导航

    • 登录
    • 搜索
    • 版块
    • 产品
    • 教程
    • 论坛
    • 淘宝
    1. 主页
    2. cg26
    C
    • 举报资料
    • 资料
    • 关注
    • 粉丝
    • 屏蔽
    • 帖子
    • 楼层
    • 最佳
    • 群组

    cg26

    @cg26

    0
    声望
    3
    楼层
    413
    资料浏览
    0
    粉丝
    0
    关注
    注册时间 最后登录

    cg26 关注

    cg26 发布的帖子

    • RE: 多颜色识别 串口发送数据 颜色识别成功 发送的时候错误

      串口的函数写错了 但是我改回来了 还是不行 还是一样的错误

      发布在 OpenMV Cam
      C
      cg26
    • 多颜色识别 串口发送数据 颜色识别成功 发送的时候错误

      0_1600162319732_b6af11df-0e5f-4d11-9412-99346cf7b007-image.png

      我已经崩溃了
      # Single Color RGB565 Blob Tracking Example
      #
      # This example shows off single color RGB565 tracking using the OpenMV Cam.
      
      import sensor, image, time, math
      from pyb import UART
      
      threshold_index = 0 # 0 for red, 1 for green, 2 for blue
      foxiang=0
      shuihu=0
      dingshuji=0
      output_shuju=0
      
      # Color Tracking Thresholds (L Min, L Max, A Min, A Max, B Min, B Max)
      # The below thresholds track in general red/green/blue things. You may wish to tune them...
      thresholds = [(100, 10, 127, -128, -33, -128), # 订书机
                    (34, 58, -128, 127, 32, 127), # 佛像阈值
                    (7, 58, 15, 38, -30, 11)] #紫色水壶阈值
      
      uart = UART(3, 115200)
      
      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()
      
          
      while(True):
          clock.tick()
          img = sensor.snapshot()
          for blob    in  img.find_blobs([thresholds[1]], pixels_threshold=2000, area_threshold=2000,merge=True):
                  foxiang=blob
                  img.draw_rectangle(blob.rect(),(255,0,0))        #画框
                  img.draw_cross(blob.cx(), blob.cy())    #通过读取到的坐标在图像中心画十字
          if foxiang:
                   print("佛像坐标为",blob[5],blob[6])
          for blob    in  img.find_blobs([thresholds[2]], pixels_threshold=2000, area_threshold=2000,merge=True):
                       shuihu=blob
                       img.draw_rectangle(blob.rect(),(0,255,0)) 
                       img.draw_cross(blob.cx(), blob.cy())
          if  shuihu   :
              print("水壶的坐标为",blob[5],blob[6])
          for blob    in  img.find_blobs([thresholds[0]], pixels_threshold=300, area_threshold=300,merge=True):
                           dingshuji=blob
                           img.draw_rectangle(blob.rect(),(0,0,255)) 
                           img.draw_cross(blob.cx(), blob.cy())
          if  dingshuji   :
               print("蓝色物体的坐标为",blob[5],blob[6])
               output_shuju="[%d,%d]" % (blob.cx(),blob.cy())
               usrt.write(output_shuju'\r\n')
          print(clock.fps())里粘贴
      
      发布在 OpenMV Cam
      C
      cg26
    • 颜色识别 索引问题 超出索引

      0_1600083359914_b8708381-a0fe-40c4-9ef9-397476047a55-image.png

      为什么我这样索引会有错误呢?我已经赋值给他了 不是应该跟blob的数值相等吗?

      threshold_index = 0 # 0 for red, 1 for green, 2 for blue
      foxiang=0
      shuihu=0
      dingshuji=0
      
      # Color Tracking Thresholds (L Min, L Max, A Min, A Max, B Min, B Max)
      # The below thresholds track in general red/green/blue things. You may wish to tune them...
      thresholds = [(100, 20, -122, 127, -128, 127), # 黑色阈值
                    (34, 58, -128, 127, 32, 127), # 佛像阈值
                    (7, 58, 15, 38, -30, 11)] #紫色水壶阈值
      
      
      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()
      
      
      while(True):
          clock.tick()
          img = sensor.snapshot()
          foxiang=img.find_blobs([thresholds[1]])
          if foxiang:
              print("坐标为",foxiang[5])
          print(clock.fps())
      
      
      发布在 OpenMV Cam
      C
      cg26