeological Site.International Conference on CAD﹠amp; CG[C] .2009:324-329.].Because reconstruction and reparation to the ancient site building are that a comparatively complicated process and a manpower and materials consumption is bigger, also are easy to ruins are damaged, and have therefore occurred the ruins playback system that uses the augmented reality technology to realize in recent years.This type systematic is by technological orientation visitors' such as GPS or bluetooth position, come user's attitude is determined by compass or vision technique, and the information relevant with ancient site strengthened demonstration, generally include that three-dimensional original appearance model, the ruins of ancient site are historical to be introduced etc.

4, with the smart mobile phone be the outdoor augmented reality application of platform.This class is used and is made the augmented reality technology break away from the restriction of large volume PC platform, and low in energy consumption, the required storage space of algorithm is little.Present first item augmented reality mobile phone browser-LayAR that for example Dutch a company released in this year.This browser can run on the Android cell phone platform.The user only need aim at scene of interest with the camera of mobile phone, GPS is the consumer positioning position at first, compass is judged the direction that camera is faced, the user just can see the information relevant with captured scene below the screen of mobile phone subsequently, even also comprises the information of the practicality such as information of discount, job notice and ATM in peripheral house to let, bar and restaurant.Apple's this class application and development on the Iphone mobile phone also starts to walk early, the at present existing corresponding running software of many moneys is on Iphone3 generation and 4 generation products, as LondonPipes, the user can use this system to go sight-seeing in the street corner, London, and it can discern buildings and automatically to the detailed road information of user's displaying contents.

The characteristics that outdoor augmented reality is used are that the residing environmental field of user is big, user's interest scene quantity more (for example numerous building target, a large amount of museum's showpiece target and many places ancient sites are built target etc.).Therefore, this class is used a problem that at first needs to solve and is pre-determined user's present located scene exactly, and this process is referred to as scene Recognition usually.At present existent method is generally by adopting hardware approach to come the consumer positioning position or itself and the visible sensation method that adopts software being discerned the user place scene line trace location of going forward side by side.In the method that adopts hardware to position, LayAR system for example, usually use GPS or wireless communication technologys such as bluetooth, WiFi to come customer location is positioned, again according to sensors such as compass further determine the user towards and the orientation, finally definite user place scene.Some other system combines the hardware and software method, museum guiding for example above-mentioned system, ruins playback system, and at present at the Theodolite system of Iphone4 mobile phone development of new generation.These systems at first adopt technology such as GPS, compass that customer location is carried out Primary Location, and the visible sensation method that uses a computer is afterwards accurately discerned scene and user's attitude is registered, and final realization strengthens demonstration accurately.Usually physical sensors exists refreshing frequency and the lower problem of bearing accuracy, and increasing along with target object quantity simultaneously, the range of search of visual identity can increase, cause the recognition accuracy and the real-time performance of visible sensation method all can descend gradually, the locator meams that therefore present most systems adopts software and hardware technology to combine is finished the scene Recognition under the outdoor environment on a large scale, this also is the subject matter that the present invention pays close attention to and will solve, promptly how the combination by above dual mode realize outdoor augmented reality use in scene Recognition fast and accurately.

Summary of the invention

In view of this, fundamental purpose of the present invention is to provide a kind of method of scene Recognition fast and accurately for complicated out of doors environment on a large scale develops the augmented reality technology down, this method synthesis utilizes profile and two kinds of composite characters of texture to represent scene, and by sorter simple in structure composite character is carried out supervised learning.Simultaneously information constrained in conjunction with the secondary spatial geographical locations, further dwindle the range of search of the current scene of living in of identification user, and in this scope, use visual identity method set forth above to finish scene Recognition.

Technical scheme of the present invention is:

, scene kind big according to the outdoor environment scope and a fairly large number of characteristics position the position of user in environment by GPS, by the locus constraint information range of search of user's scene of living in to be identified are dwindled.Use sorter that the profile and the texture blend feature of scene are discerned subsequently, and discern current scene by the identification of composite character.Algorithm mainly comprises off-line preparation and two parts of ONLINE RECOGNITION, and concrete steps comprise:

(1) the off-line preparatory stage:

The first step for the residing environment of user (for example campus, city or an area), is used GPS that its spatial dimension is measured and demarcated, and is adopted longitude and latitude to represent this scope.

