// ######################################################################
GenericFrame RasterInputSeries::readFrame()
{
if (itsFrameNumber < 0)
LFATAL("frame number is %d, but readFrame() requires a "
"non-negative frame number", itsFrameNumber);
// figure out the file name to use:
const std::string fname(computeInputFileName(itsStem, itsFrameNumber));
// check if we've already read that file; if so, then return an
// empty image
if (fname == itsPrevFilename)
{
LINFO("repeated input file skipped: %s", fname.c_str());
return GenericFrame();
}
// check whether the file exists; if not, then return an empty image:
if (!Raster::fileExists(fname, itsRasterFileFormat.getVal()))
{
LINFO("no such file: %s", fname.c_str());
return GenericFrame();
}
// load the image:
const GenericFrame ima =
Raster::ReadFrame(fname, itsRasterFileFormat.getVal());
itsPrevFilename = fname;
textLog(itsLogFile.getVal(), "ReadFrame", fname);
return ima;
}
// ######################################################################
GenericFrame RasterlistInputSeries::readFrame()
{
if (itsFrameNumber < 0)
LFATAL("expected a non-negative frame number, but got %d",
itsFrameNumber);
if (size_t(itsFrameNumber) >= itsFiles.size())
// out of input; end of stream
return GenericFrame();
if (!Raster::fileExists(itsFiles[itsFrameNumber]))
{
LINFO("at line %d of %s: no such file: %s",
itsFrameNumber, itsListFname.c_str(),
itsFiles[itsFrameNumber].c_str());
return GenericFrame();
}
const GenericFrame result =
Raster::ReadFrame(itsFiles[itsFrameNumber]);
//if (result.frameSpec() != itsFrameSpec)
// LFATAL("at line %d of %s: expected %s to have format '%s', "
// "but got format '%s'",
// itsFrameNumber, itsListFname.c_str(),
// itsFiles[itsFrameNumber].c_str(),
// itsFrameSpec.getDescription().c_str(),
// result.frameSpec().getDescription().c_str());
return result;
}
// ######################################################################
GenericFrame PngParser::getFrame()
{
if (rep->isGray()) return GenericFrame(parseGray());
else if (rep->isColor()) return GenericFrame(parseRGB());
// else...
rep->onError("unsupported image type (neither grayscale nor RGB)");
/* can't happen */ return GenericFrame();
}
GenericFrame JpegParser::getFrame()
{
if (rep->rgb.initialized())
return GenericFrame(rep->rgb);
// else...
ASSERT(rep->gray.initialized());
return GenericFrame(rep->gray);
}
// ######################################################################
GenericFrame V4Lgrabber::readFrame()
{
const GenericFrame frame =
itsStreamingMode.getVal()
? GenericFrame(this->grabRaw())
: GenericFrame(this->grabSingleRaw());
if (itsListener.get() != 0)
itsListener->onRawFrame(frame);
return frame;
}
Point2D evolveBrain(Image<PixRGB<byte> > &img, DescriptorVec& descVec, int ii)
{
nub::ref<StdBrain> brain = dynCastWeak<StdBrain>(mgr->subComponent("Brain"));
nub::ref<SimEventQueueConfigurator> seqc =
dynCastWeak<SimEventQueueConfigurator>(mgr->subComponent("SimEventQueueConfigurator"));
nub::soft_ref<SimEventQueue> seq = seqc->getQ();
LINFO("Evolve Brain");
if (mgr->started()){ //give the image to the brain
if (img.initialized())
{
//place the image in the inputFrame queue
rutz::shared_ptr<SimEventInputFrame>
e(new SimEventInputFrame(brain.get(), GenericFrame(img), 0));
seq->post(e);
// brain->input(img, seq);
descVec.setInputImg(img);
}
SimTime end_time = seq->now() + SimTime::MSECS(3.0);
while (seq->now() < end_time)
{
brain->evolve(*seq); //evolve the brain
// Any new WTA winner?
