Thank you for sharing the presentation, I have a couple of questions: Firstly the global position and orientation is obtained through camera motion estimation or directly for each tracking object? Secondly, the re-identification is based on the shape parameters of SMPL models of humans or others? If yes, what if the people's body shape is similar to each other. Finally, It only works for humans or other types of objects?
Thanks. 1.global orientation and translation are directly estimated as one of the outputs. 2.tracking is performed by associating detections to complete trajectory, uses cues are not only body pose and shape but also the unique 3D translation of each subject. 3. TRACE only support human.
😍😍😍👏🙌 love this
Thank you for sharing the presentation, I have a couple of questions: Firstly the global position and orientation is obtained through camera motion estimation or directly for each tracking object? Secondly, the re-identification is based on the shape parameters of SMPL models of humans or others? If yes, what if the people's body shape is similar to each other. Finally, It only works for humans or other types of objects?
Thanks. 1.global orientation and translation are directly estimated as one of the outputs. 2.tracking is performed by associating detections to complete trajectory, uses cues are not only body pose and shape but also the unique 3D translation of each subject. 3. TRACE only support human.