@kidswong999 ok了！！！ 完美的想哭， 我换成灰度图了

利用“histogram.get_threshold()”得到最佳阈值后，想使用“threshold.value()”拿出阈值，失败了..

THRESHOLD = [0, 100] # Grayscale threshold for dark things...
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
from pyb import LED

sensor.reset()
sensor.set_pixformat(sensor.GRAYSCALE)
sensor.set_framesize(sensor.QQQVGA) # 80x60 (4,800 pixels) - O(N^2) max = 2,3040,000.
sensor.skip_frames(time = 2000)     # WARNING: If you use QQVGA it may take seconds
clock = time.clock()                # to process a frame sometimes.

LED(1).on()
LED(2).on()
LED(3).on()

while(True):
    clock.tick()
    img = sensor.snapshot().lens_corr(strength = 0.5, zoom = 1.0)
    img.gaussian(3, unsharp=True)

    histogram = img.get_histogram()#得到直方图
    Thresholds = histogram.get_threshold()#得到最佳阈值
    THR=threshold.value()#获取当前阈值

    #img.binary([THRESHOLD])if BINARY_VISIBLE else sensor.snapshot()

    line = img.get_regression([(255,255) if BINARY_VISIBLE else THRESHOLD], robust = True)

    if (line): img.draw_line(line.line(), color = 127)

想做一个巡线小车，用的是手动阈值，发现这个阈值太依赖环境了，换个环境就很不准确了，不知道怎么办，
尝试使用自适应阈值，但是非目标颜色也会选中

@kidswong999 好像传不了 bmp

import sensor, image, time,machine
from pyb import LED

sensor.reset()
sensor.set_vflip(False)
sensor.set_hmirror(False)
sensor.set_pixformat(sensor.RGB565)
sensor.set_framesize(sensor.QQVGA) # 80x60 (4,800 pixels) - O(N^2) max = 2,3040,000.
#sensor.set_windowing([0,20,80,40])
sensor.skip_frames(time = 2000)     # WARNING: If you use QQVGA it may take seconds
clock = time.clock()                # to process a frame sometimes.


LED(1).on()
LED(2).on()
LED(3).on()


while(True):
    clock.tick()
    img = sensor.snapshot().lens_corr(strength = 0.5, zoom = 1.0)
    #img=sensor.snapshot().save("lvbo_2.jpg")  #获取图像
    img.bilateral(3,color_sigma=0.1,space_sigma=0.1)#采用双边滤波
    img.gaussian(3, unsharp=True,)#图像消除锐化
    histogram = img.get_histogram()
    Thresholds = histogram.get_threshold()
    img.binary(threshold)
    print(Thresholds)



    #line = img.get_regression([(100,100,0,0,0,0)], robust = True)

    #if(line):img.draw_line(line.line(), color = 127)

    #print(clock.fps()


我更改了图片格式以及大小，依旧持续报错，主要原因应该是那句“copy_to_fb=True”,不执行这一句，不报错
@kidswong999

我更改了图片格式以及大小，依旧持续报错，主要原因应该是那句“copy_to_fb=True”,不执行这一句，不报错
@15342342443

想使用OTSU算法，找到了“histogram.get_threhsold()”函数，但是在传参数的时候一直报错，希望大佬解救