source: proiecte/pmake3d/make3d_original/Make3dSingleImageStanford_version0.1/LearningCode/Inference/OldVersion/PredictPlaneDiff.m @ 37

Last change on this file since 37 was 37, checked in by (none), 14 years ago

Added original make3d
File size: 18.5 KB
Line 
1% *  This code was used in the following articles:
2% *  [1] Learning 3-D Scene Structure from a Single Still Image,
3% *      Ashutosh Saxena, Min Sun, Andrew Y. Ng,
4% *      In ICCV workshop on 3D Representation for Recognition (3dRR-07), 2007.
5% *      (best paper)
6% *  [2] 3-D Reconstruction from Sparse Views using Monocular Vision,
7% *      Ashutosh Saxena, Min Sun, Andrew Y. Ng,
8% *      In ICCV workshop on Virtual Representations and Modeling
9% *      of Large-scale environments (VRML), 2007.
10% *  [3] 3-D Depth Reconstruction from a Single Still Image,
11% *      Ashutosh Saxena, Sung H. Chung, Andrew Y. Ng.
12% *      International Journal of Computer Vision (IJCV), Aug 2007.
13% *  [6] Learning Depth from Single Monocular Images,
14% *      Ashutosh Saxena, Sung H. Chung, Andrew Y. Ng.
15% *      In Neural Information Processing Systems (NIPS) 18, 2005.
16% *
17% *  These articles are available at:
18% *  http://make3d.stanford.edu/publications
19% *
20% *  We request that you cite the papers [1], [3] and [6] in any of
21% *  your reports that uses this code.
22% *  Further, if you use the code in image3dstiching/ (multiple image version),
23% *  then please cite [2].
24% * 
25% *  If you use the code in third_party/, then PLEASE CITE and follow the
26% *  LICENSE OF THE CORRESPONDING THIRD PARTY CODE.
27% *
28% *  Finally, this code is for non-commercial use only.  For further
29% *  information and to obtain a copy of the license, see
30% *
31% *  http://make3d.stanford.edu/publications/code
32% *
33% *  Also, the software distributed under the License is distributed on an
34% * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either
35% *  express or implied.   See the License for the specific language governing
36% *  permissions and limitations under the License.
37% *
38% */
39function []=PredictPlane(DepthDirectory,logScale)
40%this function generate the predicted plane
41% It is the depth MRF
42
43
44% define global variable
45global GeneralDataFolder ScratchDataFolder LocalFolder ClusterExecutionDirectory...
46    ImgFolder VertYNuPatch VertYNuDepth HoriXNuPatch HoriXNuDepth a_default b_default Ox_default Oy_default...
47    Horizon_default filename batchSize NuRow_default SegVertYSize SegHoriXSize WeiBatchSize;
48
49% load data
50load([ScratchDataFolder '/data/LowResImgIndexSuperpixelSep.mat']); % load LowResImgIndexSuperpixelSep
51load([ScratchDataFolder '/data/DiffLowResImgIndexSuperpixelSep.mat']); % load DiffLowResImgIndexSuperpixelSep(medi$large)
52load([ScratchDataFolder '/data/TextLowResImgIndexSuperpixelSep.mat']); % load TextLowResImgIndexSuperpixelSep using Textrea
53load([ScratchDataFolder '/data/MaskGSky.mat']); % load maskg maskSky from CMU's output
54load([ScratchDataFolder '/data/maskO.mat']);
55% load useful features
56load([ScratchDataFolder '/data/FeatureSuperpixel.mat']); % load the feature relate to position and shape of superpixe
57
58% prepare to store the predictedM
59system(['mkdir ' ScratchDataFolder '/_predicted_' DepthDirectory]);
60
61% set parameter
62ZTiltFactor = 1; % both can be estimated after group fit that estimate the Norm_floor
63YTiltFactor = 1;
64% initial parameter
65NuPics = size(filename,2);
66for i = [10]%1 : NuPics
67        i
68        % load picsinfo just for the horizontal value
69        PicsinfoName = strrep(filename{i},'img','picsinfo');
