# Race_G

**Repository Path**: missper/race_g

## Basic Information

- **Project Name**: Race_G
- **Description**: 2020电子设计竞赛G题 非接触物体尺寸形态测量
郑铁无线电协会2021720~2021724模拟电赛第二题 
- **Primary Language**: Python
- **License**: GPL-3.0
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 6
- **Forks**: 0
- **Created**: 2021-07-28
- **Last Updated**: 2026-04-01

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# About OpenMV

> 参考这个打开串口: [Python背景知识 · OpenMV中文入门教程](https://book.openmv.cc/python-background.html)

## 产品型号

在串口终端中输入: `import sys;print(sys.version)`

得到产品型号: 

> MicroPython v1.12-omv-2-g1e4e3ec80 OpenMV v3.6.9-4-gc90f9cc7-dirty 2020-11-07; 
>
> OPENMV4P-STM32H743
>
> 镜头: ov5460-MOD R3

# 使用串口(UART)

在串口终端中输入: `help()`: 

```bash
Welcome to MicroPython!

For online help please visit http://micropython.org/help/.

Quick overview of commands for the board:
  pyb.info()    -- print some general information
  pyb.delay(n)  -- wait for n milliseconds
  pyb.millis()  -- 获取自硬复位以来的毫秒数
  pyb.Switch()  -- create a switch object
                   Switch methods: (), callback(f)
  pyb.LED(n)    -- create an LED object for LED n (n=1,2,3,4)
                   LED methods: on(), off(), toggle(), intensity(<n>)
  pyb.Pin(pin)  -- get a pin, eg pyb.Pin('X1')
  pyb.Pin(pin, m, [p]) -- get a pin and configure it for IO mode m, pull mode p
                   Pin methods: init(..), value([v]), high(), low()
  pyb.ExtInt(pin, m, p, callback) -- create an external interrupt object
  pyb.ADC(pin)  -- make an analog object from a pin
                   ADC methods: read(), read_timed(buf, freq)
  pyb.DAC(port) -- make a DAC object
                   DAC methods: triangle(freq), write(n), write_timed(buf, freq)
  pyb.RTC()     -- make an RTC object; methods: datetime([val])
  pyb.rng()     -- get a 30-bit hardware random number
  pyb.Servo(n)  -- create Servo object for servo n (n=1,2,3,4)
                   Servo methods: calibration(..), angle([x, [t]]), speed([x, [t]])
  pyb.Accel()   -- create an Accelerometer object
                   Accelerometer methods: x(), y(), z(), tilt(), filtered_xyz()

Pins are numbered X1-X12, X17-X22, Y1-Y12, or by their MCU name
Pin IO modes are: pyb.Pin.IN, pyb.Pin.OUT_PP, pyb.Pin.OUT_OD
Pin pull modes are: pyb.Pin.PULL_NONE, pyb.Pin.PULL_UP, pyb.Pin.PULL_DOWN
Additional serial bus objects: pyb.I2C(n), pyb.SPI(n), pyb.UART(n)

Control commands:
  CTRL-A        -- on a blank line, enter raw REPL mode
  CTRL-B        -- on a blank line, enter normal REPL mode
  CTRL-C        -- interrupt a running program
  CTRL-D        -- on a blank line, do a soft reset of the board
  CTRL-E        -- on a blank line, enter paste mode

For further help on a specific object, type help(obj)
For a list of available modules, type help('modules')
```





# 控制电机(Servo)

查看当前电机配置

`Servo.calibration([pulse_min, pulse_max, pulse_centre, pulse_angle_90, pulse_speed_100])`

* 若未给定参数，这个函数返回当前的5元组校准数据。

* 若给定参数，该函数设定计时校准：

> - `pulse_min` 是允许的最小脉宽。
> - `pulse_max` 是允许的最大脉冲。
> - `pulse_centre` 是中心/零位置对应的脉宽。
> - `pulse_angle_90` 是90度对应的脉宽。
> - `pulse_speed_100` 是速度100对应的脉宽。

```python
# hobby - By: 22598 - 周三 7月 21 2021

# https://docs.singtown.com/micropython/zh/latest/openmvcam/library/pyb.Servo.html#servo-hobby
import pyb

s1 = pyb.Servo(1) # 对应P7口输出PWM

# while True:
s1.angle(0) # 转到指定角度
print(s1.calibration()) # (640, 2420, 1500, 2470, 2200)
```



# [`sensor`](https://docs.singtown.com/micropython/zh/latest/openmvcam/library/omv.sensor.html#module-sensor) — 感光元件





# Image对象

[ OpenMV 图片对象（目标识别基础）_handsomeswp的专栏-CSDN博客_openmv图像识别](https://blog.csdn.net/handsomeswp/article/details/108901689)

```python
# Image - By: 22598 - 周三 7月 21 2021

import sensor, image, time, pyb

sensor.reset()
sensor.set_pixformat(sensor.RGB565) # RGB565 GRAYSCALE
sensor.set_framesize(sensor.VGA) #FHD QVGA
sensor.skip_frames(time = 0) # 2000
sensor.set_auto_whitebal(False) # 关闭白平衡
# sensor.set_vflip(True) 垂直翻转

clock = time.clock()

# grenn_threshold = (38,98,-79,-23,0,50) # 绿色乒乓球
# yellow_threshold = (21,65,-36,38,20,50) # 乒乓球
yellow_threshold = (25,48,18,42,22,38) # 协会后面的排球


def find_max(blobs):
    max_size=0
    for blob in blobs:
        if blob[2]*blob[3] > max_size:
            max_blob=blob
            max_size=blob[2]*blob[3]
    return max_blob



while(True):
    img = sensor.snapshot()
    img.draw_cross(160, 120, 10, 10) # 以像素坐标 (x, y) 为中心画个十字。
    # img.draw_rectangle(150, 110, 20, 20) # 矩形 x,y,x_length,y_length
    # img.draw_circle(160, 120, 10) # 以像素坐标 (x, y) 为圆心, diameter 为直径画一个圆。
    print(clock.fps())
    blobs = img.find_blobs([yellow_threshold])
    if len(blobs)>0:
        tar_blob=find_max(blobs)
        diameter=tar_blob.corners()[1][0] - tar_blob.corners()[0][0]
        img.draw_circle(tar_blob.cx(),tar_blob.cy(),diameter)
        img.draw_cross(tar_blob.cx(),tar_blob.cy())
        print(tar_blob.rect())
```







# 图像二值化滤波

滤波之后可精确框选出目标物体, 





* 神经网络模型
* 模板匹配   [template_matching 模板匹配 · OpenMV中文入门教程](https://book.openmv.cc/example/09-Feature-Detection/template-matching.html)
* keypoints特征点检测 [keypoints 特征点检测 · OpenMV中文入门教程](https://book.openmv.cc/example/09-Feature-Detection/keypoints.html)
* AprilTag识别
* 颜色追踪
* LBP特征  [目标检测的图像特征提取之（二）LBP特征 - 莫小 - 博客园 (cnblogs.com)](https://www.cnblogs.com/nsnow/p/4461998.html)
* HOG梯度特征-多用于行人检测  [HOG特征（Histogram of Gradient）学习总结 - wyu123 - 博客园 (cnblogs.com)](https://www.cnblogs.com/wyuzl/p/6792216.html)



滤波   图像处理   特征点提取  



阈值确定二维物体,

​	

特征点匹配,模板匹配确定三维物体