# Real-Time-Drone-Detection-System
This project demonstrates real-time drone detection using YOLOv8 based on YOLOv5 and OpenCV for more easier and faster detection. It detects drones in real-time and displays a warning when a drone is detected inside or near a defined rectangle.
## Features
- Real-time drone detection using YOLOv8 based on YOLOv5 framework
- Interactive rectangle creation and adjustment
- Warning message displayed when a drone is detected inside or near the rectangle
## Benefits
1. Live Feedback
Immediate alerting and notifications offer prompt reactions to potential drone risks.
2. Automated Surveillance
Minimize human monitoring with the automation of drone identification through computer vision and machine learning techniques.
3. Adaptable and User-Friendly
Set and modify the detection zone with an intuitive rectangular tool for precise and flexible identification.
4. Elevated Safety Measures
Immediate drone identification for bolstered security at airports, public gatherings, and limited-access zones.
## About the Dataset (Roboflow)
The Drone Detection model utilized a comprehensive dataset with 1400 images showcasing various drone types. This dataset was meticulously assembled and annotated to guarantee precision in the labels. It encompasses an extensive variety of drone sizes, styles, angles, and environments.
The dataset was crafted using the "Roboflow Platform" and was retrieved via its API. This approach simplified the data preparation phase and guaranteed top-notch inputs for model training.
Having access to such a varied and meticulously labeled dataset allows the Drone Detection model to be trained on a broad spectrum of drone images, leading to enhanced precision and dependability in real-world detection situations.
## Requirements
- Python 3.x
- OpenCV
- PyTorch
- YOLOv5
- Numpy
- PIL
## Installation
1. Clone the repository:
- git clone https://github.com/thesabbirahmed/YOLOv8-Real-Time-Drone-Detection-by-Sabbir
2. Install the required Python libraries:
- pip install opencv-python torch numpy pillow
3. USe the YOLOv8 model based on YOLOv5 framework:
- YOLOv8 is built on the YOLOv5 framework and includes several architectural and developer experience improvements. YOLOv8 based on YOLOv5 is easier to use, faster and more accurate.
## Usage
1. Run the `Advanced_Drone_Detection.py` script:
- python Advanced_Drone_Detection.py
2. The program initiates a real-time video stream using the primary camera.
- Press and drag the mouse across the video feed to outline the rectangle's boundaries.
- You can modify the rectangle by pulling its corners.
- An alert will pop up when a drone is spotted within or close to the rectangle.
3. Press 'q' to quit the program.
没有合适的资源?快使用搜索试试~ 我知道了~
基于 YOLOv5 和 OpenCV 的 YOLOv8 进行实时无人机检测,以实现更轻松、更快速的检测
共3个文件
py:1个
pt:1个
md:1个
1.该资源内容由用户上传,如若侵权请联系客服进行举报
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
版权申诉
0 下载量 191 浏览量
2024-05-19
20:50:26
上传
评论
收藏 12.52MB ZIP 举报
温馨提示
实时无人机检测系统 该项目演示了使用基于 YOLOv5 和 OpenCV 的 YOLOv8 进行实时无人机检测,以实现更轻松、更快速的检测。它实时检测无人机,并在定义的矩形内或附近检测到无人机时显示警告。 特征 基于YOLOv5框架的YOLOv8无人机实时检测 交互式矩形创建和调整 在矩形内部或附近检测到无人机时显示警告消息 好处 实时反馈 即时警报和通知可对潜在的无人机风险做出迅速反应。 自动监控 通过计算机视觉和机器学习技术实现无人机识别自动化,最大限度地减少人工监控。 适应性强且用户友好 使用直观的矩形工具设置和修改检测区域,以实现精确灵活的识别。 加强安全措施 即时识别无人机,以加强机场、公共集会和限制进入区域的安全。 关于数据集 (Roboflow) 无人机检测模型利用了一个包含 1400 张图像的综合数据集,展示了各种无人机类型。该数据集经过精心组装和注释,以保证标签的准确性。它涵盖了各种各样的无人机尺寸、样式、角度和环境。 该数据集是使用“Roboflow 平台”制作的,并通过其 API 进行检索。这种方法简化了数据准备阶段,并保证了模型训练的一流输入。
资源推荐
资源详情
资源评论
收起资源包目录
YOLOv8-Real-Time-Drone-Detection-by-Sabbir-main.zip (3个子文件)
YOLOv8-Real-Time-Drone-Detection-by-Sabbir-main
best.pt 13.65MB
Advanced_Drone_Detection.py 4KB
README.md 3KB
共 3 条
- 1
资源评论
hakesashou
- 粉丝: 4652
- 资源: 1350
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功