Added VOC 2012 dev kit (VOCdevkit_18-May-2011.tar) as an external.

external/VOCdevkit/VOCcode/PASemptyobject.m

@@ -0,0 +1,11 @@
+function object=PASemptyobject
+  object.label='';
+  object.orglabel='';
+  object.bbox=[];
+  object.polygon=[];
+  object.mask='';
+  object.class='';
+  object.view='';
+  object.truncated=false;
+  object.difficult=false;
+return

external/VOCdevkit/VOCcode/PASemptyrecord.m

@@ -0,0 +1,6 @@
+function record=PASemptyrecord
+  record.imgname='';
+  record.imgsize=[];
+  record.database='';
+  record.objects=PASemptyobject;
+return

external/VOCdevkit/VOCcode/PASerrmsg.m

@@ -0,0 +1,7 @@
+function PASerrmsg(PASerr,SYSerr)
+  fprintf('Pascal Error Message: %s\n',PASerr);
+  fprintf('System Error Message: %s\n',SYSerr);
+  k=input('Enter K for keyboard, any other key to continue or ^C to quit ...','s');
+  if (~isempty(k)), if (lower(k)=='k'), keyboard; end; end;
+  fprintf('\n');
+return

external/VOCdevkit/VOCcode/PASreadrecord.m

@@ -0,0 +1,11 @@
+function rec = PASreadrecord(path)
+
+if length(path)<4
+    error('unable to determine format: %s',path);
+end
+
+if strcmp(path(end-3:end),'.txt')
+    rec=PASreadrectxt(path);
+else
+    rec=VOCreadrecxml(path);
+end

external/VOCdevkit/VOCcode/PASreadrectxt.m

@@ -0,0 +1,99 @@
+function record=PASreadrectxt(filename)
+  [fd,syserrmsg]=fopen(filename,'rt');
+  if (fd==-1),
+    PASmsg=sprintf('Could not open %s for reading',filename);
+    PASerrmsg(PASmsg,syserrmsg); 
+  end;
+
+  matchstrs=initstrings;
+  record=PASemptyrecord;
+  notEOF=1;
+  while (notEOF),
+    line=fgetl(fd);
+    notEOF=ischar(line);
+    if (notEOF),
+      matchnum=match(line,matchstrs);
+      switch matchnum,
+    case 1, [imgname]=strread(line,matchstrs(matchnum).str);
+	        record.imgname=char(imgname);
+	case 2, [x,y,c]=strread(line,matchstrs(matchnum).str);
+	        record.imgsize=[x y c];
+	case 3, [database]=strread(line,matchstrs(matchnum).str);
+	        record.database=char(database);
+	case 4, [obj,lbl,xmin,ymin,xmax,ymax]=strread(line,matchstrs(matchnum).str);
+	        record.objects(obj).label=char(lbl);
+		record.objects(obj).bbox=[min(xmin,xmax),min(ymin,ymax),max(xmin,xmax),max(ymin,ymax)];
+	case 5, tmp=findstr(line,' : ');
+	        [obj,lbl]=strread(line(1:tmp),matchstrs(matchnum).str);
+	        record.objects(obj).label=char(lbl);
+    		record.objects(obj).polygon=sscanf(line(tmp+3:end),'(%d, %d) ')';
+	case 6, [obj,lbl,mask]=strread(line,matchstrs(matchnum).str);
+	        record.objects(obj).label=char(lbl);
+    		record.objects(obj).mask=char(mask);
+	case 7, [obj,lbl,orglbl]=strread(line,matchstrs(matchnum).str);
+            lbl=char(lbl);
+	        record.objects(obj).label=lbl;
+    		record.objects(obj).orglabel=char(orglbl);
+            if strcmp(lbl(max(end-8,1):end),'Difficult')
+                record.objects(obj).difficult=true;
+                lbl(end-8:end)=[];
+            else
+                record.objects(obj).difficult=false;
+            end
+            if strcmp(lbl(max(end-4,1):end),'Trunc')
+                record.objects(obj).truncated=true;
+                lbl(end-4:end)=[];
+            else
+                record.objects(obj).truncated=false;
+            end
+            t=find(lbl>='A'&lbl<='Z');
+            t=t(t>=4);
+            if ~isempty(t)
+                record.objects(obj).view=lbl(t(1):end);
+                lbl(t(1):end)=[];
+            else
+                record.objects(obj).view='';                
+            end
+            record.objects(obj).class=lbl(4:end);
+
+	otherwise, %fprintf('Skipping: %s\n',line);
+      end;
+    end;
+  end;
+  fclose(fd);
+return
+
+function matchnum=match(line,matchstrs)
+  for i=1:length(matchstrs),
+    matched(i)=strncmp(line,matchstrs(i).str,matchstrs(i).matchlen);
+  end;
+  matchnum=find(matched);
+  if isempty(matchnum), matchnum=0; end;
+  if (length(matchnum)~=1), 
+    PASerrmsg('Multiple matches while parsing','');
+  end;
+return
+
+function s=initstrings
+  s(1).matchlen=14;
+  s(1).str='Image filename : %q';
+
+  s(2).matchlen=10;
+  s(2).str='Image size (X x Y x C) : %d x %d x %d';
+
+  s(3).matchlen=8;
+  s(3).str='Database : %q';
+
+  s(4).matchlen=8;
+  s(4).str='Bounding box for object %d %q (Xmin, Ymin) - (Xmax, Ymax) : (%d, %d) - (%d, %d)';
+
+  s(5).matchlen=7;
+  s(5).str='Polygon for object %d %q (X, Y)';
+
+  s(6).matchlen=5;
+  s(6).str='Pixel mask for object %d %q : %q';
+
+  s(7).matchlen=8;
+  s(7).str='Original label for object %d %q : %q';
+
+return

