In this paper, we present an unsupervised probabilistic model and associated estimation algorithm for multi-object tracking (MOT) based on a dynamical variational autoencoder (DVAE), called DVAE-UMOT. The DVAE is a latent-variable deep generative model that can be seen as an extension of the variational autoencoder for the modeling of temporal sequences. It is included in DVAE-UMOT to model the objects' dynamics, after being pre-trained on an unlabeled synthetic dataset of single-object trajectories. Then the distributions and parameters of DVAE-UMOT are estimated on each multi-object sequence to track using the principles of variational inference: Definition of an approximate posterior distribution of the latent variables and maximization of the corresponding evidence lower bound of the data likehood function. DVAE-UMOT is shown experimentally to compete well with and even surpass the performance of two state-of-the-art probabilistic MOT models. Code and data are publicly available.
翻译:在本文中,我们提出了一个基于动态变异自动编码器(DVAE-UMOT)的多物体跟踪(MOT)不受监督的概率模型和相关估算算法(MOT),该模型称为DVAE-UMOT。DVAE是一种潜在的、可变的深基因模型,可被视为用于模拟时间序列的变异自动编码器的延伸。DVAE-UMOT中包括了该模型,用于模拟物体的动态,先在单一物体轨迹未加标签的合成数据集上接受预先训练。然后,DVAE-UMOT的分布和参数在每一个多物体序列上进行估算,以使用变异推断原则跟踪:潜在变量的近似后方分布的定义和相应证据下限对数据像功能的最大化。DVAE-UMOT实验性地显示DVAE-UMOT与两种状态的概率模型进行竞争,甚至超过其性能。代码和数据是公开提供的。