Scholarlink

This research project proposes an Intelligent Real-Time Vehicle Tracking System utilizing cameras powered by Raspberry Pi to address urban security challenges in tracking vehicle locations. The system integrates strategically placed cameras with Automatic Number Plate Recognition (ANPR) technology, transmitting real-time data to a central cloud or on-premise server. The collected information is securely stored in scalable cloud storage, and a user-friendly software interface allows local security administrations to visualize tracked vehicles for efficient monitoring and quick identification. This system uses Raspberry Pi, OpenCV, and IR sensors to detect signs of driver fatigue, while also enabling license plate recognition and vehicle tracking. The project addresses key challenges such as improving license plate recognition accuracy under varying conditions, optimizing communication protocols for real-time data transmission, and developing a robust database architecture. The system achieved 92% accuracy in detecting drowsiness and maintained consistent license plate recognition across diverse lighting conditions. The system is designed to be modular and flexible, allowing customization to meet the specific needs of different authorities. Anticipated benefits include prompt vehicle location recognition, improved urban security, and data-driven decision-making for law enforcement. The stored data also supports urban planning efforts by offering insights to optimize road networks. This adaptable system provides a comprehensive solution for enhancing public safety through advanced technology. This system can potentially reduce road accidents caused by driver fatigue, contributing to safer and smarter cities.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Non-GPS-Based Car Location Tracking System Using Deep Learning and IOT

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Samyak Gauri,
  • Soumyadeep Chakraborty,
  • Samya Goswami,
  • Sudipta Sahana

摘要

This research project proposes an Intelligent Real-Time Vehicle Tracking System utilizing cameras powered by Raspberry Pi to address urban security challenges in tracking vehicle locations. The system integrates strategically placed cameras with Automatic Number Plate Recognition (ANPR) technology, transmitting real-time data to a central cloud or on-premise server. The collected information is securely stored in scalable cloud storage, and a user-friendly software interface allows local security administrations to visualize tracked vehicles for efficient monitoring and quick identification. This system uses Raspberry Pi, OpenCV, and IR sensors to detect signs of driver fatigue, while also enabling license plate recognition and vehicle tracking. The project addresses key challenges such as improving license plate recognition accuracy under varying conditions, optimizing communication protocols for real-time data transmission, and developing a robust database architecture. The system achieved 92% accuracy in detecting drowsiness and maintained consistent license plate recognition across diverse lighting conditions. The system is designed to be modular and flexible, allowing customization to meet the specific needs of different authorities. Anticipated benefits include prompt vehicle location recognition, improved urban security, and data-driven decision-making for law enforcement. The stored data also supports urban planning efforts by offering insights to optimize road networks. This adaptable system provides a comprehensive solution for enhancing public safety through advanced technology. This system can potentially reduce road accidents caused by driver fatigue, contributing to safer and smarter cities.