Second step, space density size according to scene in the size of environmental field and the environment, entire environment is divided into several zones, the longitude and latitude spatial dimension in zone is n * m, and the unit of n and m is identical with longitude and latitude here, i.e. degree (°) divide (') and second ("); the standard of n and m value size is the scene that has some in each zone of assurance; in order to ensure the accuracy of visual identity, the present invention specify this quantity be no more than 15 (for example in certain campus environment, n=m=5 ").These ready-portioned zones are referred to as submap, and are numbered submap-1 respectively, submap-2 ..., submap-N (N is the zone sum);

The 3rd goes on foot, and has the scene of some in each submap, and these scenes exist in a certain order in the space and this spatial order remains unchanged.Therefore,,, and be numbered subscene-1 in order respectively for each scene among each submap is given a geographical location information label according to the locus order, subscene-2 ..., subscene-n (n is a scene sum in each zone).Then submap-i-subscene-j represents j scene in i the zone;

In the 4th step, take the key frame images of different points of view and extract profile and the texture blend feature at each scene.Use the Ferns sorter that composite character is carried out supervised learning;

(2) the ONLINE RECOGNITION stage: in the 5th step,, determine which submap is user's present located scene belong to according to each regional locus scope of GPS spatial orientation information and off-line phase demarcation;

The 6th step, if present frame is first frame, then system according to submap information should the zone in all scenes be shown to the user in the button mode, and determine the subscene label of current scene by the mode that the user manually selects, finish scene Recognition; If present frame is not first frame,, determine the range of search of identification current scene subscene then according to the subscene information of previous frame;

The k step, take current frame image for the residing current scene of user, and in the range of search that previous step is determined, adopt visible sensation method that current scene is discerned, obtain the subscene label of current scene, finish scene Recognition.

A kind of new scene Recognition technology that is used for outdoor augmented reality system of the present invention has the following advantages:

(1) in technical scheme of the present invention, owing to be at first by using texture and two kinds of composite characters of profile to come user place scene is expressed, therefore compare with the expression way of using single feature in the past, improved the ability to express for outdoor complex scene, the introducing of Ferns sorter has realized especially for the effective supervised learning of composite character and identification more fast and accurately.Therefore, can provide comparatively efficiently for the augmented reality system under the outdoor complicated environment on a large scale, scene Recognition result accurately.

(2) in technical scheme of the present invention, the range of search based on the scene Recognition of visible sensation method has been dwindled in the introducing of secondary spatial positional information constraint and the use of GPS information to a great extent, further shortened thus follow-up scene identifying processing time, realized higher scene Recognition success ratio.

Description of drawings

Fig. 1 is scene recognizer process flow diagram among the present invention.

Fig. 2 extracts result and PHOG histogram thereof for LoG unique point, part textural characteristics, the contour feature that obtains at some Object Extraction among the present invention.

Fig. 3 is Ferns sorter structure evolution synoptic diagram among the present invention.

The submap spatial geographical locations information labeling synoptic diagram of Fig. 4 among the present invention a certain campus environment being carried out.

The recognition result synoptic diagram of Fig. 5 for obtaining after according to the proposed method the some scenes in certain campus environment being discerned.

Embodiment

Below in conjunction with accompanying drawing the present invention is elaborated.

Fig. 1 is scene recognizer process flow diagram among the present invention.Be introduced at each the key step embodiment in the algorithm flow below.

Fig. 2 extracts result and PHOG histogram thereof for LoG unique point, part textural characteristics, the contour feature of some objects among the present invention.

