cascadeclassifier.cpp 20.7 KB
Newer Older
wester committed
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565
#include "opencv2/core.hpp"

#include "cascadeclassifier.h"
#include <queue>

using namespace std;
using namespace cv;

static const char* stageTypes[] = { CC_BOOST };
static const char* featureTypes[] = { CC_HAAR, CC_LBP, CC_HOG };

CvCascadeParams::CvCascadeParams() : stageType( defaultStageType ),
    featureType( defaultFeatureType ), winSize( cvSize(24, 24) )
{
    name = CC_CASCADE_PARAMS;
}
CvCascadeParams::CvCascadeParams( int _stageType, int _featureType ) : stageType( _stageType ),
    featureType( _featureType ), winSize( cvSize(24, 24) )
{
    name = CC_CASCADE_PARAMS;
}

//---------------------------- CascadeParams --------------------------------------

void CvCascadeParams::write( FileStorage &fs ) const
{
    string stageTypeStr = stageType == BOOST ? CC_BOOST : string();
    CV_Assert( !stageTypeStr.empty() );
    fs << CC_STAGE_TYPE << stageTypeStr;
    string featureTypeStr = featureType == CvFeatureParams::HAAR ? CC_HAAR :
                            featureType == CvFeatureParams::LBP ? CC_LBP :
                            featureType == CvFeatureParams::HOG ? CC_HOG :
                            0;
    CV_Assert( !stageTypeStr.empty() );
    fs << CC_FEATURE_TYPE << featureTypeStr;
    fs << CC_HEIGHT << winSize.height;
    fs << CC_WIDTH << winSize.width;
}

bool CvCascadeParams::read( const FileNode &node )
{
    if ( node.empty() )
        return false;
    string stageTypeStr, featureTypeStr;
    FileNode rnode = node[CC_STAGE_TYPE];
    if ( !rnode.isString() )
        return false;
    rnode >> stageTypeStr;
    stageType = !stageTypeStr.compare( CC_BOOST ) ? BOOST : -1;
    if (stageType == -1)
        return false;
    rnode = node[CC_FEATURE_TYPE];
    if ( !rnode.isString() )
        return false;
    rnode >> featureTypeStr;
    featureType = !featureTypeStr.compare( CC_HAAR ) ? CvFeatureParams::HAAR :
                  !featureTypeStr.compare( CC_LBP ) ? CvFeatureParams::LBP :
                  !featureTypeStr.compare( CC_HOG ) ? CvFeatureParams::HOG :
                  -1;
    if (featureType == -1)
        return false;
    node[CC_HEIGHT] >> winSize.height;
    node[CC_WIDTH] >> winSize.width;
    return winSize.height > 0 && winSize.width > 0;
}

void CvCascadeParams::printDefaults() const
{
    CvParams::printDefaults();
    cout << "  [-stageType <";
    for( int i = 0; i < (int)(sizeof(stageTypes)/sizeof(stageTypes[0])); i++ )
    {
        cout << (i ? " | " : "") << stageTypes[i];
        if ( i == defaultStageType )
            cout << "(default)";
    }
    cout << ">]" << endl;

    cout << "  [-featureType <{";
    for( int i = 0; i < (int)(sizeof(featureTypes)/sizeof(featureTypes[0])); i++ )
    {
        cout << (i ? ", " : "") << featureTypes[i];
        if ( i == defaultStageType )
            cout << "(default)";
    }
    cout << "}>]" << endl;
    cout << "  [-w <sampleWidth = " << winSize.width << ">]" << endl;
    cout << "  [-h <sampleHeight = " << winSize.height << ">]" << endl;
}

void CvCascadeParams::printAttrs() const
{
    cout << "stageType: " << stageTypes[stageType] << endl;
    cout << "featureType: " << featureTypes[featureType] << endl;
    cout << "sampleWidth: " << winSize.width << endl;
    cout << "sampleHeight: " << winSize.height << endl;
}

bool CvCascadeParams::scanAttr( const string prmName, const string val )
{
    bool res = true;
    if( !prmName.compare( "-stageType" ) )
    {
        for( int i = 0; i < (int)(sizeof(stageTypes)/sizeof(stageTypes[0])); i++ )
            if( !val.compare( stageTypes[i] ) )
                stageType = i;
    }
    else if( !prmName.compare( "-featureType" ) )
    {
        for( int i = 0; i < (int)(sizeof(featureTypes)/sizeof(featureTypes[0])); i++ )
            if( !val.compare( featureTypes[i] ) )
                featureType = i;
    }
    else if( !prmName.compare( "-w" ) )
    {
        winSize.width = atoi( val.c_str() );
    }
    else if( !prmName.compare( "-h" ) )
    {
        winSize.height = atoi( val.c_str() );
    }
    else
        res = false;
    return res;
}