if (SeC<SimEventWTAwinner> e = seq->check<SimEventWTAwinner>(brain.get()))
{
const Point2D winner = e->winner().p;
//get the saliency map output
if (debug)
{
if (SeC<SimEventSaliencyMapOutput> smo =
seq->check<SimEventSaliencyMapOutput>(brain.get(), SEQ_ANY))
{
Image<float> img = smo->sm();
//SHOWIMG(rescale(img, img.getWidth()*16, img.getHeight()*16));
}
}
seq->evolve();
return winner;
}
seq->evolve();
LINFO("Evolve 1\n");
}
}
return Point2D();
}
void Logger::saveSingleEventFrame(MbariImage< PixRGB<byte> >& img,
int frameNum,
MbariVisualEvent::VisualEvent *event) {
ASSERT(event->frameInRange(frameNum));
// create the file stem
string evnum;
if (itsSaveEventFeatures.getVal().length() > 0)
evnum = sformat("%s_evt%04d_", itsSaveEventFeatures.getVal().c_str(), event->getEventNum() );
else
evnum = sformat("evt%04d_", event->getEventNum());
Dims maxDims = event->getMaxObjectDims();
Dims d((float)maxDims.w()*itsScaleW, (float)maxDims.h()*itsScaleH);
// compute the correct bounding box and cut it out
Rectangle bbox1 = event->getToken(frameNum).bitObject.getBoundingBox();
Rectangle bbox = Rectangle::tlbrI(bbox1.top()*itsScaleH, bbox1.left()*itsScaleW,
bbox1.bottomI()*itsScaleH, bbox1.rightI()*itsScaleW);
//Point2D cen = event.getToken(frameNum).bitObject.getCentroid();
// first the horizontal direction
int wpad = (d.w() - bbox.width()) / 2;
int ll = bbox.left() - wpad;
//int ll = cen.i - d.w() / 2;
int rr = ll + d.w();
if (ll < 0) {
rr -= ll;
ll = 0;
}
if (rr >= img.getWidth()) {
rr = img.getWidth() - 1;
ll = rr - d.w();
}
// now the same thing with the vertical direction
int hpad = (d.h() - bbox.height()) / 2;
int tt = bbox.top() - hpad;
//int tt = cen.j - d.h() / 2;
int bb = tt + d.h();
if (tt < 0) {
bb -= tt;
tt = 0;
}
if (bb >= img.getHeight()) {
bb = img.getHeight() - 1;
tt = bb - d.h();
}
Rectangle bboxFinal = Rectangle::tlbrI(tt, ll, bb, rr);
bboxFinal = bboxFinal.getOverlap(Rectangle(Point2D<int>(0, 0), img.getDims() - 1));
// scale if needed and cut out the rectangle and save it
Image< PixRGB<byte> > cut = crop(img, bboxFinal);
itsOfs->writeFrame(GenericFrame(cut), evnum, FrameInfo(evnum, SRC_POS));
}
// ######################################################################
GenericFrame QuickTimeGrabber::readFrame()
{
if (!this->started())
LFATAL("start() must be called before readFrame()");
#ifndef HAVE_QUICKTIME_QUICKTIME_H
LFATAL("you must have QuickTime installed to use QuickTimeGrabber");
/* can't happen */ return GenericFrame();
#else
ASSERT(rep != 0);
return rep->readFrame();
#endif
}
// ######################################################################
GenericFrame QuickTimeGrabber::Impl::readFrame()
{
if (!itsStreamStarted)
this->startStream();
while (1)
{
itsGotFrame = false;
itsErrorMsg = "";
if (noErr != SGIdle(itsSeqGrab.it))
LFATAL("SGIdle() failed");
if (itsErrorMsg.length() > 0)
{
// some error specific to SGIdle occurred - any errors
// returned from the data proc will also show up here and we
// don't want to write over them
// in QT 4 you would always encounter a cDepthErr error
// after a user drags the window, this failure condition has
// been greatly relaxed in QT 5 it may still occur but
// should only apply to vDigs that really control the screen
// you don't always know where these errors originate from,
// some may come from the VDig...
LFATAL("QuickTimeGrabber error during SGIdle (%s)",
itsErrorMsg.c_str());
// ...to fix this we simply call SGStop and SGStartRecord
// again calling stop allows the SG to release and
// re-prepare for grabbing hopefully fixing any problems,
// this is obviously a very relaxed approach
SGStop(itsSeqGrab.it);
SGStartRecord(itsSeqGrab.it);
}
if (itsGotFrame)
return GenericFrame(itsCurrentImage);
usleep(20000);
}
}
// Main function
int main(const int argc, const char **argv)
{
MYLOGVERB = LOG_INFO; // suppress debug messages
// Instantiate a ModelManager:
ModelManager manager("Gist Features Extraction");
// we cannot use saveResults() on our various ModelComponent objects
// here, so let's not export the related command-line options.