Scene complexity in the outdoor environment, the characteristic feature that different scene had has nothing in common with each other.For example the contour feature of object such as buildings, vehicle will be than its textural characteristics more obvious (as shown in Figure 2).Therefore if will use two automobiles in the textural characteristics component-bar chart 2 just may obtain correct result.Textural characteristics is represented (is the textural characteristics at center with red unique point as some that show among Fig. 2) with the image block that in the image with the unique point is the center usually.The present invention's proposition combines two kinds of features of texture and profile and describes a scene.Wherein, the required unique point of texture feature extraction adopts LoG (Laplacian-of-Gaussian) unique point comparatively commonly used at present, and it is proved to be the most stable local feature point operator at present.When using the LoG feature, at first the Laplacian-of-Gaussian multiscale space of computed image is chosen the peaked scale-value of the Laplacian operator yardstick of image the most, afterwards extract minutiae on this yardstick.Contour feature uses PHOG (Pyramid Histogram of Gradient) operator, and the PHOG operator is the improvement to HOG (Histogram of Oriented Gradients) operator.PHOG is divided into n zone according to the direction of gradient with the Grad at edge, has added the pyramidal characteristic in space afterwards on the basis of histogram of gradients, has further improved the stability of this feature.Be structure space pyramid, at the 1st layer, image is divided into the 2l sub regions, and distinguishes statistic histogram on subregion.

Shown in the binary tree structure among Fig. 3, Ferns sorter used in the present invention is the improvement to random tree classification device (Randomized Tree).It is based on binary tree, change the hierarchical structure of setting at random into the flat structure, by corresponding test is set in each child node rational spatial division is carried out in the feature samples set, and the posterior probability that finally counts each category feature at each leaf node distributes, and by seeking the maximum a posteriori probability scoring target to be identified classified.

The Ferns algorithm with each image block in the image and under various image change the image block of gained be considered as a class.Use the Ferns sorter that an image block is discerned, will find that class the most similar in fact exactly to this image block.Make c _k(k=1,2,3 ..., L, class add up to L) represent k class; Make t _j(j=1,2,3 ..., M) the two-value test set of carrying out for each child node classification is required.The standard of then image block being carried out discriminator is:

$\widehat{{.c}_k}=\underset{c_k}{\arg \max }P(C=c_k|{\mathrm{<figure-callout\; id="1"\; label="t"\; filenames="HSA00000323479100041.png,HSA00000323479100051.png"\; state="\{\{state\}\}">t</figure-callout>}}_1,{\mathrm{<figure-callout\; id="2"\; label="t"\; filenames="HSA00000323479100051.png"\; state="\{\{state\}\}">t</figure-callout>}}_2,...,t_M).---\left(1\right)$

Wherein, C is the stochastic variable of an any class of representative.

According to bayesian theory, P (C=c _k| t ₁, t ₂...., t _M) can calculate in the following manner:

$P(C=c_k|{\mathrm{<figure-callout\; id="1"\; label="t"\; filenames="HSA00000323479100041.png,HSA00000323479100051.png"\; state="\{\{state\}\}">t</figure-callout>}}_1,{\mathrm{<figure-callout\; id="2"\; label="t"\; filenames="HSA00000323479100051.png"\; state="\{\{state\}\}">t</figure-callout>}}_2,...,t_M)=\frac{P({\mathrm{<figure-callout\; id="1"\; label="t"\; filenames="HSA00000323479100041.png,HSA00000323479100051.png"\; state="\{\{state\}\}">t</figure-callout>}}_1,{\mathrm{<figure-callout\; id="2"\; label="t"\; filenames="HSA00000323479100051.png"\; state="\{\{state\}\}">t</figure-callout>}}_2,...,t_M|C=c_k)P(C=c_k)}{P({\mathrm{<figure-callout\; id="1"\; label="t"\; filenames="HSA00000323479100041.png,HSA00000323479100051.png"\; state="\{\{state\}\}">t</figure-callout>}}_1,{\mathrm{<figure-callout\; id="2"\; label="t"\; filenames="HSA00000323479100051.png"\; state="\{\{state\}\}">t</figure-callout>}}_2,...,t_M)}---\left(2\right)$

Because P (t ₁, t ₂...., t _M) be a factor that has nothing to do with classification, so formula (1) can be reduced to:

$\widehat{c_k}=\underset{c_k}{\arg \max }P({\mathrm{<figure-callout\; id="1"\; label="t"\; filenames="HSA00000323479100041.png,HSA00000323479100051.png"\; state="\{\{state\}\}">t</figure-callout>}}_1,{\mathrm{<figure-callout\; id="2"\; label="t"\; filenames="HSA00000323479100051.png"\; state="\{\{state\}\}">t</figure-callout>}}_2,...,t_M|C=c_k)---\left(3\right)$

Wherein, two-value test item t _jOnly with image block in any two pixel d _{J, 1}And d _{J, 2}Gray-scale value relevant, can be expressed as:

$t_j=\left\{\begin{array}{cc}0& I\left(d_{j,1}\right)-I\left(d_{j,2}\right)\&GreaterEqual;0\\ 1& \mathrm{otherwise}\end{array}\right.---\left(4\right)$

What wherein I represented is grey scale pixel value, pixel d _{J, 1}And d _{J, 2}It is picked at random in advance.