external/VOCdevkit/VOCcode/VOCap.m

@@ -0,0 +1,10 @@
+function ap = VOCap(rec,prec)
+
+mrec=[0 ; rec ; 1];
+mpre=[0 ; prec ; 0];
+for i=numel(mpre)-1:-1:1
+    mpre(i)=max(mpre(i),mpre(i+1));
+end
+i=find(mrec(2:end)~=mrec(1:end-1))+1;
+ap=sum((mrec(i)-mrec(i-1)).*mpre(i));
+

external/VOCdevkit/VOCcode/VOCevalaction.m

@@ -0,0 +1,59 @@
+function [rec,prec,ap] = VOCevalaction(VOCopts,id,cls,draw)
+
+% load test set
+[gtimg,gtobj,gt]=textread(sprintf(VOCopts.action.clsimgsetpath,cls,VOCopts.testset),'%s %d %d');
+
+% hash image/object ids
+gtid=cell(numel(gtimg),1);
+for i=1:numel(gtimg);
+    gtid{i}=sprintf('%s/%d',gtimg{i},gtobj(i));
+end
+hash=VOChash_init(gtid);
+
+% load results
+[img,obj,confidence]=textread(sprintf(VOCopts.action.respath,id,cls),'%s %d %f');
+
+% map results to ground truth objects
+out=ones(size(gt))*-inf;
+tic;
+for i=1:length(img)
+    % display progress
+    if toc>1
+        fprintf('%s: pr: %d/%d\n',cls,i,length(img));
+        drawnow;
+        tic;
+    end
+
+    % find ground truth object
+    k=sprintf('%s/%d',img{i},obj(i));
+    j=VOChash_lookup(hash,k);
+    if isempty(j)
+        error('unrecognized object "%s"',k);
+    elseif length(j)>1
+        error('multiple image "%s"',k);
+    else
+        out(j)=confidence(i);
+    end
+end
+
+% compute precision/recall
+
+[so,si]=sort(-out);
+tp=gt(si)>0;
+fp=gt(si)<0;
+
+fp=cumsum(fp);
+tp=cumsum(tp);
+rec=tp/sum(gt>0);
+prec=tp./(fp+tp);
+
+ap=VOCap(rec,prec);
+
+if draw
+    % plot precision/recall
+    plot(rec,prec,'-');
+    grid;
+    xlabel 'recall'
+    ylabel 'precision'
+    title(sprintf('class: %s, subset: %s, AP = %.3f',cls,VOCopts.testset,ap));
+end

external/VOCdevkit/VOCcode/VOCevalcls.m

@@ -0,0 +1,54 @@
+function [rec,prec,ap] = VOCevalcls(VOCopts,id,cls,draw)
+
+% load test set
+[gtids,gt]=textread(sprintf(VOCopts.clsimgsetpath,cls,VOCopts.testset),'%s %d');
+
+% hash image ids
+hash=VOChash_init(gtids);
+
+% load results
+[ids,confidence]=textread(sprintf(VOCopts.clsrespath,id,cls),'%s %f');
+
+% map results to ground truth images
+out=ones(size(gt))*-inf;
+tic;
+for i=1:length(ids)
+    % display progress
+    if toc>1
+        fprintf('%s: pr: %d/%d\n',cls,i,length(ids));
+        drawnow;
+        tic;
+    end
+
+    % find ground truth image
+    j=VOChash_lookup(hash,ids{i});
+    if isempty(j)
+        error('unrecognized image "%s"',ids{i});
+    elseif length(j)>1
+        error('multiple image "%s"',ids{i});
+    else
+        out(j)=confidence(i);
+    end
+end
+
+% compute precision/recall
+
+[so,si]=sort(-out);
+tp=gt(si)>0;
+fp=gt(si)<0;
+
+fp=cumsum(fp);
+tp=cumsum(tp);
+rec=tp/sum(gt>0);
+prec=tp./(fp+tp);
+
+ap=VOCap(rec,prec);
+
+if draw
+    % plot precision/recall
+    plot(rec,prec,'-');
+    grid;
+    xlabel 'recall'
+    ylabel 'precision'
+    title(sprintf('class: %s, subset: %s, AP = %.3f',cls,VOCopts.testset,ap));
+end