//---------------------------- CascadeClassifier --------------------------------------

bool CvCascadeClassifier::train( const string _cascadeDirName,
                                const string _posFilename,
                                const string _negFilename,
                                int _numPos, int _numNeg,
                                int _precalcValBufSize, int _precalcIdxBufSize,
                                int _numStages,
                                const CvCascadeParams& _cascadeParams,
                                const CvFeatureParams& _featureParams,
                                const CvCascadeBoostParams& _stageParams,
                                bool baseFormatSave,
                                double acceptanceRatioBreakValue )
{
    // Start recording clock ticks for training time output
    const clock_t begin_time = clock();

    if( _cascadeDirName.empty() || _posFilename.empty() || _negFilename.empty() )
        CV_Error( CV_StsBadArg, "_cascadeDirName or _bgfileName or _vecFileName is NULL" );

    string dirName;
    if (_cascadeDirName.find_last_of("/\\") == (_cascadeDirName.length() - 1) )
        dirName = _cascadeDirName;
    else
        dirName = _cascadeDirName + '/';

    numPos = _numPos;
    numNeg = _numNeg;
    numStages = _numStages;
    if ( !imgReader.create( _posFilename, _negFilename, _cascadeParams.winSize ) )
    {
        cout << "Image reader can not be created from -vec " << _posFilename
                << " and -bg " << _negFilename << "." << endl;
        return false;
    }
    if ( !load( dirName ) )
    {
        cascadeParams = _cascadeParams;
        featureParams = CvFeatureParams::create(cascadeParams.featureType);
        featureParams->init(_featureParams);
        stageParams = makePtr<CvCascadeBoostParams>();
        *stageParams = _stageParams;
        featureEvaluator = CvFeatureEvaluator::create(cascadeParams.featureType);
        featureEvaluator->init( featureParams, numPos + numNeg, cascadeParams.winSize );
        stageClassifiers.reserve( numStages );
    }else{
        // Make sure that if model parameters are preloaded, that people are aware of this,
        // even when passing other parameters to the training command
        cout << "---------------------------------------------------------------------------------" << endl;
        cout << "Training parameters are pre-loaded from the parameter file in data folder!" << endl;
        cout << "Please empty this folder if you want to use a NEW set of training parameters." << endl;
        cout << "---------------------------------------------------------------------------------" << endl;
    }
    cout << "PARAMETERS:" << endl;
    cout << "cascadeDirName: " << _cascadeDirName << endl;
    cout << "vecFileName: " << _posFilename << endl;
    cout << "bgFileName: " << _negFilename << endl;
    cout << "numPos: " << _numPos << endl;
    cout << "numNeg: " << _numNeg << endl;
    cout << "numStages: " << numStages << endl;
    cout << "precalcValBufSize[Mb] : " << _precalcValBufSize << endl;
    cout << "precalcIdxBufSize[Mb] : " << _precalcIdxBufSize << endl;
    cout << "acceptanceRatioBreakValue : " << acceptanceRatioBreakValue << endl;
    cascadeParams.printAttrs();
    stageParams->printAttrs();
    featureParams->printAttrs();

    int startNumStages = (int)stageClassifiers.size();
    if ( startNumStages > 1 )
        cout << endl << "Stages 0-" << startNumStages-1 << " are loaded" << endl;
    else if ( startNumStages == 1)
        cout << endl << "Stage 0 is loaded" << endl;

    double requiredLeafFARate = pow( (double) stageParams->maxFalseAlarm, (double) numStages ) /
                                (double)stageParams->max_depth;
    double tempLeafFARate;

    for( int i = startNumStages; i < numStages; i++ )
    {
        cout << endl << "===== TRAINING " << i << "-stage =====" << endl;
        cout << "<BEGIN" << endl;

        if ( !updateTrainingSet( requiredLeafFARate, tempLeafFARate ) )
        {
            cout << "Train dataset for temp stage can not be filled. "
                    "Branch training terminated." << endl;
            break;
        }
        if( tempLeafFARate <= requiredLeafFARate )
        {
            cout << "Required leaf false alarm rate achieved. "
                    "Branch training terminated." << endl;
            break;
        }
        if( (tempLeafFARate <= acceptanceRatioBreakValue) && (acceptanceRatioBreakValue >= 0) ){
            cout << "The required acceptanceRatio for the model has been reached to avoid overfitting of trainingdata. "
                    "Branch training terminated." << endl;
            break;
        }

