Wangyida
9 years ago
parent
197fba68f4
commit
97d49a8834
8 changed files with 313 additions and 31 deletions
@ -0,0 +1,75 @@ |
||||
Training data generation using Icosphere {#tutorial_data_generation} |
||||
============= |
||||
|
||||
Goal |
||||
---- |
||||
|
||||
In this tutorial you will learn how to |
||||
|
||||
- Conduct a point cloud of camera view on sphere. |
||||
- Generate training images using 3D model. |
||||
|
||||
Code |
||||
---- |
||||
|
||||
You can download the code from [here ](https://github.com/Wangyida/opencv_contrib/blob/cnn_3dobj/samples/demo_sphereview_data.cpp). |
||||
@include cnn_3dobj/samples/demo_sphereview_data.cpp |
||||
|
||||
Explanation |
||||
----------- |
||||
|
||||
Here is the general structure of the program: |
||||
|
||||
- Create a window. |
||||
@code{.cpp} |
||||
viz::Viz3d myWindow("Coordinate Frame"); |
||||
@endcode |
||||
|
||||
- Set window size as 64*64, we use this scale as default. |
||||
@code{.cpp} |
||||
myWindow.setWindowSize(Size(64,64)); |
||||
@endcode |
||||
|
||||
- Add coordinate axes. |
||||
@code{.cpp} |
||||
myWindow.showWidget("Coordinate Widget", viz::WCoordinateSystem()); |
||||
myWindow.setBackgroundColor(viz::Color::gray()); |
||||
myWindow.spin(); |
||||
@endcode |
||||
|
||||
- Create a Mesh widget, loading .ply models. |
||||
@code{.cpp} |
||||
viz::Mesh objmesh = viz::Mesh::load(plymodel); |
||||
@endcode |
||||
- Get the center of the generated mesh widget, cause some .ply files. |
||||
@code{.cpp} |
||||
Point3d cam_focal_point = ViewSphere.getCenter(objmesh.cloud); |
||||
@endcode |
||||
|
||||
- Get the pose of the camera using makeCameraPoses. |
||||
@code{.cpp} |
||||
Affine3f cam_pose = viz::makeCameraPose(campos.at(pose)*radius+cam_focal_point, cam_focal_point, cam_y_dir*radius+cam_focal_point); |
||||
@endcode |
||||
|
||||
- Get the transformation matrix from camera coordinate system to global. |
||||
@code{.cpp} |
||||
Affine3f transform = viz::makeTransformToGlobal(Vec3f(1.0f,0.0f,0.0f), Vec3f(0.0f,1.0f,0.0f), Vec3f(0.0f,0.0f,1.0f), campos.at(pose)); |
||||
viz::WMesh mesh_widget(objmesh); |
||||
@endcode |
||||
|
||||
- Save screen shot as images. |
||||
@code{.cpp} |
||||
myWindow.saveScreenshot(filename); |
||||
@endcode |
||||
|
||||
- Write images into binary files for further using in CNN training. |
||||
@code{.cpp} |
||||
ViewSphere.writeBinaryfile(filename, binaryPath, headerPath,(int)campos.size()*num_class, label_class, (int)(campos.at(pose).x*100), (int)(campos.at(pose).y*100), (int)(campos.at(pose).z*100), rgb_use); |
||||
@endcode |
||||
|
||||
Results |
||||
------- |
||||
|
||||
Here is collection images created by this demo using 4 model. |
||||
|
||||
 |
||||
@ -0,0 +1,66 @@ |
||||
Classify {#tutorial_classify} |
||||
=============== |
||||
|
||||
Goal |
||||
---- |
||||
|
||||
In this tutorial you will learn how to |
||||
|
||||
- How to extract feature from an image |
||||
- How to extract features from images under a given root path |
||||
- How to make a prediction using reference images and target image |
||||
|
||||
Code |
||||
---- |
||||
|
||||
You can download the code from [here ](https://github.com/Wangyida/opencv_contrib/blob/cnn_3dobj/samples/demo_classify.cpp). |
||||
@include cnn_3dobj/samples/demo_classify.cpp |
||||
|
||||
Explanation |
||||
----------- |
||||
|
||||
Here is the general structure of the program: |
||||
|
||||
- Initialize a net work with Device. |
||||
@code{.cpp} |
||||
cv::cnn_3dobj::descriptorExtractor descriptor(device); |
||||
@endcode |
||||
|
||||
- Load net with the caffe trained net work parameter and structure. |
||||
@code{.cpp} |
||||
if (strcmp(mean_file.c_str(), "no") == 0) |
||||
descriptor.loadNet(network_forIMG, caffemodel); |
||||
else |
||||
descriptor.loadNet(network_forIMG, caffemodel, mean_file); |
||||
@endcode |
||||
|
||||
- List the file names under a given path. |
||||
@code{.cpp} |
||||