70        temp = dir([GeneralDataFolder '/PicsInfo/' PicsinfoName '.mat']);
71        if size(temp,1) == 0
72            a = a_default;
73            b = b_default;
74            Ox = Ox_default;
75            Oy = Oy_default;
76            Horizon = Horizon_default;
77        else   
78            load([GeneralDataFolder '/PicsInfo/' PicsinfoName '.mat']);
79        end
80   
81        % load useful feature
82        BatchNumber = ceil(i/batchSize);
83        PicsNumber = mod(i,batchSize);
84        if PicsNumber ==0
85         PicsNumber = 10;
86        end
87%         load([ScratchDataFolder '/data/feature_sqrt_H4_ray' int2str(BatchNumber) '.mat']); % 'f'
88%         f = f{PicsNumber};
89%         f = f(:,1);
90%         fsup = FeatureSuperpixel{i};
91%         f = (fsup(1,f))';
92       
93        % load depthMap
94        depthfile = strrep(filename{i},'img','depth_learned'); % the depth filename
95        if logScale == 1
96            load([ScratchDataFolder '/_LearnDLogScale_' DepthDirectory '/' depthfile '.mat']);
97        else
98            load([ScratchDataFolder '/_LearnD_' DepthDirectory '/' depthfile '.mat']);
99        end
100           
101        LearnedDepth = depthMap; clear depthMap;
102       
103        % initialize parameter
104        NuPatch = VertYNuDepth*HoriXNuDepth;
105       
106        % generate specific ray for whole pics
107        RayCenter = GenerateRay(HoriXNuDepth,VertYNuDepth,'center',a,b,Ox,Oy); %[ horiXSizeLowREs VertYSizeLowREs 3]
108        Rx = RayCenter(:,:,1);
109        Rx = Rx(:);
110        Ry = RayCenter(:,:,2);
111        Ry = Ry(:);
112        Rz = RayCenter(:,:,3);
113        Rz = Rz(:);
114        %RayCorner = GenerateRay(HoriXNuDepth,VertYNuDepth,'corner',a,b,Ox,Oy); %[ horiXSizeLowREs+1 VertYSizeLowREs+1 3]
115%=====================================================       
116        % MRF reshape the 3d cloud
117
118%============================
119        % setting the estimated Ground Verticl Sky segmentation (generated from CMU's code)
120        maskEstGVS = 2*ones(VertYNuDepth,HoriXNuDepth);
121        maskEstGVS(maskg{i}) = 1;
122        maskEstGVS(maskSky{i}) = 3;
123        %GSize = sum(maskg{i});
124        %SkySize = sum(maskSky{i});
125%============================
126
127        NuSupType = size(LowResImgIndexSuperpixelSep,2)+size(DiffLowResImgIndexSuperpixelSep,2)...
128                   +size(TextLowResImgIndexSuperpixelSep,2)*size(TextLowResImgIndexSuperpixelSep,3);
129
130        for j = 1:NuSupType  % total 21 seg : 3 RGB 6*3= 18 texture filters
131
132            % pick the specific segmentation
133            if j==1
134                sup = LowResImgIndexSuperpixelSep{i,1};
135            elseif j<=3
136                sup = DiffLowResImgIndexSuperpixelSep{i,j-1};
137            else
138                Subm = mod((j-3),6);
139                if Subm==0
140                   Subm=6;
141                end
142                sup = TextLowResImgIndexSuperpixelSep{i,Subm,ceil((j-3)/6)};
143            end
144
145            % extend the estimated maskGVS to the new segmentation
146            NewSupInd = (unique(sup))';
147            NewEstGSup = zeros(VertYNuDepth,HoriXNuDepth);
148            NewEstVSup = zeros(VertYNuDepth,HoriXNuDepth);
149            NewEstSSup = zeros(VertYNuDepth,HoriXNuDepth);
150            for m = NewSupInd
151                mask = sup == m;
152                if any(maskEstGVS(mask)==1) && any(maskEstGVS(mask)==3)
153                    GVSInd = analysesupinpatch(maskEstGVS(mask));
154                elseif any(maskEstGVS(mask)==1)
155                    GVSInd =1;
156                elseif any(maskEstGVS(mask)==3)
157                    GVSInd =3;
