使用YOLOv5实现多路摄像头实时目标检测

---

前言

YOLOV5模型从发布到现在都是炙手可热的目标检测模型，被广泛运用于各大场景之中。因此，我们不光要知道如何进行yolov5模型的训练，而且还要知道怎么进行部署应用。在本篇博客中，我将利用yolov5模型简单的实现从摄像头端到web端的部署应用demo，为读者提供一些部署思路。

---

一、YOLOV5的强大之处

你与目标检测高手之差一个YOLOV5模型。YOLOV5可以说是现目前几乎将所有目标检测tricks运用于一身的模型了。在它身上能找到很多目前主流的数据增强、模型训练、模型后处理的方法，下面我们就简单总结一下yolov5所使用到的方法：

• yolov5增加的功能：
  

• yolov5训练和预测的tricks：
  

二、YOLOV5部署多路摄像头的web应用

1.多路摄像头读取

在此篇博客中，采用了yolov5源码的datasets.py代码中的LoadStreams类进行多路摄像头视频流的读取。因为，我们只会用到datasets.py中视频流读取的部分代码，所以，将其提取出来，新建一个camera.py文件，下面则是camera.py文件的代码部分：

# coding:utf-8
import os
import cv2
import glob
import time
import numpy as np
from pathlib import Path
from utils.datasets import letterbox
from threading import Thread
from utils.general import clean_str


img_formats = ['bmp', 'jpg', 'jpeg', 'png', 'tif', 'tiff', 'dng', 'webp']  # acceptable image suffixes
vid_formats = ['mov', 'avi', 'mp4', 'mpg', 'mpeg', 'm4v', 'wmv', 'mkv']  # acceptable video suffixes


class LoadImages:  # for inference
    def __init__(self, path, img_size=640, stride=32):
        p = str(Path(path).absolute())  # os-agnostic absolute path
        if '*' in p:
            files = sorted(glob.glob(p, recursive=True))  # glob
        elif os.path.isdir(p):
            files = sorted(glob.glob(os.path.join(p, '*.*')))  # dir
        elif os.path.isfile(p):
            files = [p]  # files
        else:
            raise Exception(f'ERROR: {p} does not exist')

        images = [x for x in files if x.split('.')[-1].lower() in img_formats]
        videos = [x for x in files if x.split('.')[-1].lower() in vid_formats]
        ni, nv = len(images), len(videos)

        self.img_size = img_size
        self.stride = stride
        self.files = images + videos
        self.nf = ni + nv  # number of files
        self.video_flag = [False] * ni + [True] * nv
        self.mode = 'image'
        if any(videos):
            self.new_video(videos[0])  # new video
        else:
            self.cap = None
        assert self.nf > 0, f'No images or videos found in {p}. ' \
                            f'Supported formats are:\nimages: {img_formats}\nvideos: {vid_formats}'

    def __iter__(self):
        self.count = 0
        return self

    def __next__(self):
        if self.count == self.nf:
            raise StopIteration
        path = self.files[self.count]

        if self.video_flag[self.count]:
            # Read video
            self.mode = 'video'
            ret_val, img0 = self.cap.read()
            if not ret_val:
                self.count += 1
                self.cap.release()
                if self.count == self.nf:  # last video
                    raise StopIteration
                else:
                    path = self.files[self.count]
                    self.new_video(path)
                    ret_val, img0 = self.cap.read()

            self.frame += 1
            print(f'video {self.count + 1}/{self.nf} ({self.frame}/{self.nframes}) {path}: ', end='')

        else:
            # Read image
            self.count += 1
            img0 = cv2.imread(path)  # BGR
            assert img0 is not None, 'Image Not Found ' + path
            print(f'image {self.count}/{self.nf} {path}: ', end='')

        # Padded resize
        img = letterbox(img0, self.img_size, stride=self.stride)[0]

        # Convert
        img = img[:, :, ::-1].transpose(2, 0, 1)  # BGR to RGB, to 3x416x416
        img = np.ascontiguousarray(img)

        return path, img, img0, self.cap

    def new_video(self, path):
        self.frame = 0
        self.cap = cv2.VideoCapture(path)
        self.nframes = int(self.cap.get(cv2.CAP_PROP_FRAME_COUNT))

    def __len__(self):
        return self.nf  # number of files


class LoadWebcam:  # for inference
    def __init__(self, pipe='0', img_size=640, stride=32):
        self.img_size = img_size
        self.stride = stride

        if pipe.isnumeric():
            pipe = eval(pipe)  # local camera
        # pipe = 'rtsp://192.168.1.64/1'  # IP camera
        # pipe = 'rtsp://username:password@192.168.1.64/1'  # IP camera with login
        # pipe = 'http://wmccpinetop.axiscam.net/mjpg/video.mjpg'  # IP golf camera

        self.pipe = pipe
        self.cap = cv2.VideoCapture(pipe)  # video capture object
        self.cap.set(cv2.CAP_PROP_BUFFERSIZE, 3)  # set buffer size

    def __iter__(self):
        self.count = -1
        return self

    def __next__(self):
        self.count += 1
        if cv2.waitKey(1) == ord('q'):  # q to quit
            self.cap.release()
            cv2.destroyAllWindows()
            raise StopIteration

        # Read frame
        if self.pipe == 0:  # local camera
            ret_val, img0 = self.cap.read()
            img0