manager.allowOptions(OPTEXP_ALL & (~OPTEXP_SAVE));
// Instantiate our various ModelComponents:
nub::soft_ref<SimEventQueueConfigurator>
seqc(new SimEventQueueConfigurator(manager));
manager.addSubComponent(seqc);
nub::soft_ref<InputMPEGStream>
ims(new InputMPEGStream(manager, "Input MPEG Stream", "InputMPEGStream"));
manager.addSubComponent(ims);
nub::soft_ref<StdBrain> brain(new StdBrain(manager));
manager.addSubComponent(brain);
nub::ref<SpatialMetrics> metrics(new SpatialMetrics(manager));
manager.addSubComponent(metrics);
manager.exportOptions(MC_RECURSE);
metrics->setFOAradius(30); // FIXME
metrics->setFoveaRadius(30); // FIXME
// setting up the GIST ESTIMATOR
manager.setOptionValString(&OPT_GistEstimatorType,"Std");
//manager.setOptionValString(&OPT_GistEstimatorType,"FFT");
// Request a bunch of option aliases (shortcuts to lists of options):
REQUEST_OPTIONALIAS_NEURO(manager);
// Parse command-line:
if (manager.parseCommandLine(argc, argv, "<*.mpg or *_gistList.txt>",
1, 1) == false)
return(1);
nub::soft_ref<SimEventQueue> seq = seqc->getQ();
// if the file passed ends with _gistList.txt
// we have a different protocol
bool isGistListInput = false;
int ifLen = manager.getExtraArg(0).length();
if(ifLen > 13 &&
manager.getExtraArg(0).find("_gistList.txt",ifLen - 13) !=
std::string::npos)
isGistListInput = true;
// NOTE: this could now be controlled by a command-line option
// --preload-mpeg=true
manager.setOptionValString(&OPT_InputMPEGStreamPreload, "true");
// do post-command-line configs:
std::vector<std::string> tag;
std::vector<int> start;
std::vector<int> num;
unsigned int cLine = 0; int cIndex = 0;
if(isGistListInput)
{
LINFO("we have a gistList input");
getGistFileList(manager.getExtraArg(0).c_str(), tag, start, num);
cIndex = start[0];
}
else
{
LINFO("we have an mpeg input");
ims->setFileName(manager.getExtraArg(0));
manager.setOptionValString(&OPT_InputFrameDims,
convertToString(ims->peekDims()));
}
// frame delay in seconds
//double fdelay = 33.3667/1000.0; // real time
double fdelay = 3.3667/1000.0;
// let's get all our ModelComponent instances started:
manager.start();
// get the GistEstimator
nub::soft_ref<GistEstimatorStd> ge;////// =
/////// dynCastWeak<GistEstimatorStd>(brain->getGE());
LFATAL("fixme");
if (ge.isInvalid()) LFATAL("I am useless without a GistEstimator");
// MAIN LOOP
SimTime prevstime = SimTime::ZERO();
int fNum = 0;
Image< PixRGB<byte> > inputImg; Image< PixRGB<byte> > dispImg;
Image<double> cgist;
std::string folder = "";
std::string::size_type sPos = manager.getExtraArg(0).rfind("/",ifLen);
if(sPos != std::string::npos)
folder = manager.getExtraArg(0).substr(0,sPos+1);
LINFO("let's start");
while(1)
{
// has the time come for a new frame?
