多色识别不同追踪

6f4a

当收到“a”时开启颜色识别，识别到不同颜色执行不同程序，小车有不同的反应，但是一开启摄像头老是识别到不是你设点的颜色，不知道为啥？急用，请帮我看下，非常感谢

This example shows off how to use the find_blobs function to find color

blobs in the image. This example in particular looks for dark green objects.

from pyb import UART
uart = UART(3,9600)
import sensor, image, time
import car
from pid import PID
sensor.reset() # Initialize the camera sensor.
sensor.set_pixformat(sensor.RGB565) # use RGB565.
sensor.set_framesize(sensor.QQVGA) # use QQVGA for speed.
sensor.skip_frames(10) # Let new settings take affect.
sensor.set_auto_gain(False)
sensor.set_auto_whitebal(False) # turn this off.
clock = time.clock() # Tracks FPS.

For color tracking to work really well you should ideally be in a very, very,

very, controlled enviroment where the lighting is constant...

green_threshold =(63, 38, 15, -65, -11, -112)
red_threshold =(41, 13, -78, -13, -24, 72)
blue_threshold =(10, 36, -18, 17, -19, 13)
size_threshold = 10000
x_pid = PID(p=0.5, i=1, imax=100)
h_pid = PID(p=0.05, i=0.1, imax=50)

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

You may need to tweak the above settings for tracking green things...

Select an area in the Framebuffer to copy the color settings.

while True:
if(uart.any()):
data = uart.readline()
print("reseived:",data)
if data.decode().startswith('a'):
while(True):
clock.tick() # Track elapsed milliseconds between snapshots().
img = sensor.snapshot() # Take a picture and return the image.

            blob1 = img.find_blobs([green_threshold])
            blob2 = img.find_blobs([red_threshold])
            blob3 = img.find_blobs([blue_threshold])
            if blob1:
                max_blob = find_max(blob1)
                x_error = max_blob[5]-img.width()/2
                h_error = max_blob[2]*max_blob[3]-size_threshold
                print("x error: ", x_error)
                '''
                for b in blobs:
                    # Draw a rect around the blob.
                    img.draw_rectangle(b[0:4]) # rect
                    img.draw_cross(b[5], b[6]) # cx, cy
                '''
                img.draw_rectangle(max_blob[0:4]) # rect
                img.draw_cross(max_blob[5], max_blob[6]) # cx, cy
                x_output=x_pid.get_pid(x_error,1)
                h_output=h_pid.get_pid(h_error,1)
                print("h_output",h_output)
                car.run(-h_output-x_output,-h_output+x_output)
                print("a")
            elif blob2:
                max_blob = find_max(blob2)
                x_error = max_blob[5]-img.width()/2
                h_error = max_blob[2]*max_blob[3]-size_threshold
                print("x error: ", x_error)
                '''
                for b in blobs:
                    # Draw a rect around the blob.
                    img.draw_rectangle(b[0:4]) # rect
                    img.draw_cross(b[5], b[6]) # cx, cy
                '''
                img.draw_rectangle(max_blob[0:4]) # rect
                img.draw_cross(max_blob[5], max_blob[6])
                uart.write("b")
                time.sleep(1000)
                uart.write("c")
                print("10")
                time.sleep(3000)
                print("11")
                #for i in range(100000):
                car.run(30,-30)

            elif blob3:
                max_blob = find_max(blob3)
                #x_error = max_blob[5]-img.width()/2
                #h_error = max_blob[2]*max_blob[3]-size_threshold
                print("x error: ", x_error)
                '''
                for b in blobs:
                    # Draw a rect around the blob.
                    img.draw_rectangle(b[0:4]) # rect
                    img.draw_cross(b[5], b[6]) # cx, cy
                '''
                #img.draw_rectangle(max_blob[0:4]) # rect
                #img.draw_cross(max_blob[5], max_blob[6])
                print("T")
                car.run(0,0)
                break
            else:
                car.run(30,-30)
                print("b")
    else:
            car.run(0,0)
else:
    car.run(0,0)

kidswong999

如何设定颜色阈值的问题，请看教程

6f4a

但是我，一个颜色就不会，多个颜色就会

6f4a

@kidswong999 你帮我看下程序可以吗，我怕程序写漏了什么，非常感谢，急用

kidswong999

我没懂你是什么意思，你的问题是什么？

6f4a

@kidswong999 就是它老是别别的颜色识别进去，你可以帮我看下，程序那里出错了吗？需要怎么改

kidswong999

请回答以下问题

你的代码要实现什么功能，应该有什么现象？
你的代码现在有什么故障，什么现象现象？

你认为是代码的哪里有问题？
程序的逻辑是否用流程图设计过？
你又做了什么来检查问题？

6f4a

我觉得应该是阈值的问题，我那程序阈值的设置和调用大概是这样子，你帮我看下阈值这样设，对不对
green_threshold =(63, 38, 15, -65, -11, -112)
red_threshold =(41, 13, -78, -13, -24, 72)
blue_threshold =(10, 36, -18, 17, -19, 13)

blob1 = img.find_blobs([green_threshold])
blob2 = img.find_blobs([red_threshold])
blob3 = img.find_blobs([blue_threshold])

if blob1:
程序1
elif blob2:
程序2
elif blob3:
程序3
else:
程序4

kidswong999

你说的没错，可是你也没回答我的问题

6f4a

@kidswong999 让它识别到不同的颜色，执行不同的运动，当收到a时，开启颜色识别，当检测到绿色，跟着绿色走，红色的话，让他发送一个b，延时后再发送一个c，蓝色的话先停止然后结束，因为a只发了一次，所以这时跳出判断后，就不会再进行颜色识别，检测绿色是，打印一个a，可以在终端看执行程序那部分，同理蓝色时打印10,11也是，代码没有错误，但是运行的时候，你没把绿色，蓝色放在摄像头里，它老是把别的颜色识别进去。你可以把程序烧进去看下，就很快知道怎么回事了

kidswong999

你应该自己调试，你可以print 来看你的逻辑执行的过程