HALCON示例程序forest.hdev識(shí)別森林中的樹(shù)

示例程序源碼（加注釋）

• 關(guān)于顯示類(lèi)函數(shù)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(guò)面積進(jìn)行區(qū)域篩選
  select_shape (BlueBrightConnection, Path, ‘a(chǎn)rea’, ‘a(chǎn)nd’, 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(jìn)行區(qū)域篩選
  select_shape (RedBrightConnection, RedBrightBig, ‘a(chǎn)rea’, ‘a(chǎn)nd’, 1500, 10000000)
• 使用圓形元素進(jìn)行閉運(yùn)算
  closing_circle (RedBrightBig, RedBrightClosing, 7.5)
• 使用圓形元素進(jìn)行開(kāi)運(yùn)算
  opening_circle (RedBrightClosing, RedBrightOpening, 9.5)
• 分割連通域
  connection (RedBrightOpening, RedBrightOpeningConnection)
• 使用面積進(jìn)行區(qū)域篩選
  select_shape (RedBrightOpeningConnection, BeechBig, ‘a(chǎn)rea’, ‘a(chǎn)nd’, 1000, 100000000)
• 使用區(qū)域的平均灰度進(jìn)行區(qū)域篩選
  select_gray (BeechBig, Blue, Beech, ‘mean’, ‘a(chǎn)nd’, 0, 59)
  dev_display (Red)
  dev_display (Beech)
  disp_continue_message (WindowHandle, ‘black’, ‘true’)
  stop ()
• 聯(lián)合區(qū)域
  union1 (Beech, BeechUnion)
• 返回區(qū)域的補(bǔ)集
  complement (BeechUnion, NotBeech)
• 求取兩區(qū)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(guò)面積篩選區(qū)域
  select_shape (BrightRestConnection, Meadow, ‘a(chǎn)rea’, ‘a(chǎn)nd’, 500, 1000000)
  dev_display (Red)
  dev_display (Meadow)
  disp_continue_message (WindowHandle, ‘black’, ‘true’)
  stop ()
• 將兩個(gè)對(duì)象合為一個(gè)對(duì)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(shù):)
  smooth_image (Red, RedGauss, ‘gauss’, 4.0)
• invert_image - 反轉(zhuǎn)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(guò)面積與灰度進(jìn)行區(qū)域篩選
  select_shape (SpruceRed, SpruceRedLarge, ‘a(chǎn)rea’, ‘a(chǎn)nd’, 100, 5000)
  select_gray (SpruceRedLarge, Red, SpruceRedInitial, ‘max’, ‘a(chǎn)nd’, 100, 200)
• 生成一個(gè)空對(duì)象
  gen_empty_obj (LocalThresh)
• 計(jì)算對(duì)象數(shù)量
  count_obj (SpruceRedInitial, NumSpruce)
  dev_update_var (‘off’)
  dev_update_pc (‘off’)
  for i := 1 to NumSpruce by 1
  • 在組員對(duì)象中選取指定對(duì)象
    select_obj (SpruceRedInitial, SingleSpruce, i)
  • 求取最大最小灰度值，當(dāng)?shù)谌齻€(gè)參數(shù)設(shè)置為50時(shí)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(qū)域
    select_shape_std (SingleSpruceBrightCon, MaxAreaSpruce, ‘max_area’, 70)
  • 將多個(gè)區(qū)域合并到一個(gè)組員下，但不改變對(duì)象個(gè)數(shù)
    concat_obj (MaxAreaSpruce, LocalThresh, LocalThresh)

endfor

• 開(kāi)運(yùn)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(gè)例子是主要講解了如何通過(guò)無(wú)人機(jī)拍攝的圖像識(shí)別其中的對(duì)象。smooth_image 、watersheds 等算子被應(yīng)用。

后記
大家有什么問(wèn)題可以向我提問(wèn)哈，我看到了第一時(shí)間回復(fù)，希望在學(xué)習(xí)的路上多多結(jié)交良師益友。

總結(jié)

以上是生活随笔為你收集整理的HALCON示例程序forest.hdev识别森林中的树的全部?jī)?nèi)容，希望文章能夠幫你解決所遇到的問(wèn)題。

如果覺(jué)得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。