The Suspicious Activity Detection in Hospital is an automated video analysis system developed using Deep Learning based YOLO algorithm. It identifies potential threats like individuals carrying weapons (e.g., guns) and alerts hospital authorities. The system also detects suspicious activities such as fire incidents and prohibited behaviors like smoking. By automating the detection process, it reduces reliance on manual surveillance and enables a swift response. The system enhances overall security measures, ensuring the safety of patients, staff, and visitors. It provides peace of mind and facilitates a proactive approach to security in the hospital environment.
Main Objectives of Project are as follows ,
- Enhancing the security at hospitals by detecting any suspicious person while they engage in suspicious activities such as destruction or causing harm to others.
- Strengthening security during accidental emergencies when the vulnerability is high, enabling the detection of unauthorized individuals with malicious intent and weapons entering the hospital premises.
- Alerting authorized personnel if a patient is alone in their room and someone attempts to harm them using a weapon.
- Alerting authorized personnel if there is fire in the hospital which will minimize the harm to hospital and patients as well.
- Finding and alerting if anyone is smoking in hospital premises.
- Upgrading existing security and safety measures by integrating Internet of Things (IoT) technology.