Because t _jBelong to a kind of comparatively simple test mode, therefore need carry out a large amount of tests could realize accurate classification.Cause algorithm that each class is discerned the data that need store about 2N order of magnitude when estimating thus and could express the joint probability density shown in the formula (3) comparatively accurately, when the value of N hour, handle that the required storage space of these data is less, the time is shorter, but when the value of N is big, along with required storage space of increase algorithm and processing time of N increases sharply, finally can't satisfy the requirement of real-time.Therefore, the Ferns method proposes that above test process is divided into Z group carries out, and the amount of capacity of each group is S, and S=N/Z.At this moment, the conditional probability in the formula (3) can be expressed as:

$P({\mathrm{<figure-callout\; id="1"\; label="t"\; filenames="HSA00000323479100041.png,HSA00000323479100051.png"\; state="\{\{state\}\}">t</figure-callout>}}_1,{\mathrm{<figure-callout\; id="2"\; label="t"\; filenames="HSA00000323479100051.png"\; state="\{\{state\}\}">t</figure-callout>}}_2,...,t_M|C=c_k)=\underset{a=1}{\overset{Z}{\mathrm{\&Sigma;}}}P\left(F_a\right|C=c_k)---\left(5\right)$

F wherein _a={ t _{σ (a, 1)}, t _{σ (a, 2)}...., t _{σ (a, S)}, a=1,2 ...., Z represents a Ferns, and σ () is a permutation function at random, and scope is between 1～N.Because the Ferns algorithm divides into groups the child node test process, make the number of parameter by original 2 ^NReduce to Z * 2 ^S, not only make the calculating of conditional probability become simpler, and on the fairly large classification and identification of processing, have very obvious speed and storage advantage.

In off-line phase, algorithm is estimated conditional probability P (F by the supervised learning mode for each Ferns _z| C=c _k), shown in formula:

$p_{d,c_k}=P(F_z=d|C=c_k)---\left(6\right)$

The two-value total number measured that each Ferns need carry out is D=2 ^S, conditional probability then

Need satisfy following condition:

$\underset{d=1}{\overset{D}{\mathrm{\&Sigma;}}}{p}_{d,c_k}=1---\left(7\right)$

For feature class c _k, by sorter all images piece sample that belongs to such is carried out supervised learning, finally the posterior probability to this class is calculated in each leaf node, and account form is as follows:

$p_{d,c_k}=\frac{N_{d,c_k}+1}{N_{c_k}+D}---\left(8\right)$

Wherein,

Representative belongs to class c _kAll images piece sample in fall into the image block number of samples of d leaf node,

Representative belongs to class c _kThe sum of all images piece sample.Repeat above training process at each Fern, finally finish training whole Ferns.

The online stage, each image block that extracts on the current frame image is put among the Ferns sorter, determine classification under this image block by the posterior probability on its final leaf node that arrives.

According to the posterior probability calculation method of the Ferns sorter of above introduction, the present invention carries out probability model to texture and contour feature in the following ways and estimates.