external/VOCdevkit/VOCcode/VOCevaldet.m

@@ -0,0 +1,123 @@
+function [rec,prec,ap] = VOCevaldet(VOCopts,id,cls,draw)
+
+% load test set
+
+cp=sprintf(VOCopts.annocachepath,VOCopts.testset);
+if exist(cp,'file')
+    fprintf('%s: pr: loading ground truth\n',cls);
+    load(cp,'gtids','recs');
+else
+    [gtids,t]=textread(sprintf(VOCopts.imgsetpath,VOCopts.testset),'%s %d');
+    for i=1:length(gtids)
+        % display progress
+        if toc>1
+            fprintf('%s: pr: load: %d/%d\n',cls,i,length(gtids));
+            drawnow;
+            tic;
+        end
+
+        % read annotation
+        recs(i)=PASreadrecord(sprintf(VOCopts.annopath,gtids{i}));
+    end
+    save(cp,'gtids','recs');
+end
+
+fprintf('%s: pr: evaluating detections\n',cls);
+
+% hash image ids
+hash=VOChash_init(gtids);
+
+% extract ground truth objects
+
+npos=0;
+gt(length(gtids))=struct('BB',[],'diff',[],'det',[]);
+for i=1:length(gtids)
+    % extract objects of class
+    clsinds=strmatch(cls,{recs(i).objects(:).class},'exact');
+    gt(i).BB=cat(1,recs(i).objects(clsinds).bbox)';
+    gt(i).diff=[recs(i).objects(clsinds).difficult];
+    gt(i).det=false(length(clsinds),1);
+    npos=npos+sum(~gt(i).diff);
+end
+
+% load results
+[ids,confidence,b1,b2,b3,b4]=textread(sprintf(VOCopts.detrespath,id,cls),'%s %f %f %f %f %f');
+BB=[b1 b2 b3 b4]';
+
+% sort detections by decreasing confidence
+[sc,si]=sort(-confidence);
+ids=ids(si);
+BB=BB(:,si);
+
+% assign detections to ground truth objects
+nd=length(confidence);
+tp=zeros(nd,1);
+fp=zeros(nd,1);
+tic;
+for d=1:nd
+    % display progress
+    if toc>1
+        fprintf('%s: pr: compute: %d/%d\n',cls,d,nd);
+        drawnow;
+        tic;
+    end
+
+    % find ground truth image
+    i=VOChash_lookup(hash,ids{d});
+    if isempty(i)
+        error('unrecognized image "%s"',ids{d});
+    elseif length(i)>1
+        error('multiple image "%s"',ids{d});
+    end
+
+    % assign detection to ground truth object if any
+    bb=BB(:,d);
+    ovmax=-inf;
+    for j=1:size(gt(i).BB,2)
+        bbgt=gt(i).BB(:,j);
+        bi=[max(bb(1),bbgt(1)) ; max(bb(2),bbgt(2)) ; min(bb(3),bbgt(3)) ; min(bb(4),bbgt(4))];
+        iw=bi(3)-bi(1)+1;
+        ih=bi(4)-bi(2)+1;
+        if iw>0 & ih>0                
+            % compute overlap as area of intersection / area of union
+            ua=(bb(3)-bb(1)+1)*(bb(4)-bb(2)+1)+...
+               (bbgt(3)-bbgt(1)+1)*(bbgt(4)-bbgt(2)+1)-...
+               iw*ih;
+            ov=iw*ih/ua;
+            if ov>ovmax
+                ovmax=ov;
+                jmax=j;
+            end
+        end
+    end
+    % assign detection as true positive/don't care/false positive
+    if ovmax>=VOCopts.minoverlap
+        if ~gt(i).diff(jmax)
+            if ~gt(i).det(jmax)
+                tp(d)=1;            % true positive
+		gt(i).det(jmax)=true;
+            else
+                fp(d)=1;            % false positive (multiple detection)
+            end
+        end
+    else
+        fp(d)=1;                    % false positive
+    end
+end
+
+% compute precision/recall
+fp=cumsum(fp);
+tp=cumsum(tp);
+rec=tp/npos;
+prec=tp./(fp+tp);
+
+ap=VOCap(rec,prec);
+
+if draw
+    % plot precision/recall
+    plot(rec,prec,'-');
+    grid;
+    xlabel 'recall'
+    ylabel 'precision'
+    title(sprintf('class: %s, subset: %s, AP = %.3f',cls,VOCopts.testset,ap));
+end