Wireless Violence Detection
Jordan Holeman, Junior
Dr. Xiaohong Yuan
Computer vision continues to improve its ability to detect human activity. However, detecting violent scenes intelligently has been a challenge and there is no effective solution to execute Violence Detection (VD) methods in the video surveillance. NCAT Grad Student Hamza Khan has been developing a more efficient way of detecting violent videos using AI-Assisted Edge Vision in IoT-Based Industrial Surveillance Networks. This semester, I have been assisting Hamza with researching papers to aid in making the system more effective and running the program. The model that is being used for this system is convolution long short-term memory (ConcLSTM). Video frames with objects such as weapons are forwarded to cloud for a detailed investigation by extracting specific features using ConcLSTM.
Holeman, Jordan, "Wireless Violence Detection" (2023). Undergraduate Research and Creative Inquiry Symposia. 280.