Commit e5917a8f authored by Alexander Alekhin's avatar Alexander Alekhin

Merge pull request #13580 from LaurentBerger:PythonStitch2

parents 40959fcc 49a43dfc
......@@ -96,10 +96,63 @@ or (dataset from professional book scanner):
Examples above expects POSIX platform, on windows you have to provide all files names explicitly
(e.g. `boat1.jpg` `boat2.jpg`...) as windows command line does not support `*` expansion.
See also
Stitching detailed (python opencv >4.0.1)
--------
If you want to study internals of the stitching pipeline or you want to experiment with detailed
configuration see
[stitching_detailed.cpp](https://github.com/opencv/opencv/tree/master/samples/cpp/stitching_detailed.cpp)
in `opencv/samples/cpp` folder.
configuration you can use stitching_detailed source code available in C++ or python
<H4>stitching_detailed</H4>
@add_toggle_cpp
[stitching_detailed.cpp](https://raw.githubusercontent.com/opencv/opencv/master/samples/cpp/stitching_detailed.cpp)
@end_toggle
@add_toggle_python
[stitching_detailed.py](https://raw.githubusercontent.com/opencv/opencv/master/samples/python/stitching_detailed.py)
@end_toggle
stitching_detailed program uses command line to get stitching parameter. Many parameters exists. Above examples shows some command line parameters possible :
boat5.jpg boat2.jpg boat3.jpg boat4.jpg boat1.jpg boat6.jpg --work_megapix 0.6 --features orb --matcher homography --estimator homography --match_conf 0.3 --conf_thresh 0.3 --ba ray --ba_refine_mask xxxxx --save_graph test.txt --wave_correct no --warp fisheye --blend multiband --expos_comp no --seam gc_colorgrad
![](images/fisheye.jpg)
Pairwise images are matched using an homography --matcher homography and estimator used for transformation estimation too --estimator homography
Confidence for feature matching step is 0.3 : --match_conf 0.3. You can decrease this value if you have some difficulties to match images
Threshold for two images are from the same panorama confidence is 0. : --conf_thresh 0.3 You can decrease this value if you have some difficulties to match images
Bundle adjustment cost function is ray --ba ray
Refinement mask for bundle adjustment is xxxxx ( --ba_refine_mask xxxxx) where 'x' means refine respective parameter and '_' means don't. Refine one, and has the following format: fx,skew,ppx,aspect,ppy
Save matches graph represented in DOT language to test.txt ( --save_graph test.txt) : Labels description: Nm is number of matches, Ni is number of inliers, C is confidence
![](images/gvedit.jpg)
Perform wave effect correction is no (--wave_correct no)
Warp surface type is fisheye (--warp fisheye)
Blending method is multiband (--blend multiband)
Exposure compensation method is not used (--expos_comp no)
Seam estimation estimator is Minimum graph cut-based seam (--seam gc_colorgrad)
you can use those arguments on command line too :
boat5.jpg boat2.jpg boat3.jpg boat4.jpg boat1.jpg boat6.jpg --work_megapix 0.6 --features orb --matcher homography --estimator homography --match_conf 0.3 --conf_thresh 0.3 --ba ray --ba_refine_mask xxxxx --wave_correct horiz --warp compressedPlaneA2B1 --blend multiband --expos_comp channels_blocks --seam gc_colorgrad
You will get :
![](images/compressedPlaneA2B1.jpg)
For images captured using a scanner or a drone ( affine motion) you can use those arguments on command line :
newspaper1.jpg newspaper2.jpg --work_megapix 0.6 --features surf --matcher affine --estimator affine --match_conf 0.3 --conf_thresh 0.3 --ba affine --ba_refine_mask xxxxx --wave_correct no --warp affine
![](images/affinepano.jpg)
You can find all images in https://github.com/opencv/opencv_extra/tree/master/testdata/stitching
......@@ -73,7 +73,7 @@ public:
@param corners Source images top-left corners
@param sizes Source image sizes
*/
CV_WRAP void prepare(const std::vector<Point> &corners, const std::vector<Size> &sizes);
CV_WRAP virtual void prepare(const std::vector<Point> &corners, const std::vector<Size> &sizes);
/** @overload */
CV_WRAP virtual void prepare(Rect dst_roi);
/** @brief Processes the image.