If Ω={ ω ₁, ω ₂, L, ω _nBe the set that comprises the scene of all categories, scene classification number is n.F _Texture={ F _T1, F _T2, L, F _TnRepresent the textural characteristics of n scene to gather, wherein

Be the unique point set of i scene, m _iBe i scene characteristic point sum, F _Shape={ f _S1, f _S2, L, f _SnThe contour feature of n scene of expression gathers.According to Bayes's criterion, classification ω under the current scene ^*That class for posterior probability maximum in all categories:

${\mathrm{\&omega;}}^{*}=\underset{{\mathrm{\&omega;}}_i\&Element;\mathrm{\&Omega;}}{\arg \max }\frac{1}{T}\underset{t=1}{\overset{T}{\mathrm{\&Sigma;}}}{P}_{t,l}\left({\mathrm{\&omega;}}_i\right|F_{\mathrm{texture}}^{\mathrm{obs}},f_{\mathrm{shape}}^{\mathrm{obs}})---\left(9\right)$

Wherein Be the textural characteristics of current scene,

Represent the current scene profile, wherein l represents that composite character is t the leaf node numbering of setting arrival at random.According to bayesian theory:

$P_{t,l}\left({\mathrm{\&omega;}}_i\right|F_{\mathrm{texture}}^{\mathrm{obs}},f_{\mathrm{shape}}^{\mathrm{obs}})=\frac{P_{t,l}(F_{\mathrm{texture}}^{\mathrm{obs}},f_{\mathrm{shape}}^{\mathrm{obs}}|{\mathrm{\&omega;}}_i)P\left({\mathrm{\&omega;}}_i\right)}{\underset{i=1}{\overset{n}{\mathrm{\&Sigma;}}}{P}_{t,l}\left({\mathrm{\&omega;}}_i\right)}---\left(10\right)$

$\&Proportional;P_{t,l}(F_{\mathrm{texture}}^{\mathrm{obs}},f_{\mathrm{shape}}^{\mathrm{obs}}|{\mathrm{\&omega;}}_i)P\left({\mathrm{\&omega;}}_i\right)$

Suppose that Same Scene textural characteristics and contour feature are independent, m ₀Individual textural characteristics is equally divided into the M group, and every group has

Individual feature, and independent between every group of textural characteristics, then:

$P_{t,l}(F_{\mathrm{texture}}^{\mathrm{obs}},f_{\mathrm{shape}}^{\mathrm{obs}}|{\mathrm{\&omega;}}_i)=P_{t,l}\left(F_{\mathrm{texture}}^{\mathrm{obs}}\right|{\mathrm{\&omega;}}_i)P_{t,l}\left(f_{\mathrm{shape}}^{\mathrm{obs}}\right|{\mathrm{\&omega;}}_i)$

$=P_{t,l}\left(\right\{f_{\mathrm{to}}^1,f_{\mathrm{to}}^2,L,f_{\mathrm{to}}^{m_o}\left\}\right|{\mathrm{\&omega;}}_i)\&CenterDot;P_{t,l}\left(f_{\mathrm{shape}}^{\mathrm{obs}}\right|{\mathrm{\&omega;}}_i)---\left(11\right)$

$=\left(\underset{k=1}{\overset{M_o}{\mathrm{\&Pi;}}}{P}_{t,l}\left(F_{\mathrm{to}}^k\right|{\mathrm{\&omega;}}_i)\right)\&CenterDot;P_{t,l}\left(f_{\mathrm{shape}}^{\mathrm{obs}}\right|{\mathrm{\&omega;}}_i)$

Wherein K=1, L, M _oRepresent the k node layer of Ferns, (k s) represents from 1 to m σ ₀Random mapping function.Then

${\mathrm{\&omega;}}^{*}=\underset{{\mathrm{\&omega;}}_i\&Element;\mathrm{\&Omega;}}{\arg \max }\frac{1}{T}\underset{t=1}{\overset{T}{\mathrm{\&Sigma;}}}(\underset{k=1}{\overset{M_o}{\mathrm{\&Pi;}}}{P}_{t,l}\left(F_{\mathrm{to}}^k\right|{\mathrm{\&omega;}}_i)\&CenterDot;P_{t,l}\left(f_{\mathrm{shape}}^{\mathrm{obs}}\right|{\mathrm{\&omega;}}_i))P\left({\mathrm{\&omega;}}_i\right)---\left(12\right)$

The probability of supposing each scene appearance is identical, i.e. P (ω _i) obey evenly distribution, adopt the method among the Ferns to estimate expression formula simultaneously

$\underset{k=1}{\overset{M_o}{\mathrm{\&Pi;}}}{P}_{t,l}\left(F_{\mathrm{to}}^k\right|{\mathrm{\&omega;}}_i)\&CenterDot;P_{t,l}\left(f_{\mathrm{shape}}^{\mathrm{obs}}\right|{\mathrm{\&omega;}}_i)---\left(13\right)$

Probability distribution.