listDir(src_dir.c_str(), name_gallery, false); |
||||
for (unsigned int i = 0; i < name_gallery.size(); i++) |
||||
{ |
||||
name_gallery[i] = src_dir + name_gallery[i]; |
||||
} |
||||
@endcode |
||||
|
||||
- Extract feature from a set of images. |
||||
@code{.cpp} |
||||
descriptor.extract(img_gallery, feature_reference, feature_blob); |
||||
@endcode |
||||
|
||||
- Initialize a matcher which using L2 distance. |
||||
@code{.cpp} |
||||
cv::BFMatcher matcher(NORM_L2); |
||||
std::vector<std::vector<cv::DMatch> > matches; |
||||
@endcode |
||||
|
||||
- Have a KNN match on the target and reference images. |
||||
@code{.cpp} |
||||
matcher.knnMatch(feature_test, feature_reference, matches, num_candidate); |
||||
@endcode |
||||
|
||||
- Print features of the reference images. |
||||
@code{.cpp}std::cout << std::endl << "---------- Features of target image: " << target_img << "----------" << endl << feature_test << std::endl; |
||||
@endcode |
||||
Results |
||||
------- |
||||
@ -0,0 +1,60 @@ |
||||
Training data generation using Icosphere {#tutorial_model_analysis} |
||||
============= |
||||
|
||||
Goal |
||||
---- |
||||
|
||||
In this tutorial you will learn how to |
||||
|
||||
- Extract feature from particular image. |
||||
- Have a meaningful comparation on the extracted feature. |
||||
|
||||
Code |
||||
---- |
||||
|
||||
You can download the code from [here ](https://github.com/Wangyida/opencv_contrib/blob/cnn_3dobj/samples/demo_model_analysis.cpp). |
||||
@include cnn_3dobj/samples/demo_model_analysis.cpp |
||||
|
||||
Explanation |
||||
----------- |
||||
|
||||
Here is the general structure of the program: |
||||
|
||||
- Sample which is most closest in pose to reference image and also the same class. |
||||
@code{.cpp} |
||||
ref_img.push_back(ref_img1); |
||||
@endcode |
||||
|
||||
- Sample which is less closest in pose to reference image and also the same class. |
||||
@code{.cpp} |
||||
ref_img.push_back(ref_img2); |
||||
@endcode |
||||
|
||||
- Sample which is very close in pose to reference image but not the same class. |
||||
@code{.cpp} |
||||
ref_img.push_back(ref_img3); |
||||
@endcode |
||||
|
||||
- Initialize a net work with Device. |
||||
@code{.cpp} |
||||
cv::cnn_3dobj::descriptorExtractor descriptor(device, dev_id); |
||||
@endcode |
||||
- Load net with the caffe trained net work parameter and structure. |
||||
@code{.cpp} |
||||
if (strcmp(mean_file.c_str(), "no") == 0) |
||||
descriptor.loadNet(network_forIMG, caffemodel); |
||||
else |
||||
descriptor.loadNet(network_forIMG, caffemodel, mean_file); |
||||
@endcode |
||||
|
||||
- Have comparations on the distance between reference image and 3 other images |
||||
distance between closest sample and reference image should be smallest and |
||||
distance between sample in another class and reference image should be largest. |
||||
@code{.cpp} |
||||
if (matches[0] < matches[1] && matches[0] < matches[2]) |
||||
pose_pass = true; |
||||
if (matches[1] < matches[2]) |
||||
class_pass = true; |
||||
@endcode |
||||
Results |
||||
------- |
||||
@ -0,0 +1,26 @@ |
||||
CNN for 3D Object Classification and Pose Estimation {#tutorial_table_of_content_cnn_3dobj} |
||||
========== |
||||
|
||||
- @subpage tutorial_data_generation |
||||
|
||||
*Compatibility:* \> OpenCV 3.0.0 |
||||
|
||||
*Author:* Yida Wang |
||||
|
||||
You will learn how to generate training images from 3D models with proper poses for CNN training. |
||||
|
||||
- @subpage tutorial_feature_classification |
||||
|
||||
*Compatibility:* \> OpenCV 3.0.0 |
||||
|
||||
*Author:* Yida Wang |
||||
|
||||
You will learn how to extract features from images and make a prediction using descriptor. |
||||
|
||||
- @subpage tutorial_model_analysis |
||||
|
||||
*Compatibility:* \> OpenCV 3.0.0 |
||||
|
||||
*Author:* Yida Wang |
||||
|
||||
You will learn how to have an analysis on performance of the trained Model. |
||||
Loading…
Reference in new issue