HALCON 杂记

1.emphasize — Enhance contrast of the image.   增强图像对比度

  emphasize(Image : ImageEmphasize : MaskWidth, MaskHeight, Factor : ) 

 

read_image(Image,'mreut')
dev_display (Image)
*手动划区域 draw_region(Region,WindowHandle) reduce_domain(Image,Region,Mask) emphasize(Mask,Sharp,
7,7,2.0) dev_display (Sharp)

 2.draw_region — Interactive drawing of a closed region   手动画一个封闭任意区域

3.set_rgb( : : WindowHandle, Red, Green, Blue : )   rgb值来设置颜色

4.harmonic_interpolation — Perform a harmonic interpolation on an image region.   

 

 5.gen_binocular_rectification_map  -----Generate transformation maps that describe the mapping of the images of a binocular camera pair to a common rectified image plane.

 

复制代码
* Set internal and external stereo parameters.
* Note that, typically, these values are the result of a prior
* calibration.
gen_cam_par_area_scan_division (0.01, -665, 5.2e-006, 5.2e-006, \
                                622, 517, 1280, 1024, CamParam1)
gen_cam_par_area_scan_division (0.01, -731, 5.2e-006, 5.2e-006, \
                                654, 519, 1280, 1024, CamParam2)
create_pose (0.1535,-0.0037,0.0447,0.17,319.84,359.89, \
             'Rp+T', 'gba', 'point', RelPose)

* Compute the mapping for rectified images.
gen_binocular_rectification_map (Map1, Map2, CamParam1, CamParam2, \
                                 RelPose, 1,'viewing_direction', 'bilinear',\
                                 CamParamRect1, CamParamRect2, \
                                 CamPoseRect1, CamPoseRect2, \
                                 RelPoseRect)

* Compute the disparities in online images.
while (1)
  grab_image_async (Image1, AcqHandle1, -1)
  map_image (Image1, Map1, ImageMapped1)

  grab_image_async (Image2, AcqHandle2, -1)
  map_image (Image2, Map2, ImageMapped2)

  binocular_disparity(ImageMapped1, ImageMapped2, Disparity, Score, \
                      'sad', 11, 11, 20, -40, 20, 2, 25, \
                      'left_right_check', 'interpolation')
endwhile
复制代码

6.binocular_disparity — Compute the disparities of a rectified image pair using correlation techniques.

 

 7.binocular_distance — Compute the distance values for a rectified stereo image pair using correlation techniques.

使用相关技术计算校正立体图像对的距离值。

8.disparity_image_to_xyz — Transform a disparity image into 3D points in a rectified stereo system.   

将视差图像转换为校正立体系统中的 3D 点。

9.xyz_attrib_to_object_model_3d — Transform 3D points from images to a 3D object model, and add extended attributes to the points of the object model. 

将 3D 点从图像转换为 3D 对象模型,并向对象模型的点添加扩展属性。

xyz_attrib_to_object_model_3d (X, Y, Z, ImageRGB, ['&red', '&green', '&blue'], ObjectModel3D)
prepare_object_model_3d (ObjectModel3D, 'segmentation', 'true', [], [])
visualize_object_model_3d (WindowHandle, ObjectModel3D, [], [], ['red_channel_attrib', 'green_channel_attrib', 'blue_channel_attrib'], ['&red', '&green', '&blue'], [], [], [], PoseOut)

10.prepare_object_model_3d — Prepare a 3D object model for a certain operation.

