Probabilistic Motion Estimation Based on Temporal Coherence

01/05/2012
by   Pierre-Yves Burgi, et al.
0

We develop a theory for the temporal integration of visual motion motivated by psychophysical experiments. The theory proposes that input data are temporally grouped and used to predict and estimate the motion flows in the image sequence. This temporal grouping can be considered a generalization of the data association techniques used by engineers to study motion sequences. Our temporal-grouping theory is expressed in terms of the Bayesian generalization of standard Kalman filtering. To implement the theory we derive a parallel network which shares some properties of cortical networks. Computer simulations of this network demonstrate that our theory qualitatively accounts for psychophysical experiments on motion occlusion and motion outliers.

READ FULL TEXT
research
07/31/2019

Probabilistic Motion Modeling from Medical Image Sequences: Application to Cardiac Cine-MRI

We propose to learn a probabilistic motion model from a sequence of imag...
research
06/18/2018

Repetition Estimation

Visual repetition is ubiquitous in our world. It appears in human activi...
research
11/17/2021

Temporally Consistent Online Depth Estimation in Dynamic Scenes

Temporally consistent depth estimation is crucial for real-time applicat...
research
07/02/2023

Bidirectional Temporal Diffusion Model for Temporally Consistent Human Animation

We introduce a method to generate temporally coherent human animation fr...
research
02/10/2023

Data-Driven Stochastic Motion Evaluation and Optimization with Image by Spatially-Aligned Temporal Encoding

This paper proposes a probabilistic motion prediction method for long mo...

Please sign up or login with your details

Forgot password? Click here to reset