Optical flow modeling and computation: A survey

Abstract

a b s t r a c tOptical flow estimation is one of the oldest and still most active research domains in computer vision. In 35 years, many methodological concepts have been introduced and have progressively improved performances, while opening the way to new challenges. In the last decade, the growing interest in evaluation benchmarks has stimulated a great amount of work. In this paper, we propose a survey of optical flow estimation classifying the main principles elaborated during this evolution, with a particular concern given to recent developments. It is conceived as a tutorial organizing in a comprehensive framework current approaches and practices. We give insights on the motivations, interests and limitations of modeling and optimization techniques, and we highlight similarities between methods to allow for a clear understanding of their behavior.

Detecting acceleration for gait and crime scene analysis

“…Optical flow refers to the apparent motion between the observer and the observed object caused by relative motion [7] and it has been steadily developed over 30 years since Horn and Schunck presented the first variational approach in computer vision [8]. Nowadays optical flow estimation methods have achieved a remarkable level of reliability and precision [9,10,11]. Among them, DeepFlow 2 Image is taken from: http://physics.tutorvista.com/motion/tangential-acceleration.html [12] is a recent technique with excellent performance for large displacement estimation and non-rigid matching.…”

Improved optical flow velocity analysis in SO<sub>2</sub> camera images of volcanic plumes – implications for emission-rate retrievals investigated at Mt Etna, Italy and Guallatiri, Chile

“…In the following, the basic principles of the OF computation are briefly introduced as well as different optimisation strategies (see e.g. Jähne, 1997, Fleet and Weiss, 2006, Fortun et al, 2015 for a comprehensive introduction into the topic). OF algorithms are based on the assumption that a certain image quantity, such as the brightness I or the local phase φ, is conserved between consecutive frames.…”

Attitude-Trajectory Estimation for Forward-Looking Multibeam Sonar Based on Acoustic Image Registration

“…Alternatively, pixels may be grouped by particular attributes to form super pixels [21]. Matching the elements between frames is then achieved through minimization of a suitable cost function [14].…”

“…3280×2464 pixels [13]. Optical registration techniques often select image segments assumed to be associated with a particular movement [14]. However, FLS images typically have a low signal to noise ratio (SNR).…”