if (fNum == 0 ||
(seq->now() - 0.5 * (prevstime - seq->now())).secs() - fNum * fdelay > fdelay)
{
// load new frame
std::string fName;
if(isGistListInput)
{
if (cLine >= tag.size()) break; // end of input list
// open the current file
char tNumStr[100]; sprintf(tNumStr,"%06d",cIndex);
fName = folder + tag[cLine] + std::string(tNumStr) + ".ppm";
inputImg = Raster::ReadRGB(fName);
cIndex++;
if(cIndex >= start[cLine] + num[cLine])
{
cLine++;
if (cLine < tag.size()) cIndex = start[cLine];
}
// reformat the file name to a gist name
int fNameLen = fName.length();
unsigned int uPos = fName.rfind("_",fNameLen);
fName = fName.substr(0,uPos)+ ".ppm";
}
else
{
fName = manager.getExtraArg(0);
inputImg = ims->readRGB(); //Raster::ReadRGB(manager.getExtraArg(1));
if (inputImg.initialized() == false) break; // end of input stream
// format new frame
inputImg = crop(inputImg,
Rectangle(Point2D<int>(0,25),
Dims(inputImg.getHeight(),
inputImg.getWidth()-25+1)));
cIndex = fNum+1;
}
dispImg = inputImg;
LINFO("\nnew frame :%d",fNum);
// pass input to brain:
rutz::shared_ptr<SimEventInputFrame>
e(new SimEventInputFrame(brain.get(), GenericFrame(inputImg), 0));
seq->post(e); // post the image to the brain
// get the gist feature vector
cgist = ge->getGist();
//for(uint k = 0; k < cgist.getSize(); k++) LINFO("%d: %f",k, cgist.getVal(0,k));
// // setup display at the start of stream
// if (fNum == 0)
// {
// int s = SQ_SIZE;
// inputWin = new XWinManaged(Dims(w, h), 0, 0, manager.getExtraArg(0).c_str());
// wList.add(inputWin);
// gistWin = new XWinManaged(Dims(NUM_GIST_COL * s, NUM_GIST_FEAT * s), 0,0, "Gist");
// wList.add(gistWin);
// }
// // display the input image and the gist histogram
// drawGrid(dispImg, w/4,h/4,1,1,PixRGB<byte>(255,255,255));
// inputWin->drawImage(dispImg,0,0);
// gistWin->drawImage(ge->getGistHistogram(SQ_SIZE),0,0);
// SAVE GIST FEATURES TO A FILE
saveData(cgist, fName, cIndex-1);
//LINFO("\nFrame number just saved:%d",fNum);Raster::waitForKey();
// increase frame count
fNum++;
}
// evolve brain:
prevstime = seq->now(); // time before current step
const SimStatus status = seq->evolve();
if (SIM_BREAK == status) // Brain decided it's time to quit
break;
}
// stop all our ModelComponents
manager.stop();
// all done!
return 0;
}
void Logger::save(const Image< PixRGB<byte> >& img,
const uint frameNum,
const string& resultName,
const int resNum) {
itsOfs->writeFrame(GenericFrame(img), getFileStem(resultName, resNum), FrameInfo(resultName, SRC_POS));
}
void Logger::save(const Image<float>& img,
const uint frameNum,
const string& resultName,
const int resNum) {
itsOfs->writeFrame(GenericFrame(img, FLOAT_NORM_0_255), getFileStem(resultName, resNum), FrameInfo(resultName, SRC_POS));
}
// ######################################################################
GenericFrame MgzJDecoder::readFrame()
{
// Grab the journal entry for this frame and allocate an appropriate GenericFrame
MgzJEncoder::journalEntry entry = itsJournal.at(itsFrameNum);
const Dims dims(entry.width, entry.height);
const GenericFrame::NativeType pix_type = GenericFrame::NativeType(entry.pix_type);
const int num_pix = dims.sz();
GenericFrame frame;
//Read in the compressed image to a buffer
uint64 comp_image_buf_size = entry.end_byte - entry.start_byte;
byte * comp_image_buf = new byte[comp_image_buf_size];
itsFile.seekg(entry.start_byte, std::ios::beg);
itsFile.read((char*)comp_image_buf, comp_image_buf_size);
//Prepare zlib to do the decompression
z_stream strm;
strm.zalloc = Z_NULL;
strm.zfree = Z_NULL;
strm.opaque = Z_NULL;
strm.avail_in = 0;
strm.next_in = Z_NULL;
int ret = inflateInit(&strm);
if(ret != Z_OK)
LFATAL("Could not initialize zlib!");
strm.avail_in = comp_image_buf_size;
strm.next_in = comp_image_buf;
switch(pix_type)
{
case GenericFrame::GRAY_U8:
{
Image<byte> img(dims, NO_INIT);
strm.avail_out = num_pix * sizeof(byte);
strm.next_out = (unsigned char*)img.getArrayPtr();
ret = inflate(&strm, Z_FINISH);
