End-to-end Recurrent Multi-Object Tracking and Trajectory Prediction with Relational Reasoning
By Fabian B. Fuchs, Adam R. Kosiorek, Li Sun, Oiwi Parker Jones, Ingmar Posner. 2019
16 citations recorded by the source corpus.
The majority of contemporary object-tracking approaches do not model interactions between objects. This contrasts with the fact that objects' paths are not independent: a cyclist might abruptly deviate from a previously planned trajectory in order to avoid colliding with a car. Building upon HART, a neural class-agnostic single-object tracker, we introduce a multi-object tracking method MOHART capable of relational reasoning. Importantly, the entire system, including the understanding of interactions and relations between objects, is class-agnostic and learned simultaneously in an end-to-end fashion. We explore a number of relational reasoning architectures and show that multi-headed self-attention outperforms the provided baselines and better accounts for complex physical interactions in a challenging toy experiment. We find that it leads to consistent performance gains in tracking as well as future trajectory prediction on three real-world datasets (MOTChallenge, UA-DETRAC, and Stanford Drone dataset), particularly in the presence of ego-motion, occlusions, crowded scenes, and faulty sensor inputs.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Yoshua Bengio
- Andrea Vedaldi
- Sergey Levine
- Trevor Darrell
- Dacheng Tao
- Abhinav Kumar Gupta
- Ruslan Salakhutdinov
- Quoc V. Le
Citations in the corpus
- Conditional Object-Centric Learning from Video (2021, methodology): “…Jaegle et al., 2021b;a), object-centric models for dynamic visual reasoning (Yi et al., 2020; Ding et al., 2021a; Bar et al., 2021), and supervised attention-based object-centric models (Fuchs et al., 2019; Carion et al., 2020; Kamath et al., 2021; Meinhardt et al., 2021) in Appendix A.1.”