......
......@@ -120,6 +120,8 @@ final transformation for each camera.
*/
class CV_EXPORTS_W AffineBasedEstimator : public Estimator
{
public:
CV_WRAP AffineBasedEstimator(){}
private:
virtual bool estimate(const std::vector<ImageFeatures> &features,
const std::vector<MatchesInfo> &pairwise_matches,
......
......@@ -133,7 +133,6 @@ void Blender::blend(InputOutputArray dst, InputOutputArray dst_mask)
dst_mask_.release();
}
void FeatherBlender::prepare(Rect dst_roi)
{
Blender::prepare(dst_roi);
......@@ -231,7 +230,6 @@ MultiBandBlender::MultiBandBlender(int try_gpu, int num_bands, int weight_type)
weight_type_ = weight_type;
}
void MultiBandBlender::prepare(Rect dst_roi)
{
dst_roi_final_ = dst_roi;
......
......@@ -83,8 +83,11 @@ parser.add_argument('--seam_megapix',action = 'store', default = 0.1,help=' Reso
parser.add_argument('--seam',action = 'store', default = 'no',help='Seam estimation method. The default is "gc_color".',type=str,dest = 'seam' )
parser.add_argument('--compose_megapix',action = 'store', default = -1,help='Resolution for compositing step. Use -1 for original resolution.',type=float,dest = 'compose_megapix' )
parser.add_argument('--expos_comp',action = 'store', default = 'no',help='Exposure compensation method. The default is "gain_blocks".',type=str,dest = 'expos_comp' )
parser.add_argument('--expos_comp_nr_feeds',action = 'store', default = 1,help='Number of exposure compensation feed.',type=np.int32,dest = 'expos_comp_nr_feeds' )
parser.add_argument('--expos_comp_nr_filtering',action = 'store', default = 2,help='Number of filtering iterations of the exposure compensation gains',type=float,dest = 'expos_comp_nr_filtering' )
parser.add_argument('--expos_comp_block_size',action = 'store', default = 32,help='BLock size in pixels used by the exposure compensator.',type=np.int32,dest = 'expos_comp_block_size' )
parser.add_argument('--blend',action = 'store', default = 'multiband',help='Blending method. The default is "multiband".',type=str,dest = 'blend' )
parser.add_argument('--blend_strength',action = 'store', default = 5,help='Blending strength from [0,100] range.',type=int,dest = 'blend_strength' )
parser.add_argument('--blend_strength',action = 'store', default = 5,help='Blending strength from [0,100] range.',type=np.int32,dest = 'blend_strength' )
parser.add_argument('--output',action = 'store', default = 'result.jpg',help='The default is "result.jpg"',type=str,dest = 'output' )
parser.add_argument('--timelapse',action = 'store', default = None,help='Output warped images separately as frames of a time lapse movie, with "fixed_" prepended to input file names.',type=str,dest = 'timelapse' )
parser.add_argument('--rangewidth',action = 'store', default = -1,help='uses range_width to limit number of images to match with.',type=int,dest = 'rangewidth' )
......@@ -119,10 +122,16 @@ elif args.expos_comp=='gain':
expos_comp_type = cv.detail.ExposureCompensator_GAIN
elif args.expos_comp=='gain_blocks':
expos_comp_type = cv.detail.ExposureCompensator_GAIN_BLOCKS
elif args.expos_comp=='channel':