if(ret != Z_STREAM_END)
{ LFATAL("Could Not Inflate Frame! %d, %s", ret, strm.msg); }
frame = GenericFrame(img);
break;
}
case GenericFrame::GRAY_U16:
{
Image<uint16> img(dims, NO_INIT);
strm.avail_out = num_pix * sizeof(uint16);
strm.next_out = (unsigned char*)img.getArrayPtr();
ret = inflate(&strm, Z_FINISH);
if(ret != Z_STREAM_END)
{ LFATAL("Could Not Inflate Frame! %d, %s", ret, strm.msg); }
frame = GenericFrame(img);
break;
}
case GenericFrame::GRAY_F32:
{
Image<float> img(dims, NO_INIT);
strm.avail_out = num_pix * sizeof(float);
strm.next_out = (unsigned char*)img.getArrayPtr();
ret = inflate(&strm, Z_FINISH);
if(ret != Z_STREAM_END)
{ LFATAL("Could Not Inflate Frame! %d, %s", ret, strm.msg); }
frame = GenericFrame(img, entry.flags);
break;
}
case GenericFrame::RGB_U8:
{
Image<PixRGB<byte> > img(dims, NO_INIT);
strm.avail_out = num_pix * sizeof(PixRGB<byte>);
strm.next_out = (unsigned char*)img.getArrayPtr();
ret = inflate(&strm, Z_FINISH);
if(ret != Z_STREAM_END)
{ LFATAL("Could Not Inflate Frame! %d, %s", ret, strm.msg); }
frame = GenericFrame(img);
break;
}
case GenericFrame::RGB_U16:
{
Image<PixRGB<uint16> > img(dims, NO_INIT);
strm.avail_out = num_pix * sizeof(PixRGB<uint16>);
strm.next_out = (unsigned char*)img.getArrayPtr();
ret = inflate(&strm, Z_FINISH);
if(ret != Z_STREAM_END)
{ LFATAL("Could Not Inflate Frame! %d, %s", ret, strm.msg); }
frame = GenericFrame(img);
break;
}
case GenericFrame::RGB_F32:
{
Image<PixRGB<float> > img(dims, NO_INIT);
strm.avail_out = num_pix * sizeof(PixRGB<float>);
strm.next_out = (unsigned char*)img.getArrayPtr();
ret = inflate(&strm, Z_FINISH);
if(ret != Z_STREAM_END)
{ LFATAL("Could Not Inflate Frame! %d, %s", ret, strm.msg); }
frame = GenericFrame(img, entry.flags);
break;
}
case GenericFrame::VIDEO:
{
const size_t vidSize = getFrameSize(VideoFormat(entry.flags), dims);
ArrayHandle<byte> vidBuffer(new ArrayData<byte>(Dims(vidSize,1), NO_INIT));
strm.avail_out = vidSize;
strm.next_out = (unsigned char*)vidBuffer.uniq().dataw();
ret = inflate(&strm, Z_FINISH);
if(ret != Z_STREAM_END)
{ LFATAL("Could Not Inflate Frame! %d, %s", ret, strm.msg); }
frame = GenericFrame(VideoFrame(vidBuffer, dims, VideoFormat(entry.flags), bool(entry.byte_swap)));
break;
}
default:
LFATAL("Could Not Open Frame Of Type: %d!", pix_type);
}
inflateEnd(&strm);
delete [] comp_image_buf;
return frame;
}
// ######################################################################
void Logger::run(nub::soft_ref<MbariResultViewer> rv, MbariImage<PixRGB <byte> >& img,
MbariVisualEvent::VisualEventSet& eventSet, const Dims scaledDims)
{
// adjust scaling if needed
Dims d = img.getDims();
itsScaleW = (float)d.w()/(float)scaledDims.w();
itsScaleH = (float)d.h()/(float)scaledDims.h();
// initialize property vector and FOE estimator
MbariVisualEvent::PropertyVectorSet pvs;
// this is a list of all the events that have a token in this frame
std::list<MbariVisualEvent::VisualEvent *> eventFrameList;
// this is a complete list of all those events that are ready to be written
std::list<MbariVisualEvent::VisualEvent *> eventListToSave;
// get event frame list for this frame and those events that are ready to be saved
// this is a list of all the events that have a token in this frame
eventFrameList = eventSet.getEventsForFrame(img.getFrameNum());
// this is a complete list of all those events that are ready to be written
eventListToSave = eventSet.getEventsReadyToSave(img.getFrameNum());
// write out eventSet?
if (itsSaveEventsName.getVal().length() > 0 ) saveVisualEvent(eventSet, eventFrameList);
// write out summary ?
if (itsSaveSummaryEventsName.getVal().length() > 0) saveVisualEventSummary(Version::versionString(), eventListToSave);
// flag events that have been saved for delete
std::list<MbariVisualEvent::VisualEvent *>::iterator i;
for (i = eventListToSave.begin(); i != eventListToSave.end(); ++i)
(*i)->flagWriteComplete();
// write out positions?
