Stereo 3D Object Trajectory Reconstruction
This work addresses trajectory reconstruction for vehicles in urban scenes, offering an incremental improvement by integrating stereo and temporal cues.
The authors tackled the problem of reconstructing 3D trajectories of moving objects from stereo video by combining instance-aware segmentation, optical flow, and Structure from Motion with stereo constraints, resulting in a method that avoids degenerated cases common in monocular approaches.
We present a method to reconstruct the three-dimensional trajectory of a moving instance of a known object category using stereo video data. We track the two-dimensional shape of objects on pixel level exploiting instance-aware semantic segmentation techniques and optical flow cues. We apply Structure from Motion (SfM) techniques to object and background images to determine for each frame initial camera poses relative to object instances and background structures. We refine the initial SfM results by integrating stereo camera constraints exploiting factor graphs. We compute the object trajectory by combining object and background camera pose information. In contrast to stereo matching methods, our approach leverages temporal adjacent views for object point triangulation. As opposed to monocular trajectory reconstruction approaches, our method shows no degenerated cases. We evaluate our approach using publicly available video data of vehicles in urban scenes.