Motion analysis

Summary

Motion analysis is used in computer vision, , high-speed photography and machine vision that studies methods and applications in which two or more consecutive images from an image sequences, e.g., produced by a video camera or high-speed camera, are processed to produce information based on the apparent motion in the images. In some applications, the camera is fixed relative to the scene and objects are moving around in the scene, in some applications the scene is more or less fixed and the camera is moving, and in some cases both the camera and the scene are moving. The motion analysis processing can in the simplest case be to detect motion, i.e., find the points in the image where something is moving. More complex types of processing can be to track a specific object in the image over time, to group points that belong to the same rigid object that is moving in the scene, or to determine the magnitude and direction of the motion of every point in the image. The information that is

Official source

https://en.wikipedia.org/wiki/Motion_analysis

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Related publications (17)

Related publications

Related people (2)

Related people

Related units (1)

Related units

Related concepts

Related courses (2)

Related courses

Related lectures (2)

Related lectures

Related publications (17)

Research Proposal

Shima Sepehri

n this thesis, we will work on medical image processing. More particularly, we will focus on Wall Motion Tracking in Intracranial Aneurysms by means of accurate and robust segmentation in a 4D Electrocardiography (ECG)-gated Computed Tomography (CT) image series. Detection of this barely- perceptible motion is a challenging task and has been given relatively little attention in the literature. Moreover, the existing state-of-the-art suffers from lack of accuracy and/or automation. Our goal is therefore to contribute to the improvement of the existing image segmentation and motion tracking models and methods by addressing this specific and difficult application. Since motion analysis is aimed at being used as the basis of vital decisions, its method must be validated using realistic phantoms. This is an important missing element in the recent studies, which we would also like to address. Intracranial aneurysm is a very dangerous and widespread problem. Fortunately, by the increasing use of medical imaging in different diagnoses, un-ruptured aneurysms are nowadays detected fortuitously while checking for other problems and may be treated in one of three ways: preventive surgery, neuro-radiological intervention or careful observation. At the moment, treatment depends mainly on the size and location of the aneurysm. According to studies [Wiebers et al., 2003], and considering the risks involved in surgery, careful observation is preferred for small aneurysms. However, a study in 2004 of 280 patients with ruptured aneurysms showed that a large proportion had small or very small aneurysms [Ohashi et al., 2004]. This means that at the moment there is no reliable means of predicting the rupture. Since observations during surgery shows that the aneurysms pulse, medical researchers are keen to study the relationship between the pulsatility and the rupture. However, there is no existing reliable method to detect this motion. We are therefore working on developing such a method for quantifying pulsation. Considering the fact that the motion is in the range of the noise or image artefacts, pre-processing is of utmost importance. Afterwards, we will focus on improving the state-of-the-art in accurate and robust segmentation. Finally, we want to go beyond the motion estimation methods, to improve current accuracy and automation. The following sections will present the state-of-the-art, the status of the present research, the detailed research plan and the schedule.

2012

, ,

Identity spoofing is a contender for high-security face recognition applications. With the advent of social media and globalized search, our face images and videos are wide-spread on the internet and can be potentially used to attack biometric systems without previous user consent. Yet, research to counter these threats is just on its infancy – we lack public standard databases, protocols to measure spoofing vulnerability and baseline methods to detect these attacks. The contributions of this work to the area are three-fold: firstly we introduce a publicly available PHOTO-ATTACK database with associated protocols to measure the effectiveness of counter-measures. Based on the data available, we conduct a study on current state-of-the-art spoofing detection algorithms based on motion analysis, showing they fail under the light of these new dataset. By last, we propose a new technique of counter-measure solely based on foreground/background motion correlation using Optical Flow that outperforms all other algorithms achieving nearly perfect scoring with an equal-error rate of 1.52% on the available test data. The source code leading to the reported results is made available for the replicability of findings in this article.

2014

A realistic Computed Tomography simulator for small motion analysis of cerebral aneurysms

Shima Sepehri, Jean-Philippe Thiran

2013

Research Proposal

Shima Sepehri

2012