Each child node is tested in the following manner in the Ferns sorter:

$F_{\mathrm{texture}}=\left\{\begin{array}{cc}1& \mathrm{if}{I}_i<I_j\\ 0& \mathrm{Otherwise}\end{array}\right.$

(14)

$f_{\mathrm{shape}}=\left\{\begin{array}{cc}1& \mathrm{if}{w}^{T}x+b<0\\ 0& \mathrm{Otherwise}\end{array}\right.$

Wherein w is the vector that has identical dimensional n with the contour feature vector x, in the test process from vectorial w a picked at random a component (a ∈ [1, n]), component index is at random, and component value is between [1,1], (0 arrives b ∈

).

The secondary spatial geographic information annotation results of Fig. 4 for coming according to the proposed method certain campus is carried out.Merely based on the scene Recognition algorithm of vision, its discrimination is no more than 75% at present, further improves discrimination and need use complicated more recognizer.And in fact, during the augmented reality under outdoor environment was on a large scale used, system can make full use of positional information in spatial relation and the ground, utilizes this category information to retrain and dwindle the hunting zone of scene to be identified, significantly improves recognition success rate.

The present invention proposes to use a kind of secondary space constraint to dwindle the range of search of scene Recognition, and specific practice is: at first use gps system that Primary Location is carried out in the position of user in environment.Consider that employed gps system can provide the longitude and latitude of user position, and measuring accuracy is 0.01 ".Therefore, the outdoor environment that scope is bigger (for example campus environment of certain shown in Fig. 4) carries out the division of regional area according to the specification of 5 " * 5 ", and this regional area is referred to as submap, and each submap is numbered, for example submap-i represents the regional area (as among Fig. 4 campus environment being divided several submap zones that obtain) of i 5 " * 5 ".System uses the locating information that GPS provided accurately to demarcate the pairing longitude and latitude scope of each submap (yellow mesh lines as shown in Figure 4 and corresponding longitude and latitude thereof).

Owing to all comprised the scene of some in each submap, this quantity be designated as V (V 〉=1).Sometimes the V value in certain submap is bigger, carries out scene Recognition and still can't guarantee 100% correct recognition rata in this scope.Therefore, the present invention proposes each scene among the submap is carried out the geography information mark, a label is given for it in proper order in adjacent position according to each scene, and is designated as subscene-j, represents the 3rd scene in the 3rd zone as label submap-3-subscene-3.

When system's real time execution, GPS at first positions user's current location, determine the affiliated submap of user, system dwindles the range of search of the current place of user scene in conjunction with the scene geographic information tags in this submap, and uses visible sensation method to identify current scene in this scope.

Even the situation of recognition failures also can appear in the visual identity method in a small range sometimes, in order to address this problem, algorithm is after by visible sensation method identification scene, can sort according to similarity degree to recognition result, with the scene that comes forward position as the alternative user of being shown to, so that the user can select correct current scene when finding the scene Recognition mistake.

The recognition result that obtains after according to the proposed method the some scenes in certain campus environment being discerned as shown in Figure 5, the result has comprised the secondary spatial geographic information of each scene that measures and the scene Recognition result who represents by label.

More than a kind of new scene Recognition technology that is used for outdoor augmented reality system provided by the present invention is described in detail, in the literary composition principle of the present invention and embodiment are set forth, the explanation of above content just is used for helping to understand method of the present invention and core concept thereof; Simultaneously, for one of ordinary skill in the art, according to thought of the present invention, the part that all can change in specific embodiments and applications, in sum, this description should not be construed as limitation of the present invention.

Claims (8)

1. a new scene Recognition technology that is used for outdoor augmented reality system is characterized in that, may further comprise the steps:

(1) the off-line preparatory stage:

Step 1: for the residing environment of user (for example campus, city or an area), use GPS that its spatial dimension is measured and demarcated, and adopt longitude and latitude to represent this scope.