158                else
159                    GVSInd =2;
160                end
161                %GVSInd = analysesupinpatch(maskEstGVS(mask));
162                if GVSInd == 1
163                   NewEstGSup(mask) = m;
164                   NewEstVSup(mask) = 0;
165                   NewEstSSup(mask) = 0;
166                elseif GVSInd == 2
167                   NewEstVSup(mask) = m; 
168                   NewEstGSup(mask) = -1; 
169                   NewEstSSup(mask) = -1; 
170                else
171                   NewEstSSup(mask) = m;
172                   NewEstGSup(mask) = -2;
173                   NewEstVSup(mask) = -2;
174                end
175            end
176            %if j == 2
177            %   SpreadFactor = gen_SFactor(LearnedDepth,sup,Rz);
178            %end
179            %clear LowResImgIndexSuperpixelSep;
180           
181            % 2nd order smooth
182            [SecXG(j,:) SecYG(j,:)]= gen_2ndSmooth(NewEstGSup);
183            [SecXV(j,:) SecYV(j,:)]= gen_2ndSmooth(NewEstVSup);
184            [SecXS(j,:) SecYS(j,:)]= gen_2ndSmooth(NewEstSSup);
185
186            % 1st order smooth
187            [FirstYG(j,:) FirstXG(j,:)] = gen_1stSmooth(NewEstGSup);
188            [FirstYV(j,:) FirstXV(j,:)] = gen_1stSmooth(NewEstVSup);
189            [FirstYS(j,:) FirstXS(j,:)] = gen_1stSmooth(NewEstSSup);
190                %[GPy{j} ] = gen_GravityP_vertical(maskV);
191            %[PlanePriorX PlanePriorY]= gen_PlanePrior(LowResImgIndexSuperpixelSep{i,1});
192        end
193 
194        % set weight for different segmentation
195        small=50; med=25; large=5;
196        temp =[small; med; large; small*ones(6,1); med*ones(6,1) ;large*ones(6,1)]
197        Wei2ndSmoothGX = temp;
198        Wei2ndSmoothGY = temp;
199        Wei2ndSmoothVX = temp;
200        Wei2ndSmoothVY = temp;
201        Wei2ndSmoothSX = temp;
202        Wei2ndSmoothSY = temp;
203        Wei1stSmoothGX = temp;
204        Wei1stSmoothGY = temp;
205        Wei1stSmoothVX = temp;
206        Wei1stSmoothVY = temp;
207        Wei1stSmoothSX = temp;
208        Wei1stSmoothSY = temp;
209
210        % generate the smooth matrix
211        M2ndSmoothY = spdiags([ones(NuPatch,1) -2*ones(NuPatch,1) ones(NuPatch,1)],[-1 0 1],NuPatch,NuPatch);
212        M2ndSmoothX = spdiags([ones(NuPatch,1) -2*ones(NuPatch,1) ones(NuPatch,1)],...
213                              [-VertYNuDepth 0 VertYNuDepth],NuPatch,NuPatch);
214        M1stSmoothY = spdiags([ones(NuPatch,1) -ones(NuPatch,1)],[0 1],NuPatch,NuPatch);
215        M1stSmoothX = spdiags([ones(NuPatch,1) -ones(NuPatch,1)],[0 VertYNuDepth],NuPatch,NuPatch);
216
217        % generate beta
218        beta2ndSmoothGX = Wei2ndSmoothGX'*SecXG;
219        beta2ndSmoothGY = Wei2ndSmoothGY'*SecYG;
220        beta2ndSmoothVX = Wei2ndSmoothVX'*SecXV;
221        beta2ndSmoothVY = Wei2ndSmoothVY'*SecYV;
222        beta2ndSmoothSX = Wei2ndSmoothSX'*SecXS;
223        beta2ndSmoothSY = Wei2ndSmoothSY'*SecYS;
224        beta1stSmoothGY = Wei2ndSmoothGY'*FirstYG;
225        beta1stSmoothVY = Wei2ndSmoothVY'*FirstYV;
226        beta1stSmoothSY = Wei2ndSmoothSY'*FirstYS;
227        beta1stSmoothGX = Wei2ndSmoothGX'*FirstXG;
228        beta1stSmoothVX = Wei2ndSmoothVX'*FirstXV;
229        beta1stSmoothSX = Wei2ndSmoothSX'*FirstXS;
230       
231        % generate Q
232        Q2ndXx = spdiags((beta2ndSmoothGX+beta2ndSmoothVX+beta2ndSmoothSX)'...
233                 ,0,NuPatch,NuPatch)*M2ndSmoothX*spdiags(Rx,0,NuPatch,NuPatch);
234        Q2ndXy = spdiags((beta2ndSmoothGX+beta2ndSmoothVX+beta2ndSmoothSX)'...
235                 ,0,NuPatch,NuPatch)*M2ndSmoothX*spdiags(Ry,0,NuPatch,NuPatch);
236        Q2ndXz = spdiags((beta2ndSmoothGX+beta2ndSmoothVX+beta2ndSmoothSX)'...
237                 ,0,NuPatch,NuPatch)*M2ndSmoothX*spdiags(Rz,0,NuPatch,NuPatch); 
238        Q2ndYx = spdiags((beta2ndSmoothGY+beta2ndSmoothVY+beta2ndSmoothSY)'...
239                 ,0,NuPatch,NuPatch)*M2ndSmoothY*spdiags(Rx,0,NuPatch,NuPatch);   
240        Q2ndYy = spdiags((beta2ndSmoothGY+beta2ndSmoothVY+beta2ndSmoothSY)'...
241                 ,0,NuPatch,NuPatch)*M2ndSmoothY*spdiags(Ry,0,NuPatch,NuPatch);
242        Q2ndYz = spdiags((beta2ndSmoothGY+beta2ndSmoothVY+beta2ndSmoothSY)'...
243                 ,0,NuPatch,NuPatch)*M2ndSmoothY*spdiags(Rz,0,NuPatch,NuPatch);
244       
245        Q1stYz = spdiags((beta1stSmoothVY+beta1stSmoothSY)'...
246                 ,0,NuPatch,NuPatch)*M1stSmoothY*spdiags(Rz*ZTiltFactor,0,NuPatch,NuPatch);
247        Q1stYy = spdiags((beta1stSmoothGY)'...
248                 ,0,NuPatch,NuPatch)*M1stSmoothY*spdiags(Ry*YTiltFactor,0,NuPatch,NuPatch);
249        Q1stXz = spdiags((beta1stSmoothGX+beta1stSmoothVX+beta1stSmoothSX)'...
250                 ,0,NuPatch,NuPatch)*M1stSmoothX*spdiags(Rz*ZTiltFactor,0,NuPatch,NuPatch);
251%         Q2ndGXx = spdiags(beta2ndSmoothGX',0,NuPatch,NuPatch)*M2ndSmoothX*spdiags(Rx,0,NuPatch,NuPatch);
252%         Q2ndGXy = spdiags(beta2ndSmoothGX',0,NuPatch,NuPatch)*M2ndSmoothX*spdiags(Ry,0,NuPatch,NuPatch);
253%         Q2ndGXz = spdiags(beta2ndSmoothGX',0,NuPatch,NuPatch)*M2ndSmoothX*spdiags(Rz,0,NuPatch,NuPatch);
254%         Q2ndVXx = spdiags(beta2ndSmoothVX',0,NuPatch,NuPatch)*M2ndSmoothX*spdiags(Rx,0,NuPatch,NuPatch);
255%         Q2ndVXy = spdiags(beta2ndSmoothVX',0,NuPatch,NuPatch)*M2ndSmoothX*spdiags(Ry,0,NuPatch,NuPatch);
256%         Q2ndVXz = spdiags(beta2ndSmoothVX',0,NuPatch,NuPatch)*M2ndSmoothX*spdiags(Rz,0,NuPatch,NuPatch);
257%         Q2ndSXx = spdiags(beta2ndSmoothSX',0,NuPatch,NuPatch)*M2ndSmoothX*spdiags(Rx,0,NuPatch,NuPatch);
258%         Q2ndSXy = spdiags(beta2ndSmoothSX',0,NuPatch,NuPatch)*M2ndSmoothX*spdiags(Ry,0,NuPatch,NuPatch);
259%         Q2ndSXz = spdiags(beta2ndSmoothSX',0,NuPatch,NuPatch)*M2ndSmoothX*spdiags(Rz,0,NuPatch,NuPatch);
260%       
261%         Q2ndGYx = spdiags(beta2ndSmoothGY',0,NuPatch,NuPatch)*M2ndSmoothY*spdiags(Rx,0,NuPatch,NuPatch);
262%         Q2ndGYy = spdiags(beta2ndSmoothGY',0,NuPatch,NuPatch)*M2ndSmoothY*spdiags(Ry,0,NuPatch,NuPatch);
263%         Q2ndGYz = spdiags(beta2ndSmoothGY',0,NuPatch,NuPatch)*M2ndSmoothY*spdiags(Rz,0,NuPatch,NuPatch);
264%         Q2ndVYx = spdiags(beta2ndSmoothVY',0,NuPatch,NuPatch)*M2ndSmoothY*spdiags(Rx,0,NuPatch,NuPatch);
265%         Q2ndVYy = spdiags(beta2ndSmoothVY',0,NuPatch,NuPatch)*M2ndSmoothY*spdiags(Ry,0,NuPatch,NuPatch);
266%         Q2ndVYz = spdiags(beta2ndSmoothVY',0,NuPatch,NuPatch)*M2ndSmoothY*spdiags(Rz,0,NuPatch,NuPatch);
267%         Q2ndSYx = spdiags(beta2ndSmoothSY',0,NuPatch,NuPatch)*M2ndSmoothY*spdiags(Rx,0,NuPatch,NuPatch);
268%         Q2ndSYy = spdiags(beta2ndSmoothSY',0,NuPatch,NuPatch)*M2ndSmoothY*spdiags(Ry,0,NuPatch,NuPatch);
