Abstract: State-of-the-art object detection algorithms (e.g., EfficientDet, Faster-RCNN, and YOLO) and their variants are integrated into an end-to-end IoT cloud-based system deployment. The system can (1) receive real-time video streaming (RTSP/RTMP/SDP) from most CCTV systems and devices with cameras, (2) extract frames from the video streams, (3) feed the frames to multiple AI models simultaneously, and (4) compute a probability for the presence of fire and/or smoke. Based on custom risk thresholds, the outputs can be compiled programmatically into a video clip that is sent to a user automatically for real-time alerts.