“…In recent years, the depth-assisted systems [13,14,10] achieve better detection recall rates on the same datasets [8] and also outperform in other scenarios, so we choose to use the numerical results from [13,14,10] and compare our recall rate (successful tracked objects/total annotations), derived from the same evaluation criteria in [8,13,14,10]), with the defined best recall rates (false posi- Fig. 9.…”