if (itsSavePositionsName.getVal().length() > 0) savePositions(eventFrameList);
MbariVisualEvent::PropertyVectorSet pvsToSave = eventSet.getPropertyVectorSetToSave();
// write out property vector set?
if (itsSavePropertiesName.getVal().length() > 0) saveProperties(pvsToSave);
// TODO: this is currently not used...look back in history to where this got cut-out
// need to obtain the property vector set?
if (itsLoadPropertiesName.getVal().length() > 0) pvs = eventSet.getPropertyVectorSet();
// get a list of events for this frame
eventFrameList = eventSet.getEventsForFrame(img.getFrameNum());
// write out eventSet to XML?
if (itsSaveXMLEventSetName.getVal().length() > 0) {
saveVisualEventSetToXML(eventFrameList,
img.getFrameNum(),
img.getMetaData().getTC(),
itsFrameRange);
}
const int circleRadiusRatio = 40;
const int circleRadius = img.getDims().w() / circleRadiusRatio;
Image< PixRGB<byte> > output = rv->createOutput(img,
eventSet,
circleRadius,
itsScaleW, itsScaleH);
// write ?
if (itsSaveOutput.getVal())
itsOfs->writeFrame(GenericFrame(output), "results", FrameInfo("results", SRC_POS));
// display output ?
rv->display(output, img.getFrameNum(), "Results");
// need to save any event clips?
if (itsSaveEventNumsAll) {
//save all events
std::list<MbariVisualEvent::VisualEvent *>::iterator i;
for (i = eventFrameList.begin(); i != eventFrameList.end(); ++i)
saveSingleEventFrame(img, img.getFrameNum(), *i);
} else {
// need to save any particular event clips?
uint csavenum = numSaveEventClips();
for (uint idx = 0; idx < csavenum; ++idx) {
uint evnum = getSaveEventClipNum(idx);
if (!eventSet.doesEventExist(evnum)) continue;
MbariVisualEvent::VisualEvent *event = eventSet.getEventByNumber(evnum);
if (event->frameInRange(img.getFrameNum()))
saveSingleEventFrame(img, img.getFrameNum(), event);
}
}
//flag events that have been saved for delete otherwise takes too much memory
for (i = eventListToSave.begin(); i != eventListToSave.end(); ++i)
(*i)->flagForDelete();
while (!eventFrameList.empty()) eventFrameList.pop_front();
while (!eventListToSave.empty()) eventListToSave.pop_front();
}
// ######################################################################
GenericFrame XCgrabberFlex::readFrame()
{
return GenericFrame(this->grabRaw());
}
int main(const int argc, const char **argv)
{
MYLOGVERB = LOG_INFO;
mgr = new ModelManager("Test LabelMeSaliency");
nub::soft_ref<SimEventQueueConfigurator>
seqc(new SimEventQueueConfigurator(*mgr));
mgr->addSubComponent(seqc);
//our brain
nub::ref<StdBrain> brain(new StdBrain(*mgr));
mgr->addSubComponent(brain);
mgr->exportOptions(MC_RECURSE);
mgr->setOptionValString(&OPT_RawVisualCortexChans, "IOC");
//mgr.setOptionValString(&OPT_RawVisualCortexChans, "I");
//mgr->setOptionValString(&OPT_RawVisualCortexChans, "GNO");
//mgr.setOptionValString(&OPT_RawVisualCortexChans, "N");
//manager.setOptionValString(&OPT_UseOlderVersion, "false");
// set the FOA and fovea radii
mgr->setOptionValString(&OPT_SaliencyMapType, "Fast");
mgr->setOptionValString(&OPT_SMfastInputCoeff, "1");
mgr->setOptionValString(&OPT_WinnerTakeAllType, "Fast");
mgr->setOptionValString(&OPT_SimulationTimeStep, "0.2");
mgr->setModelParamVal("FOAradius", 128, MC_RECURSE);
mgr->setModelParamVal("FoveaRadius", 128, MC_RECURSE);
mgr->setOptionValString(&OPT_IORtype, "Disc");
if (mgr->parseCommandLine(
(const int)argc, (const char**)argv, "<path to images>", 1, 1) == false);
