I’m doing object reconstruction from structure from motion. The current situation right now, is I’m getting a multiple views for a car and apply a mask rcnn for that object to remove the background, because I only want that object to reconstruct and have a clean object.
- My current issues, right now are that The Object is not fully reconstructured.
- The mask that I get from Mask RCNN is not always have a fixed size for the SFM to work
- A background noise is still present in the scene reconstructed object
- Camera parameters are messed up when I use only the mask that are got from different views, how to fix that ?
Here are some results:
Original image of course there are mutliple views of it
Mask RCNN results that I use for SFM
and here is the result from SFM
// Draw the predicted bounding box, colorize and show the mask on the image
void drawBox(Mat& frame, int classId, float conf, Rect box, Mat& objectMask, std::vector<Mat> &contours_images)
{
//Draw a rectangle displaying the bounding box
//rectangle(frame, Point(box.x, box.y), Point(box.x + box.width, box.y + box.height), Scalar(255, 178, 50), 3);
//Get the label for the class name and its confidence
string label = format("%.2f", conf);
if (!classes.empty())
{
CV_Assert(classId < (int)classes.size());
label = classes[classId] + ":" + label;
}
//Display the label at the top of the bounding box
int baseLine;
Size labelSize = getTextSize(label, FONT_HERSHEY_SIMPLEX, 0.5, 1, &baseLine);
box.y = max(box.y, labelSize.height);
//rectangle(frame, Point(box.x, box.y - round(1.5 * labelSize.height)), Point(box.x + round(1.5 * labelSize.width), box.y + baseLine), Scalar(255, 255, 255), FILLED);
//putText(frame, label, Point(box.x, box.y), FONT_HERSHEY_SIMPLEX, 0.75, Scalar(0, 0, 0), 1);
// Resize the mask, threshold, color and apply it on the image
// Scalar color = colors[classId % colors.size()];
// Resize the mask, threshold, color and apply it on the image
resize(objectMask, objectMask, Size(box.width, box.height));
Mat mask = (objectMask > maskThreshold);
//Mat coloredRoi = (0.3 * color + 0.7 * frame(box));
// coloredRoi.convertTo(coloredRoi, CV_8UC3);
Mat coloredRoi(frame(box));
// Draw the contours on the image
vector<Mat> contours;
Mat hierarchy;
mask.convertTo(mask, CV_8U);
findContours(mask, contours, hierarchy, RETR_CCOMP, cv::CHAIN_APPROX_NONE);
//drawContours(coloredRoi, contours, -1, color, 5, LINE_8, hierarchy, 100);
// coloredRoi.copyTo(frame(box), mask);
Mat outframe;
coloredRoi.copyTo(outframe, mask);
cv::resize(outframe, outframe, cv::Size(400, 400));
contours_images.push_back(outframe);
// imshow("outframe", outframe);
// waitKey(0);
}
// For each frame, extract the bounding box and mask for each detected object
void postprocess(Mat& frame, const vector<Mat>& outs, vector<Mat> & maskes)
{
Mat outDetections = outs[0];
Mat outMasks = outs[1];
// Output size of masks is NxCxHxW where
// N - number of detected boxes
// C - number of classes (excluding background)
// HxW - segmentation shape
const int numDetections = outDetections.size[2];
const int numClasses = outMasks.size[1];
outDetections = outDetections.reshape(1, outDetections.total() / 7);
for (int i = 0; i < numDetections; ++i)
{
float score = outDetections.at<float>(i, 2);
if (score > confThreshold)
{
// Extract the bounding box
int classId = static_cast<int>(outDetections.at<float>(i, 1));
int left = static_cast<int>(frame.cols * outDetections.at<float>(i, 3));
int top = static_cast<int>(frame.rows * outDetections.at<float>(i, 4));
int right = static_cast<int>(frame.cols * outDetections.at<float>(i, 5));
int bottom = static_cast<int>(frame.rows * outDetections.at<float>(i, 6));
left = max(0, min(left, frame.cols - 1));
top = max(0, min(top, frame.rows - 1));
right = max(0, min(right, frame.cols - 1));
bottom = max(0, min(bottom, frame.rows - 1));
Rect box = Rect(left, top, right - left + 1, bottom - top + 1);
// Extract the mask for the object
Mat objectMask(outMasks.size[2], outMasks.size[3], CV_32F, outMasks.ptr<float>(i, classId));
// Draw bounding box, colorize and show the mask on the image
drawBox(frame, classId, score, box, objectMask, maskes);
}
}
}