Stacked Homography Transformations for Multi-View Pedestrian Detection
     Liangchen Song1 , Jialian Wu1 , Ming Yang2 , Qian Zhang2 , Yuan Li3 , and Junsong Yuan1
           1
            University at Buffalo 2 Horizon Robotics, Inc. 3 Google, Inc.
                    {lsong8,jialianw,jsyuan}@buffalo.edu

             Abstract                          Input: Multi-view Images

  Multi-view pedestrian detection aims to predict a bird’s
eye view (BEV) occupancy map from multiple camera views.
Th ...