expos_comp_type = cv.detail.ExposureCompensator_CHANNELS
elif args.expos_comp=='channel_blocks':
expos_comp_type = cv.detail.ExposureCompensator_CHANNELS_BLOCKS
else:
print("Bad exposure compensation method")
exit
exit()
expos_comp_nr_feeds = args.expos_comp_nr_feeds
expos_comp_nr_filtering = args.expos_comp_nr_filtering
expos_comp_block_size = args.expos_comp_block_size
match_conf = args.match_conf
seam_find_type = args.seam
blend_type = args.blend
......@@ -180,7 +189,7 @@ for name in img_names:
img = cv.resize(src=full_img, dsize=None, fx=seam_scale, fy=seam_scale, interpolation=cv.INTER_LINEAR_EXACT)
images.append(img)
if matcher_type== "affine":
matcher = cv.detail.AffineBestOf2NearestMatcher_create(False, try_cuda, match_conf)
matcher = cv.detail_AffineBestOf2NearestMatcher(False, try_cuda, match_conf)
elif range_width==-1:
matcher = cv.detail.BestOf2NearestMatcher_create(try_cuda, match_conf)
else:
......@@ -189,14 +198,14 @@ p=matcher.apply2(features)
matcher.collectGarbage()
if save_graph:
f = open(save_graph_to,"w")
# f.write(matchesGraphAsString(img_names, pairwise_matches, conf_thresh))
f.write(cv.detail.matchesGraphAsString(img_names, p, conf_thresh))
f.close()
indices=cv.detail.leaveBiggestComponent(features,p,0.3)
img_subset =[]
img_names_subset=[]
full_img_sizes_subset=[]
num_images=len(indices)
for i in range(0,num_images):
for i in range(len(indices)):
img_names_subset.append(img_names[indices[i,0]])
img_subset.append(images[indices[i,0]])
full_img_sizes_subset.append(full_img_sizes[indices[i,0]])
......@@ -273,26 +282,33 @@ for i in range(0,num_images):
masks.append(um)
warper = cv.PyRotationWarper(warp_type,warped_image_scale*seam_work_aspect) # warper peut etre nullptr?
for i in range(0,num_images):
K = cameras[i].K().astype(np.float32)
for idx in range(0,num_images):
K = cameras[idx].K().astype(np.float32)
swa = seam_work_aspect
K[0,0] *= swa
K[0,2] *= swa
K[1,1] *= swa
K[1,2] *= swa
corner,image_wp =warper.warp(images[i],K,cameras[i].R,cv.INTER_LINEAR, cv.BORDER_REFLECT)
corner,image_wp =warper.warp(images[idx],K,cameras[idx].R,cv.INTER_LINEAR, cv.BORDER_REFLECT)
corners.append(corner)
sizes.append((image_wp.shape[1],image_wp.shape[0]))
images_warped.append(image_wp)
p,mask_wp =warper.warp(masks[i],K,cameras[i].R,cv.INTER_NEAREST, cv.BORDER_CONSTANT)
masks_warped.append(mask_wp)
p,mask_wp =warper.warp(masks[idx],K,cameras[idx].R,cv.INTER_NEAREST, cv.BORDER_CONSTANT)
masks_warped.append(mask_wp.get())
images_warped_f=[]
for img in images_warped:
imgf=img.astype(np.float32)
images_warped_f.append(imgf)
compensator=cv.detail.ExposureCompensator_createDefault(expos_comp_type)
compensator.feed(corners, images_warped, masks_warped)
if cv.detail.ExposureCompensator_CHANNELS == expos_comp_type:
compensator = cv.detail_ChannelsCompensator(expos_comp_nr_feeds)
# compensator.setNrGainsFilteringIterations(expos_comp_nr_filtering)
elif cv.detail.ExposureCompensator_CHANNELS_BLOCKS == expos_comp_type:
compensator=cv.detail_BlocksChannelsCompensator(expos_comp_block_size, expos_comp_block_size,expos_comp_nr_feeds)
