Please refer to FIG. 3(a). FIG. 3(a) is a schematic diagram of a method of acquiring detection zone in image according to an embodiment of the present disclosure. In detail, an implementation of performing the clustering procedure to the moving traces MT to obtain the boundary points can be the computing device deriving the normal distribution function based on the moving traces MT, and defining the boundary lines of the detection zone DZ with two boundary values of the confidence interval of the normal distribution function, wherein the confidence interval is, for example, 68% to 95% of the normal distribution function. The present disclosure is not limited thereto. Especially, according to the implementation of the normal distribution function, the computing device obtains a normal distribution of multiple first intersections N1 and two first boundary points BP1 of its confidence interval, and obtains a normal distribution of multiple second intersections N2 and two second boundary points BP2 of its confidence interval. The computing device then uses an area enclosed by the two first boundary points BP1 and the two second boundary points BP2 as the detection zone DZ. The multiple first intersections N1 are the intersections of the moving traces MT and the reference line L1; the multiple intersections N2 are the intersections of the moving traces MT and the reference line L2. Each of these moving traces MT extends from its starting point to its ending point, and the first intersections N1 preferably includes the starting point of one of the moving traces MT, and the second intersections N2 preferably includes the ending point of one of the moving traces MT.