Another Vertical View: A Hierarchical Network for Heterogeneous Trajectory Prediction via Spectrums
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929610779787264 |
|---|---|
| author | Xia, Beihao Wong, Conghao Xu, Duanquan Peng, Qinmu You, Xinge |
| author_facet | Xia, Beihao Wong, Conghao Xu, Duanquan Peng, Qinmu You, Xinge |
| contents | With the fast development of AI-related techniques, the applications of trajectory prediction are no longer limited to easier scenes and trajectories. More and more trajectories with different forms, such as coordinates, bounding boxes, and even high-dimensional human skeletons, need to be analyzed and forecasted. Among these heterogeneous trajectories, interactions between different elements within a frame of trajectory, which we call ``Dimension-wise Interactions'', would be more complex and challenging. However, most previous approaches focus mainly on a specific form of trajectories, and potential dimension-wise interactions are less concerned. In this work, we expand the trajectory prediction task by introducing the trajectory dimensionality $M$, thus extending its application scenarios to heterogeneous trajectories. We first introduce the Haar transform as an alternative to Fourier transform to better capture the time-frequency properties of each trajectory-dimension. Then, we adopt the bilinear structure to model and fuse two factors simultaneously, including the time-frequency response and the dimension-wise interaction, to forecast heterogeneous trajectories via trajectory spectrums hierarchically in a generic way. Experiments show that the proposed model outperforms most state-of-the-art methods on ETH-UCY, SDD, nuScenes, and Human3.6M with heterogeneous trajectories, including 2D coordinates, 2D/3D bounding boxes, and 3D human skeletons. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2304_05106 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Another Vertical View: A Hierarchical Network for Heterogeneous Trajectory Prediction via Spectrums Xia, Beihao Wong, Conghao Xu, Duanquan Peng, Qinmu You, Xinge Computer Vision and Pattern Recognition With the fast development of AI-related techniques, the applications of trajectory prediction are no longer limited to easier scenes and trajectories. More and more trajectories with different forms, such as coordinates, bounding boxes, and even high-dimensional human skeletons, need to be analyzed and forecasted. Among these heterogeneous trajectories, interactions between different elements within a frame of trajectory, which we call ``Dimension-wise Interactions'', would be more complex and challenging. However, most previous approaches focus mainly on a specific form of trajectories, and potential dimension-wise interactions are less concerned. In this work, we expand the trajectory prediction task by introducing the trajectory dimensionality $M$, thus extending its application scenarios to heterogeneous trajectories. We first introduce the Haar transform as an alternative to Fourier transform to better capture the time-frequency properties of each trajectory-dimension. Then, we adopt the bilinear structure to model and fuse two factors simultaneously, including the time-frequency response and the dimension-wise interaction, to forecast heterogeneous trajectories via trajectory spectrums hierarchically in a generic way. Experiments show that the proposed model outperforms most state-of-the-art methods on ETH-UCY, SDD, nuScenes, and Human3.6M with heterogeneous trajectories, including 2D coordinates, 2D/3D bounding boxes, and 3D human skeletons. |
| title | Another Vertical View: A Hierarchical Network for Heterogeneous Trajectory Prediction via Spectrums |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2304.05106 |