opencv/opencv_contribPublic

NotificationsYou must be signed in to change notification settings
Fork5.9k
Star9.9k

[GSoC] Point Cloud Object Fitting#2584

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to ourterms of service andprivacy statement. We’ll occasionally send you account related emails.

Already on GitHub?Sign in to your account

Jump to bottom

Open

devanshbatra04 wants to merge8 commits intoopencv:4.x

base:4.x

Choose a base branch

fromdevanshbatra04:ptcloud

Open

[GSoC] Point Cloud Object Fitting#2584

devanshbatra04 wants to merge8 commits intoopencv:4.xfromdevanshbatra04:ptcloud

Conversation

Copy link

Contributor

devanshbatra04 commentedJun 30, 2020•
edited
Loading

This PR would contain the work done towards the GSoC 2020 project on Point Cloud object fitting.

This is a test to see whether the PR builds. I will continue adding changes.
cc:@mihaibujanca

Pull Request Readiness Checklist

See details athttps://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

I agree to contribute to the project under OpenCV (BSD) License.
To the best of my knowledge, the proposed patch is not based on a code under GPL or other license that is incompatible with OpenCV
The PR is proposed to proper branch
There is reference to original bug report and related work
There is accuracy test, performance test and test data in opencv_extra repository, if applicable
Patch to opencv_extra has the same branch name.
The feature is well documented and sample code can be built with the project CMake

devanshbatra04 added5 commits

June 30, 2020 18:59

initial commit for ptcloud object fitting

8d59f7c

corrected build issue and added sample data and code

325ce02

added highgui as dependency and removed imgproc

cb009e4

include DOXYGEN docs

1a40d52

remove redundant doxygen param

3b0990b

tompollok reviewed

Jul 1, 2020

View reviewed changes

modules/ptcloud/include/opencv2/ptcloud/sac_segmentation.hpp

		#include <vector>
		#include <utility>
		#include "opencv2/viz.hpp"
		#define PLANE_MODEL 1

Copy link

Contributor

tompollokJul 1, 2020

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

enums are a better choice than defines

devanshbatra04 added3 commits

July 25, 2020 20:02

completed cylinder fitting

806549f

added code and sample program for segmentation

1283fee

removed trailing whitespace and minor warning corrections

5eea165

Copy link

mihaibujanca commentedNov 11, 2020

@devanshbatra04 Any update on this, please?

berak reviewed

Nov 15, 2020

View reviewed changes

modules/ptcloud/src/sac_segmentation.cpp


		bool getSphereFromPoints(const Vec3f* &points, const std::vector<unsigned> &inliers, Point3d& center, double& radius) {
		// assert that size of points is 3.
		Mat temp(5,5,CV_32FC1);

Copy link

Contributor

berakNov 14, 2020

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

this should be a 4x4 Mat, with the last column set to 1

(as it is now, it has 10 uninitialized values, wrecking any determinant calculated later)

modules/ptcloud/src/sac_segmentation.cpp


		assert(normals_cld.cols == cloud.cols);

		const Point3d* points = cloud.ptr<Point3d>(0);

Copy link

Contributor

berakNov 14, 2020

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

this must be Point3f (the point cloud is in float format, not double)

modules/ptcloud/src/sac_segmentation.cpp


		double magnitude_abc = sqrt(ModelCoefficients[0]ModelCoefficients[0] + ModelCoefficients[1] ModelCoefficients[1] + ModelCoefficients[2] * ModelCoefficients[2]);

		assert (magnitude_abc == 0);

Copy link

Contributor

berakNov 14, 2020

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

for sure you want != 0 here

modules/ptcloud/src/sac_segmentation.cpp

		return result;
		}

		viz::WCylinder SACCylinderModel::WindowWidget () {

Copy link

Contributor

berakNov 14, 2020

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

probably, we should outsource any drawing functionality to the samples.

having a dependancy of thelibrary code to the viz module (which again depends on vtk) is some major bummer, this could/should be made optional

modules/ptcloud/src/sac_segmentation.cpp

		break;
		}
		vector<unsigned> latest_model_inliers = inliers.back();
		num_segmented_points += latest_model_inliers.size();

Copy link

Contributor

berakNov 14, 2020

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

bail out, ifnum_segmented_points==0 ?

(since the rng is reseeded insidefit_once() it cannot do anything different, if the labels array wasn't changed, leading to an infinite loop)

modules/ptcloud/src/sac_segmentation.cpp

		}

		if (model_type == CYLINDER_MODEL) {
		assert(this->normals_available == true);

Copy link

Contributor

berakNov 14, 2020

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others.Learn more.

so, currently, normals are not optional here.

maybe we can add another method for adding a hypothesis based on 3 points (2 points parallel to the axis, just on the outer hull, and a 3rd, somewhat opposite) ?

generating normals from 12 (!) knn neighbours only seems to work nicely for very dense clouds, but not for sparse, synthetic or sfm generated clouds

Copy link

mihaibujanca commentedJan 12, 2021

Hi,@devanshbatra04 it's been quite some time without an update. Can you please refactor the code as suggested so we can merge the PR?

Copy link

Contributor

berak commentedFeb 23, 2021•
edited
Loading

would there be a way to work on this (and still keep the original commits /@devanshbatra04 as author) ?

i think i gotsome improvements

Copy link

Member

WanliZhong commentedMar 18, 2021

would there be a way to work on this (and still keep the original commits /@devanshbatra04 as author) ?
i think i gotsome improvements

Hi, we notice that you are improving the object detection feature. Our group hopes to complete the feature. What do you think we can do for this feature? Thank you.