今日光电 有人说,20世纪是电的世纪,21世纪是光的世纪;知光解电,再小的个体都可以被赋能。追光逐电,光赢未来...欢迎来到今日光电!

----追光逐电 光赢未来----

作者:DoubleLi

来源:https://www.cnblogs.com/lidabo/p/15931138.html

1. 为什么要拼接如果你的被射物足够小;如果你的镜头视野足够大;如果你的银子足够多,可以买更牛的相机,更牛的镜头。。。

如果你没有那么多的如果,项目多了,图像拼接在所难免。

2. 效果是啥借助Halcon自带的例子,就是将下面两张图像,拼接为一个更宽的图像。

图像1:

图像2:

拼接后的图像:

有没有变得更宽?

3. 拼接步骤读取图像

提取特征点

计算变换矩阵

拼接

参考Halcon例程proj_match_points_distortion_ransac.hdev,逐步分析。该例程是基于特征点来拼接图像的。

3.1. 读取图像并显示图像代码:

read_image (Image1, 'building_01')read_image (Image2, 'building_02')get_image_size (Image1, Width, Height)dev_close_window ()dev_open_window (0, 0, Width, Height, 'white', WindowHandle)set_display_font (WindowHandle, 16, 'mono', 'true', 'false')dev_display (Image1)disp_message (WindowHandle, 'Image 1 to be matched', 'image', -1, -1, 'black', 'true')disp_continue_message (WindowHandle, 'black', 'true')stop ()dev_display (Image2)disp_message (WindowHandle, 'Image 2 to be matched', 'image', -1, -1, 'black', 'true')disp_continue_message (WindowHandle, 'black', 'true')

效果:

3.2. 获取特征点该例程是基于图像的特征点进行拼接图像的,需要获取两张图像的特征点。何为特征点?根据算子points_foerstner的解释,特征点有两类,一类名为交点特征点,指的是那些图像边沿的点,另一类称作区域特征点,如,图像的颜色和亮度与周围不同的点。

代码:

points_foerstner (Image1, 1, 2, 3, 50, 0.1, 'gauss', 'true', Rows1, Columns1, CoRRJunctions, CoRCJunctions, CoCCJunctions, RowArea, ColumnArea, CoRRArea, CoRCArea, CoCCArea)points_foerstner (Image2, 1, 2, 3, 50, 0.1, 'gauss', 'true', Rows2, Columns2, CoRRJunctions, CoRCJunctions, CoCCJunctions, RowArea, ColumnArea, CoRRArea, CoRCArea, CoCCArea)

3.3. 计算仿射变换矩阵根据两幅图像的特征点,计算出仿射变换矩阵。

代码:

proj_match_points_ransac (Image1, Image2, Rows1, Columns1, Rows2, Columns2, 'ncc', 10, 0, 0, Height, Width, 0, 0.5, 'gold_standard', 2, 42, HomMat2DUnrectified, Points1Unrectified, Points2Unrectified)

3.3. 拼接根据仿射变换矩阵进行拼接。

代码:

concat_obj (Image1, Image2, Images)gen_projective_mosaic (Images, MosaicImageUnrectified, 1, 1, 2, HomMat2DUnrectified, 'default', 'false', MosaicMatrices2DUnrectified)

效果:

显示接缝代码:

projective_trans_pixel (MosaicMatrices2DUnrectified[9:17], [0,493], [0,0], RowTrans, ColumnTrans)gen_contour_polygon_xld (Contour, RowTrans, ColumnTrans)

接缝效果:

仔细观察图像拼接的接缝处,发现拼接的效果并不理想,接缝是错开的。原因是两张图像的径向畸变造成的。何为径向畸变?这是镜头固有的,当焦距很大或很小时,拍出的图像尤其明显,图像的边缘处向前凹,或者向里凸的效果,仔细观察原来的两张图像,边缘处是向里凸进去的。

课外知识相机内参数:

f:相机的主矩,即焦距k:径向扭曲的大小,即径向畸变,一般不考虑切向畸变sx,sy:图像传感器在水平和垂直方向上相邻像素之间的距离cx,cy: 投影中心在成像平面的垂直投影

相机外参数:

平移向量X,Y,Z旋转向量X,Y,Z透视矫正

相机的内外参数是相机标定的重点。

因此,例程的后半部分就是消除这种径向畸变对拼接的影响,Halcon中有对应的算子,使用起来很方便。

4. 消除径向畸变4.1. 读出图像同上

4.2. 计算仿射变换矩阵注意,使用了消除径向畸变的算子。代码:

proj_match_points_distortion_ransac (Image1, Image2, Rows1, Columns1, Rows2, Columns2, 'ncc', 10, 0, 0, Height, Width, 0, 0.5, 'gold_standard', 1, 42, HomMat2D, Kappa, Error, Points1, Points2)

4.3. 预处理消除图像中的镜像畸变。

代码:

CamParDist := [0.0,Kappa,1.0,1.0,0.5 * (Width - 1),0.5 * (Height - 1),Width,Height]change_radial_distortion_cam_par ('fixed', CamParDist, 0, CamPar)change_radial_distortion_image (Image1, Image1, Image1Rect, CamParDist, CamPar)change_radial_distortion_image (Image2, Image2, Image2Rect, CamParDist, CamPar)

效果:

图像1(原图)

图像1(去除径向畸变后)

图像2(原图)

图像2(去除径向畸变后)第一组图效果不是很明显,仔细观察第二组图,两个边缘是不是被拉平了?

4.4. 图像拼接同上。

最终的效果:

仔细观察接缝处,这次图像拼接的很好。

5. 代码完整代码如下:

* This example shows how to use proj_match_points_distortion_ransac to* match two images in a mosaicking application.* 该例子说明在拼接应用中,如何使用proj_match_points_distortion_ransac算子* 拼接两张图片(基于特征点匹配拼接图像)* * Initialization* 初始化dev_update_off ()* Read and display the images* 读取并显示图像read_image (Image1, 'building_01')read_image (Image2, 'building_02')get_image_size (Image1, Width, Height)dev_close_window ()dev_open_window (0, 0, Width, Height, 'white', WindowHandle)set_display_font (WindowHandle, 16, 'mono', 'true', 'false')dev_display (Image1)disp_message (WindowHandle, 'Image 1 to be matched', 'image', -1, -1, 'black', 'true')disp_continue_message (WindowHandle, 'black', 'true')stop ()dev_display (Image2)disp_message (WindowHandle, 'Image 2 to be matched', 'image', -1, -1, 'black', 'true')disp_continue_message (WindowHandle, 'black', 'true')stop ()* * Extract points to be matched from the images* 获取特征点points_foerstner (Image1, 1, 2, 3, 50, 0.1, 'gauss', 'true', Rows1, Columns1, CoRRJunctions, CoRCJunctions, CoCCJunctions, RowArea, ColumnArea, CoRRArea, CoRCArea, CoCCArea)points_foerstner (Image2, 1, 2, 3, 50, 0.1, 'gauss', 'true', Rows2, Columns2, CoRRJunctions, CoRCJunctions, CoCCJunctions, RowArea, ColumnArea, CoRRArea, CoRCArea, CoCCArea)* * We will first perform a normal projective matching that does not take* the radial distortions into account to show the errors that are caused* by neglecting the radial distortions.* 首先,不考虑径向畸变的情况下,执行图像拼接,我们会看到由于径向畸变的影响* 接缝处的拼接效果并不理想proj_match_points_ransac (Image1, Image2, Rows1, Columns1, Rows2, Columns2, 'ncc', 10, 0, 0, Height, Width, 0, 0.5, 'gold_standard', 2, 42, HomMat2DUnrectified, Points1Unrectified, Points2Unrectified)* Construct a projective mosaic from the two unrectified images.* 将两个未修改(有径向畸变)的图像构造为一个投影拼接(projective mosaic)concat_obj (Image1, Image2, Images)gen_projective_mosaic (Images, MosaicImageUnrectified, 1, 1, 2, HomMat2DUnrectified, 'default', 'false', MosaicMatrices2DUnrectified)* * Display unrectified results* 显示结果get_image_size (MosaicImageUnrectified, Width, Height)dev_set_window_extents (-1, -1, Width, Height)dev_clear_window ()dev_display (MosaicImageUnrectified)* Display seam line* 显示拼接缝隙projective_trans_pixel (MosaicMatrices2DUnrectified[9:17], [0,493], [0,0], RowTrans, ColumnTrans)gen_contour_polygon_xld (Contour, RowTrans, ColumnTrans)set_line_style (WindowHandle, [1,5])dev_set_line_width (1)dev_set_color ('yellow')dev_display (Contour)set_line_style (WindowHandle, [])dev_set_draw ('margin')dev_set_color ('red')dev_set_line_width (3)gen_circle (Circle, [82,402], [228,223], [15,15])dev_display (Circle)* 从结果看,不考虑径向畸变的情况下,接缝处的拼接效果并不理想,接缝处是错开的Message := 'The mosaic image does not fit'Message[1] := 'perfectly, if radial distortions'Message[2] := 'are not taken into account.'disp_message (WindowHandle, Message, 'image', 200, 300, 'black', 'true')disp_continue_message (WindowHandle, 'black', 'true')stop ()* * Now, we will perform a projective matching that takes the radial* distortions into account.* 这次,去除径向畸变的影响,再次执行拼接get_image_size (Image1, Width, Height)proj_match_points_distortion_ransac (Image1, Image2, Rows1, Columns1, Rows2, Columns2, 'ncc', 10, 0, 0, Height, Width, 0, 0.5, 'gold_standard', 1, 42, HomMat2D, Kappa, Error, Points1, Points2)* Construct camera parameters for the purpose of rectifying the images,* i.e., to remove the radial distortions.* 为了修改图像,构造相机参数* 如,去除径向畸变CamParDist := [0.0,Kappa,1.0,1.0,0.5 * (Width - 1),0.5 * (Height - 1),Width,Height]* Remove the radial distortions from the images.* 去除图像中的径向畸变change_radial_distortion_cam_par ('fixed', CamParDist, 0, CamPar)change_radial_distortion_image (Image1, Image1, Image1Rect, CamParDist, CamPar)change_radial_distortion_image (Image2, Image2, Image2Rect, CamParDist, CamPar)* Construct a mosaic from the two rectified images. Note that the images* fit together perfectly.* 使用去除了径向畸变的图像构造拼接图像* 可以看到图像拼接的很好concat_obj (Image1Rect, Image2Rect, ImagesRect)gen_projective_mosaic (ImagesRect, MosaicImage, 1, 1, 2, HomMat2D, 'default', 'false', MosaicMatrices2D)* * Display rectified results* 显示修改后的结果get_image_size (MosaicImage, Width, Height)dev_set_window_extents (-1, -1, Width, Height)dev_clear_window ()dev_display (MosaicImage)* Display seam line* 显示接缝projective_trans_pixel (MosaicMatrices2D[9:17], [0,493], [0,0], RowTrans, ColumnTrans)gen_contour_polygon_xld (Contour2, RowTrans, ColumnTrans)set_line_style (WindowHandle, [1,5])dev_set_line_width (1)dev_set_color ('yellow')dev_display (Contour2)set_line_style (WindowHandle, [])dev_set_draw ('margin')dev_set_color ('green')dev_set_line_width (3)gen_circle (Circle, [124,496], [244,239], [15,15])dev_display (Circle)Message := 'The mosaic image fits perfectly,'Message[1] := 'if radial distortions are taken'Message[2] := 'into account.'disp_message (WindowHandle, Message, 'image', 200, 300, 'black', 'true')* 输出拼接后的图像write_image(MosaicImage, 'bmp', 0,'result.bmp')

资料

Halcon例程和帮助文档

利用halcon进行图像拼接的基本教程来源:机械视觉沙龙

申明:感谢原创作者的辛勤付出。本号转载的文章均会在文中注明,若遇到版权问题请联系我们处理。

----与智者为伍 为创新赋能----

【说明】欢迎企业和个人洽谈合作,投稿发文。欢迎联系我们诚招运营合伙人 ,对新媒体感兴趣,对光电产业和行业感兴趣。非常有意者通过以下方式联我们!条件待遇面谈投稿丨合作丨咨询联系邮箱:uestcwxd@126.com

QQ:493826566