269%         Q2ndSYz = spdiags(beta2ndSmoothSY',0,NuPatch,NuPatch)*M2ndSmoothY*spdiags(Rz,0,NuPatch,NuPatch);
270% ============================START MRF OPTMIZATIOM=========================================================
271         %=================
272         % generate mask for depth difference
273         YDiff = repmat(logical([ones(VertYNuDepth-1,1); 0]),1,HoriXNuDepth);
274         XDiff = repmat(([ones(1,HoriXNuDepth-1) 0]),VertYNuDepth,1);
275         DMatrixY = spdiags([ones(NuPatch,1) -ones(NuPatch,1)],[0 1],NuPatch,NuPatch);
276         DMatrixY = DMatrixY(~maskO,:);
277         DMatrixX = spdiags([ones(NuPatch,1) -ones(NuPatch,1)],[0 VertYNuDepth],NuPatch,NuPatch);
278         %=================
279         tic;
280%         B = [DMatrixY;spdiags(maskO(:),[0],NuPatch,NuPatch)];
281%         Q = [Q2ndXz;Q2ndYz];
282%         A = [B -speye(size(B,1)) sparse(size(B,1),size(Q,1));...
283%             -B -speye(size(B,1)) sparse(size(B,1),size(Q,1));...
284%              Q sparse(size(Q,1),size(B,1)) -speye(size(Q,1));...
285%             -Q sparse(size(Q,1),size(B,1)) -speye(size(Q,1));...
286%             -speye(NuPatch) sparse(NuPatch,size(B,1)+size(Q,1))];
287%         bb = [B*LearnedDepth(:); - B*LearnedDepth(:);...
288%               sparse(size(Q,1)*2,1); -5*ones(NuPatch,1)];
289%         f = [sparse(NuPatch,1); ones(size(B,1)+size(Q,1),1)];
290%         x = linprog(f,A,bb);
291%         predictedM = spdiags([ones(1,NuPatch) sparse(1,size(B,1)+size(Q,1))]',0,NuPatch...
292%                             ,NuPatch+size(B,1)+size(Q,1))*x;
293        %predictedM = (LearnedDepth(:));
294         cvx_begin
295             cvx_quiet(false);
296             variable predictedM(NuPatch,1);
297             minimize(norm(DMatrixY*(predictedM - LearnedDepth(:)),1)...
298             +norm((predictedM(maskO) - LearnedDepth(maskO)),1)...
299             +norm([Q2ndXz;Q2ndYz]*predictedM)...
300             +norm([Q1stXz]*predictedM));
301             
302             %+norm((beta1stSmoothGY+beta1stSmoothGX)'.*(predictedM - LearnedDepth(:)))...
303             %+norm([Q1stYy ;Q1stYz; Q1stXz]*predictedM));
304             %minimize(norm(predictedM - LearnedDepth(:))...
305%              +norm([Q1stYy ;Q1stYz; Q1stXz]*predictedM)...
306%              +norm([Q2ndXz;Q2ndYz]*predictedM));%...  % 2nd smooth Ground
307%              %+norm([Q1stYz]*predictedM));
308% %              +norm([Q2ndXz;Q2ndVYz]*predictedM,1)...  % vertical
309% %              +norm([Q2ndSXz;Q2ndSYz]*predictedM,1));    % Sky
310% %              +norm([Q2ndGXx;Q2ndGXy;Q2ndGXz;Q2ndGYx;Q2ndGYy;Q2ndGYz]*predictedM)...  % 2nd smooth Ground
311% %              +norm([Q2ndVXx;Q2ndVXy;Q2ndVXz;Q2ndVYx;Q2ndVYy;Q2ndVYz]*predictedM)...  % vertical
312% %              +norm([Q2ndSXx;Q2ndSXy;Q2ndSXz;Q2ndSYx;Q2ndSYy;Q2ndSYz]*predictedM));    % Sky
313% %            + 100*norm(IPx{1}*(predictedM),1)...%+ 10*norm(IPx{2}*(predictedM.*Ry))+ 10*norm(IPx{2}*(predictedM.*Rz))..
