This commit is contained in:
Jonas Perolini 2025-06-03 07:12:42 -07:00 committed by GitHub
commit 6e089dba67
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
5 changed files with 517 additions and 19 deletions

View File

@ -318,6 +318,32 @@ public:
CV_WRAP void detectMarkers(InputArray image, OutputArrayOfArrays corners, OutputArray ids, CV_WRAP void detectMarkers(InputArray image, OutputArrayOfArrays corners, OutputArray ids,
OutputArrayOfArrays rejectedImgPoints = noArray()) const; OutputArrayOfArrays rejectedImgPoints = noArray()) const;
/** @brief Marker detection with uncertainty computation
*
* @param image input image
* @param corners vector of detected marker corners. For each marker, its four corners
* are provided, (e.g std::vector<std::vector<cv::Point2f> > ). For N detected markers,
* the dimensions of this array is Nx4. The order of the corners is clockwise.
* @param ids vector of identifiers of the detected markers. The identifier is of type int
* (e.g. std::vector<int>). For N detected markers, the size of ids is also N.
* The identifiers have the same order than the markers in the imgPoints array.
* @param markersUnc contains the normalized uncertainty [0;1] of the markers' detection,
* defined as percentage of incorrect pixel detections, with 0 describing a pixel perfect detection.
* The uncertainties are of type float (e.g. std::vector<float>)
* @param rejectedImgPoints contains the imgPoints of those squares whose inner code has not a
* correct codification. Useful for debugging purposes.
*
* Performs marker detection in the input image. Only markers included in the first specified dictionary
* are searched. For each detected marker, it returns the 2D position of its corner in the image
* and its corresponding identifier.
* Note that this function does not perform pose estimation.
* @note The function does not correct lens distortion or takes it into account. It's recommended to undistort
* input image with corresponding camera model, if camera parameters are known
* @sa undistort, estimatePoseSingleMarkers, estimatePoseBoard
*/
CV_WRAP void detectMarkersWithUnc(InputArray image, OutputArrayOfArrays corners, OutputArray ids, OutputArray markersUnc,
OutputArrayOfArrays rejectedImgPoints = noArray()) const;
/** @brief Refine not detected markers based on the already detected and the board layout /** @brief Refine not detected markers based on the already detected and the board layout
* *
* @param image input image * @param image input image

View File

@ -71,7 +71,6 @@ class CV_EXPORTS_W_SIMPLE Dictionary {
*/ */
CV_WRAP int getDistanceToId(InputArray bits, int id, bool allRotations = true) const; CV_WRAP int getDistanceToId(InputArray bits, int id, bool allRotations = true) const;
/** @brief Generate a canonical marker image /** @brief Generate a canonical marker image
*/ */
CV_WRAP void generateImageMarker(int id, int sidePixels, OutputArray _img, int borderBits = 1) const; CV_WRAP void generateImageMarker(int id, int sidePixels, OutputArray _img, int borderBits = 1) const;
@ -84,7 +83,7 @@ class CV_EXPORTS_W_SIMPLE Dictionary {
/** @brief Transform list of bytes to matrix of bits /** @brief Transform list of bytes to matrix of bits
*/ */
CV_WRAP static Mat getBitsFromByteList(const Mat &byteList, int markerSize); CV_WRAP static Mat getBitsFromByteList(const Mat &byteList, int markerSize, int rotationId = 0);
}; };

View File

@ -313,10 +313,10 @@ static void _detectInitialCandidates(const Mat &grey, vector<vector<Point2f> > &
* the border bits * the border bits
*/ */
static Mat _extractBits(InputArray _image, const vector<Point2f>& corners, int markerSize, static Mat _extractBits(InputArray _image, const vector<Point2f>& corners, int markerSize,
int markerBorderBits, int cellSize, double cellMarginRate, double minStdDevOtsu) { int markerBorderBits, int cellSize, double cellMarginRate, double minStdDevOtsu, OutputArray _cellPixelRatio = noArray()) {
CV_Assert(_image.getMat().channels() == 1); CV_Assert(_image.getMat().channels() == 1);
CV_Assert(corners.size() == 4ull); CV_Assert(corners.size() == 4ull);
CV_Assert(markerBorderBits > 0 && cellSize > 0 && cellMarginRate >= 0 && cellMarginRate <= 1); CV_Assert(markerBorderBits > 0 && cellSize > 0 && cellMarginRate >= 0 && cellMarginRate <= 0.5);
CV_Assert(minStdDevOtsu >= 0); CV_Assert(minStdDevOtsu >= 0);
// number of bits in the marker // number of bits in the marker
@ -339,6 +339,7 @@ static Mat _extractBits(InputArray _image, const vector<Point2f>& corners, int m
// output image containing the bits // output image containing the bits
Mat bits(markerSizeWithBorders, markerSizeWithBorders, CV_8UC1, Scalar::all(0)); Mat bits(markerSizeWithBorders, markerSizeWithBorders, CV_8UC1, Scalar::all(0));
Mat cellPixelRatio(markerSizeWithBorders, markerSizeWithBorders, CV_32FC1, Scalar::all(0));
// check if standard deviation is enough to apply Otsu // check if standard deviation is enough to apply Otsu
// if not enough, it probably means all bits are the same color (black or white) // if not enough, it probably means all bits are the same color (black or white)
@ -349,10 +350,15 @@ static Mat _extractBits(InputArray _image, const vector<Point2f>& corners, int m
meanStdDev(innerRegion, mean, stddev); meanStdDev(innerRegion, mean, stddev);
if(stddev.ptr< double >(0)[0] < minStdDevOtsu) { if(stddev.ptr< double >(0)[0] < minStdDevOtsu) {
// all black or all white, depending on mean value // all black or all white, depending on mean value
if(mean.ptr< double >(0)[0] > 127) if(mean.ptr< double >(0)[0] > 127){
bits.setTo(1); bits.setTo(1);
else cellPixelRatio.setTo(1);
}
else {
bits.setTo(0); bits.setTo(0);
cellPixelRatio.setTo(0);
}
if(_cellPixelRatio.needed()) cellPixelRatio.copyTo(_cellPixelRatio);
return bits; return bits;
} }
@ -369,9 +375,14 @@ static Mat _extractBits(InputArray _image, const vector<Point2f>& corners, int m
// count white pixels on each cell to assign its value // count white pixels on each cell to assign its value
size_t nZ = (size_t) countNonZero(square); size_t nZ = (size_t) countNonZero(square);
if(nZ > square.total() / 2) bits.at<unsigned char>(y, x) = 1; if(nZ > square.total() / 2) bits.at<unsigned char>(y, x) = 1;
// define the cell pixel ratio as the ratio of the white pixels. For inverted markers, the ratio will be inverted.