        Ptr<CvCascadeBoost> tempStage = makePtr<CvCascadeBoost>();
        bool isStageTrained = tempStage->train( featureEvaluator,
                                                curNumSamples, _precalcValBufSize, _precalcIdxBufSize,
                                                *stageParams );
        cout << "END>" << endl;

        if(!isStageTrained)
            break;

        stageClassifiers.push_back( tempStage );

        // save params
        if( i == 0)
        {
            std::string paramsFilename = dirName + CC_PARAMS_FILENAME;
            FileStorage fs( paramsFilename, FileStorage::WRITE);
            if ( !fs.isOpened() )
            {
                cout << "Parameters can not be written, because file " << paramsFilename
                        << " can not be opened." << endl;
                return false;
            }
            fs << FileStorage::getDefaultObjectName(paramsFilename) << "{";
            writeParams( fs );
            fs << "}";
        }
        // save current stage
        char buf[10];
        sprintf(buf, "%s%d", "stage", i );
        string stageFilename = dirName + buf + ".xml";
        FileStorage fs( stageFilename, FileStorage::WRITE );
        if ( !fs.isOpened() )
        {
            cout << "Current stage can not be written, because file " << stageFilename
                    << " can not be opened." << endl;
            return false;
        }
        fs << FileStorage::getDefaultObjectName(stageFilename) << "{";
        tempStage->write( fs, Mat() );
        fs << "}";

        // Output training time up till now
        float seconds = float( clock () - begin_time ) / CLOCKS_PER_SEC;
        int days = int(seconds) / 60 / 60 / 24;
        int hours = (int(seconds) / 60 / 60) % 24;
        int minutes = (int(seconds) / 60) % 60;
        int seconds_left = int(seconds) % 60;
        cout << "Training until now has taken " << days << " days " << hours << " hours " << minutes << " minutes " << seconds_left <<" seconds." << endl;
    }

    if(stageClassifiers.size() == 0)
    {
        cout << "Cascade classifier can't be trained. Check the used training parameters." << endl;
        return false;
    }

    save( dirName + CC_CASCADE_FILENAME, baseFormatSave );

    return true;
}

int CvCascadeClassifier::predict( int sampleIdx )
{
    CV_DbgAssert( sampleIdx < numPos + numNeg );
    for (vector< Ptr<CvCascadeBoost> >::iterator it = stageClassifiers.begin();
        it != stageClassifiers.end(); it++ )
    {
        if ( (*it)->predict( sampleIdx ) == 0.f )
            return 0;
    }
    return 1;
}

bool CvCascadeClassifier::updateTrainingSet( double minimumAcceptanceRatio, double& acceptanceRatio)
{
    int64 posConsumed = 0, negConsumed = 0;
    imgReader.restart();
    int posCount = fillPassedSamples( 0, numPos, true, 0, posConsumed );
    if( !posCount )
        return false;
    cout << "POS count : consumed   " << posCount << " : " << (int)posConsumed << endl;

    int proNumNeg = cvRound( ( ((double)numNeg) * ((double)posCount) ) / numPos ); // apply only a fraction of negative samples. double is required since overflow is possible
    int negCount = fillPassedSamples( posCount, proNumNeg, false, minimumAcceptanceRatio, negConsumed );
    if ( !negCount )
        return false;

    curNumSamples = posCount + negCount;
    acceptanceRatio = negConsumed == 0 ? 0 : ( (double)negCount/(double)(int64)negConsumed );
    cout << "NEG count : acceptanceRatio    " << negCount << " : " << acceptanceRatio << endl;
    return true;
}

int CvCascadeClassifier::fillPassedSamples( int first, int count, bool isPositive, double minimumAcceptanceRatio, int64& consumed )
{
    int getcount = 0;
    Mat img(cascadeParams.winSize, CV_8UC1);
    for( int i = first; i < first + count; i++ )
    {
        for( ; ; )
        {
            if( consumed != 0 && ((double)getcount+1)/(double)(int64)consumed <= minimumAcceptanceRatio )
                return getcount;

            bool isGetImg = isPositive ? imgReader.getPos( img ) :
                                           imgReader.getNeg( img );
            if( !isGetImg )
                return getcount;
            consumed++;

            featureEvaluator->setImage( img, isPositive ? 1 : 0, i );
            if( predict( i ) == 1 )
            {
                getcount++;
                printf("%s current samples: %d\r", isPositive ? "POS":"NEG", getcount);
                break;
            }
        }
    }
    return getcount;
}

