openMV使用---找到图像中的圆形
主要想实现一个功能，就是找到图像中固定大小的圆形，然后将其标记出来。
openmv给的示例程序中有相关程序，今天主要对该程序进行讲解，并改进。
import sensor, image, time
sensor.reset()#重启摄像头
#设置为彩色， 颜色格式为RGB565
# 也就是说，颜色存储 红色（5位），绿色（6位）， 蓝色（5位）
# sensor.GRAYSCALE: 灰度，每个像素8位。
sensor.set_pixformat(sensor.RGB565) # grayscale is faster
#设置图像的大小
#就是你拍摄的画面的长和宽分别是多少个像素点
#sensor.QQQQCIF: 22x18
#sensor.QQQCIF: 44x36
#sensor.QQCIF: 88x72
#sensor.QCIF: 176x144
#sensor.CIF: 352x288
#sensor.QQQQSIF: 22x15
#sensor.QQQSIF: 44x30
#sensor.QQSIF: 88x60
#sensor.QSIF: 176x120
#sensor.SIF: 352x240
#sensor.QQQQVGA: 40x30
#sensor.QQQVGA: 80x60
#sensor.QQVGA: 160x120
#sensor.QVGA: 320x240
#sensor.VGA: 640x480
#sensor.HQQQQVGA: 40x20
#sensor.HQQQVGA: 80x40
#sensor.HQQVGA: 160x80
#sensor.HQVGA: 240x160
#sensor.HVGA: 480x320
#sensor.LCD: 128x160 (for use with the lcd shield)
#sensor.QQVGA2: 128x160 (for use with the lcd shield)
#sensor.B40x30: 160x120 (for use with image.find_displacement)
#sensor.B64x32: 160x120 (for use with image.find_displacement)
#sensor.B64x64: 160x120 (for use with image.find_displacement)
#sensor.SVGA: 800x600 (only in JPEG mode for the OV2640 sensor)
#sensor.SXGA: 1280x1024 (only in JPEG mode for the OV2640 sensor)
#sensor.UXGA: 1600x1200 (only in JPEG mode for the OV2640 sensor)
sensor.set_framesize(sensor.QQVGA)#表示拍摄画面的大小为160×120像素
#因为sensor参数设定之后， 图像质量不稳定， 要过一段时间。 跳过n张照片，在更改
#设置后，跳过一些帧，等待感光元件变稳定。这里是跳过2000毫秒
sensor.skip_frames(time = 2000)
#创建一个时钟对象来追踪FPS
#FPS是测量用于保存、显示动态视频的信息数量。通俗来讲就是指每秒变化的画面数。
clock = time.clock()
while(True):
clock.tick() #每次循环更新时钟
# 拍摄一张照片，snapshot()函数返回一个image对象
#lens_corr函数用于非鱼眼畸变矫正，默认设置参数为1.8，
#然后根据图像情况进行调整
img = sensor.snapshot().lens_corr(1.8)
# threshold:设置要找到圆的个数，阈值越大，表示要找的圆越少
#`x_margin`, `y_margin`, and `r_margin`：控制相似圆的合并，就是说多大范围的圆，
#将其认为是同一个圆。
#r_min, r_max, and r_step：控制圆的大小范围，就是说我想找半径在这个范围内的圆
for c in img.find_circles(threshold = 2000, x_margin = 10, y_margin = 10, r_margin = 10,
r_min = 2, r_max = 100, r_step = 2):
img.draw_circle(c.x(), c.y(), c.r(), color = (255, 0, 0))
print(c)
print("FPS %f" % clock.fps())
以上代码效果不是很好，添加边缘增强滤波，以及使用灰度图像之后，效果好很多。
import sensor, image, time
kernel_size = 1 # kernel width = (size*2)+1, kernel height = (size*2)+1
kernel = [-1, -1, -1,\
-1, +8, -1,\
-1, -1, -1]
thresholds = [(100, 255)] # grayscale thresholds
sensor.reset()#
sensor.set_pixformat(sensor.GRAYSCALE) # grayscale is faster
sensor.set_framesize(sensor.QQVGA)
sensor.skip_frames(time = 2000)
clock = time.clock()
while(True):
clock.tick()
img = sensor.snapshot().lens_corr(1.8)
img.morph(kernel_size, kernel)
img.binary(thresholds)
# Circle objects have four values: x, y, r (radius), and magnitude. The
# magnitude is the strength of the detection of the circle. Higher is
# better...
# `threshold` controls how many circles are found. Increase its value
# to decrease the number of circles detected...
# `x_margin`, `y_margin`, and `r_margin` control the merging of similar
# circles in the x, y, and r (radius) directions.
# r_min, r_max, and r_step control what radiuses of circles are tested.
# Shrinking the number of tested circle radiuses yields a big performance boost.
for c in img.find_circles(threshold = 3000, x_margin = 10, y_margin = 10, r_margin = 10,
r_min = 2, r_max = 10, r_step = 2):
if c.r()>28 and c.r()<38:
img.draw_circle(c.x(), c.y(), c.r(), color = (255,255, 255))
print(c)
print("FPS %f" % clock.fps())
