最大类间方差法的应用（一）

基于OpenMV平台：

1.获取图像

2.利用最大类间方差法进行图像二值化

3.对图像中面积大于阈值的物体进行标注

试验结果示意图：

试验代码：

import sensor, image, time, math, pyb

GRAYSCALE_THRESHOLD = [(0, 64)]

ROIS = [0, 0, 160, 120]

most_pixels = 500

led = pyb.LED(3)                          # Red LED = 1, Green LED = 2, Blue LED = 3, IR LEDs = 4.

def senser_init():                         # 摄像头传感器初始化函数

    sensor.reset()                         # Initialize the camera sensor.

    sensor.set_pixformat(sensor.GRAYSCALE) # use grayscale.

    sensor.set_framesize(sensor.QQVGA)     # use QQVGA for speed.

    sensor.skip_frames(30)                 # Let new settings take affect.

    sensor.set_auto_gain(True)             # must be turned off for color tracking

    sensor.set_auto_whitebal(True)         # must be turned off for color tracking

    return;

def hardware_init():

    led.on()            #亮灯

    time.sleep(100)     #延时150ms

    led.off()           #暗灯

    time.sleep(100)

    return;

def Maximum_interclass_variance_method(grayFrame):

    w = 0

    avgValue = 0

    t = 0

    maxVariance = 0

    statistics_data = grayFrame.get_statistics()

    u = statistics_data.mean()

    histogram_data = grayFrame.get_histogram()    #获取灰度直方图

    histogram_bins = histogram_data.bins()   #获取灰度直方图的列表

    for i in range(len(histogram_bins)):

        w += (histogram_bins[i]+0.0000001)

        avgValue  += i * (histogram_bins[i]+0.0000001)

        t = avgValue/w - u

        variance = t * t * w /(1 - w)

        if(variance > maxVariance):

            maxVariance = variance;

            threshold = i;

    return threshold

#主函数

hardware_init();

senser_init();

while(True):

    img = sensor.snapshot()

    h = Maximum_interclass_variance_method(img);

    GRAYSCALE_THRESHOLD =[(0, h)]

    blobs = img.find_blobs(GRAYSCALE_THRESHOLD, roi=ROIS[0:4], merge=True)

    if blobs:

        for i in range(len(blobs)):

            if blobs[i].pixels() > most_pixels:

                img.draw_rectangle(blobs[i].rect())