Step 2: according to the space density size of scene in the size of environmental field and the environment, entire environment is divided into several zones, the longitude and latitude spatial dimension in zone is n * m, here the unit of n and m is identical with longitude and latitude, i.e. degree (°) divide (') and second ("), the standard of n and m value size is the scene that has some in each zone of assurance, in order to ensure the accuracy of visual identity; the present invention specify this quantity be no more than 15 (for example in certain campus environment, n=m=5 ").These ready-portioned zones are referred to as submap, and are numbered submap-1 respectively, submap-2 ..., submap-N (N is the zone sum).

Step 3: have the scene of some in each submap, these scenes exist in a certain order in the space and this spatial order remains unchanged.Therefore,,, and be numbered subscene-1 in order respectively for each scene among each submap is given a geographical location information label according to the locus order, subscene-2 ..., subscene-n (n is a scene sum in each zone).Then submap-i-subscene-j represents j scene in i the zone.

Step 4: take the key frame images of different points of view and extract profile and the texture blend feature at each scene.Use the Ferns sorter that composite character is carried out supervised learning.

(2) the ONLINE RECOGNITION stage:

Step 5:, determine which submap is user's present located scene belong to according to each regional locus scope of GPS spatial orientation information and off-line phase demarcation.

Step 6: if present frame is first frame, then system according to submap information should the zone in all scenes be shown to the user in the button mode, and determine the subscene label of current scene by the mode that the user manually selects, finish scene Recognition; If present frame is not first frame,, determine the range of search of identification current scene subscene then according to the subscene information of previous frame.

Step 7: take current frame image for the residing current scene of user, and in the range of search that previous step is determined, adopt visible sensation method that current scene is discerned, obtain the subscene label of current scene, finish scene Recognition.

2. a kind of new scene Recognition technology that is used for outdoor augmented reality system as claimed in claim 1 is characterized in that: in step 1, use GPS that its spatial dimension is measured and demarcated, and adopt longitude and latitude to represent this scope.The measurement means of this its spatial location and mode are not limited to the GPS method, can also be by wireless space position measurement modes such as bluetooth, Wifi.

3. a kind of new scene Recognition technology that is used for outdoor augmented reality system as claimed in claim 1, it is characterized in that: in step 2, space density size according to scene in the size of entire environment scope and the environment comes the zone of entire environment is divided, the division methods of each regional extent and representation unit are different and different according to the metering system that uses in the step 1, for example use GPS as metering system, then usage degree (°) divide (') and second (") is used as the representation unit of regional extent.

4. a kind of new scene Recognition technology that is used for outdoor augmented reality system as claimed in claim 1, it is characterized in that: in step 2 and step 3, use secondary spatial geographical locations information to come each scene in the environment is represented, a kind of like this expression mode of secondary positional information is: first order information is determined by the metering system in the step 1 for the area of space information at this scene place, the expression mode of this information; Second-level message is in the area of space of this scene at its place, and the neighbouring relations of other scenes in this scene and the zone are represented and determined.

5. a kind of new scene Recognition technology that is used for outdoor augmented reality system as claimed in claim 1, it is characterized in that: in step 4, in order to reach the purpose that scene is expressed more accurately, use profile and texture blend feature to express scene, this composite character wherein also can be more kinds of combination of features.For composite character being carried out supervised learning and real-time identification, the comparatively simple sorter of utilization structure is trained it and is discerned simultaneously, and the sorter kind here can be Ferns, also can be other sorters that can carry out real-time feature identification.

6. a kind of new scene Recognition technology that is used for outdoor augmented reality system as claimed in claim 1, it is characterized in that: in step 5, corresponding to spatial position measuring means and mode come user's current location is measured in use and step 1, the step 2.

7. a kind of new scene Recognition technology that is used for outdoor augmented reality system as claimed in claim 1 is characterized in that: in step 6, use with three in scene space position, the corresponding to second level represent that mode comes the position of current scene is discerned.

8. a kind of new scene Recognition technology that is used for outdoor augmented reality system as claimed in claim 1, it is characterized in that: in step 7, to discern the range of search of current scene by the secondary spatial positional information and dwindle, use subsequently with step 4 in the recognition methods of corresponding to computer vision finish the final identification of scene.

After above-described processing, just can realize the identification of the current scene in the augmented reality system under the outdoor environment.

Images