if(_cellPixelRatio.needed()) cellPixelRatio.at<float>(y, x) = (nZ / (float)square.total());
} }
} }
if(_cellPixelRatio.needed()) cellPixelRatio.copyTo(_cellPixelRatio);
return bits; return bits;
} }
@ -403,6 +414,50 @@ static int _getBorderErrors(const Mat &bits, int markerSize, int borderSize) {
} }
/** @brief Given a matrix containing the percentage of white pixels in each marker cell, returns the normalized marker uncertainty [0;1] for the specific id.
* The uncertainty is defined as percentage of incorrect pixel detections, with 0 describing a pixel perfect detection.
* The rotation is set to 0,1,2,3 for [0, 90, 180, 270] deg CCW rotations.
*/
static float _getMarkerUnc(const Mat& groundTruthbits, const Mat &cellPixelRatio, const int markerSize, const int borderSize) {
CV_Assert(markerSize == groundTruthbits.cols && markerSize == groundTruthbits.rows);
const int sizeWithBorders = markerSize + 2 * borderSize;
CV_Assert(markerSize > 0 && cellPixelRatio.cols == sizeWithBorders && cellPixelRatio.rows == sizeWithBorders);
// Get border uncertainty. cellPixelRatio has the opposite color as the borders --> it is the uncertainty.
float tempBorderUnc = 0.f;
for(int y = 0; y < sizeWithBorders; y++) {
for(int k = 0; k < borderSize; k++) {
// Left and right vertical sides
tempBorderUnc += cellPixelRatio.ptr<float>(y)[k];
tempBorderUnc += cellPixelRatio.ptr<float>(y)[sizeWithBorders - 1 - k];
}
}
for(int x = borderSize; x < sizeWithBorders - borderSize; x++) {
for(int k = 0; k < borderSize; k++) {
// Top and bottom horizontal sides
tempBorderUnc += cellPixelRatio.ptr<float>(k)[x];
tempBorderUnc += cellPixelRatio.ptr<float>(sizeWithBorders - 1 - k)[x];
}
}
// Get the inner marker uncertainty. For a white or black cell, the uncertainty is the ratio of black or white pixels respectively.
float tempInnerUnc = 0.f;
for(int y = borderSize; y < markerSize + borderSize; y++) {
for(int x = borderSize; x < markerSize + borderSize; x++) {
tempInnerUnc += abs(groundTruthbits.ptr<float>(y - borderSize)[x - borderSize] - cellPixelRatio.ptr<float>(y)[x]);
}
}
// Compute the overall normalized marker uncertainty
float normalizedMarkerUnc = (tempInnerUnc + tempBorderUnc) / (sizeWithBorders * sizeWithBorders);
return normalizedMarkerUnc;
}
/** /**
* @brief Tries to identify one candidate given the dictionary * @brief Tries to identify one candidate given the dictionary
* @return candidate typ. zero if the candidate is not valid, * @return candidate typ. zero if the candidate is not valid,
@ -412,6 +467,7 @@ static int _getBorderErrors(const Mat &bits, int markerSize, int borderSize) {
static uint8_t _identifyOneCandidate(const Dictionary& dictionary, const Mat& _image, static uint8_t _identifyOneCandidate(const Dictionary& dictionary, const Mat& _image,
const vector<Point2f>& _corners, int& idx, const vector<Point2f>& _corners, int& idx,
const DetectorParameters& params, int& rotation, const DetectorParameters& params, int& rotation,
float &markerUnc,
const float scale = 1.f) { const float scale = 1.f) {
CV_DbgAssert(params.markerBorderBits > 0); CV_DbgAssert(params.markerBorderBits > 0);
uint8_t typ=1; uint8_t typ=1;
@ -423,10 +479,12 @@ static uint8_t _identifyOneCandidate(const Dictionary& dictionary, const Mat& _i
scaled_corners[i].y = _corners[i].y * scale; scaled_corners[i].y = _corners[i].y * scale;
} }
Mat cellPixelRatio;
Mat candidateBits = Mat candidateBits =
_extractBits(_image, scaled_corners, dictionary.markerSize, params.markerBorderBits, _extractBits(_image, scaled_corners, dictionary.markerSize, params.markerBorderBits,
params.perspectiveRemovePixelPerCell, params.perspectiveRemovePixelPerCell,
params.perspectiveRemoveIgnoredMarginPerCell, params.minOtsuStdDev); params.perspectiveRemoveIgnoredMarginPerCell, params.minOtsuStdDev,
cellPixelRatio);
// analyze border bits // analyze border bits
int maximumErrorsInBorder = int maximumErrorsInBorder =
@ -439,6 +497,7 @@ static uint8_t _identifyOneCandidate(const Dictionary& dictionary, const Mat& _i
// to get from 255 to 1 // to get from 255 to 1
Mat invertedImg = ~candidateBits-254; Mat invertedImg = ~candidateBits-254;
int invBError = _getBorderErrors(invertedImg, dictionary.markerSize, params.markerBorderBits); int invBError = _getBorderErrors(invertedImg, dictionary.markerSize, params.markerBorderBits);
cellPixelRatio = -1.0 * cellPixelRatio + 1;
// white marker // white marker
if(invBError<borderErrors){ if(invBError<borderErrors){
borderErrors = invBError; borderErrors = invBError;
