HALCON示例程序forest.hdev識別森林中的樹

示例程序源碼（加注釋）

• 關于顯示類函數解釋
  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)
• 分割連通域
  connection (BlueBright, BlueBrightConnection)
• 通過面積進行區域篩選
  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 ()
• 二值化紅色通道圖像
  threshold (Red, RedBright, 120, 255)
• 分割連通域
  connection (RedBright, RedBrightConnection)
• 使用面積進行區域篩選
  select_shape (RedBrightConnection, RedBrightBig, ‘area’, ‘and’, 1500, 10000000)
• 使用圓形元素進行閉運算
  closing_circle (RedBrightBig, RedBrightClosing, 7.5)
• 使用圓形元素進行開運算
  opening_circle (RedBrightClosing, RedBrightOpening, 9.5)
• 分割連通域
  connection (RedBrightOpening, RedBrightOpeningConnection)
• 使用面積進行區域篩選
  select_shape (RedBrightOpeningConnection, BeechBig, ‘area’, ‘and’, 1000, 100000000)
• 使用區域的平均灰度進行區域篩選
  select_gray (BeechBig, Blue, Beech, ‘mean’, ‘and’, 0, 59)
  dev_display (Red)
  dev_display (Beech)
  disp_continue_message (WindowHandle, ‘black’, ‘true’)
  stop ()
• 聯合區域
  union1 (Beech, BeechUnion)
• 返回區域的補集
  complement (BeechUnion, NotBeech)
• 求取兩區域不相交部分
  difference (NotBeech, Path, NotBeechNotPath)
• 縮小定義域
  reduce_domain (Red, NotBeechNotPath, NotBeechNotPathRed)
• 二值化
  threshold (NotBeechNotPathRed, BrightRest, 150, 255)
• 分割連通域
  connection (BrightRest, BrightRestConnection)
• 通過面積篩選區域
  select_shape (BrightRestConnection, Meadow, ‘area’, ‘and’, 500, 1000000)
  dev_display (Red)
  dev_display (Meadow)
  disp_continue_message (WindowHandle, ‘black’, ‘true’)
  stop ()
• 將兩個對象合為一個對象
  union2 (Path, RedBrightClosing, BeechPath)
• smooth_image - 使用各種濾鏡平滑圖像。
• smooth_image（原圖：平滑后的圖像：濾波器，濾波參數:)
  smooth_image (Red, RedGauss, ‘gauss’, 4.0)
• invert_image - 反轉圖像。
  invert_image (RedGauss, Invert)
• watersheds - 從圖像中提取流域和盆地。
• watersheds （圖片：盆地，流域::）
  watersheds (Invert, SpruceRed, Watersheds)
• 通過面積與灰度進行區域篩選
  select_shape (SpruceRed, SpruceRedLarge, ‘area’, ‘and’, 100, 5000)
  select_gray (SpruceRedLarge, Red, SpruceRedInitial, ‘max’, ‘and’, 100, 200)
• 生成一個空對象
  gen_empty_obj (LocalThresh)
• 計算對象數量
  count_obj (SpruceRedInitial, NumSpruce)
  dev_update_var (‘off’)
  dev_update_pc (‘off’)
  for i := 1 to NumSpruce by 1
  • 在組員對象中選取指定對象
    select_obj (SpruceRedInitial, SingleSpruce, i)
  • 求取最大最小灰度值，當第三個參數設置為50時返回中值
    min_max_gray (SingleSpruce, Red, 50, Min, Max, Range)
  • 減少定義域
    reduce_domain (Red, SingleSpruce, SingleSpruceRed)
  • 二值化
    threshold (SingleSpruceRed, SingleSpruceBright, Min, 255)
  • 分割連通域
    connection (SingleSpruceBright, SingleSpruceBrightCon)
  • 選取最大面積的區域
    select_shape_std (SingleSpruceBrightCon, MaxAreaSpruce, ‘max_area’, 70)
  • 將多個區域合并到一個組員下，但不改變對象個數
    concat_obj (MaxAreaSpruce, LocalThresh, LocalThresh)

endfor

• 開運算
  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)

處理思路

這個例子是主要講解了如何通過無人機拍攝的圖像識別其中的對象。smooth_image 、watersheds 等算子被應用。

后記
大家有什么問題可以向我提問哈，我看到了第一時間回復，希望在學習的路上多多結交良師益友。