top of page

3D Object Tracking


InterTrack: Interaction Transformer for 3D Multi-Object Tracking

John Willes, Cody Reading, Steven L. Waslander

Our proposed solution, InterTrack, introduces the Interaction Transformer for 3D MOT to generate discriminative object representations for data association.


Paper       Video       Dataset

aUToTrack: A Lightweight Object Detection and Tracking System for the SAE AutoDrive Challenge

Keenan Burnett, Sepehr Samavi, Steven L. Waslander, Timothy D. Barfoot, Angela P. Schoellig
Conference on Robots and Vision (CRV), 2019

We present a new object tracking dataset (UofTPed50), and propose a lightweight object detection and tracking system (aUToTrack) that achieves SOTA performance on the KITTI Object Tracking benchmark.


Joint 3D Object Detection and Tracking

Jason Zhou and Steven L. Waslander

We are currently investigating a joint 3D object detection and tracking framework that aims to achieve tracklets-aware temporal detection to improve robustness and consistency when there is temporary or partial occlusion.


Sliding Window 3D Multi-Object Tracking

Sandro Papais and Steven L Waslander

We are currently investigating a multiple hypothesis tracking method that learns track-level object similarities for solving online tracking with a sliding window approach.

bottom of page