@ -458,6 +517,12 @@ static uint8_t _identifyOneCandidate(const Dictionary& dictionary, const Mat& _i
if(!dictionary.identify(onlyBits, idx, rotation, params.errorCorrectionRate)) if(!dictionary.identify(onlyBits, idx, rotation, params.errorCorrectionRate))
return 0; return 0;
// compute the candidate's uncertainty
Mat groundTruthbits;
Mat bitsUints = dictionary.getBitsFromByteList(dictionary.bytesList.rowRange(idx, idx + 1), dictionary.markerSize, rotation);
bitsUints.convertTo(groundTruthbits, CV_32F);
markerUnc = _getMarkerUnc(groundTruthbits, cellPixelRatio, dictionary.markerSize, params.markerBorderBits);
return typ; return typ;
} }
@ -657,7 +722,7 @@ struct ArucoDetector::ArucoDetectorImpl {
* @brief Detect markers either using multiple or just first dictionary * @brief Detect markers either using multiple or just first dictionary
*/ */
void detectMarkers(InputArray _image, OutputArrayOfArrays _corners, OutputArray _ids, void detectMarkers(InputArray _image, OutputArrayOfArrays _corners, OutputArray _ids,
OutputArrayOfArrays _rejectedImgPoints, OutputArray _dictIndices, DictionaryMode dictMode) { OutputArrayOfArrays _rejectedImgPoints, OutputArray _dictIndices, OutputArray _markersUnc, DictionaryMode dictMode) {
CV_Assert(!_image.empty()); CV_Assert(!_image.empty());
CV_Assert(detectorParams.markerBorderBits > 0); CV_Assert(detectorParams.markerBorderBits > 0);
@ -717,6 +782,7 @@ struct ArucoDetector::ArucoDetectorImpl {
vector<vector<Point2f> > candidates; vector<vector<Point2f> > candidates;
vector<vector<Point> > contours; vector<vector<Point> > contours;
vector<int> ids; vector<int> ids;
vector<float> markersUnc;
/// STEP 2.a Detect marker candidates :: using AprilTag /// STEP 2.a Detect marker candidates :: using AprilTag
if(detectorParams.cornerRefinementMethod == (int)CORNER_REFINE_APRILTAG){ if(detectorParams.cornerRefinementMethod == (int)CORNER_REFINE_APRILTAG){
@ -738,7 +804,7 @@ struct ArucoDetector::ArucoDetectorImpl {
/// STEP 2: Check candidate codification (identify markers) /// STEP 2: Check candidate codification (identify markers)
identifyCandidates(grey, grey_pyramid, selectedCandidates, candidates, contours, identifyCandidates(grey, grey_pyramid, selectedCandidates, candidates, contours,
ids, dictionary, rejectedImgPoints); ids, dictionary, rejectedImgPoints, markersUnc);
/// STEP 3: Corner refinement :: use corner subpix /// STEP 3: Corner refinement :: use corner subpix
if (detectorParams.cornerRefinementMethod == (int)CORNER_REFINE_SUBPIX) { if (detectorParams.cornerRefinementMethod == (int)CORNER_REFINE_SUBPIX) {
@ -766,7 +832,7 @@ struct ArucoDetector::ArucoDetectorImpl {
// temporary variable to store the current candidates // temporary variable to store the current candidates
vector<vector<Point2f>> currentCandidates; vector<vector<Point2f>> currentCandidates;
identifyCandidates(grey, grey_pyramid, candidatesPerDictionarySize.at(currentDictionary.markerSize), currentCandidates, contours, identifyCandidates(grey, grey_pyramid, candidatesPerDictionarySize.at(currentDictionary.markerSize), currentCandidates, contours,
ids, currentDictionary, rejectedImgPoints); ids, currentDictionary, rejectedImgPoints, markersUnc);
if (_dictIndices.needed()) { if (_dictIndices.needed()) {
dictIndices.insert(dictIndices.end(), currentCandidates.size(), dictIndex); dictIndices.insert(dictIndices.end(), currentCandidates.size(), dictIndex);
} }
@ -849,6 +915,9 @@ struct ArucoDetector::ArucoDetectorImpl {
if (_dictIndices.needed()) { if (_dictIndices.needed()) {
Mat(dictIndices).copyTo(_dictIndices); Mat(dictIndices).copyTo(_dictIndices);
} }
if (_markersUnc.needed()) {
Mat(markersUnc).copyTo(_markersUnc);
}
} }
/** /**
@ -982,9 +1051,10 @@ struct ArucoDetector::ArucoDetectorImpl {
*/ */
void identifyCandidates(const Mat& grey, const vector<Mat>& image_pyr, vector<MarkerCandidateTree>& selectedContours, void identifyCandidates(const Mat& grey, const vector<Mat>& image_pyr, vector<MarkerCandidateTree>& selectedContours,
vector<vector<Point2f> >& accepted, vector<vector<Point> >& contours, vector<vector<Point2f> >& accepted, vector<vector<Point> >& contours,
vector<int>& ids, const Dictionary& currentDictionary, vector<vector<Point2f>>& rejected) const { vector<int>& ids, const Dictionary& currentDictionary, vector<vector<Point2f>>& rejected, vector<float>& markersUnc) const {
size_t ncandidates = selectedContours.size(); size_t ncandidates = selectedContours.size();
