I am the general chair for the European Signal Processing Conference (EUSIPCO) 2021 organised in Dublin. Proceedings are published with IEEEXplore and open access with EURASIP.
Follow us on twitter @eusipco2021 and check out the conference website.
Automatic Asset Mapping
Using computer vision and deep learning to automate registration of assets for telecoms operators, utility companies and civil infrastructure providers, AIMapIT replaces manual site surveys with fast, accurate detection and geotagging of assets from street level imagery with 2m accuracy.
ADAPT Research centre
I am a Principal Investigator with the SFI Adapt Research Centre facilitating research collaborations
GRAISearch project (Use of Graphics Rendering and Artificial Intelligence for Improved Mobile Search Capabilities, Grant agreement ID: 612334) is aiming at developing and applying revolutionary graphics rendering and artificial intelligence (AI) methods to an existing social media search engine platform.
Computer Animation and Virtual Worlds (2017),
Computers & Graphics (2017)
Bonseyes project (Platform for Open Development of Systems of Artificial Intelligence,Grant agreement ID: 732204) is an open and expandable AI platform. It will transform AI development from a cloud centric model, dominated by large internet companies, to an edge device centric model through a marketplace and an open AI platform.
ACM Internet of Thing (2020),
Deep Learning (or Machine Learning with Neural Networks) is a very popular approach for designing
data-driven artificial intelligence (AI). It is used in many of our applications for object detection, image enhancement, data synthesis etc.
Latest publications: IEEE ICASSP (2021),
ACM IoT (2020),
Shapes & Patterns
Pattern analysis is an important part for image processing.
Some of our works have focused on developping robust techniques (e.g. M-estimation, Hough Transform, L2) for pattern registration (e.g. ellipse fitting) and reconstruction (e.g. 3D reconstruction from multiple views using RGB and RGB-D cameras).
Pattern Recognition (PR) (2018),
Colour transfer aims at changing the colour feel of an image (target image) using the colour palette of another image (palette image). Colour transfer can also be applied to videos, and for creating dynamic effects on static images.
We have proposed several approaches to solve this problem based on Optimal Transport and information theory (L2 with GMM) as cost functions to minimize between colour distributions.
Road Scene Analysis
Object detection in road scene sequential images has many applications from mapping to autonomous driving. My PhD thesis (2001) investigated linear machine learning techniques (PCA) and histogram backprojections for object detection and recognition. Our more recent approaches use Convolutional Neural Networks (CNNs).
Publications: IMVIP (2020), Remote Sensing (2018), ICIP 2018,
Climate change is affecting people and their way of life including transportation of goods and people. Our work (2019) proposes to analyse satellite imagery in combination with street view imagery posted on social media during flooding events, for assessing the passability of roads. More recently (2020), we propose to infer 3d shape of roofs from aerial imagery (e.g. for measuring solar energy potentials).
Latest publications: Remote Sensing (2020)
Signal Processing: Image Communication (2019)
AI and Graphs
This research project addresses Deep Learning and Structural Knowledge for image analysis.
It is a collaboration between University of Angers (Jean-Baptiste Fasquel lead PI, and Jérémy Chopin PhD candidate), Nantes (Harold Mouchère, LS2N/IPI), and Paris (Isabelle Bloch (LTCI, Paris).
Latest publications: IPTA (2020)
Blendshape facial rigs are used extensively in the industry for facial
animation of virtual humans. This research project explores the noticeability of blendshapes
and presents new perceptually
based models to predict perceptual importance of blendshapes (collaboration with Rachel McDonnell lead PI).
Latest publications: MIG (2020 Best short paper award)
Drone Images Trinity 2017
Capturing and inferring 3D maps have many applications for Augmented Reality, GIS, urban planning, etc.
In collaboration with Intel Movidius, a drone survey of TCD campus was captured
in the summer 2017 allowing images and 3D point cloud to be available as open dataset.
Dataset Publication: Tara (2017)
This github repo shares some of the material (i.e. code in R and Rmd + lecturenotes in pdf and tex)
used for teaching Applied Forecasting (5 ECTS) in Trinity College Dublin (2008-2020) for Sophisters.
Please give credits if you find these materials useful.
Links: Github and Lecturenotes.
Generalized Linear Models
My lecturenotes are available online in html format.
These were used for teaching a course (5 ECTS) in Trinity College Dublin (2008-2018) for Sophisters.
Please give credits if you find these materials useful.
Bootstrap, Jackknife and other resampling methods
This github repo contains some of the materials used for teaching Bootstrap, Jackknife and other resampling methods
(6 contact hours as part of a 5 ECTS Sophister class in Trinity College Dublin, 2005 & 2007).
Beamer slides are provided as tex files and the resulting PDF RzDBootstrap.pdf is also available.
I share several templates on overleaf for writing documents in LaTeX: a Report Template, the Article Template used in the IMVIP
and a template for putting together several pdf articles to form a book that has been used for the IMVIP book of proceedings Book of PDFs Template.
Videos are available on youtube presenting demos, seminars, interviews from my group,
and I also edited a few for preparing EUSIPCO 2021.