小车AI视觉交互--7. 自动驾驶地图沙盘Mini版

一、运行前必做

1.关闭开机大程序，如何关闭可以参考【小车基础课程】里的“00.开发前的准备”

2.调节四路巡线模块，如何调节可以参考【小车基础教程】‘’07.四路巡线模块状态打印‘’

3.因摄像头受环境光线影响较大，确保环境光线充足，且环境光线均匀。环境光线昏暗将会影响路标识别。

4.启动前将jupyter leb内核环境切换为yolo环境

路标摆放说明

路标指示功能说明

1号车库	2号车库	鸣笛	限速
取消限速	左转	右转	红绿灯

路标功能解释：

1号车库：小车倒车进1号车库

2号车库：小车倒车进2号车库

鸣笛：小车蜂鸣器响一声

限速：小车减速行驶

取消限速：小车加速行驶

左转：小车执行左转命令

右转：小车执行右转命令

红绿灯：红灯亮小车停止，红灯灭小车前进

二、实验源码 

import cv2,time
import torch
from numpy import random
import queue

from models.experimental import attempt_load
from utils.datasets import LoadStreams
from utils.general import check_img_size, non_max_suppression, scale_coords, set_logging, clean_str
from utils.plots import plot_one_box
from utils.torch_utils import select_device, time_synchronized

import sys
sys.path.append('/home/pi/project_demo/lib')
from McLumk_Wheel_Sports import *

#复位舵机 Reset the servo
bot.Ctrl_Servo(1, 90)
bot.Ctrl_Servo(2, 25)

#bgr8转jpeg格式 bgr8 to jpeg format
import enum


def bgr8_to_jpeg(value, quality=75):
    return bytes(cv2.imencode('.jpg', value)[1])

#显示摄像头组件 Display camera components
import traitlets
import ipywidgets.widgets as widgets
from IPython.display import display
import time
# 线程功能操作库 Thread function operation library
import threading
import inspect
import ctypes

global classes
classes=classestemp=None
flag=rightrunflag=leftrunflag=1
leftflag=rightflag=pack1flag=pack2flag=stopflag=classflag=0
speed=5 # 速度不宜过快 The speed should not be too fast
image_widget = widgets.Image(format='jpeg', width=640, height=480)

def _async_raise(tid, exctype):
    """raises the exception, performs cleanup if needed"""
    tid = ctypes.c_long(tid)
    if not inspect.isclass(exctype):
        exctype = type(exctype)
    res = ctypes.pythonapi.PyThreadState_SetAsyncExc(tid, ctypes.py_object(exctype))
    if res == 0:
        raise ValueError("invalid thread id")
    elif res != 1:
        # """if it returns a number greater than one, you're in trouble,
        # and you should call it again with exc=NULL to revert the effect"""
        ctypes.pythonapi.PyThreadState_SetAsyncExc(tid, None)
        
def stop_thread(thread):
    _async_raise(thread.ident, SystemExit)

def detect(weights='weights/best.pt', source='0', img_size=320, conf_thres=0.70, iou_thres=0.35, device=''):
    #Default: best.pt yolov5 model
    #best1.pt yolov5lite model
    global classes
    # Initialize
    set_logging()
    device = select_device(device)
    half = device.type != 'cpu'  # half precision only supported on CUDA

    # Load model
    model = attempt_load(weights, map_location=device)  # load FP32 model
    stride = int(model.stride.max())  # model stride
    imgsz = check_img_size(img_size, s=stride)  # check img_size
    if half:
        model.half()  # to FP16

    # Set Dataloader
    dataset = LoadStreams(source, img_size=imgsz, stride=stride)

    # Get names and colors
    names = model.module.names if h