Publication

Impact of Topology Changes in Video Segmentation Evaluation

Touradj Ebrahimi
2004
Conference Papers

Abstract

This work addresses the problem of studying and characterizing topology changes between resulting and reference segmentation masks in video sequences. In particular, the goal of this paper is to examine the impact of individual and combined artifacts found in video object segmentation applications (e.g., added regions and holes). Added regions and holes artifacts are synthetically generated and inserted in a segmentation mask. We performed a psychophysical experiment in which human subjects were asked to rate the annoyance of the generated artifacts when presented alone or in combination. The results show how individual objective metrics can be derived and how an overall objective metric can be predicted by linearly combining individual segmentation errors for a specific video content.

Official source

https://infoscience.epfl.ch/entities/publication/367cff2c-1be5-492a-8c51-1358f644d31a

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.

Graph Chat

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Touradj Ebrahimi
2004
Conference Papers

Abstract

Official source

https://infoscience.epfl.ch/entities/publication/367cff2c-1be5-492a-8c51-1358f644d31a

About this result

Related concepts (32)

Image segmentation

In and computer vision, image segmentation is the process of partitioning a into multiple image segments, also known as image regions or image objects (sets of pixels). The goal of segmentation is to simplify and/or change the representation of an image into something that is more meaningful and easier to analyze. Image segmentation is typically used to locate objects and boundaries (lines, curves, etc.) in images. More precisely, image segmentation is the process of assigning a label to every pixel in an image such that pixels with the same label share certain characteristics.

Object co-segmentation

In computer vision, object co-segmentation is a special case of , which is defined as jointly segmenting semantically similar objects in multiple images or video frames. It is often challenging to extract segmentation masks of a target/object from a noisy collection of images or video frames, which involves object discovery coupled with . A noisy collection implies that the object/target is present sporadically in a set of images or the object/target disappears intermittently throughout the video of interest.

Final topology

In general topology and related areas of mathematics, the final topology (or coinduced, strong, colimit, or inductive topology) on a set with respect to a family of functions from topological spaces into is the finest topology on that makes all those functions continuous. The quotient topology on a quotient space is a final topology, with respect to a single surjective function, namely the quotient map. The disjoint union topology is the final topology with respect to the inclusion maps.

Related publications (7)

Impact of Topology Changes in Video Segmentation Evaluation

Chat with Graph Search

How Well Does GPT-4o Understand Vision? Evaluating Multimodal Foundation Models on Standard Computer Vision Tasks

Imaging of G protein-coupled receptors in solid-supported planar membranes at the single molecule level

An analytic finite capacity queueing network model capturing blocking, congestion and spillbacks