Abstract: Urban security and personal safety have become critical challenges due to increasing crime rates and limitations of traditional surveillance systems. Conventional CCTV-based monitoring and manual patrolling rely heavily on human intervention and often fail to provide real-time threat detection and immediate response. This paper presents an AI-driven intelligent autonomous surveillance and women safety system that integrates robotic patrolling with a personal emergency protection device. The proposed system consists of an autonomous patrol robot equipped with real-time video streaming, AI-based object detection using MobileNet SSD, line-following navigation, and metal detection for threat identification. In parallel, a compact women’s safety device is designed using GPS and GSM modules to transmit emergency alerts with live location information and provide physical self-defense during critical situations. Experimental results demonstrate effective autonomous navigation, accurate object detection, low-latency video streaming, and rapid emergency alert delivery. The integrated approach significantly reduces human dependency, enhances situational awareness, and improves response time. The proposed system is suitable for deployment in campuses, residential areas, public spaces, and other security-sensitive environments.

Keywords: Autonomous Surveillance, Artificial Intelligence, Object Detection, Women Safety, Raspberry Pi, Embedded Systems.

Downloads: | DOI: 10.17148/IARJSET.2026.13104