Deep Learning Applications (Darknet - YOLOv3, YOLOv4 | DeOldify - Image Colorization, Video Colorization | Face-Recognition) with Google Colaboratory - on the free Tesla K80/Tesla T4/Tesla P100 GPU - using Keras, Tensorflow and PyTorch.

Fire and Gun detection using yolov3 in videos as well as images. Training code, dataset and trained weight file available.

Pistol, Rifle, and Fire detection using yolov4-tiny in videos as well as images. Training code, dataset, and trained weight file available.

Video surveillance using deep learning models

Detects firearms in real-time from CCTV videos, highlighting them within bounding boxes for immediate attention

An OpenCV application that uses YOLOv3 and YOLOv3-Tiny object detection and weights trained on a custom dataset to detect firearms in a given image, video and in real-time.

YOLOv5 is applied here to detect and classify handguns and long guns, including short guns, shotguns, machine-guns, etc. A set of experiments have been performed to assess how perceptual variabilities (noise, occlusions, weapon size) in the image may affect detection.