vector<float> markersUncTmp(ncandidates, 1.f);
vector<int> idsTmp(ncandidates, -1); vector<int> idsTmp(ncandidates, -1);
vector<int> rotated(ncandidates, 0); vector<int> rotated(ncandidates, 0);
vector<uint8_t> validCandidates(ncandidates, 0); vector<uint8_t> validCandidates(ncandidates, 0);
@ -1018,11 +1088,11 @@ struct ArucoDetector::ArucoDetectorImpl {
} }
const float scale = detectorParams.useAruco3Detection ? img.cols / static_cast<float>(grey.cols) : 1.f; const float scale = detectorParams.useAruco3Detection ? img.cols / static_cast<float>(grey.cols) : 1.f;
validCandidates[v] = _identifyOneCandidate(currentDictionary, img, selectedContours[v].corners, idsTmp[v], detectorParams, rotated[v], scale); validCandidates[v] = _identifyOneCandidate(currentDictionary, img, selectedContours[v].corners, idsTmp[v], detectorParams, rotated[v], markersUncTmp[v], scale);
if (validCandidates[v] == 0 && checkCloseContours) { if (validCandidates[v] == 0 && checkCloseContours) {
for (const MarkerCandidate& closeMarkerCandidate: selectedContours[v].closeContours) { for (const MarkerCandidate& closeMarkerCandidate: selectedContours[v].closeContours) {
validCandidates[v] = _identifyOneCandidate(currentDictionary, img, closeMarkerCandidate.corners, idsTmp[v], detectorParams, rotated[v], scale); validCandidates[v] = _identifyOneCandidate(currentDictionary, img, closeMarkerCandidate.corners, idsTmp[v], detectorParams, rotated[v], markersUncTmp[v], scale);
if (validCandidates[v] > 0) { if (validCandidates[v] > 0) {
selectedContours[v].corners = closeMarkerCandidate.corners; selectedContours[v].corners = closeMarkerCandidate.corners;
selectedContours[v].contour = closeMarkerCandidate.contour; selectedContours[v].contour = closeMarkerCandidate.contour;
@ -1058,6 +1128,7 @@ struct ArucoDetector::ArucoDetectorImpl {
accepted.push_back(selectedContours[i].corners); accepted.push_back(selectedContours[i].corners);
contours.push_back(selectedContours[i].contour); contours.push_back(selectedContours[i].contour);
ids.push_back(idsTmp[i]); ids.push_back(idsTmp[i]);
markersUnc.push_back(markersUncTmp[i]);
} }
else { else {
rejected.push_back(selectedContours[i].corners); rejected.push_back(selectedContours[i].corners);
@ -1103,14 +1174,19 @@ ArucoDetector::ArucoDetector(const vector<Dictionary> &_dictionaries,
arucoDetectorImpl = makePtr<ArucoDetectorImpl>(_dictionaries, _detectorParams, _refineParams); arucoDetectorImpl = makePtr<ArucoDetectorImpl>(_dictionaries, _detectorParams, _refineParams);
} }
void ArucoDetector::detectMarkersWithUnc(InputArray _image, OutputArrayOfArrays _corners, OutputArray _ids, OutputArray _markersUnc,
OutputArrayOfArrays _rejectedImgPoints) const {
arucoDetectorImpl->detectMarkers(_image, _corners, _ids, _rejectedImgPoints, noArray(), _markersUnc, DictionaryMode::Single);
}
void ArucoDetector::detectMarkers(InputArray _image, OutputArrayOfArrays _corners, OutputArray _ids, void ArucoDetector::detectMarkers(InputArray _image, OutputArrayOfArrays _corners, OutputArray _ids,
OutputArrayOfArrays _rejectedImgPoints) const { OutputArrayOfArrays _rejectedImgPoints) const {
arucoDetectorImpl->detectMarkers(_image, _corners, _ids, _rejectedImgPoints, noArray(), DictionaryMode::Single); arucoDetectorImpl->detectMarkers(_image, _corners, _ids, _rejectedImgPoints, noArray(), noArray(), DictionaryMode::Single);
} }
void ArucoDetector::detectMarkersMultiDict(InputArray _image, OutputArrayOfArrays _corners, OutputArray _ids, void ArucoDetector::detectMarkersMultiDict(InputArray _image, OutputArrayOfArrays _corners, OutputArray _ids,
OutputArrayOfArrays _rejectedImgPoints, OutputArray _dictIndices) const { OutputArrayOfArrays _rejectedImgPoints, OutputArray _dictIndices) const {
arucoDetectorImpl->detectMarkers(_image, _corners, _ids, _rejectedImgPoints, _dictIndices, DictionaryMode::Multi); arucoDetectorImpl->detectMarkers(_image, _corners, _ids, _rejectedImgPoints, _dictIndices, noArray(), DictionaryMode::Multi);
} }
/** /**

View File

@ -194,17 +194,23 @@ Mat Dictionary::getByteListFromBits(const Mat &bits) {
} }
Mat Dictionary::getBitsFromByteList(const Mat &byteList, int markerSize) { Mat Dictionary::getBitsFromByteList(const Mat &byteList, int markerSize, int rotationId) {
CV_Assert(byteList.total() > 0 && CV_Assert(byteList.total() > 0 &&
byteList.total() >= (unsigned int)markerSize * markerSize / 8 && byteList.total() >= (unsigned int)markerSize * markerSize / 8 &&