void CvCascadeClassifier::writeParams( FileStorage &fs ) const
{
    cascadeParams.write( fs );
    fs << CC_STAGE_PARAMS << "{"; stageParams->write( fs ); fs << "}";
    fs << CC_FEATURE_PARAMS << "{"; featureParams->write( fs ); fs << "}";
}

void CvCascadeClassifier::writeFeatures( FileStorage &fs, const Mat& featureMap ) const
{
    featureEvaluator->writeFeatures( fs, featureMap );
}

void CvCascadeClassifier::writeStages( FileStorage &fs, const Mat& featureMap ) const
{
    char cmnt[30];
    int i = 0;
    fs << CC_STAGES << "[";
    for( vector< Ptr<CvCascadeBoost> >::const_iterator it = stageClassifiers.begin();
        it != stageClassifiers.end(); it++, i++ )
    {
        sprintf( cmnt, "stage %d", i );
        cvWriteComment( fs.fs, cmnt, 0 );
        fs << "{";
        (*it)->write( fs, featureMap );
        fs << "}";
    }
    fs << "]";
}

bool CvCascadeClassifier::readParams( const FileNode &node )
{
    if ( !node.isMap() || !cascadeParams.read( node ) )
        return false;

    stageParams = makePtr<CvCascadeBoostParams>();
    FileNode rnode = node[CC_STAGE_PARAMS];
    if ( !stageParams->read( rnode ) )
        return false;

    featureParams = CvFeatureParams::create(cascadeParams.featureType);
    rnode = node[CC_FEATURE_PARAMS];
    if ( !featureParams->read( rnode ) )
        return false;
    return true;
}

bool CvCascadeClassifier::readStages( const FileNode &node)
{
    FileNode rnode = node[CC_STAGES];
    if (!rnode.empty() || !rnode.isSeq())
        return false;
    stageClassifiers.reserve(numStages);
    FileNodeIterator it = rnode.begin();
    for( int i = 0; i < min( (int)rnode.size(), numStages ); i++, it++ )
    {
        Ptr<CvCascadeBoost> tempStage = makePtr<CvCascadeBoost>();
        if ( !tempStage->read( *it, featureEvaluator, *stageParams) )
            return false;
        stageClassifiers.push_back(tempStage);
    }
    return true;
}

// For old Haar Classifier file saving
#define ICV_HAAR_SIZE_NAME            "size"
#define ICV_HAAR_STAGES_NAME          "stages"
#define ICV_HAAR_TREES_NAME             "trees"
#define ICV_HAAR_FEATURE_NAME             "feature"
#define ICV_HAAR_RECTS_NAME                 "rects"
#define ICV_HAAR_TILTED_NAME                "tilted"
#define ICV_HAAR_THRESHOLD_NAME           "threshold"
#define ICV_HAAR_LEFT_NODE_NAME           "left_node"
#define ICV_HAAR_LEFT_VAL_NAME            "left_val"
#define ICV_HAAR_RIGHT_NODE_NAME          "right_node"
#define ICV_HAAR_RIGHT_VAL_NAME           "right_val"
#define ICV_HAAR_STAGE_THRESHOLD_NAME   "stage_threshold"
#define ICV_HAAR_PARENT_NAME            "parent"
#define ICV_HAAR_NEXT_NAME              "next"

void CvCascadeClassifier::save( const string filename, bool baseFormat )
{
    FileStorage fs( filename, FileStorage::WRITE );

    if ( !fs.isOpened() )
        return;

    fs << FileStorage::getDefaultObjectName(filename) << "{";
    if ( !baseFormat )
    {
        Mat featureMap;
        getUsedFeaturesIdxMap( featureMap );
        writeParams( fs );
        fs << CC_STAGE_NUM << (int)stageClassifiers.size();
        writeStages( fs, featureMap );
        writeFeatures( fs, featureMap );
    }
    else
    {
        //char buf[256];
        CvSeq* weak;
        if ( cascadeParams.featureType != CvFeatureParams::HAAR )
            CV_Error( CV_StsBadFunc, "old file format is used for Haar-like features only");
        fs << ICV_HAAR_SIZE_NAME << "[:" << cascadeParams.winSize.width <<
            cascadeParams.winSize.height << "]";
        fs << ICV_HAAR_STAGES_NAME << "[";
        for( size_t si = 0; si < stageClassifiers.size(); si++ )
        {
            fs << "{"; //stage
            /*sprintf( buf, "stage %d", si );
            CV_CALL( cvWriteComment( fs, buf, 1 ) );*/
            weak = stageClassifiers[si]->get_weak_predictors();
            fs << ICV_HAAR_TREES_NAME << "[";
            for( int wi = 0; wi < weak->total; wi++ )
            {
                int inner_node_idx = -1, total_inner_node_idx = -1;
                queue<const CvDTreeNode*> inner_nodes_queue;
                CvCascadeBoostTree* tree = *((CvCascadeBoostTree**) cvGetSeqElem( weak, wi ));

