Automatic Rifle and Sniper detection can help reduce or eliminate threats in both public and private areas, such as a rooftop, a public gathering, a conflict zone, and a VVIP protection area. In the literature, deep learning-based detectors like Yolo-NAS and Yolov7 Pose approaches have been proposed to sound an alarm if a rifle or sniper is spotted in a live video or picture. However, such detectors, like CCTV & UAV and UAV, only take into account how the weapon appears in live footage. In order to increase overall performance, we suggest combining the detector with the Multiple or Individual posture information in this study. The findings indicate a development over the first Rifle and Sniper detector. Techniques named Smart Rifle and Sniper detection systems (SRSDS) for rider posture estimation and correction using Yolo-NAS and Yolov7 Pose. However, those detectors are solely based on the weapon appearance on the image. In this research work, we apply combine the detector with the individual’s pose information in order to improve overall performance. To this end, a model that integrates grayscale images from the output of the Rifle and Sniper detector and heat map-like images that represent pose is proposed. The results show an improvement over the original Rifle and Sniper detector. The proposed network provides a maximum improvement of a 31.5% in AP of the proposed combinational model over the baseline Rifle and Sniper detector.

Rifle and Sniper, Pose Estimation, Deep Learning, Sensors, Yolo-NAS and Yolov7 Pose.