byteList.total() <= (unsigned int)markerSize * markerSize / 8 + 1); byteList.total() <= (unsigned int)markerSize * markerSize / 8 + 1);
CV_Assert(rotationId < 4);
Mat bits(markerSize, markerSize, CV_8UC1, Scalar::all(0)); Mat bits(markerSize, markerSize, CV_8UC1, Scalar::all(0));
unsigned char base2List[] = { 128, 64, 32, 16, 8, 4, 2, 1 }; unsigned char base2List[] = { 128, 64, 32, 16, 8, 4, 2, 1 };
// Use a base offset for the selected rotation
int nbytes = (bits.cols * bits.rows + 8 - 1) / 8; // integer ceil
int base = rotationId * nbytes;
int currentByteIdx = 0; int currentByteIdx = 0;
// we only need the bytes in normal rotation unsigned char currentByte = byteList.ptr()[base + currentByteIdx];
unsigned char currentByte = byteList.ptr()[0];
int currentBit = 0; int currentBit = 0;
for(int row = 0; row < bits.rows; row++) { for(int row = 0; row < bits.rows; row++) {
for(int col = 0; col < bits.cols; col++) { for(int col = 0; col < bits.cols; col++) {
if(currentByte >= base2List[currentBit]) { if(currentByte >= base2List[currentBit]) {
@ -214,7 +220,7 @@ Mat Dictionary::getBitsFromByteList(const Mat &byteList, int markerSize) {
currentBit++; currentBit++;
if(currentBit == 8) { if(currentBit == 8) {
currentByteIdx++; currentByteIdx++;
currentByte = byteList.ptr()[currentByteIdx]; currentByte = byteList.ptr()[base + currentByteIdx];
// if not enough bits for one more byte, we are in the end // if not enough bits for one more byte, we are in the end
// update bit position accordingly // update bit position accordingly
if(8 * (currentByteIdx + 1) > (int)bits.total()) if(8 * (currentByteIdx + 1) > (int)bits.total())

View File

@ -321,6 +321,385 @@ void CV_ArucoDetectionPerspective::run(int) {
} }
} }
// Helper struct and functions for CV_ArucoDetectionUnc
// Inverts a square subregion inside selected cells of a marker to simulate uncertainty
enum class MarkerRegionToTemper {
BORDER, // Only invert cells within the marker border bits
INNER, // Only invert cells in the inner part of the marker (excluding borders)
ALL // Invert any cells
};
// Define the characteristics of cell inversions
struct MarkerTemperingConfig {
float cellRatioToTemper; // [0,1] ratio of the cell to invert
int numCellsToTemper; // Number of cells to invert
MarkerRegionToTemper markerRegionToTemper; // Which cells to invert (BORDER, INNER, ALL)
};
// Test configs for CV_ArucoDetectionUnc
struct ArucoUncTestConfig {
MarkerTemperingConfig markerTemperingConfig; // Configuration of cells to invert (percentage, number and markerRegionToTemper)
float perspectiveRemoveIgnoredMarginPerCell; // Width of the margin of pixels on each cell not considered for the marker identification
int markerBorderBits; // Number of bits of the marker border
float distortionRatio; // Percentage of offset used for perspective distortion, bigger means more distorted
};
enum class markerRot
{
NONE = 0,
ROT_90,
ROT_180,
ROT_270
};
struct markerDetectionGT {
int id; // Marker identification
double uncertainty; // Pixel-based uncertainty defined as inverted area / total area
bool expectDetection; // True if we expect to detect the marker
};
struct MarkerCreationConfig {
int id; // Marker identification
int markerSidePixels; // Marker size (in pixels)
markerRot rotation; // Rotation of the marker in degrees (0, 90, 180, 270)
};
void rotateMarker(Mat &marker, const markerRot rotation)
{
if(rotation == markerRot::NONE)
return;
if (rotation == markerRot::ROT_90) {
cv::transpose(marker, marker);
cv::flip(marker, marker, 0);
} else if (rotation == markerRot::ROT_180) {
cv::flip(marker, marker, -1);
} else if (rotation == markerRot::ROT_270) {
cv::transpose(marker, marker);
cv::flip(marker, marker, 1);
}
}
void distortMarker(Mat &marker, const float distortionRatio)
{
if (distortionRatio < FLT_EPSILON)
return;
// apply a distortion (a perspective warp) to simulate a non-ideal capture
vector<Point2f> src = { {0, 0},
{static_cast<float>(marker.cols), 0},
{static_cast<float>(marker.cols), static_cast<float>(marker.rows)},
{0, static_cast<float>(marker.rows)} };
float offset = marker.cols * distortionRatio; // distortionRatio % offset for distortion
vector<Point2f> dst = { {offset, offset},
{marker.cols - offset, 0},
{marker.cols - offset, marker.rows - offset},
{0, marker.rows - offset} };
Mat M = getPerspectiveTransform(src, dst);
warpPerspective(marker, marker, M, marker.size(), INTER_LINEAR, BORDER_CONSTANT, Scalar(255));
}
/**
* @brief Inverts a square subregion inside selected cells of a marker image to simulate uncertainty.
