A method and computer system for detecting crowds in a location tracking system utilizes a grid and the pigeonhole principle to minimize an amount of hardware, memory and/or processing capability required in the location tracking system. In particular, an amount of storage required to determine whether a location update has resulted in a crowd grows only linearly, rather than quadratically, with the number of objects being tracked because a number of active grid points will be, at most, four times the number of objects being tracked. By determining whether an individual active grid point is within a crowd area, the computational time required for detecting a crowd within this crowd area is independent from the total number of objects being tracked.