HALCON示例程序forest.hdev识别森林中的树

HALCON示例程序forest.hdev识别森林中的树

示例程序源码（加注释）

• 关于显示类函数解释
  dev_close_window ()
  dev_update_window (‘off’)
  read_image (Forest, ‘forest_air1’)
  get_image_size (Forest, Width, Height)
  dev_open_window (0, 0, Width, Height, ‘black’, WindowHandle)
  decompose3 (Forest, Red, Green, Blue)
  dev_display (Red)
• 二值化
  threshold (Blue, BlueBright, 80, 255)
• 分割连通域
  connection (BlueBright, BlueBrightConnection)
• 通过面积进行区域筛选
  select_shape (BlueBrightConnection, Path, ‘area’, ‘and’, 100, 100000000)
  dev_set_color (‘red’)
  dev_set_draw (‘margin’)
  dev_display (Path)
  disp_continue_message (WindowHandle, ‘black’, ‘true’)
  stop ()
• 二值化红色通道图像
  threshold (Red, RedBright, 120, 255)
• 分割连通域
  connection (RedBright, RedBrightConnection)
• 使用面积进行区域筛选
  select_shape (RedBrightConnection, RedBrightBig, ‘area’, ‘and’, 1500, 10000000)
• 使用圆形元素进行闭运算
  closing_circle (RedBrightBig, RedBrightClosing, 7.5)
• 使用圆形元素进行开运算
  opening_circle (RedBrightClosing, RedBrightOpening, 9.5)
• 分割连通域
  connection (RedBrightOpening, RedBrightOpeningConnection)
• 使用面积进行区域筛选
  select_shape (RedBrightOpeningConnection, BeechBig, ‘area’, ‘and’, 1000, 100000000)
• 使用区域的平均灰度进行区域筛选
  select_gray (BeechBig, Blue, Beech, ‘mean’, ‘and’, 0, 59)
  dev_display (Red)
  dev_display (Beech)
  disp_continue_message (WindowHandle, ‘black’, ‘true’)
  stop ()
• 联合区域
  union1 (Beech, BeechUnion)
• 返回区域的补集
  complement (BeechUnion, NotBeech)
• 求取两区域不相交部分
  difference (NotBeech, Path, NotBeechNotPath)
• 缩小定义域
  reduce_domain (Red, NotBeechNotPath, NotBeechNotPathRed)
• 二值化
  threshold (NotBeechNotPathRed, BrightRest, 150, 255)
• 分割连通域
  connection (BrightRest, BrightRestConnection)
• 通过面积筛选区域
  select_shape (BrightRestConnection, Meadow, ‘area’, ‘and’, 500, 1000000)
  dev_display (Red)
  dev_display (Meadow)
  disp_continue_message (WindowHandle, ‘black’, ‘true’)
  stop ()
• 将两个对象合为一个对象
  union2 (Path, RedBrightClosing, BeechPath)
• smooth_image - 使用各种滤镜平滑图像。
• smooth_image（原图：平滑后的图像：滤波器，滤波参数:)
  smooth_image (Red, RedGauss, ‘gauss’, 4.0)
• invert_image - 反转图像。
  invert_image (RedGauss, Invert)
• watersheds - 从图像中提取流域和盆地。
• watersheds （图片：盆地，流域::）
  watersheds (Invert, SpruceRed, Watersheds)
• 通过面积与灰度进行区域筛选
  select_shape (SpruceRed, SpruceRedLarge, ‘area’, ‘and’, 100, 5000)
  select_gray (SpruceRedLarge, Red, SpruceRedInitial, ‘max’, ‘and’, 100, 200)
• 生成一个空对象
  gen_empty_obj (LocalThresh)
• 计算对象数量
  count_obj (SpruceRedInitial, NumSpruce)
  dev_update_var (‘off’)
  dev_update_pc (‘off’)
  for i := 1 to NumSpruce by 1
  • 在组员对象中选取指定对象
    select_obj (SpruceRedInitial, SingleSpruce, i)
  • 求取最大最小灰度值，当第三个参数设置为50时返回中值
    min_max_gray (SingleSpruce, Red, 50, Min, Max, Range)
  • 减少定义域
    reduce_domain (Red, SingleSpruce, SingleSpruceRed)
  • 二值化
    threshold (SingleSpruceRed, SingleSpruceBright, Min, 255)
  • 分割连通域
    connection (SingleSpruceBright, SingleSpruceBrightCon)
  • 选取最大面积的区域
    select_shape_std (SingleSpruceBrightCon, MaxAreaSpruce, ‘max_area’, 70)
  • 将多个区域合并到一个组员下，但不改变对象个数
    concat_obj (MaxAreaSpruce, LocalThresh, LocalThresh)

endfor

• 开运算
  opening_circle (LocalThresh, FinalSpruce, 1.5)
  dev_set_line_width (2)
  dev_set_color (‘red’)
  dev_display (Red)
  dev_display (FinalSpruce)
  dev_set_color (‘green’)
  dev_display (Beech)
  dev_set_color (‘yellow’)
  dev_display (Meadow)

处理思路

这个例子是主要讲解了如何通过无人机拍摄的图像识别其中的对象。smooth_image 、watersheds 等算子被应用。

后记
大家有什么问题可以向我提问哈，我看到了第一时间回复，希望在学习的路上多多结交良师益友。