如果你发现OpenCV函数繁多！！！
如果你发现OpenCV配置繁琐！！！
如果你发现自己买不起miniPC！！！
请选择OpenMV来完成你的项目吧！！！
新篇章新阶段，来自其他小白提醒
OpenMV，其目标是成为机器视觉界的“Arduino”，它以STM32CPU为核心，提供Python的编程接口，成本低，拓展性好，不仅能够用来进行图像处理，还可以当作一个普通的单片机使用。OpenMV的像素较小，所以适用范围是一些对精度要求不高的视觉任务，例如：扫码，色块检测，目标跟踪，以及 一些简单的机器学习任务（当然，这里仅仅介绍与视觉有关的内容，除非你想用它去做嵌入式开发）。
OpenMV的安装不需要像OpenMV一样配置一系列的环境，非常简便！！！
具体安装步骤可参考官网：
OpenMV IDE安装 | 星瞳科技singtown.com/learn/49989/
如果你想尽快的对OpenMV的功能做出了解，并能够通过代码去实现简单的功能，可以参考如下材料：
10分钟快速上手 · OpenMV中文入门教程book.openmv.cc/quick-starter.html正在上传…重新上传取消
如果我们去网页搜索我们想要完成的任务，我们搜到的基本都是使用OpenCV实现的代码，关于OpenMV的博客显然屈指可数，在这种情况下IDE中的示例则显得尤为重要，而官方的函数手册则更为重要了。
例如我们想进行色块检测并打印图中的色块摆放的顺序结果编码（如图从左向右从上向下编码为123312）1——红，2——绿，3——蓝：
首先我们可以在示例中发现multi_color_blob_tracking.py的例程：
# Multi Color Blob Tracking Example
#
# This example shows off multi color blob tracking using the OpenMV Cam.
import sensor, image, time, math
# Color Tracking Thresholds (L Min, L Max, A Min, A Max, B Min, B Max)
# The below thresholds track in general red/green things. You may wish to tune them...
thresholds = [(30, 100, 15, 127, 15, 127), # generic_red_thresholds
(30, 100, -64, -8, -32, 32), # generic_green_thresholds
(0, 15, 0, 40, -80, -20)] # generic_blue_thresholds
# You may pass up to 16 thresholds above. However, it's not really possible to segment any
# scene with 16 thresholds before color thresholds start to overlap heavily.
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()
# Only blobs that with more pixels than "pixel_threshold" and more area than "area_threshold" are
# returned by "find_blobs" below. Change "pixels_threshold" and "area_threshold" if you change the
# camera resolution. Don't set "merge=True" becuase that will merge blobs which we don't want here.
while(True):
clock.tick()
img = sensor.snapshot()
for blob in img.find_blobs(thresholds, pixels_threshold=200, 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())
# 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(clock.fps())
根据例程如何得到我们想要的程序呢？代码中的img.find_blobs（）很明显是一个Lists，代表着很多个色块对象，我们想要获取色块位置就需要知道包络色块的矩形框的信息，这些信息都包含在这个对象的成员中。这就需要用到函数手册
https://docs.openmv.io/docs.openmv.io/
我们搜索Blobs这个类可以看到其成员，之后的事情就是我们自己写代码了，通过调用其成员对色块进行筛选和处理，最终打印位置编码。
最终的程序和结果如下：
#color_test
# Multi Color Blob Tracking Example
#
# This example shows off multi color blob tracking using the OpenMV Cam.
import sensor, image, time, math
# Color Tracking Thresholds (L Min, L Max, A Min, A Max, B Min, B Max)
# The below thresholds track in general red/green things. You may wish to tune them...
thresholds = [(38, 65, 49, 114, -8, 113), # generic_red_thresholds
(30, 80, -62, -33, -30, 74), # generic_green_thresholds
(27, 56, -40, 59, -86, -41)] # generic_blue_thresholds
# You may pass up to 16 thresholds above. However, it's not really possible to segment any
# scene with 16 thresholds before color thresholds start to overlap heavily.
thresholds_red=((38, 65, 49, 114, -8, 113))
thresholds_green=((30, 80, -62, -33, -30, 74))
thresholds_blue=((27, 56, -40, 59, -86, -41))
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()