复制代码
* This example program shows the usage of the procedure
* xyz_attrib_to_object_model_3d.
* It can be used to create 3D object models from X, Y and Z images,
* and simultaneously attach attributes to every point.
*
* Initialization
dev_update_off ()
dev_close_window ()
*
* Read the digital surface model.
read_image (Z, 'mreut_dgm_2.0.tif')
get_image_size (Z, Width, Height)
*
* Read image that contains the gray values that will be added
* to the 3D object model as attribute.
read_image (AerialImage, 'mreut4_3.png')
*
* Generate a label image with a second attribute.
* In this case, we label different terrain types very simply,
* just for demonstration purposes.
auto_threshold (AerialImage, Regions, 4)
region_to_label (Regions, LabelImage, 'byte', Width, Height)
*
* Create a multichannel image from both attribute images.
compose2 (AerialImage, LabelImage, MultiChannelAttribImage)
*
* Create images that contain X and Y coordinates in a regular grid.
* For a simple gray ramp, the input parameters of
* gen_image_surface_first_order are very simple:
GroundResolution := 2.0
gen_image_surface_first_order (X, 'real', 0, GroundResolution, 0, 0, 0, Width, Height)
gen_image_surface_first_order (Y, 'real', -GroundResolution, 0, 0, 0, 0, Width, Height)
*
* The following procedure creates a 3D object model from
* the X, Y and Z image and adds the information contained
* in the attribute image to each point.
AttribName := ['&gray','&terrain']
xyz_attrib_to_object_model_3d (X, Y, Z, MultiChannelAttribImage, AttribName, ObjectModel3D)
*
* Display results
*
dev_open_window (Height / 2, 0, Width / 2, Height / 2, 'black', WindowHandle1)
dev_set_part (0, 0, Height - 1, Width - 1)
set_display_font (WindowHandle1, 16, 'mono', 'true', 'false')
dev_set_color (['red','green','blue'])
dev_set_draw ('fill')
dev_display (Regions)
disp_message (WindowHandle1, 'Terrain types', 'window', 12, 12, 'black', 'true')
*
dev_open_window (0, 0, Width / 2, Height / 2, 'black', WindowHandle2)
set_display_font (WindowHandle2, 16, 'mono', 'true', 'false')
dev_display (AerialImage)
disp_message (WindowHandle2, 'Aerial image', 'window', 12, 12, 'black', 'true')
*
dev_open_window (0, Width / 2 + 8, Width, Height, 'gray', WindowHandle3)
set_display_font (WindowHandle3, 16, 'mono', 'true', 'false')
dev_display (Z)
*
disp_message (WindowHandle3, 'Digital surface model', 'window', 12, 12, 'black', 'true')
disp_continue_message (WindowHandle3, 'black', 'true')
stop ()
*
* Perform fast triangulation of the object model for better visualization.
prepare_object_model_3d (ObjectModel3D, 'segmentation', 'true', [], [])
* Visualize 3d object model interactively
create_pose (-620, -85, 17000, 135, 2, 10, 'Rp+T', 'gba', 'point', Pose)
Instructions := 'Rotate: Left button'
Instructions[1] := 'Zoom: Shift + left button'
Instructions[2] := 'Move: Ctrl + left button'
visualize_object_model_3d (WindowHandle3, ObjectModel3D, [], Pose, ['color_attrib','color_attrib_start','color_attrib_end'], ['&gray',0,255], ['Created 3D model','Attribute used for visualization: \'&gray\''], [], Instructions, PoseOut)
visualize_object_model_3d (WindowHandle3, ObjectModel3D, [], PoseOut, ['color_attrib','lut'], ['&terrain','color1'], ['Created 3D model','Attribute used for visualization: \'&terrain\''], [], Instructions, PoseOut)
disp_end_of_program_message (WindowHandle3, 'black', 'true')
复制代码

11.get_domain — Get the domain of an image.    输入图像转为一个区域

The operator get_domain returns the definition domains of all input images as a region.

12.complement — Return the complement of a region.   返回一个区域的补集

13.full_domain — Expand the domain of an image to maximum.

将映像的域扩展到最大

 

posted @   echo-efun  阅读(112)  评论(0编辑  收藏  举报
相关博文:
阅读排行:
· 阿里最新开源QwQ-32B,效果媲美deepseek-r1满血版,部署成本又又又降低了!
· 单线程的Redis速度为什么快?
· SQL Server 2025 AI相关能力初探
· AI编程工具终极对决:字节Trae VS Cursor,谁才是开发者新宠?
· 展开说说关于C#中ORM框架的用法!
点击右上角即可分享
微信分享提示