可以将文章内容翻译成中文,广告屏蔽插件可能会导致该功能失效(如失效,请关闭广告屏蔽插件后再试):
问题:
I have a project, which I want to detect objects in the images; my aim is to use HOG features. By using OpenCV SVM implementation , I could find the code for detecting people, and I read some papers about tuning the parameters in order to detect object instead of people. Unfortunately, I couldn't do that for a few reasons; first of all, I am probably tuning the parameters incorrectly, second of all, I am not a good programmer in C++ but I have to do it with C++/OpenCV... here you can find the code for detecting HOG features for people by using C++/OpenCV.
Let's say that I want to detect the object in this image. Now, I will show you what I have tried to change in the code but it didn't work out with me.
The code that I tried to change:
HOGDescriptor hog;
hog.setSVMDetector(HOGDescriptor::getDefaultPeopleDetector());
I tried to change getDefaultPeopleDetector()
with the following parameters, but it didn't work:
(Size(64, 128), Size(16, 16), Size(8, 8), Size(8, 8), 9, 0,-1, 0, 0.2, true, cv::HOGDescriptor::DEFAULT_NLEVELS)
I then tried to make a vector, but when I wanted to print the results, it seems to be empty.
vector<float> detector;
HOGDescriptor hog(Size(64, 128), Size(16, 16), Size(8, 8), Size(8, 8), 9, 0,-1, 0, 0.2, true, cv::HOGDescriptor::DEFAULT_NLEVELS);
hog.setSVMDetector(detector);
Please, I need help solving this problem.
回答1:
In order to detect arbitrary objects with using opencv HOG descriptors and SVM classifier, you need to first train the classifier. Playing with the parameters will not help here, sorry :( .
In broad terms, you will need to complete the following steps:
Step 1) Prepare some training images of the objects you want to detect (positive samples). Also you will need to prepare some images with no objects of interest (negative samples).
Step 2) Detect HOG features of the training sample and use this features to train an SVM classifier (also provided in OpenCV).
Step 3) Use the coefficients of the trained SVM classifier in HOGDescriptor::setSVMDetector() method.
Only then, you can use the peopledetector.cpp sample code, to detect the objects you want to detect.
回答2:
I've been dealing with the same problem and surprised with the lack of some clean C++ solutions I have create ~> this wrapper of SVMLight <~, which is a static library that provides classes SVMTrainer
and SVMClassifier
that simplify the training to something like:
// we are going to use HOG to obtain feature vectors:
HOGDescriptor hog;
hog.winSize = Size(32,48);
// and feed SVM with them:
SVMLight::SVMTrainer svm("features.dat");
then for each training sample:
// obtain feature vector describing sample image:
vector<float> featureVector;
hog.compute(img, featureVector, Size(8, 8), Size(0, 0));
// and write feature vector to the file:
svm.writeFeatureVectorToFile(featureVector, true); // true = positive sample
till the features.dat
file contains feature vectors for all samples and at the end you just call:
std::string modelName("classifier.dat");
svm.trainAndSaveModel(modelName);
Once you have a file with model (or features.dat
that you can just train the classifier with):
SVMLight::SVMClassifier c(classifierModelName);
vector<float> descriptorVector = c.getDescriptorVector();
hog.setSVMDetector(descriptorVector);
...
vector<Rect> found;
Size padding(Size(0, 0));
Size winStride(Size(8, 8));
hog.detectMultiScale(segment, found, 0.0, winStride, padding, 1.01, 0.1);
just check the documentation of HOGDescriptor for more info :)
回答3:
I have done similar things as you did: collect samples of positive and negative images using HOG to extract features of car, train the feature set using linear SVM (I use SVM light), then use the model to detect car using HOG multidetect function.
I get lot of false positives, then I retrain the data using positive samples and false positive+negative samples. The resulting model is then tested again. The resulting detection improves (less false positives) but the result is not satisfying (average 50% hit rate and 50% false positives). Tuning up multidetect parameters improve the result but not much (10% less false positives and increase in hit rate).
Edit
I can share you the source code if you'd like, and I am very open for discussion as I have not get satisfactory results using HOG. Anyway, I think the code can be good starting point on using HOG for training and detection
Edit: adding code
static void calculateFeaturesFromInput(const string& imageFilename, vector<float>& featureVector, HOGDescriptor& hog)
{
Mat imageData = imread(imageFilename, 1);
if (imageData.empty()) {
featureVector.clear();
printf("Error: HOG image '%s' is empty, features calculation skipped!\n", imageFilename.c_str());
return;
}
// Check for mismatching dimensions
if (imageData.cols != hog.winSize.width || imageData.rows != hog.winSize.height) {
featureVector.clear();
printf("Error: Image '%s' dimensions (%u x %u) do not match HOG window size (%u x %u)!\n", imageFilename.c_str(), imageData.cols, imageData.rows, hog.winSize.width, hog.winSize.height);
return;
}
vector<Point> locations;
hog.compute(imageData, featureVector, winStride, trainingPadding, locations);
imageData.release(); // Release the image again after features are extracted
}
...
