YOLO：输入mp4视频数据，经过YOLO目标检测算法，输出带有目标框的新视频

本文将介绍输入mp4视频数据，经过YOLO目标检测算法，输出带有目标框的新视频的代码脚本。

文章目录

- - 一、代码

一、代码

代码只需要安装好cv2、ultralytics，然后修改模型路径、输入mp4视频文件路径、保存文件的路径。点击运行即可进行对视频数据的推理，结果保存一个新的带有目标框的新视频。

python 复制代码

import cv2
from ultralytics import YOLO
import datetime

# 加载YOLOv8n模型
model = YOLO('../预训练模型/yolov8n.pt')  # 替换为你的模型路径

# 打开输入视频
input_video_path = '../测试mp4视频/yourInputVideo.mp4'  # 替换为你的输入视频路径
cap = cv2.VideoCapture(input_video_path)

# 获取视频信息
frame_width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
frame_height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
fps = cap.get(cv2.CAP_PROP_FPS)
frame_count = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))

# 获取当前时间并生成时间戳后缀
now = datetime.datetime.now()
time_str = now.strftime("%Y%m%d_%H%M%S")

# 定义输出视频路径并加上时间戳后缀
output_video_path = f'./runsVideo/output_video_{time_str}.mp4'  # 替换为你的输出视频路径
fourcc = cv2.VideoWriter_fourcc(*'mp4v')
out = cv2.VideoWriter(output_video_path, fourcc, fps, (frame_width, frame_height))

frame_number = 0

while cap.isOpened():
    ret, frame = cap.read()
    if not ret:
        break

    # 使用YOLOv8进行检测
    results = model(frame)

    # 解析结果并绘制检测框
    for result in results:
        boxes = result.boxes
        for box in boxes:
            x1, y1, x2, y2 = map(int, box.xyxy[0])  # 获取检测框坐标
            confidence = float(box.conf[0])  # 获取置信度
            cls = int(box.cls[0])  # 获取类别
            label = model.names[cls]  # 获取类别名称

            # 绘制检测框和标签
            cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
            cv2.putText(frame, f"{label} {confidence:.2f}", (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)

    # 获取当前时间并绘制到帧上
    now = datetime.datetime.now()
    time_str = now.strftime("%Y-%m-%d %H:%M:%S")
    cv2.putText(frame, time_str, (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2, cv2.LINE_AA)

    # 写入处理后的帧
    out.write(frame)

    frame_number += 1
    print(f'Processing frame {frame_number}/{frame_count}')

# 释放资源
cap.release()
out.release()