nub::soft_ref<SimEventQueue> seq = seqc->getQ();
mgr->start();
//nub::ref<StdBrain> brain = dynCastWeak<StdBrain>(mgr->subComponent("Brain"));
//"/lab/ilab15/tmp/objectsDB/mit/labelMe/05june05_static_indoor",
ComplexChannel *cc =
&*dynCastWeak<ComplexChannel>(brain->getVC());
TestImages testImages(mgr->getExtraArg(0).c_str(), TestImages::MIT_LABELME);
Image<float> allObjImg = Raster::ReadFloat("allObjImg.pfm", RASFMT_PFM);
inplaceNormalize(allObjImg, 0.0F, 1.0F);
printf("## \"Filename\", \"Size\",\"fovea Radius\",\"Number of objects\",\"Salient Location\", \"Hits\",");
printf("\"Obj Saliency Max\",\"Obj Saliency Min\",\"Obj Saliency Sum\",\"Obj Saliency Area\"");
printf("\"Dist Saliency Max\",\"Dist Saliency Min\",\"Dist Saliency Sum\",\"Dist Saliency Area\"");
printf("\n");
for(uint scene=0; scene<testImages.getNumScenes(); scene++)
{
//get the image
LINFO("Get scene %i", scene);
Image<PixRGB<byte> > img = testImages.getScene(scene);
std::string sceneFile = testImages.getSceneFilename(scene);
LINFO("Size %ix%i", img.getWidth(), img.getHeight());
//set the fovea and foa radius to be 1/4 the size of the image width
int fRadius = 128; //(img.getWidth()/16);
//TODO: fixme
//brain->getSM()->setFoveaRadius(fRadius);
//brain->getSM()->setFOAradius(fRadius);
initRandomNumbers();
if (testImages.getNumObj() > 0) //if we have any labled objects
{
//bias the vc
Image<float> mask = rescale(allObjImg, img.getDims());
biasVC(*cc, mask);
//evolve the brain
Image<float> SMap;
rutz::shared_ptr<SimEventInputFrame> //place the image in the queue
e(new SimEventInputFrame(brain.get(), GenericFrame(img), 0));
seq->post(e);
//set the task relevance map
Point2D<int> winner;
float interestLevel=100.0F;
int nHits=0;
int nTimes=95;
printf("[ ");
Point2D<int> lastLoc(-1,-1);
while(interestLevel > 0.01F && nTimes < 100) //do until no more activation
{
nTimes++;
LINFO("InterestLevel %f", interestLevel);
Point2D<int> currentWinner = evolveBrain(img, SMap, &interestLevel, seq);
if (debug)
{
if (lastLoc.isValid())
{
drawLine(img, lastLoc, currentWinner,
PixRGB<byte>(0, 255, 0), 4);
} else {
drawCircle(img, currentWinner, fRadius-10, PixRGB<byte>(255,0,0), 3);
}
lastLoc = currentWinner;
drawCircle(img, currentWinner, fRadius, PixRGB<byte>(0,255,0), 3);
}
//check if the winner is inside an object (all objects)
int hit = -1;
for (uint obj=0; obj<testImages.getNumObj(); obj++)
{
int lineWidth = int(img.getWidth()*0.003);
std::vector<Point2D<int> > objPoly = testImages.getObjPolygon(obj);
if (debug)
{
Point2D<int> p1 = objPoly[0];
for(uint i=1; i<objPoly.size(); i++)
{
drawLine(img, p1, objPoly[i], PixRGB<byte>(255, 0, 0), lineWidth);
p1 = objPoly[i];
}
drawLine(img, p1, objPoly[0], PixRGB<byte>(255, 0, 0), lineWidth); //close the polygon
}
// if (testImages.pnpoly(objPoly, winner))
// hit = 1;
if (testImages.pnpoly(objPoly, currentWinner))
{
hit = obj;
}
}
printf("%i ", hit);
if (hit != -1)
{
winner = currentWinner;
nHits++;
}
}
if (debug)
{
Raster::WriteRGB(img, "IORSaliency.ppm");
Image<PixRGB<byte> > tmp = rescale(img, 512, 512);
SHOWIMG(tmp);
}
printf("] ");
printf("\"%s\",\"%ix%i\",\"%i\",\"%i\",\"(%i,%i)\",\"%i\"",
sceneFile.c_str(), img.getWidth(), img.getHeight(), fRadius,
testImages.getNumObj(), winner.i, winner.j, nHits);
printf("\n");
if (debug)
{
Image<PixRGB<byte> > tmp = rescale(img, 512, 512);
SHOWIMG(tmp);
}
//Compute the saliency ratio
/*Image<byte> imgMask;
//get the obj mask
for (uint obj=0; obj<testImages.getNumObj(); obj++)