                fs << "[";
                /*sprintf( buf, "tree %d", wi );
                CV_CALL( cvWriteComment( fs, buf, 1 ) );*/

                const CvDTreeNode* tempNode;

                inner_nodes_queue.push( tree->get_root() );
                total_inner_node_idx++;

                while (!inner_nodes_queue.empty())
                {
                    tempNode = inner_nodes_queue.front();
                    inner_node_idx++;

                    fs << "{";
                    fs << ICV_HAAR_FEATURE_NAME << "{";
                    ((CvHaarEvaluator*)featureEvaluator.get())->writeFeature( fs, tempNode->split->var_idx );
                    fs << "}";

                    fs << ICV_HAAR_THRESHOLD_NAME << tempNode->split->ord.c;

                    if( tempNode->left->left || tempNode->left->right )
                    {
                        inner_nodes_queue.push( tempNode->left );
                        total_inner_node_idx++;
                        fs << ICV_HAAR_LEFT_NODE_NAME << total_inner_node_idx;
                    }
                    else
                        fs << ICV_HAAR_LEFT_VAL_NAME << tempNode->left->value;

                    if( tempNode->right->left || tempNode->right->right )
                    {
                        inner_nodes_queue.push( tempNode->right );
                        total_inner_node_idx++;
                        fs << ICV_HAAR_RIGHT_NODE_NAME << total_inner_node_idx;
                    }
                    else
                        fs << ICV_HAAR_RIGHT_VAL_NAME << tempNode->right->value;
                    fs << "}"; // ICV_HAAR_FEATURE_NAME
                    inner_nodes_queue.pop();
                }
                fs << "]";
            }
            fs << "]"; //ICV_HAAR_TREES_NAME
            fs << ICV_HAAR_STAGE_THRESHOLD_NAME << stageClassifiers[si]->getThreshold();
            fs << ICV_HAAR_PARENT_NAME << (int)si-1 << ICV_HAAR_NEXT_NAME << -1;
            fs << "}"; //stage
        } /* for each stage */
        fs << "]"; //ICV_HAAR_STAGES_NAME
    }
    fs << "}";
}

bool CvCascadeClassifier::load( const string cascadeDirName )
{
    FileStorage fs( cascadeDirName + CC_PARAMS_FILENAME, FileStorage::READ );
    if ( !fs.isOpened() )
        return false;
    FileNode node = fs.getFirstTopLevelNode();
    if ( !readParams( node ) )
        return false;
    featureEvaluator = CvFeatureEvaluator::create(cascadeParams.featureType);
    featureEvaluator->init( featureParams, numPos + numNeg, cascadeParams.winSize );
    fs.release();

    char buf[10];
    for ( int si = 0; si < numStages; si++ )
    {
        sprintf( buf, "%s%d", "stage", si);
        fs.open( cascadeDirName + buf + ".xml", FileStorage::READ );
        node = fs.getFirstTopLevelNode();
        if ( !fs.isOpened() )
            break;
        Ptr<CvCascadeBoost> tempStage = makePtr<CvCascadeBoost>();

        if ( !tempStage->read( node, featureEvaluator, *stageParams ))
        {
            fs.release();
            break;
        }
        stageClassifiers.push_back(tempStage);
    }
    return true;
}

void CvCascadeClassifier::getUsedFeaturesIdxMap( Mat& featureMap )
{
    int varCount = featureEvaluator->getNumFeatures() * featureEvaluator->getFeatureSize();
    featureMap.create( 1, varCount, CV_32SC1 );
    featureMap.setTo(Scalar(-1));

    for( vector< Ptr<CvCascadeBoost> >::const_iterator it = stageClassifiers.begin();
        it != stageClassifiers.end(); it++ )
        (*it)->markUsedFeaturesInMap( featureMap );

    for( int fi = 0, idx = 0; fi < varCount; fi++ )
        if ( featureMap.at<int>(0, fi) >= 0 )
            featureMap.ptr<int>(0)[fi] = idx++;
}