• 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。
  • 为什么这个程序他只能识别出红色?



    • import sensor, image, time, math
       
      # Color Tracking Thresholds (L Min, L Max, A Min, A Max, B Min, B Max)
      # The below thresholds track in general red/green things. You may wish to tune them...
      thresholds = [(13, 30, 1, 45, -24, 47), # generic_red_thresholds
                   (23, 55, -44, -24, -2, 39), # generic_green_thresholds
                   (0, 15, 0, 40, -80, -20)] # generic_blue_thresholds
      # You may pass up to 16 thresholds above. However, it's not really possible to segment any
      # scene with 16 thresholds before color thresholds start to overlap heavily.
       
      sensor.reset()
      sensor.set_pixformat(sensor.RGB565)
      sensor.set_framesize(sensor.QVGA)
      sensor.skip_frames(time = 2000)
      sensor.set_auto_gain(False) # must be turned off for color tracking
      sensor.set_auto_whitebal(False) # must be turned off for color tracking
      clock = time.clock()
       
      # Only blobs that with more pixels than "pixel_threshold" and more area than "area_threshold" are
      # returned by "find_blobs" below. Change "pixels_threshold" and "area_threshold" if you change the
      # camera resolution. Don't set "merge=True" becuase that will merge blobs which we don't want here.
       
       
      while(True):
         clock.tick()
         red=[]
         green=[]
         blue=[]
         shit=[]
         order=[]
         img = sensor.snapshot().lens_corr(1.8)
         for r in img.find_rects(threshold = 10000):
             img.draw_rectangle(r.rect(), color = (255, 0, 0))
             for p in r.corners(): img.draw_circle(p[0], p[1], 5, color = (0, 255, 0))
             area = (r.rect())
             #area为识别到的矩形的区域
             statistics = img.get_statistics(roi=area)#像素颜色统计i=0,j=0,n=0
             #print(statistics)
             #(0,100,0,120,0,120)是红色的阈值
             #l_mode(),a_mode(),b_mode()是L通道,A通道,B通道的众数。
             if 8<statistics.l_mode()<20 and 10<statistics.a_mode()<45 and 0<statistics.b_mode()<36:
       
                img.draw_rectangle(area, color = (255, 0, 0))#识别到的红色矩形用红色的矩形框出来
                if 1.8<(r.w()/r.h())<2.2:
       
                     red.append(r.y())
       
                elif (0.8<(r.w()/r.h())<1.2):
       
       
                     red.append(r.y())
                     red.append(r.y()-r.h()/2)
       
       
                 elif (0.5<=(r.w()/r.h())<=0.79):
       
                     red.append(r.y()-2*r.h()/3)
                     red.append(r.y()-r.h()/3)
                     red.append(r.y())
       
             if 30<statistics.l_mode()<51 and -45<statistics.a_mode()<-21 and 9<statistics.b_mode()<46:
       
                 img.draw_rectangle(area, color = (255, 0, 0))
                 if 1.8<=r.w()/r.h()<=2.2:
       
                     green.append(r.y())
       
                 elif(0.8<=r.w()/r.h()<=1.2):
       
                     green.append(r.y())
                     green.append(r.y()-r.h()/2)
       
                 elif(0.5<=r.w()/r.h()<0.8):
       
                     green.append(r.y())
                     green.append(r.y()-2*r.h()/3)
                     green.append(r.y()-r.h()/3)
       
             if 44<statistics.l_mode()<55 and -30<statistics.a_mode()<-5 and -24<statistics.b_mode()<0:
       
                 img.draw_rectangle(area, color = (255, 0, 0))
                 if 1.8<=r.w()/r.h()<=2.2:
       
                     blue.append(r.y())
       
                 elif(0.8<=r.w()/r.h()<=1.2):
       
                     blue.append(r.y()-r.h()/2)
                     blue.append(r.y())
       
                 elif(0.5<=r.w()/r.h()<0.8):
       
                     blue.append(r.y())
                     blue.append(r.y()-2*r.h()/3)
                     blue.append(r.y()-h/3)
       
         l1=len(red)
         l2=len(green)
         l3=len(blue)
         i=0
         while i<l1:
            shit.append(red[i])
            order.append(3)
            i=i+1
         while i<(l1+l2):
       
             shit.append(green[i-l1])
             order.append(1)
             i=i+1
       
         while i<(l1+l2+l3):
       
             shit.append(blue[i-l1-l2])
             order.append(2)
             i=i+1
       
         i=0
         n=0
         print('red')
         print(red)
         while len(shit)<6:
       
             shit.append(0)
             order.append(0)
             n=n+1
       
          for i in range(5):
             for j in range(5-i):
                 if shit[j]>shit[j+1]:
       
                     shit[j],shit[j+1]=shit[j+1],shit[j]
                     order[j],order[j+1]=order[j+1],order[j]
       
       
       
         print(order)
      


    • 这段代码大致就是六个色块,从上往下排列,一个色块有一种颜色(总共三种),一个数字代表一个色块,然后你按顺序输出对应的数字,但是他最后只能识别到红色,(我觉得我阈值设置的没有问题



    • 在第42行,62行,80行,都加入print,你就能看出来到底是什么。逻辑问题自己慢慢就能挑出来。