Flask-based AI app that summarizes surveillance videos using Whisper (audio), ViT-GPT2 (frame captions), and Groq LLM (narratives). Produces both general and law enforcement-style summaries.

A multimodal deep learning framework for anomalous event detection. Integrates spatio-temporal video features with acoustic signal patterns to identify irregularities in surveillance and monitoring environments, leveraging the complementary strengths of audio-visual data fusion.

AI surveillance intelligence system — YOLOv8 detection · ByteTrack tracking · behavioral heatmaps · OSINT privacy audit · FastAPI · Docker · Live on HuggingFace