导航

    • 登录
    • 搜索
    • 版块
    • 产品
    • 教程
    • 论坛
    • 淘宝
    1. 主页
    2. asyh
    A
    • 举报资料
    • 资料
    • 关注
    • 粉丝
    • 屏蔽
    • 帖子
    • 楼层
    • 最佳
    • 群组

    asyh

    @asyh

    0
    声望
    4
    楼层
    328
    资料浏览
    0
    粉丝
    0
    关注
    注册时间 最后登录

    asyh 关注

    asyh 发布的帖子

    • 将模板匹配历程中的灰度改成彩色,会报错,如何修改

      0_1722234891360_b6d3a353-a5a2-453b-a842-57f895acef2e-image.png

      Template Matching Example - Normalized Cross Correlation (NCC)

      This example shows off how to use the NCC feature of your OpenMV Cam to match

      image patches to parts of an image... expect for extremely controlled environments

      NCC is not all to useful.

      WARNING: NCC supports needs to be reworked! As of right now this feature needs

      a lot of work to be made into somethin useful. This script will remain to show

      that the functionality exists, but, in its current state is inadequate.

      import time
      import sensor
      import image
      from image import SEARCH_EX

      from image import SEARCH_DS

      Reset sensor

      sensor.reset()#摄像头重置

      Set sensor settings

      sensor.set_contrast(1)#设置对比度
      sensor.set_gainceiling(16)#自动增益

      Max resolution for template matching with SEARCH_EX is QQVGA

      sensor.set_framesize(sensor.QQVGA)#分辨率大小,最大支持QQVGA

      You can set windowing to reduce the search image.

      sensor.set_windowing(((640-80)//2, (480-60)//2, 80, 60))

      sensor.set_pixformat(sensor.RGB565)#灰度

      Load template.

      Template should be a small (eg. 32x32 pixels) grayscale image.

      #template1 = image.Image("/1.pgm")#模板图片pgm格式
      template4 = image.Image("/4.pgm")#模板图片pgm格式
      template5 = image.Image("/5.pgm")#模板图片pgm格式

      clock = time.clock()

      Run template matching

      while True:
      clock.tick()
      img = sensor.snapshot()

      # find_template(template, threshold, [roi, step, search])
      # ROI: The region of interest tuple (x, y, w, h).
      # Step: The loop step used (y+=step, x+=step) use a bigger step to make it faster.
      # Search is either image.SEARCH_EX for exhaustive search or image.SEARCH_DS for diamond search
      #
      # Note1: ROI has to be smaller than the image and bigger than the template.
      # Note2: In diamond search, step and ROI are both ignored.
      """
      r1 = img.find_template(#调用模板匹配函数
          template1, 0.70, step=4, search=SEARCH_EX
      )  # , roi=(10, 0, 60, 60))#template图片,0.7匹配阈值,roi设置了是在规定区域寻找图像,不设置了默认整个区域寻找
      if r1:#如果找到模板图片
          img.draw_rectangle(r1,color=(0,0,0))
      """
      
      r4 = img.find_template(#调用模板匹配函数
          template4, 0.70, step=4, search=SEARCH_EX
      )  # , roi=(10, 0, 60, 60))#template图片,0.7匹配阈值,roi设置了是在规定区域寻找图像,不设置了默认整个区域寻找
      if r4:#如果找到模板图片
          img.draw_rectangle(r4,color=(255,0,0))
      
      
      r5 = img.find_template(#调用模板匹配函数
          template5, 0.70, step=4, search=SEARCH_EX
      )  # , roi=(10, 0, 60, 60))#template图片,0.7匹配阈值,roi设置了是在规定区域寻找图像,不设置了默认整个区域寻找
      if r5:#如果找到模板图片
          img.draw_rectangle(r5,color=(0,0,0))
      
      print(clock.fps())
      发布在 OpenMV Cam
      A
      asyh
    • 用该代码,2代表2,3代表1,但是方框只会显示一个颜色,而且无论什么数字都能被方框罩住
      # Template Matching Example - Normalized Cross Correlation (NCC)
      #
      # This example shows off how to use the NCC feature of your OpenMV Cam to match
      # image patches to parts of an image... expect for extremely controlled environments
      # NCC is not all to useful.
      #
      # WARNING: NCC supports needs to be reworked! As of right now this feature needs
      # a lot of work to be made into somethin useful. This script will remain to show
      # that the functionality exists, but, in its current state is inadequate.
      
