Extending Multi-Object Tracking systems to better exploit appearance and 3D information
This work addresses multi-object tracking for self-driving and similar real-world applications, but appears incremental as it combines existing methods.
The paper tackled multi-object tracking for real-time applications like self-driving by combining Siamese networks and RNNs to exploit appearance and motion information, and introduced heuristics for 3D tracking in Birds Eye View Space as a constrained optimization problem, but did not report specific performance numbers.
Tracking multiple objects in real time is essential for a variety of real-world applications, with self-driving industry being at the foremost. This work involves exploiting temporally varying appearance and motion information for tracking. Siamese networks have recently become highly successful at appearance based single object tracking and Recurrent Neural Networks have started dominating both motion and appearance based tracking. Our work focuses on combining Siamese networks and RNNs to exploit appearance and motion information respectively to build a joint system capable of real time multi-object tracking. We further explore heuristics based constraints for tracking in the Birds Eye View Space for efficiently exploiting 3D information as a constrained optimization problem for track prediction.