*
* The function computes the marker grid parameters and then applies a bitwise inversion
* on a square markerRegionToTemper inside the chosen cells. The number of cells to be inverted is determined by
* the parameter 'numCellsToTemper'. The candidate cells can be filtered to only include border cells,
* inner cells, or all cells according to the parameter 'markerRegionToTemper'.
*
* @param marker The marker image
* @param markerSidePixels The total size of the marker in pixels (inner and border).
* @param markerId The id of the marker
* @param params The Aruco detector configuration (provides border bits, margin ratios, etc.).
* @param dictionary The Aruco marker dictionary (used to determine marker grid size).
* @param cellTempConfig Cell tempering config as defined in MarkerTemperingConfig
* @return Cell tempering ground truth as defined in markerDetectionGT
*/
markerDetectionGT applyTemperingToMarkerCells(cv::Mat &marker,
const int markerSidePixels,
const int markerId,
const aruco::DetectorParameters &params,
const aruco::Dictionary &dictionary,
const MarkerTemperingConfig &cellTempConfig)
{
// nothing to invert
if(cellTempConfig.numCellsToTemper <= 0 || cellTempConfig.cellRatioToTemper <= FLT_EPSILON)
return {markerId, 0.0, true};
// compute the overall grid dimensions.
const int markerSizeWithBorders = dictionary.markerSize + 2 * params.markerBorderBits;
const int cellSidePixelsSize = markerSidePixels / markerSizeWithBorders;
// compute the margin within each cell used for identification.
const int cellMarginPixels = static_cast<int>(params.perspectiveRemoveIgnoredMarginPerCell * cellSidePixelsSize);
const int innerCellSizePixels = cellSidePixelsSize - 2 * cellMarginPixels;
// determine the size of the square that will be inverted in each cell.
// (cellSidePixelsInvert / innerCellSizePixels)^2 should equal cellRatioToTemper.
const int cellSidePixelsInvert = min(cellSidePixelsSize, static_cast<int>(innerCellSizePixels * std::sqrt(cellTempConfig.cellRatioToTemper)));
const int inversionOffsetPixels = (cellSidePixelsSize - cellSidePixelsInvert) / 2;
// nothing to invert
if(cellSidePixelsInvert <= 0)
return {markerId, 0.0, true};
int cellsTempered = 0;
int borderErrors = 0;
int innerCellsErrors = 0;
// iterate over each cell in the grid.
for (int row = 0; row < markerSizeWithBorders; row++) {
for (int col = 0; col < markerSizeWithBorders; col++) {
// decide if this cell falls in the markerRegionToTemper to temper.
const bool isBorder = (row < params.markerBorderBits ||
col < params.markerBorderBits ||
row >= markerSizeWithBorders - params.markerBorderBits ||
col >= markerSizeWithBorders - params.markerBorderBits);
const bool inRegion = (cellTempConfig.markerRegionToTemper == MarkerRegionToTemper::ALL ||
(isBorder && cellTempConfig.markerRegionToTemper == MarkerRegionToTemper::BORDER) ||
(!isBorder && cellTempConfig.markerRegionToTemper == MarkerRegionToTemper::INNER));
// apply the inversion to simulate tempering.
if (inRegion && (cellsTempered < cellTempConfig.numCellsToTemper)) {
const int xStart = col * cellSidePixelsSize + inversionOffsetPixels;
const int yStart = row * cellSidePixelsSize + inversionOffsetPixels;
cv::Rect cellRect(xStart, yStart, cellSidePixelsInvert, cellSidePixelsInvert);
cv::Mat cellROI = marker(cellRect);
cv::bitwise_not(cellROI, cellROI);
++cellsTempered;
// cell too tempered, no detection expected
if(cellTempConfig.cellRatioToTemper > 0.5f) {
if(isBorder){
++borderErrors;
} else {
++innerCellsErrors;
}
}
}
if(cellsTempered >= cellTempConfig.numCellsToTemper)
break;
}
if(cellsTempered >= cellTempConfig.numCellsToTemper)
break;
}
// compute the ground-truth uncertainty
const double invertedArea = cellsTempered * cellSidePixelsInvert * cellSidePixelsInvert;
const double totalDetectionArea = markerSizeWithBorders * innerCellSizePixels * markerSizeWithBorders * innerCellSizePixels;
const double groundTruthUnc = invertedArea / totalDetectionArea;
// check if marker is expected to be detected
const int maximumErrorsInBorder = static_cast<int>(dictionary.markerSize * dictionary.markerSize * params.maxErroneousBitsInBorderRate);
const int maxCorrectionRecalculed = static_cast<int>(dictionary.maxCorrectionBits * params.errorCorrectionRate);
const bool expectDetection = static_cast<bool>(borderErrors <= maximumErrorsInBorder && innerCellsErrors <= maxCorrectionRecalculed);
return {markerId, groundTruthUnc, expectDetection};
}
/**
* @brief Create an image of a marker with inverted (tempered) regions to simulate detection uncertainty
*
* Applies an optional rotation and an optional perspective warp to simulate a distorted marker.