int main(int argc, char** argv) {
// <editor-fold defaultstate="collapsed" desc="Init">
HOGDescriptor hog; // Use standard parameters here
hog.winSize.height = 128;
hog.winSize.width = 64;
// Get the files to train from somewhere
static vector<string> tesImages;
static vector<string> positiveTrainingImages;
static vector<string> negativeTrainingImages;
static vector<string> validExtensions;
validExtensions.push_back("jpg");
validExtensions.push_back("png");
validExtensions.push_back("ppm");
validExtensions.push_back("pgm");
// </editor-fold>
// <editor-fold defaultstate="collapsed" desc="Read image files">
getFilesInDirectory(posSamplesDir, positiveTrainingImages, validExtensions);
getFilesInDirectory(negSamplesDir, negativeTrainingImages, validExtensions);
/// Retrieve the descriptor vectors from the samples
unsigned long overallSamples = positiveTrainingImages.size() + negativeTrainingImages.size();
// </editor-fold>
// <editor-fold defaultstate="collapsed" desc="Calculate HOG features and save to file">
// Make sure there are actually samples to train
if (overallSamples == 0) {
printf("No training sample files found, nothing to do!\n");
return EXIT_SUCCESS;
}
/// @WARNING: This is really important, some libraries (e.g. ROS) seems to set the system locale which takes decimal commata instead of points which causes the file input parsing to fail
setlocale(LC_ALL, "C"); // Do not use the system locale
setlocale(LC_NUMERIC,"C");
setlocale(LC_ALL, "POSIX");
printf("Reading files, generating HOG features and save them to file '%s':\n", featuresFile.c_str());
float percent;
/**
* Save the calculated descriptor vectors to a file in a format that can be used by SVMlight for training
* @NOTE: If you split these steps into separate steps:
* 1. calculating features into memory (e.g. into a cv::Mat or vector< vector<float> >),
* 2. saving features to file / directly inject from memory to machine learning algorithm,
* the program may consume a considerable amount of main memory
*/
fstream File;
File.open(featuresFile.c_str(), ios::out);
if (File.good() && File.is_open()) {
File << "# Use this file to train, e.g. SVMlight by issuing $ svm_learn -i 1 -a weights.txt " << featuresFile.c_str() << endl; // Remove this line for libsvm which does not support comments
// Iterate over sample images
for (unsigned long currentFile = 0; currentFile < overallSamples; ++currentFile) {
storeCursor();
vector<float> featureVector;
// Get positive or negative sample image file path
const string currentImageFile = (currentFile < positiveTrainingImages.size() ? positiveTrainingImages.at(currentFile) : negativeTrainingImages.at(currentFile - positiveTrainingImages.size()));
// Output progress
if ( (currentFile+1) % 10 == 0 || (currentFile+1) == overallSamples ) {
percent = ((currentFile+1) * 100 / overallSamples);
printf("%5lu (%3.0f%%):\tFile '%s'", (currentFile+1), percent, currentImageFile.c_str());
fflush(stdout);
resetCursor();
}
// Calculate feature vector from current image file
calculateFeaturesFromInput(currentImageFile, featureVector, hog);
if (!featureVector.empty()) {
/* Put positive or negative sample class to file,
* true=positive, false=negative,
* and convert positive class to +1 and negative class to -1 for SVMlight
*/
File << ((currentFile < positiveTrainingImages.size()) ? "+1" : "-1");
// Save feature vector components
for (unsigned int feature = 0; feature < featureVector.size(); ++feature) {
File << " " << (feature + 1) << ":" << featureVector.at(feature);
}
File << endl;
}
}
printf("\n");
File.flush();
File.close();
} else {
printf("Error opening file '%s'!\n", featuresFile.c_str());
return EXIT_FAILURE;
}
// </editor-fold>
// <editor-fold defaultstate="collapsed" desc="Pass features to machine learning algorithm">
/// Read in and train the calculated feature vectors
printf("Calling SVMlight\n");
SVMlight::getInstance()->read_problem(const_cast<char*> (featuresFile.c_str()));
SVMlight::getInstance()->train(); // Call the core libsvm training procedure
printf("Training done, saving model file!\n");
SVMlight::getInstance()->saveModelToFile(svmModelFile);
// </editor-fold>
// <editor-fold defaultstate="collapsed" desc="Generate single detecting feature vector from calculated SVM support vectors and SVM model">
printf("Generating representative single HOG feature vector using svmlight!\n");
vector<float> descriptorVector;
vector<unsigned int> descriptorVectorIndices;
// Generate a single detecting feature vector (v1 | b) from the trained support vectors, for use e.g. with the HOG algorithm
SVMlight::getInstance()->getSingleDetectingVector(descriptorVector, descriptorVectorIndices);
// And save the precious to file system
saveDescriptorVectorToFile(descriptorVector, descriptorVectorIndices, descriptorVectorFile);
// </editor-fold>
// <editor-fold defaultstate="collapsed" desc="Test detecting vector">
cout << "Test Detecting Vector" << endl;
hog.setSVMDetector(descriptorVector); // Set our custom detecting vector
cout << "descriptorVector size: " << sizeof(descriptorVector) << endl;
getFilesInDirectory(tesSamplesDir, tesImages, validExtensions);
namedWindow("Test Detector", 1);
for( size_t it = 0; it < tesImages.size(); it++ )
{
cout << "Process image " << tesImages[it] << endl;
Mat image = imread( tesImages[it], 1 );
detectAndDrawObjects(image, hog);
for(;;)
{
int c = waitKey();
if( (char)c == 'n')
break;
else if( (char)c == '\x1b' )
exit(0);
}
}
// </editor-fold>
return EXIT_SUCCESS;
}