# Only blobs that with more pixels than "pixel_threshold" and more area than "area_threshold" are
# returned by "find_blobs" below. Change "pixels_threshold" and "area_threshold" if you change the
# camera resolution. Don't set "merge=True" becuase that will merge blobs which we don't want here.
while(True):
clock.tick()
img = sensor.snapshot()
blobs_red=img.find_blobs([thresholds_red], pixels_threshold=200, area_threshold=200)
blobs_green=img.find_blobs([thresholds_green], pixels_threshold=200, area_threshold=200)
blobs_blue=img.find_blobs([thresholds_blue], pixels_threshold=200, area_threshold=200)
for blobs in blobs_red:
img.draw_rectangle(blobs.rect())
for blobs in blobs_green:
img.draw_rectangle(blobs.rect())
for blobs in blobs_blue:
img.draw_rectangle(blobs.rect())
if len(blobs_red)==2:
if blobs_red[0].cy()<blobs_red[1].cy():
blobs_red_on=blobs_red[0]
blobs_red_under=blobs_red[1]
else:
blobs_red_on=blobs_red[1]
blobs_red_under=blobs_red[0]
else:
continue
if len(blobs_green)==2:
if blobs_green[0].cy()<blobs_green[1].cy():
blobs_green_on=blobs_green[0]
blobs_green_under=blobs_green[1]
else:
blobs_green_on=blobs_green[1]
blobs_green_under=blobs_green[0]
else:
continue
if len(blobs_blue)==2:
if blobs_blue[0].cy()<blobs_blue[1].cy():
blobs_blue_on=blobs_blue[0]
blobs_blue_under=blobs_blue[1]
else:
blobs_blue_on=blobs_blue[1]
blobs_blue_under=blobs_blue[0]
else:
continue
color_list="abcdef"
list_on=[blobs_red_on.cx(),blobs_green_on.cx(),blobs_blue_on.cx()]
list_under=[blobs_red_under.cx(),blobs_green_under.cx(),blobs_blue_under.cx()]
if min(list_on)==blobs_red_on.cx():
color_list=color_list.replace('a','1')
if max(list_on)==blobs_green_on.cx():
color_list=color_list.replace('c','2')
color_list=color_list.replace('b','3')
else:
color_list=color_list.replace('c','3')
color_list=color_list.replace('b','2')
if min(list_on)==blobs_green_on.cx():
color_list=color_list.replace('a','2')
if max(list_on)==blobs_red_on.cx():
color_list=color_list.replace('c','1')
color_list=color_list.replace('b','3')
else:
color_list=color_list.replace('c','3')
color_list=color_list.replace('b','1')
if min(list_on)==blobs_blue_on.cx():
color_list=color_list.replace('a','3')
if max(list_on)==blobs_red_on.cx():
color_list=color_list.replace('c','1')
color_list=color_list.replace('b','2')
else:
color_list=color_list.replace('c','2')
color_list=color_list.replace('b','1')
if min(list_under)==blobs_red_under.cx():
color_list=color_list.replace('d','1')
if max(list_under)==blobs_green_under.cx():
color_list=color_list.replace('f','2')
color_list=color_list.replace('e','3')
else:
color_list=color_list.replace('f','3')
color_list=color_list.replace('e','2')
if min(list_under)==blobs_green_under.cx():
color_list=color_list.replace('d','2')
if max(list_under)==blobs_red_under.cx():
color_list=color_list.replace('f','1')
color_list=color_list.replace('e','3')
else:
color_list=color_list.replace('f','3')
color_list=color_list.replace('e','1')
if min(list_under)==blobs_blue_under.cx():
color_list=color_list.replace('d','3')
if max(list_under)==blobs_red_under.cx():
color_list=color_list.replace('f','1')
color_list=color_list.replace('e','2')
else:
color_list=color_list.replace('f','2')
color_list=color_list.replace('e','1')
print(color_list)
print(clock.fps())
输出的是“123312”的编码以及帧率。
这里借助这个小例程分析如何基于例程进行程序的移植，希望能够对刚入手OpenMV的小伙伴有所启发。
类似的移植方法也可以用来进行串口通信，二维码的扫描等这些常用的功能。
OpenMV提供了许多帮助调试的小工具，可以在界面——工具一栏中找到，例如在上述例程中需要标定thresholds，则点击“工具——视觉终端——阈值编辑器”可以方便的调整阈值进行标定，只需要记录下各阈值即可。
希望可以为大家快速上手OpenMV有所帮助！！！
参考资料：
OpenMV IDE安装 | 星瞳科技singtown.com/learn/49989/
Overview — MicroPython 1.15 documentation
本文内容由网友自发贡献，版权归原作者所有，本站不承担相应法律责任。如您发现有涉嫌抄袭侵权的内容，请联系:hwhale#tublm.com(使用前将#替换为@)