* Inverts a square subregion inside selected cells of a marker image to simulate uncertainty.
* Computes the ground-truth uncertainty as the ratio of inverted area to the total marker area used for identification.
*
*/
markerDetectionGT generateTemperedMarkerImage(Mat &marker, const MarkerCreationConfig &markerConfig, const MarkerTemperingConfig &markerTemperingConfig,
const aruco::DetectorParameters &params, const aruco::Dictionary &dictionary, const float distortionRatio = 0.f)
{
// generate the synthetic marker image
aruco::generateImageMarker(dictionary, markerConfig.id, markerConfig.markerSidePixels,
marker, params.markerBorderBits);
// rotate marker if necessary
rotateMarker(marker, markerConfig.rotation);
// temper with cells to simulate detection uncertainty
markerDetectionGT groundTruth = applyTemperingToMarkerCells(marker, markerConfig.markerSidePixels, markerConfig.id, params, dictionary, markerTemperingConfig);
// apply a distortion (a perspective warp) to simulate a non-ideal capture
distortMarker(marker, distortionRatio);
return groundTruth;
}
/**
* @brief Copies a marker image into a larger image at the given top-left position.
*/
void placeMarker(Mat &img, const Mat &marker, const Point2f &topLeft)
{
Rect roi(Point(static_cast<int>(topLeft.x), static_cast<int>(topLeft.y)), marker.size());
marker.copyTo(img(roi));
}
/**
* @brief Test the marker uncertainty computations
*
* Loops over a set of detector configurations (e.g. expected uncertainty, distortion, DetectorParameters)
* For each configuration, it creates a synthetic image containing four markers arranged in a 2x2 grid.
* Each marker is generated with its own configuration (id, size, rotation).
* Finally, it runs the detector and checks that each marker is detected and
* that its computed uncertainty is close to the ground truth value.
*
*/
class CV_ArucoDetectionUnc : public cvtest::BaseTest {
public:
// The parameter arucoAlgParam allows switching between detecting normal and inverted markers.
CV_ArucoDetectionUnc(ArucoAlgParams algParam) : arucoAlgParam(algParam) {}
protected:
void run(int);
ArucoAlgParams arucoAlgParam;
};
void CV_ArucoDetectionUnc::run(int) {
aruco::DetectorParameters params;
// make sure there are no bits have any detection errors
params.maxErroneousBitsInBorderRate = 0.0;
params.errorCorrectionRate = 0.0;
params.perspectiveRemovePixelPerCell = 8; // esnsure that there is enough resolution to properly handle distortions
aruco::ArucoDetector detector(aruco::getPredefinedDictionary(aruco::DICT_6X6_250), params);
const bool detectInvertedMarker = (arucoAlgParam == ArucoAlgParams::DETECT_INVERTED_MARKER);
// define several detector configurations to test different settings
// {{MarkerTemperingConfig}, perspectiveRemoveIgnoredMarginPerCell, markerBorderBits, distortionRatio}
vector<ArucoUncTestConfig> detectorConfigs = {
// No margins, No distortion
{{0.f, 64, MarkerRegionToTemper::ALL}, 0.0f, 1, 0.f},
{{0.01f, 64, MarkerRegionToTemper::ALL}, 0.0f, 1, 0.f},
{{0.05f, 100, MarkerRegionToTemper::ALL}, 0.0f, 2, 0.f},
{{0.1f, 64, MarkerRegionToTemper::ALL}, 0.0f, 1, 0.f},
{{0.15f, 30, MarkerRegionToTemper::ALL}, 0.0f, 1, 0.f},
{{0.20f, 55, MarkerRegionToTemper::ALL}, 0.0f, 2, 0.f},
// Margins, No distortion
{{0.f, 26, MarkerRegionToTemper::BORDER}, 0.05f, 1, 0.f},
{{0.01f, 56, MarkerRegionToTemper::BORDER}, 0.05f, 2, 0.f},
{{0.05f, 144, MarkerRegionToTemper::ALL}, 0.1f, 3, 0.f},
{{0.10f, 49, MarkerRegionToTemper::ALL}, 0.15f, 1, 0.f},
// No margins, distortion
{{0.f, 36, MarkerRegionToTemper::INNER}, 0.0f, 1, 0.01f},
{{0.01f, 36, MarkerRegionToTemper::INNER}, 0.0f, 1, 0.02f},
{{0.05f, 12, MarkerRegionToTemper::INNER}, 0.0f, 2, 0.05f},
{{0.1f, 64, MarkerRegionToTemper::ALL}, 0.0f, 1, 0.1f},
{{0.1f, 81, MarkerRegionToTemper::ALL}, 0.0f, 2, 0.2f},
// Margins, distortion
{{0.f, 81, MarkerRegionToTemper::ALL}, 0.05f, 2, 0.01f},
{{0.01f, 64, MarkerRegionToTemper::ALL}, 0.05f, 1, 0.02f},
{{0.05f, 81, MarkerRegionToTemper::ALL}, 0.1f, 2, 0.05f},
{{0.1f, 64, MarkerRegionToTemper::ALL}, 0.15f, 1, 0.1f},
{{0.1f, 64, MarkerRegionToTemper::ALL}, 0.0f, 1, 0.2f},
// no marker detection, too much tempering
{{0.9f, 1, MarkerRegionToTemper::ALL}, 0.05f, 2, 0.0f},
{{0.9f, 1, MarkerRegionToTemper::BORDER}, 0.05f, 2, 0.0f},