      import time
      import sensor
      import image
      from image import SEARCH_EX
      
      # from image import SEARCH_DS
      
      # Reset sensor
      sensor.reset()#摄像头重置
      
      # Set sensor settings
      sensor.set_contrast(1)#设置对比度
      sensor.set_gainceiling(16)#自动增益
      # Max resolution for template matching with SEARCH_EX is QQVGA
      sensor.set_framesize(sensor.QQVGA)#分辨率大小,最大支持QQVGA
      # You can set windowing to reduce the search image.
      # sensor.set_windowing(((640-80)//2, (480-60)//2, 80, 60))
      sensor.set_pixformat(sensor.GRAYSCALE)#灰度
      
      # Load template.
      # Template should be a small (eg. 32x32 pixels) grayscale image.
      #template1 = image.Image("/1.pgm")#模板图片pgm格式
      template2 = image.Image("/2.pgm")#模板图片pgm格式
      template3 = image.Image("/3.pgm")#模板图片pgm格式
      
      clock = time.clock()
      
      # Run template matching
      while True:
          clock.tick()
          img = sensor.snapshot()
      
          # find_template(template, threshold, [roi, step, search])
          # ROI: The region of interest tuple (x, y, w, h).
          # Step: The loop step used (y+=step, x+=step) use a bigger step to make it faster.
          # Search is either image.SEARCH_EX for exhaustive search or image.SEARCH_DS for diamond search
          #
          # Note1: ROI has to be smaller than the image and bigger than the template.
          # Note2: In diamond search, step and ROI are both ignored.
          """
          r1 = img.find_template(#调用模板匹配函数![1_1722223662403_8f4de3c4653a29c6a9df40b2281ef50.jpg](https://fcdn.singtown.com/92922a81-8e2d-4111-ae6e-6fefb02ad501.jpg) ![0_1722223662402_288e461d9390ea8d52ccbd8164ab3e0.jpg](https://fcdn.singtown.com/e7a5c6e7-7e3c-40eb-9e85-f0e2ec517e66.jpg) 
              template1, 0.70, step=4, search=SEARCH_EX
          )  # , roi=(10, 0, 60, 60))#template图片,0.7匹配阈值,roi设置了是在规定区域寻找图像,不设置了默认整个区域寻找
          if r1:#如果找到模板图片
              img.draw_rectangle(r1,color=(0,0,0))
          """
          r2 = img.find_template(#调用模板匹配函数
              template2, 0.70, step=4, search=SEARCH_EX
          )  # , roi=(10, 0, 60, 60))#template图片,0.7匹配阈值,roi设置了是在规定区域寻找图像,不设置了默认整个区域寻找
          if r2:#如果找到模板图片
              img.draw_rectangle(r2,color=(255,0,0))
      
          r3 = img.find_template(#调用模板匹配函数
              template3, 0.70, step=4, search=SEARCH_EX
          )  # , roi=(10, 0, 60, 60))#template图片,0.7匹配阈值,roi设置了是在规定区域寻找图像,不设置了默认整个区域寻找
          if r3:#如果找到模板图片
              img.draw_rectangle(r3,color=(0,0,0))
      
          print(clock.fps())
      
      
      发布在 OpenMV Cam
      A
      asyh
    • 把录入的数字1去掉后就可以了,为什莫,在NCC模板匹配章节

      0_1722220249566_fe974942-b251-4d7b-b57b-3ddf7fe52b9f-image.png

      发布在 OpenMV Cam
      A
      asyh
    • 请问下我这里探测红绿色的时候,写入了merge=true的时候为啥显示的一直是bound method而不是011

      0_1722156343246_e3fd7ae6-0560-4877-abcd-29e97c1f4685-image.png

      发布在 OpenMV Cam
      A
      asyh