多传感器融合学习笔记

小咪咪 2022-09-07 14:39 128阅读 0赞

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2phY2tlMTIx_size_16_color_FFFFFF_t_70][]

if __name__ == "__main__":
        # choose which one to run, comment out the other one
        run_on_nuscenes()  
        run_on_kitti()

[https://github.com/aleksandrkim61/EagerMOT][https_github.com_aleksandrkim61_EagerMOT]

### Download 3D and 2D detections, which ones to download depends on what you want to run: ###

We thank other researchers for opening their code and data to the community and therefore provide links to their data directly in hopes that you will also check out their great work! Data that was not available directly but was generated by us using their open source code is given through a cloud download link.

*  KITTI 2D MOTSFusion detections/segmentations from [https://github.com/tobiasfshr/MOTSFusion][https_github.com_tobiasfshr_MOTSFusion]. Under the "Results" section, they provide link to download their detections.
 *  KITTI 2D TrackRCNN detections/segmentations from [https://www.vision.rwth-aachen.de/page/mots][https_www.vision.rwth-aachen.de_page_mots]. Under the "Downloads" section they provide a link to download detections.
 *  KITTI 3D [PointGNN][], NuScenes 3D [CenterPoint][], NuScenes 2D detections using an [MMDetection][] model from the [drive][].
 *  NuScenes 3D CenterPoint detections can also be downloaded directly from [the author's page][the author_s page] for the `centerpoint_voxel_1440_dcn(flip)` config. NuScenes 2D MMDetection output was obtained using the `cascade_mask_rcnn_x101` model given in [the model zoo][]. See issue \#9 for more details.
 *  KITTI 3D AB3DMOT detections can be downloaded from the original source [https://github.com/xinshuoweng/AB3DMOT][https_github.com_xinshuoweng_AB3DMOT], but their format has recently changed and is no longer compatible with this repo. The detections provided in the above cloud link are simpy a copy downloaded at an earlier time when this the parsing code in this repo was written.

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2phY2tlMTIx_size_16_color_FFFFFF_t_70]: /images/20220829/710eb4c8d4fc454c9bff0328e519e523.png
[https_github.com_aleksandrkim61_EagerMOT]: https://github.com/aleksandrkim61/EagerMOT
[https_github.com_tobiasfshr_MOTSFusion]: https://github.com/tobiasfshr/MOTSFusion
[https_www.vision.rwth-aachen.de_page_mots]: https://www.vision.rwth-aachen.de/page/mots
[PointGNN]: https://github.com/WeijingShi/Point-GNN
[CenterPoint]: https://github.com/tianweiy/CenterPoint
[MMDetection]: https://github.com/open-mmlab/mmdetection
[drive]: https://drive.google.com/drive/folders/1MpAa9YErhAZNEJjIrC4Ky21YfNj2jatM?usp=sharing
[the author_s page]: https://github.com/tianweiy/CenterPoint/blob/master/configs/nusc/README.md
[the model zoo]: https://github.com/open-mmlab/mmdetection/tree/master/configs/cascade_rcnn
[https_github.com_xinshuoweng_AB3DMOT]: https://github.com/xinshuoweng/AB3DMOT