“…The large anchor box is used to predict large objects and the small anchor box is used to predict small objects. Therefore, the three candidate boxes [46, 83], [65,131], and [104,1989] are used to predict bounding box on the scale of 13 3 13, the three candidate boxes [18,48], [26,68], and [36,50] are used to predict bounding box on the scale of 26 3 26, and the rest three candidate boxes [9,23], [13,33], and [24,35] are used to predict small bounding box on the scale of 52 3 52. Since the results of Kmeans clustering depend on the selection of initial clustering center, six clustering experiments were done in this article, as shown in Table 2.…”