• 免费好用的星瞳AI云服务上线!简单标注,云端训练,支持OpenMV H7和OpenMV H7 Plus。可以替代edge impulse。 https://forum.singtown.com/topic/9519
  • 我们只解决官方正版的OpenMV的问题(STM32),其他的分支有很多兼容问题,我们无法解决。
  • 如果有产品硬件故障问题,比如无法开机,论坛很难解决。可以直接找售后维修
  • 发帖子之前,请确认看过所有的视频教程,https://singtown.com/learn/ 和所有的上手教程http://book.openmv.cc/
  • 每一个新的提问,单独发一个新帖子
  • 帖子需要目的,你要做什么?
  • 如果涉及代码,需要报错提示全部代码文本,请注意不要贴代码图片
  • 必看:玩转星瞳论坛了解一下图片上传,代码格式等问题。
  • 请问这段代码中line.x1 ()*r[4] 这里的*r[4]后得到的结果有什么具体含义吗?



    • ROIS = [ # [ROI, weight]
              (0, 0, 80, 120, 0.5), # You'll need to tweak the weights for you app
              (80, 0, 80, 120, 0.5) # depending on how your robot is setup.
             ]
      weight_sum = 0 #权值和初始化
      #for r in ROIS: weight_sum += r[2] # r[4] is the roi weight.A
             #计算权值和。遍历上面的三个矩形,r[4]即每个矩形的权值。
      # This is called the fast linear regression because we use the least-squares
      # method to fit the line. However, this method is NOT GOOD FOR ANY images that
      # have a lot (or really any) outlier points which corrupt the line fit...
      
      #设置阈值,(0,100)检测黑色线
      THRESHOLD = (0, 100) # Grayscale threshold for dark things...
      
      #设置是否使用img.binary()函数进行图像分割
      BINARY_VISIBLE = True # Does binary first so you can see what the linear regression
                            # is being run on... might lower FPS though.
      
      import sensor, image, time
      import json
      from pyb import UART
      uart = UART(3, 9600)
      sensor.reset()
      sensor.set_pixformat(sensor.GRAYSCALE)
      sensor.set_framesize(sensor.QQVGA)
      sensor.skip_frames(time = 2000)
      clock = time.clock()
      
      while(True):
          clock.tick()
          img = sensor.snapshot().binary([THRESHOLD]) if BINARY_VISIBLE else sensor.snapshot()
          centroid_sum = 0
          for r in ROIS:
            blobs = img.find_blobs(THRESHOLD , roi=r[0:2], merge=True)
          # Returns a line object similar to line objects returned by find_lines() and
          # find_line_segments(). You have x1(), y1(), x2(), y2(), length(),
          # theta() (rotation in degrees), rho(), and magnitude().
          #
          # magnitude() represents how well the linear regression worked. It goes from
          # (0, INF] where 0 is returned for a circle. The more linear the
          # scene is the higher the magnitude.
          #函数返回回归后的线段对象line,有x1(), y1(), x2(), y2(), length(), theta(), rho(), magnitude()参数。
          #x1 y1 x2 y2分别代表线段的两个顶点坐标,length是线段长度,theta是线段的角度。
          #magnitude表示线性回归的效果,它是(0,+∞)范围内的一个数字,其中0代表一个圆。如果场景线性回归的越好,这个值越大。
          line = img.get_regression([(255,255) if BINARY_VISIBLE else THRESHOLD])
          if (line): img.draw_line(line.line(), color = 127)
          arveage_x1 += line.x1 ()*r[4]
          arveage_x2 += line.x2 ()*r[4]
          arveage_y1 += line.y1 ()*r[4]
          arveage_y2 += line.y2 ()*r[4]
          arveage_theta += line.theta()*r[4]
          img.draw_line(arveage_x1,arveage_y1,arveage_x2,arveage_y2, color = 80)
          print("FPS %f, mag = %s" % (clock.fps(), str(line.magnitude()) if (line) else "N/A"))
      
      # About negative rho values:
      #
      # A [theta+0:-rho] tuple is the same as [theta+180:+rho].
          data_out = str(line.theta())
          uart.write(data_out )
          time.sleep(100)
          print("OUT",data_out)
      


    • 注释r中说r[4]为每个矩形的权值,但我仍然不理解坐标乘以权值能得到什么,或者说有什么含义?



    • 这个代码是什么地方的?