Method and system for continuously tracking humans in an area

A system for continuously tracking humans in an area, the system comprising:

• a processing circuitry;
• and
• a memory communicatively coupled to the processing circuitry, wherein the memory stores processor-executable instructions, which, on execution, causes the processing circuitry to:
• receive video data of an area from a plurality of overhead cameras, wherein
• the plurality of overhead cameras comprises a first overhead camera and a second overhead camera,
• the first overhead camera comprises a first Field of View (FoV) and the second overhead camera comprises a second (FoV);
• detect presence of one or more humans in the first FoV through object detection and classification models;
• assign a unique global identity (ID) for each of the one or more humans in the first FOV;
• and
• reassign the unique global ID for each of the one or more humans when each of the one or more humans moves from the first FoV to the second FoV through an overlapping region between the first FOV and the second FoV using a weighted combination of a resource assignment algorithm, intersection-over-union (IOU) based track detection, an appearance-based model, and velocity and direction estimation of a subsequent frame of the video data, wherein the overlapping region corresponds to a region of intersection between the first FoV and the second FoV;
• and
• continuously track, in real-time, each of the one or more humans in the area through the unique global ID.