Mediaspace scheduled maintenance: Aug 25, 2026 07:00 - 12:00 AM. During this time, videos will be temporarily unavailable. Check status updates.

Lecture

Segmentation: Techniques and Applications

In course

CS-442: Computer vision

Computer Vision aims at modeling the world from digital images acquired using video or infrared cameras, and other imaging sensors. We will focus on images acquired using digital cameras. We will introduce basic processing techniques and discuss their fie ...

Description

This lecture covers various segmentation techniques such as region segmentation, histogram splitting, and SLIC superpixels, along with their applications in image recognition, tracking, and compression. It also explores the use of convolutional neural networks for segmentation and the benefits of using U-Net and ConyNet models. The instructor demonstrates the process of speeding up analysis through automated and semi-automatic methods, emphasizing substantial time savings. Additionally, the lecture delves into recursive segmentation, interactive segmentation, and the importance of context features in improving segmentation accuracy.

This video is available exclusively on Mediaspace for a restricted audience. Please log in to MediaSpace to access it if you have the necessary permissions.

Watch on Mediaspace

Instructor

Pascal Fua

Pascal Fua received an engineering degree from Ecole Polytechnique, Paris, in 1984 and the Ph.D. degree in Computer Science from the University of Orsay in 1989. He then worked at SRI International and INRIA Sophia-Antipolis as a Computer Scientist. He joined EPFL in 1996 where he is now a Professor in the School of Computer and Communication Science and heads the Computer Vision Laboratory. His research interests include shape modeling and motion recovery from images, analysis of microscopy images, and Augmented Reality. His research interests include shape modeling and motion recovery from images, analysis of microscopy images, and machine learning. He has (co)authored over 300 publications in refereed journals and conferences. He is an IEEE Fellow and has been an Associate Editor of IEEE journal Transactions for Pattern Analysis and Machine Intelligence. He often serves as program committee member, area chair, and program chair of major vision conferences and has cofounded three spinoff companies (Pix4D, PlayfulVision, and NeuralConcept).

Official source

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.

Image compression

Image compression is a type of data compression applied to s, to reduce their cost for storage or transmission. Algorithms may take advantage of visual perception and the statistical properties of image data to provide superior results compared with generic data compression methods which are used for other digital data. Image compression may be lossy or lossless. Lossless compression is preferred for archival purposes and often for medical imaging, technical drawings, clip art, or comics.

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.

Data compression

In information theory, data compression, source coding, or bit-rate reduction is the process of encoding information using fewer bits than the original representation. Any particular compression is either lossy or lossless. Lossless compression reduces bits by identifying and eliminating statistical redundancy. No information is lost in lossless compression. Lossy compression reduces bits by removing unnecessary or less important information.

Compression artifact

A compression artifact (or artefact) is a noticeable distortion of media (including , audio, and video) caused by the application of lossy compression. Lossy data compression involves discarding some of the media's data so that it becomes small enough to be stored within the desired or transmitted (streamed) within the available bandwidth (known as the data rate or bit rate). If the compressor cannot store enough data in the compressed version, the result is a loss of quality, or introduction of artifacts.

Related lectures (50)

JPEG XS & JPEG XL: Next-Gen Image Compression

Explores the cutting-edge JPEG XS and JPEG XL image compression standards, emphasizing their efficiency and versatility in various applications.

JPEG 2000: Image Compression

Explores image compression principles, focusing on JPEG 2000, covering transform-based coding, quantization, entropy coding, region of interest, error resilience, and software implementations.

Deep Learning: No Free Lunch Theorem and Inductive Bias

Covers the No Free Lunch Theorem and the role of inductive bias in deep learning and reinforcement learning.

Data Compression: Shannon-Fano Algorithm

Explores the Shannon-Fano algorithm for efficient data compression and its applications in lossless and lossy compression techniques.

Data Compression and Shannon's Theorem: Lossy Compression