@kidswong999 运行起来感觉像是两秒一次处理，前一次图片替换到当前画面，去识别白色色块感觉实时性不高

还有就是刚刚试了一下结构相似性帧差法例程，这个速率很快，而且参数明显，想问下SSIM算法具体是怎么评估出相似性得分的，这个阈值（MIN_TRIGGER_THRESHOLD ）的划分

因为实际需求，想要帧差法处理两帧间距变短，例程现在好像是2s(越快越好)，然后这个clock,tick()函数虽然备注是处理时间，但是还是不知道怎么修改hhh

@kidswong999 救救孩子。

@kidswong999 代码我把没用的删了，求指导

import sensor, image, time, math

from pyb import UART
red_threshold=(0, 58, 42, 75, 21, 127)
green_threshold=(44, 100, -17, -128, 6, 127) 
blue_threshold=(0, 37, 5, 33, -63, -17)
             

sensor.reset()
sensor.set_pixformat(sensor.RGB565)
sensor.set_framesize(sensor.QVGA)
sensor.skip_frames(time = 2000)
sensor.set_auto_gain(False) 
sensor.set_auto_whitebal(False) 
clock = time.clock()
while(True):
            
    clock.tick()
    img = sensor.snapshot().lens_corr(strength = 1.8, zoom = 1.0)
    for code in img.find_qrcodes():
            print(code)
    
    for blob in img.find_blobs([red_threshold], pixels_threshold=100, area_threshold=100):       
        if blob.elongation() > 0.5:
         img.draw_rectangle(blob.rect())
         img.draw_cross(blob.cx(), blob.cy())
         a=blob.cx()
        
         
    
    

    for blob in img.find_blobs([green_threshold], pixels_threshold=100, area_threshold=100):
        if blob.elongation() > 0.5:
         img.draw_rectangle(blob.rect())
         img.draw_cross(blob.cx(), blob.cy())
         b=blob.cx()
         
         
   
    

    for blob in img.find_blobs([blue_threshold], pixels_threshold=100, area_threshold=100):
        if blob.elongation() > 0.5:
         img.draw_rectangle(blob.rect())
         img.draw_cross(blob.cx(), blob.cy())
         c=blob.cx()
        
    
        print("红：",a,"绿：",b,"蓝：",c)
        



        uart = UART(3, 19200)

while(True):
    uart.write(code.payload())
    maxn=max(a,b,c)
    minn=min(a,b,c)
    mn=a+b+c-maxn-minn
    if maxn == a and minn == b:
       uart.write("123")
    elif maxn == a and minn == c:
       uart.write ("132")
    elif maxn == b and minn == a:
       uart.write("231")
    elif maxn == b and minn == c:
       uart.write ("213")
    elif maxn == c and minn == a:
       uart.write("321")
    elif maxn == c and minn == b:
       uart.write ("312")
    
    time.sleep(1000)

@kidswong999 主要是为什么会先去图像里找颜色再进行输出。

import sensor, image, time, math

# 颜色跟踪阈值(L Min, L Max, A Min, A Max, B Min, B Max)
# 下面的阈值跟踪一般红色/绿色的东西。你不妨调整他们...
red_threshold=(45, 79, 10, 127, -128, 127) # generic_red_thresholds
green_threshold=(38, 75, -128, -35, -128, 127) # generic_green_thresholds
blue_threshold=(9, 54, -128, 20, -120, 1) # generic_blue_thresholds
             
# 您最多可以传递16个阈值。
# 但是，在颜色阈值开始重叠之前，实际上不可能使用16个阈值对任何场景进行分段。
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()

# 只有比“pixel_threshold”多的像素和多于“area_threshold”的区域才被
# 下面的“find_blobs”返回。 如果更改相机分辨率，
# 请更改“pixels_threshold”和“area_threshold”。 “merge = True”合并图像中所有重叠的色块。


while(True):
            
    clock.tick()
    
    img = sensor.snapshot()
    for code in img.find_qrcodes():
            print(code)
    for blob in img.find_blobs([red_threshold], pixels_threshold=500, area_threshold=200):
        # These values depend on the blob not being circular - otherwise they will be shaky.
        if blob.elongation() > 0.5:
         
            img.draw_edges(blob.min_corners(), color=(255,0,0))
            img.draw_line(blob.major_axis_line(), color=(0,255,0))
            img.draw_line(blob.minor_axis_line(), color=(0,0,255))
        # These values are stable all the time.
         
        img.draw_rectangle(blob.rect())
        img.draw_cross(blob.cx(), blob.cy())
        a=blob.cx()
        # Note - the blob rotation is unique to 0-180 only.
        img.draw_keypoints([(blob.cx(), blob.cy(), int(math.degrees(blob.rotation())))], size=20)
    
    

    for blob in img.find_blobs([green_threshold], pixels_threshold=500, area_threshold=200):
        # These values depend on the blob not being circular - otherwise they will be shaky.
        if blob.elongation() > 0.5:
         
            img.draw_edges(blob.min_corners(), color=(255,0,0))
            img.draw_line(blob.major_axis_line(), color=(0,255,0))
            img.draw_line(blob.minor_axis_line(), color=(0,0,255))
        # These values are stable all the time.
         
        img.draw_rectangle(blob.rect())
        img.draw_cross(blob.cx(), blob.cy())
        b=blob.cx()
        # Note - the blob rotation is unique to 0-180 only.
        img.draw_keypoints([(blob.cx(), blob.cy(), int(math.degrees(blob.rotation())))], size=20)
   
    

    for blob in img.find_blobs([blue_threshold], pixels_threshold=500, area_threshold=200):
        # These values depend on the blob not being circular - otherwise they will be shaky.
        if blob.elongation() > 0.5:
         
            img.draw_edges(blob.min_corners(), color=(255,0,0))
            img.draw_line(blob.major_axis_line(), color=(0,255,0))
            img.draw_line(blob.minor_axis_line(), color=(0,0,255))
        # These values are stable all the time.
         
        img.draw_rectangle(blob.rect())
        img.draw_cross(blob.cx(), blob.cy())
        c=blob.cx()
        # Note - the blob rotation is unique to 0-180 only.
        img.draw_keypoints([(blob.cx(), blob.cy(), int(math.degrees(blob.rotation())))], size=20)
    
        print("红：",a,"绿：",b,"蓝：",c)
        
import time
from pyb import UART

uart = UART(3, 19200)

while(True):
    uart.write(code.payload())
    maxn=max(a,b,c)
    minn=min(a,b,c)
    mn=a+b+c-maxn-minn
    if maxn == a and minn == b:
       uart.write("123")
    elif maxn == a and minn == c:
       uart.write ("132")
    elif maxn == b and minn == a:
       uart.write("231")
    elif maxn == b and minn == c:
       uart.write ("213")
    elif maxn == c and minn == a:
       uart.write("321")
    elif maxn == c and minn == b:
       uart.write ("312")
    
    time.sleep(1000)

新手哈哈，有点菜的代码。

就是在做颜色识别排序，我把各种颜色的矩形框中心坐标分别赋值给a,b,c.然后运行程序的时候就会出现，当前摄像头视野里如果没有这几种颜色，他就说我未定义，比如我b赋值的是绿色阈值的块中心X坐标，然后我画面里没有绿色，程序就会报未定义的错。

如题，畸变矫正调用例程，画面抖动

就是运行程序的时候，视野里必须有三种颜色的存在，程序才能正常运行，不然会显示某一个颜色defined.