Target Identification, Tracking & Engagement System /
Capt Abdul Mutalib, Capt Junaid Munir Shad, Capt Faraz Hanif, Capt Ausaf Anis. (BETE-56)
- ix, 33 p
This project is designed to detect and track a target and finally engage it using a control system autonomously. The system is implemented on a hardware turret and uses a combination of image processing and machine learning techniques to identify and track potential threats in real-time. The deep learning algorithm is trained on a dataset of various enemy uniforms and weapons, allowing it to recognize potential threats accurately. The system has two main modules, a recognition module, and a tracking and engaging module, which work together to detect and track potential threats autonomously. Data set is scaled down to four types, first is Pakistan Army Uniform soldier and Indian Army (enemy) uniform and other classes are weapons, animals and civilians. Model is developed and is trained to detect Pakistani Soldier, Indian Soldier, a civilian and a Gun threat involving our data set. Model has the capability of engaging only Indian uniform soldiers and recognizing Pakistan Army soldiers and civilians to protect them. We propose a model that provides a visionary sense to a machine or robot to identify the unsafe target and can also engage when a target is obvious in the edge.