Algorithm 1: Adaptive dynamic feature point selection strategy.

Input: Original feature point, Bounding box Output: Static feature point  1: if feature points in the boundingbox then  2:    Use LK optical flow to match a prior dynamic objects between frames  3:    if a priori dynamic object screen share ≥ 50% then  4:      Determine if the number of a priori dynamic objects is greater than the threshold  5:      if number of a prior dynamic objects ≥ 5 then  6:          Calculate essential matrix of prior dynamic region bwtween frame  7:          Calculating infinite norms of essential matrix  8:          Calculate the essential matrix of the expansion layer bwtween frame  9:          Calculating infinite norms of essential matrix 10:        if ratio of two infinite norm is greater than the threshold value then 11:            Delete dynamic feature points 12:        else 13:          ORB matches 14:        end if 15:      end if 16:    end if 17: end if 18: return Outputs