{
LINFO("Adding obj %i", obj);
Image<byte> objMask = testImages.getObjMask(obj);
if (imgMask.initialized())
imgMask += objMask;
else
imgMask = objMask;
}
if (debug) SHOWIMG(rescale((Image<float>)imgMask, 512, 512));
LINFO("Mask %ix%i", imgMask.getWidth(), imgMask.getHeight());
Image<float> distMask = chamfer34(imgMask, (byte)255);
Image<float> objMask = binaryReverse(distMask, 255.0F);
//normalize mask from 0 to 1
inplaceNormalize(objMask, 0.0F, 1.0F);
inplaceNormalize(distMask, 0.0F, 1.0F);
if (debug) SHOWIMG(rescale((Image<float>)objMask, 512, 512));
if (debug) SHOWIMG(rescale((Image<float>)distMask, 512, 512));
//resize the saliency map to the orig img size
SMap = rescale(SMap, imgMask.getDims());
float objMin, objMax, objSum, objArea;
getMaskedMinMaxSumArea(SMap, objMask, objMin, objMax, objSum, objArea);
float distMin, distMax, distSum, distArea;
getMaskedMinMaxSumArea(SMap, distMask, distMin, distMax, distSum, distArea);
printf("\"%f\",\"%f\",\"%f\",\"%f\",\"%f\",\"%f\",\"%f\",\"%f\"",
objMax, objMin, objSum, objArea,
distMax, distMin, distSum, distArea);
printf("\n");
*/
} else {
printf("##%s has no objects \n", sceneFile.c_str());
}
}
}
// ######################################################################
GenericFrame XMLInput::readFrame()
{
if (itsTestImages.get() == 0)
LFATAL("No scene data. Need xml file");
if (!itsGetObjects.getVal())
itsCurrentSceneNum = itsFrameNum;
//If we dont have the frame number, then return an empty image
if (itsCurrentSceneNum >= itsTestImages->getNumScenes())
{
LINFO("No more scenes");
return GenericFrame();
}
//Get the scene
TestImages::SceneData sceneData = itsTestImages->getSceneData(itsCurrentSceneNum);
rutz::shared_ptr<TestImages::SceneData> scene(new TestImages::SceneData);
scene->description = sceneData.description;
scene->filename = sceneData.filename;
scene->type = sceneData.type;
scene->useType = sceneData.useType;
// LINFO("Scene %s", sceneData.filename.c_str());
Image<PixRGB<byte> > sceneImg;
if (itsGetObjects.getVal())
{
if (itsObjectNum < sceneData.objects.size())
{
TestImages::ObjData objData = sceneData.objects[itsObjectNum];
std::vector<Point2D<int> > objPoly = objData.polygon;
Image<PixRGB<byte> > img = itsTestImages->getScene(itsCurrentSceneNum);
//Get the bounding box
Rectangle rect = findBoundingRect(objPoly, img.getDims());
sceneImg = crop(img, rect);
scene->objects.push_back(objData);
itsObjectNum++;
if (itsObjectNum >= sceneData.objects.size())
{
itsCurrentSceneNum++;
itsObjectNum = 0;
}
}
} else {
scene->objects = sceneData.objects;
sceneImg = itsTestImages->getScene(itsCurrentSceneNum);
if (itsDrawPolygons.getVal())
{
for(uint i=0; i<sceneData.objects.size(); i++)
{
TestImages::ObjData objData = sceneData.objects[i];
if (itsFilterObjectName.getVal() == objData.name || itsFilterObjectName.getVal().empty())
{
std::vector<Point2D<int> > objPoly = objData.polygon;
Point2D<int> p1 = objPoly[0];
for(uint i=1; i<objPoly.size(); i++)
{
drawLine(sceneImg, p1, objPoly[i], PixRGB<byte>(0, 255, 0), 0);
p1 = objPoly[i];
}
drawLine(sceneImg, p1, objPoly[0], PixRGB<byte>(0, 255, 0)); //close the polygon
writeText(sceneImg, objPoly[0]+10, objData.name.c_str(), PixRGB<byte>(255,255,255), PixRGB<byte>(0,0,0));
}
}
}
}
if (!sceneData.dims.isEmpty())
sceneImg = rescale(sceneImg, sceneData.dims);
scene->dims = sceneImg.getDims();
GenericFrame frame(sceneImg);
frame.addMetaData(std::string("SceneData"), scene);
return frame;
}