Variational Tracking and Prediction with Generative Disentangled State-Space Models
This addresses the problem of robust object tracking and prediction in visual data for applications like autonomous systems, though it is incremental as it builds on existing state-space models.
The paper tackles tracking and prediction of multiple moving objects in visual streams by using a disentangled latent state-space model with variational inference, resulting in significantly improved long-term prediction beyond training horizons and better tracking performance compared to prior work.
We address tracking and prediction of multiple moving objects in visual data streams as inference and sampling in a disentangled latent state-space model. By encoding objects separately and including explicit position information in the latent state space, we perform tracking via amortized variational Bayesian inference of the respective latent positions. Inference is implemented in a modular neural framework tailored towards our disentangled latent space. Generative and inference model are jointly learned from observations only. Comparing to related prior work, we empirically show that our Markovian state-space assumption enables faithful and much improved long-term prediction well beyond the training horizon. Further, our inference model correctly decomposes frames into objects, even in the presence of occlusions. Tracking performance is increased significantly over prior art.