314% %            + 100*norm(IPy{1}*(predictedM),1)...%+ 10*norm(IPy{2}*(predictedM.*Ry))+ 10*norm(IPy{2}*(predictedM.*Rz))...
315% %            + 50*norm(IPx{2}*(predictedM),1)...%+ 10*norm(IPx{2}*(predictedM.*Ry))+ 10*norm(IPx{2}*(predictedM.*Rz))..
316% %            + 50*norm(IPy{2}*(predictedM),1)...%+ 10*norm(IPy{2}*(predictedM.*Ry))+ 10*norm(IPy{2}*(predictedM.*Rz))...
317% %            + 5000*norm(GPy{5}*(predictedM.*Rz))...
318% %            + 5000*norm(spdiags([ones(GSize,1) -ones(GSize,1)],[0 1],GSize-1,GSize)*(predictedM(maskg).*Ry(maskg)))...
319% %            + 5000*norm(spdiags([ones(SkySize,1) -ones(SkySize,1)],[0 1],SkySize-1,SkySize)*(predictedM(masksky).*Rz(masksky))));
320% %                  %+ 5000*norm(Gpy*(predictedM.*Ry))...
321%                  %+ 5000*norm(spdiags([ones(SkySize,1) -1*ones(SkySize,1)],[0 1],SkySize-1,SkySize)*(predictedM(masksky).*Rz(masksky))));
322%             %spdiags([ones(GSize,1) -ones(GSize,1)],[0 1],GSize-1,GSize)*(predictedM(maskg).*Ry(maskg)) == 0;
323%             %spdiags([ones(SkySize,1) -ones(SkySize,1)],[0 1],SkySize-1,SkySize)*(predictedM(masksky).*Rz(masksky)) == 0;
324             predictedM>=5;
325%             %predictedM<=81;
326         cvx_end   
327         toc;
328        Date =date;
329        predictedM =reshape(predictedM,VertYNuDepth,[]);
330        depthMap = predictedM;
331        save([ScratchDataFolder '/_predicted_' DepthDirectory '/' depthfile '_' num2str(logScale) '_' Date '.mat'],'depthMap');
332        clear depthMap;
333       
334%=====================================================
335        % 2d to would 3d
336        [Position3DPredicted] = im_cr2w_cr(predictedM,RayCenter);
337   
338        % generate new LowResImgIndexSuperpixelSep_deoffset
339        %LowResImgIndexSuperpixelSep_deoffset = LowResImgIndexSuperpixelSep{i};
340   
341        % add on image feature
342        %global Imf;
343        %Imf= cat(1,Position3DPredicted,permute(ones(VertY,1)*[1:HoriX],[3 1 2]), permute([1:VertY]'*ones(1,HoriX),[3 1 2]),permute(double(zeros(VertY,HoriX,3)),[3 1 2]),permute(double(LowResImgIndexSuperpixelSep_deoffset),[3 1 2]),permute(double(LowResImgIndexSuperpixelSep{i}),[3 1 2]) );
344   
345        % calculate each plane parameter for each superpixel
346        %[PlaneParameterPredicted] = fit_all_planes(RayLoResCorner); % hard work around 2min
347   
348        % generate VRML
349        Date = date;
350        [VrmlName] = vrml_test_faceset_triangle(filename{i},Position3DPredicted,RayCenter,['PredictM_' DepthDirectory '_' num2str(logScale) '_' Date '_Diff'],a,b,Ox,Oy);
351        system(['gzip -9 -c ' ScratchDataFolder '/vrml/' VrmlName ' > ' ScratchDataFolder '/vrml/' VrmlName '.gz']);
352        delete([ScratchDataFolder '/vrml/' VrmlName]);
353            %vrml_test_faceset_triangle(filename{i},PlaneParameterPredicted,LowResImgIndexSuperpixelSep{i},LowResImgIndexSuperpixelSep_deoffset,[DepthDirectory '_' Date]);
354end   
Note: See TracBrowser for help on using the repository browser.