Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
[NeurIPS Workshop 2019] Official code of the paper "Probabilistic 3D Multi-Object Tracking for Autonomous Driving." First Place of the First NuScenes Tracking Challenge in the AI Driving Olympics Workshop of NeurIPS.
| Date | Stars |
|---|---|
| 2026-07-24 | 399 |
| 2026-07-25 | 399 |
| 2026-07-28 | 400 |
| 2026-07-30 | 400 |
| 2026-08-06 | 400 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Probabilistic 3D Multi-Object Tracking for Autonomous Driving Hsu-kuang Chiu<sup>1</sup>, Antonio Prioletti<sup>2</sup>, Jie Li<sup>2</sup>, Jeannette Bohg<sup>1</sup> <sup>1</sup>Stanford University, <sup>2</sup>Toyota Research Institute First Place Award, NuScenes Tracking Challenge, at AI Driving Olympics Workshop, NeurIPS 2019. ## Abstract We present our on-line tracking method, which wins the first place award of the [NuScenes Tracking Challenge](https://www.nuscenes.org/tracking)[1], held in the AI Driving Olympics Workshop at NeurIPS 2019. Our technical report is available in [arxiv](https://arxiv.org/abs/2001.05673). We also provide our source code and the step-by-step instructions to reproduce the validation set performance numbers. <img align="center" src="images/architecture.jpg"> ## Quantitative Results ### Validation Set Results The following table shows our quantitative tracking results for the validation set of NuScenes: evaluation in terms of overall Average Multi-Object Tracking Accuracy (AMOTA) and individual AMOTA for each object category in comparison with the tracking challenge official [AB3DMOT](https://github.com/xinshuoweng/AB3DMOT)[2] baseline results. The AB3DMOT[2] baseline and our method use the same [MEGVII](https://github.com/poodarchu/Det3D)[3] detection results as the input of the tracking systems. For the full validation set results including our implementation of the AB3DMOT[2] baseline and our ablations, please refer to our paper in [arxiv](https://arxiv.org/abs/2001.05673). Method | Overall | bicycle | bus | car | motorcycle | pedestrian | trailer | truck ---------- | --: | --: | --: | --: | --: | --: | --: | --: AB3DMOT\[2\] | 17.9 | 0.9 | 48.9 | 36.0 | 5.1 | 9.1 | 11.1 | 14.2 Our proposed method | 56.1 | 27.2 | 74.1 | 73.5 | 50.6 | 75.5 | 33.7 | 58.0 We can see that our method improves the AMOTAs significantly, especially for the smaller objects, such as pedestrians. ### Test Set Results The NuScenes Tracking Challenge organizer shared the test set performance of the top 3 participants and the official AB3DMOT[2] baseline, as shown in the following table. The AB3DMOT[2] baseline and our method use the same MEGVII[3] detection results as the input of the tracking systems. The full tracking challenge leaderboard can be seen at the [tracking challenge webpage](https://www.nuscenes.org/tracking). Rank | Team Name | Overall :--------: | :-- | --: 1 | StanfordIPRL-TRI (Ours) | 55.0 2 | VV_team | 37.1 3 | CenterTrack | 10.8 baseline | AB3DMOT\[2\] | 15.1 ## Qualitative Results The following figures are the bird-eye-view visualization of the tracking results from the official AB3DMOT[2] baseline and our method. For this scene, we draw all the car bounding boxes from different timesteps of the same scene in a single plot. Different colors represent different tracking ids. We also show the ground-truth annotations and the input detections as the references. For more visualization results, please refer to our paper in [arxiv](https://arxiv.org/abs/2001.05673). AB3DMOT[2] | Ours :---:|:---: <img src="images/ab3dmot.jpg" width=400px height=400px> | <img src="images/ours.jpg" width=400px height=400px> Input Detections | Ground-Truth :---:|:---: <img src="images/detection.jpg" width=400px height=400px> | <img src="images/gt.jpg" width=400px height=400px> We can see that our method is able to better track the object making a sharp turn. ## Using Our Code to Reproduce the Validation Set Results 1. Choose a directory YOUR_WORKING_DIR (mine is /juno/u/hkchiu), and download our code and setup the environment. In the following command, replace /juno/u/hkchiu with YOUR_WORKING_DIR: ``` cd /juno/u/hkchiu git clone https://github.com/eddyhkchiu/mahalanobis_3d_multi_object_tracking conda create --name probabilistic_tracking python=3.6 con
Excerpt of 9,953 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:d5235467c6b1dafb, topic:robotics, topic:autonomous-driving, desc:autonomous driving
matched fp:d5235467c6b1dafb, topic:computer-vision, name:object tracking, desc:object tracking