Pedestrian detection and tracking using modified SURF algorithm
Miso Jang, Geon‐Hui Lee, Dong-Chul Park, Soo-Young Min · AIP conference proceedings · 2015
A pedestrian detection and tracking method using modified SURF(Speed Up Robust Feature) algorithm is proposed in this paper. In calculating the location of pedestrian, the zeroth and first order moments are used with the discrete probability image. Experiments on a set image sequence data are performed for evaluation of the proposed method. The preliminary results show that the proposed tracking method can be a promising alternative over existing method based on Meanshift algorithm in terms of tracking accuracy with real time tracking speed.