# compensator.setNrGainsFilteringIterations(expos_comp_nr_filtering)
else:
compensator=cv.detail.ExposureCompensator_createDefault(expos_comp_type)
compensator.feed(corners=corners, images=images_warped, masks=masks_warped)
if seam_find_type == "no":
seam_finder = cv.detail.SeamFinder_createDefault(cv.detail.SeamFinder_NO)
elif seam_find_type == "voronoi":
......@@ -332,7 +348,7 @@ for idx,name in enumerate(img_names): # https://github.com/opencv/opencv/blob/ma
cameras[i].focal *= compose_work_aspect
cameras[i].ppx *= compose_work_aspect
cameras[i].ppy *= compose_work_aspect
sz = (full_img.shape[1] * compose_scale,full_img.shape[0] * compose_scale)
sz = (full_img_sizes[i][0] * compose_scale,full_img_sizes[i][1]* compose_scale)
K = cameras[i].K().astype(np.float32)
roi = warper.warpRoi(sz, K, cameras[i].R);
corners.append(roi[0:2])
......@@ -353,21 +369,20 @@ for idx,name in enumerate(img_names): # https://github.com/opencv/opencv/blob/ma
seam_mask = cv.resize(dilated_mask,(mask_warped.shape[1],mask_warped.shape[0]),0,0,cv.INTER_LINEAR_EXACT)
mask_warped = cv.bitwise_and(seam_mask,mask_warped)
if blender==None and not timelapse:
blender = cv.detail.Blender_createDefault(1)
dst_sz = cv.detail.resultRoi(corners,sizes)
blend_strength=1
blender = cv.detail.Blender_createDefault(cv.detail.Blender_NO)
dst_sz = cv.detail.resultRoi(corners=corners,sizes=sizes)
blend_width = np.sqrt(dst_sz[2]*dst_sz[3]) * blend_strength / 100
if blend_width < 1:
blender = cv.detail.Blender_createDefault(cv.detail.Blender_NO)
elif blend_type == "MULTI_BAND":
blender = cv.detail.Blender_createDefault(cv.detail.Blender_MULTIBAND)
elif blend_type == "multiband":
blender = cv.detail_MultiBandBlender()
blender.setNumBands((np.log(blend_width)/np.log(2.) - 1.).astype(np.int))
elif blend_type == "FEATHER":
blender = cv.detail.Blender_createDefault(cv.detail.Blender_FEATHER)
elif blend_type == "feather":
blender = cv.detail_FeatherBlender()
blender.setSharpness(1./blend_width)
blender.prepare(corners, sizes)
blender.prepare(dst_sz)
elif timelapser==None and timelapse:
timelapser = cv.detail.createDefault(timelapse_type);
timelapser = cv.detail.Timelapser_createDefault(timelapse_type)
timelapser.initialize(corners, sizes)
if timelapse:
matones=np.ones((image_warped_s.shape[0],image_warped_s.shape[1]), np.uint8)
......@@ -379,9 +394,14 @@ for idx,name in enumerate(img_names): # https://github.com/opencv/opencv/blob/ma
fixedFileName = img_names[idx][:pos_s + 1 ]+"fixed_" + img_names[idx][pos_s + 1: ]
cv.imwrite(fixedFileName, timelapser.getDst())
else:
blender.feed(image_warped_s, mask_warped, corners[idx])
blender.feed(cv.UMat(image_warped_s), mask_warped, corners[idx])
if not timelapse:
result=None
result_mask=None
result,result_mask = blender.blend(result,result_mask)
cv.imwrite(result_name,result)
zoomx =600/result.shape[1]
dst=cv.normalize(src=result,dst=None,alpha=255.,norm_type=cv.NORM_MINMAX,dtype=cv.CV_8U)
dst=cv.resize(dst,dsize=None,fx=zoomx,fy=zoomx)
cv.imshow(result_name,dst)
cv.waitKey()
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment