4. 如何在识别颜色时过滤掉后方小物块，就是同样的颜色只识别大的，如图只识别前面的红绿蓝，不识别后面的两个色块
  • OpenMV VSCode 扩展发布了，在插件市场直接搜索OpenMV就可以安装
  • 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，需要报错提示与全部代码文本，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。

    • 如何在识别颜色时过滤掉后方小物块，就是同样的颜色只识别大的，如图只识别前面的红绿蓝，不识别后面的两个色块

    • U

      0_1605148033764_6918f042-f42f-49c7-ac62-194454f772b9-image.png

      0
    • U
       

      # Untitled - By: 86183 - 周五 9月 11 2020

import sensor, image, time, math
from pyb import UART

threshold_index = 0
#thresholds = thresholds = [(11, 15, 19, 35, -27, 35), #red
#                           (7, 17, -73, 14, -46, -16), #blue
#                           (11, 68, -87, -22, -27, 58)] #green
thresholds = [(29, 88, 94, 36, 86, -54),
             (7, 63, -3, 77, -31, -69),
             (38, 81, -128, -35, -128, 127) ]

sensor.reset()
sensor.set_vflip(True)      #图像垂直翻转
 #截取图像
sensor.set_pixformat(sensor.RGB565)
sensor.set_framesize(sensor.QVGA)
sensor.skip_frames(time = 2000)
sensor.set_windowing((0,83,320,97))
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()

DetectFlag = False

def draw_keypoints(img, kpts):
    if kpts:
        print(kpts)
        img.draw_keypoints(kpts)
        img = sensor.snapshot()
        time.sleep(1000)
#初始化串口
uart = UART(1, 9600)
uart.init(9600, bits=8, parity=None, stop=1)

def find_max(blobs):
    max_size=0
    for blob in blobs:
        if blob.pixels() > max_size:
            max_blob=blob
            max_size = blob.pixels()
    return max_blob

#初始化变量
x = 0
green_position = 0
send_1 = 0  #颜色识别模块发送的内容
x_red = 0
x_blue = 0
x_green = 0
Num_Blob = 0
while(True):
        clock.tick()
        img = sensor.snapshot()

        blobs = img.find_blobs(thresholds, pixels_threshold=200, area_threshold=200)        
        if blobs:
             max_blob = find_max(blobs)
             img.draw_rectangle(max_blob.rect()) # rect
             img.draw_cross(max_blob.cx(), max_blob.cy()) # cx, cy
               

        for blob in img.find_blobs([thresholds[0]], pixels_threshold=200, area_threshold=200):
            x_red = blob.cx()
            img.draw_rectangle(blob.rect())
        for blob in img.find_blobs([thresholds[1]], pixels_threshold=200, area_threshold=200):
            x_blue = blob.cx()
            img.draw_rectangle(blob.rect())
        for blob in img.find_blobs([thresholds[2]], pixels_threshold=200, area_threshold=200):
            x_green = blob.cx()
            img.draw_rectangle(blob.rect())

        if(x_red < x_green and x_green < x_blue):
            #send_1 = 'RGB'
            send_1 = '321'
        elif(x_red < x_blue and x_blue < x_green):
            #send_1 = 'RBG'
            send_1 = '231'
        elif(x_green < x_red and x_red < x_blue):
            #send_1 = 'GRB'
            send_1 = '312'
        elif(x_green < x_blue and x_blue < x_red):
            #send_1 = 'GBR'
            send_1 = '132'
        elif(x_blue < x_red and x_red < x_green):
            #send_1 = 'BRG'
            send_1 = '213'
        elif(x_blue < x_green and x_green < x_red):
            #send_1 = 'BGR'
            send_1 = '123'
        #发串口
        print('%s' %(send_1))
        uart.write('%s' %(send_1))
        uart.write('\r\n')
        #img.draw_rectangle((0,75,321,103))
      0

    • https://book.openmv.cc/project/zhui-xiao-qiu-de-xiao-8f665d28-project-pan-tilt-md.html

      参考里面的find_max函数。

      0