{{0.9f, 1, MarkerRegionToTemper::INNER}, 0.05f, 2, 0.0f},
};
// define marker configurations for the 4 markers in each image
const int markerSidePixels = 480; // To simplify the cell division, markerSidePixels is a multiple of 8. (6x6 dict + 2 border bits)
vector<MarkerCreationConfig> markerCreationConfig = {
{0, markerSidePixels, markerRot::ROT_90}, // {id, markerSidePixels, rotation}
{1, markerSidePixels, markerRot::ROT_270},
{2, markerSidePixels, markerRot::NONE},
{3, markerSidePixels, markerRot::ROT_180}
};
// loop over each detector configuration
for (size_t cfgIdx = 0; cfgIdx < detectorConfigs.size(); cfgIdx++) {
ArucoUncTestConfig detCfg = detectorConfigs[cfgIdx];
// update detector parameters
params.perspectiveRemoveIgnoredMarginPerCell = detCfg.perspectiveRemoveIgnoredMarginPerCell;
params.markerBorderBits = detCfg.markerBorderBits;
params.detectInvertedMarker = detectInvertedMarker;
detector.setDetectorParameters(params);
// create a blank image large enough to hold 4 markers in a 2x2 grid
const int margin = markerSidePixels / 2;
const int imageSize = (markerSidePixels * 2) + margin * 3;
Mat img(imageSize, imageSize, CV_8UC1, Scalar(255));
vector<markerDetectionGT> groundTruths;
const aruco::Dictionary &dictionary = detector.getDictionary();
// place each marker into the image
for (int row = 0; row < 2; row++) {
for (int col = 0; col < 2; col++) {
int index = row * 2 + col;
MarkerCreationConfig markerCfg = markerCreationConfig[index];
// adjust marker id to be unique for each detector configuration
markerCfg.id += static_cast<int>(cfgIdx * markerCreationConfig.size());
// generate img
Mat markerImg;
markerDetectionGT gt = generateTemperedMarkerImage(markerImg, markerCfg, detCfg.markerTemperingConfig, params, dictionary, detCfg.distortionRatio);
groundTruths.push_back(gt);
// place marker in the image
Point2f topLeft(margin + col * (markerSidePixels + margin),
margin + row * (markerSidePixels + margin));
placeMarker(img, markerImg, topLeft);
}
}
// if testing inverted markers globally, invert the whole image
if (detectInvertedMarker) {
bitwise_not(img, img);
}
// run detection.
vector<vector<Point2f>> corners, rejected;
vector<int> ids;
vector<float> markerUnc;
detector.detectMarkersWithUnc(img, corners, ids, markerUnc, rejected);
// verify that every marker is detected and its uncertainty is within tolerance
for (size_t m = 0; m < groundTruths.size(); m++) {
markerDetectionGT currentGT = groundTruths[m];
// check if current marker id is present in detected markers
int detectedIdx = -1;
for (size_t k = 0; k < ids.size(); k++) {
if (currentGT.id == ids[k]) {
detectedIdx = static_cast<int>(ids[k]);
break;
}
}
// check if marker was detected or not based on GT
const int expectedIdx = currentGT.expectDetection ? currentGT.id : -1;
if (detectedIdx != expectedIdx) {
ts->printf(cvtest::TS::LOG, "Detected marker id: %d | expected idx: %d (detector config %zu)\n",
detectedIdx, expectedIdx, cfgIdx);
ts->set_failed_test_info(cvtest::TS::FAIL_MISMATCH);
return;
}
// check uncertainty if marker detected
if(detectedIdx != -1){
double gtComputationDiff = fabs(currentGT.uncertainty - markerUnc[m]);
if (gtComputationDiff > 0.05) {
ts->printf(cvtest::TS::LOG,
"Computed uncertainty: %.2f | expected uncertainty: %.2f (diff=%.2f) (Marker id: %d, detector config %zu)\n",
markerUnc[m], currentGT.uncertainty, gtComputationDiff, currentGT.id, cfgIdx);
ts->set_failed_test_info(cvtest::TS::FAIL_BAD_ACCURACY);
return;
}
}
}
}
}
/** /**
* @brief Check max and min size in marker detection parameters * @brief Check max and min size in marker detection parameters
@ -552,6 +931,18 @@ TEST(CV_ArucoBitCorrection, algorithmic) {
test.safe_run(); test.safe_run();
} }
typedef CV_ArucoDetectionUnc CV_InvertedArucoDetectionUnc;
TEST(CV_ArucoDetectionUnc, algorithmic) {
CV_ArucoDetectionUnc test(ArucoAlgParams::USE_DEFAULT);
test.safe_run();
}
TEST(CV_InvertedArucoDetectionUnc, algorithmic) {
CV_InvertedArucoDetectionUnc test(ArucoAlgParams::DETECT_INVERTED_MARKER);
test.safe_run();
}
TEST(CV_ArucoDetectMarkers, regression_3192) TEST(CV_ArucoDetectMarkers, regression_3192)
{ {
aruco::ArucoDetector detector(aruco::getPredefinedDictionary(aruco::DICT_4X4_50)); aruco::ArucoDetector detector(aruco::getPredefinedDictionary(aruco::DICT_4X4_50));