MissFormer: (In-)attention-based handling of missing observations for trajectory filtering and prediction

Abstract

In applications such as object tracking, time-series data inevitably carry missing observations. Following the success of deep learning-based models for various sequence learning tasks, these models increasingly replace classic approaches in object tracking applications for inferring the objects' motion states. While traditional tracking approaches can deal with missing observations, most of their deep counterparts are, by default, not suited for this. Towards this end, this paper introduces a transformer-based approach for handling missing observations in variable input length trajectory data. The model is formed indirectly by successively increasing the complexity of the demanded inference tasks. Starting from reproducing noise-free trajectories, the model then learns to infer trajectories from noisy inputs. By providing missing tokens, binary-encoded missing events, the model learns to in-attend to missing data and infers a complete trajectory conditioned on the remaining inputs. In the case of a sequence of successive missing events, the model then acts as a pure prediction model. The abilities of the approach are demonstrated on synthetic data and real-world data reflecting prototypical object tracking scenarios.

arXiv commentAccepted at the International Symposium on Visual Computing (ISVC) 2021

References in corpus (13)

• Adam: A Method for Stochastic Optimization
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Auto-Encoding Variational Bayes
• Decoupled Weight Decay Regularization
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• NICE: Non-linear Independent Components Estimation
• A Recurrent Latent Variable Model for Sequential Data
• Human Motion Trajectory Prediction: A Survey
• Microscopic Pedestrian Flow Characteristics: Development of an Image Processing Data Collection and Simulation Model
• Deep Learning for Vision-based Prediction: A Survey
• Pedestrian Trajectory Prediction using Context-Augmented Transformer Networks
• Handling Missing Observations with an RNN-based Prediction-Update Cycle
• Quantifying the Complexity of Standard Benchmarking Datasets for Long-Term Human Trajectory Prediction

Cited by in corpus (2)

• ViFiT: Reconstructing Vision Trajectories from IMU and Wi-Fi Fine Time Measurements
• An Analysis of Temporal Dropout in Earth Observation Time Series for Regression Tasks