ConferenceProgram

20thScandinavianConferenceonImageAnalysis12-14JuneTromsø,Norway

Sponsorships

Organizedby

Sponsorships

UiTMachine

LearningGroup

Page|1

Table of Contents

Welcome .......................................................................................... 2

Acknowledgments ............................................................................ 4

Contacts ........................................................................................... 7

General Information ......................................................................... 9

Pre-conference Tutorial .................................................................. 13

Conference Schedule ...................................................................... 16

Keynote Speakers ........................................................................... 22

Page|2

Welcome

Welcome to the 20th Scandinavian Conference on Image

Analysis.

We are pleased to welcome you to Tromsø and to Scandic

Ishavshotel. We are looking forward to an enjoyable and

stimulating event with high-quality contributions from

authors and from a strong group of invited speakers.

For this SCIA edition, we received almost 140 submissions of

which 87 have been accepted for publication in the

proceedings. The acceptance rate has been approximately

63%. 33 papers have been accepted for oral presentations,

and 54 as poster presentations.

We would like to acknowledge all the people who made

exceptional efforts and dedicated their time to bring this

conference together; we were honored to work with them.

In particular, we express our gratitude to the co-chairs, the

program committee members and the anonymous

reviewers for their invaluable support during the

Page|3

review process.

Likewise, we wish to thank our invited speakers for accepting

the invitation and for providing top-notch talks, which

contribute to make SCIA an international event with the

highest standards.

We would like to acknowledge our sponsors (inside cover).

SCIA 2017 would not be possible without their support.

At the conference, we will present the Tobii best paper award

and a best student paper award to honor some of the most

promising research from the technical program. We will also

present the best Nordic PhD thesis award (2015-2016).

We hope you will enjoy the 20th edition of SCIA and your stay

in Tromsø.

Sincerely,

Robert Jenssen

Filippo Maria Bianchi

Puneet Sharma

Page|4

Acknowledgments

SCIA 2017 is organized by the UiT The Arctic University of

Norway and NOBIM, and is sponsored by:

Tobii

The Norwegian Computing Center

SINTEF

Norut

IAPR - International Association of Pattern Recognition

The Research Council of Norway

Springer

The World Federation of Soft Computing

General chair

Robert Jenssen, Machine Learning Group, UiT The

Arctic University of Norway

Program chair

Filippo Maria Bianchi, Machine Learning Group, UiT

The Arctic University of Norway

Puneet Sharma, UiT The Arctic University of Norway

Page|5

Co-chairs

Arnt-Børre Salberg, Norwegian Computing Center, Norway

Jon Yngve Hardeberg, Norwegian University of Science and

Technology, Norway

Trym Haavardsholm, Forsvarets forskningsinstitutt, Norway

Program committee

Adrien Bartoli, ISIT – CENTI – Faculté de Médecine, France Anders Heyden, Lund University, Sweden Anne H. Schistad Solberg, University of Oslo, Norway Arnt-Børre, Norwegian Computing Center, Norway Atsuto Maki, Kungliga Tekniska Högskolan, Sweden Cristina Soguero Ruiz, Rey Juan Carlos University, Spain Daniele Nardi, University Sapienza, Italy Domenico Daniele Bloisi, University Sapienza, Italy Enrico Maiorino, University Sapeinza, Italy Erkki Oja, Aalto University, Finland Fredrik Kahl, Lund University, Sweden Gustau Camps-Valls, University of Valencia Heikki Kälviäinen, Lappeenranta University of Technology,

Finland Helene Schulerud, Sintef, Norway Ingela Nyström, Uppsala University, Sweden Janne Heikkilä, University of Oulu, Finland Jens Thielemann, SINTEF, Norway Joni Kämäräinen, Tampere University of Technology, Finland Karl Øyvind Mikalsen, UiT The Arctic University of Norway Kjersti Engan, University of Stavanger, Norway Lasse Riis Østergaard, Aalborg University, Denmark Lorenzo Livi, University of Exeter, UK Mads Nielsen, University of Copenhagen, Denmark Marco Loog, Delft University of Technology, The

Netherlands

Page|6

Michael Felsberg, Linkoping University, Sweden Michael Kampffmeyer, UiT The Arctic University of Norway Norbert Krüger, University of Southern Denmark, Denmark Rasmus Paulsen, Technical University of Denmark Sigurd Løkse, UiT The Arctic University of Norway Simone Scardapane, University Sapienza, Italy Thomas Moeslund, Aalborg University, Denmark

Page|7

Contacts

Conference Organizers

Robert Jenssen

robert.jenssen@uit.no

(+47) 41699612

Filippo Maria Bianchi

filippo.m.bianchi@uit.no

(+47) 48507933

Puneet Sharma

puneet.sharma@uit.no

(+47) 45063429

Page|8

Conference Hotel

Scandic Ishavshotel, Fredrik Langesgate 2, Tromsø

(+47) 77666400

ishavshotel@scandichotels.com

www.scandichotels.com/hotels/norway/tromso/scandic-

ishavshotel

Page|9

General information

Venue All oral paper presentations and poster presentations will take place in

a single track at Scandic Ishavshotel.

Services Included in the registration:

Free Wi-Fi

Fruit and juice buffet in the morning

Lunch buffet

Cake and fruit for the afternoon break

Coffee, tea and water available for the whole conference

duration

Icebreaker cocktail Join us on the evening of Sunday 11 at 18:30, after the tutorial, for an

icebreaker cocktail at the Polaria musem. Polaria is in walking distance

from the conference hotel. This is a great chance to meet the other

participants before the start of the conference and to explore Tromsø

city center.

Page|10

Social Dinner In the evening of Monday 12 after 17:00 there will be an organized trip

to Fjellheisen, the mountain dominating Tromsø island. The top is

easily accessible for everyone through a cable car. Dinner will take

place in the panoramic restaurant on the mountain top.

SCIA Banquet The evening of Tuesday 13 a banquet dinner will be offered to all the

conference participants at the SCIA conference hotel at 19:00.

Banks and exchange offices Banks in Norway are open Monday through Friday 09.00 to 15.00. ATM

(Automatic Teller Machine) facilities are available at most banks.

Please note that the SCIA secretariat does not offer bank services.

Drinking Water Tap water is safe to drink everywhere in Norway.

Electricity 230 Volts, 50 Hz.

Page|11

Emergency Dial 112 to the police, 110 to the fire station, 113 to the ambulance.

Smoking The conference area is non-smoking. There are designated areas for

smoking outside.

Currency The currency in Norway is the Norwegian Crown (NOK).

1 EUR ≈ 9.45 NOK.

1 USD ≈ 8.65 NOK.

Transportation

Public transportation in Tromsø includes taxi and bus.

The conference hotel can be reached from the airport by bus.

Taxi:

http://www.tromso-taxi.no/ - Tel. (+47) 03011

http://www.dintaxi.no/ - (+47) Tel. 02045

Bus:

https://www.tromskortet.no/

Bus Apps:

https://play.google.com/store/apps/details?id=no.bouvet.routeplanne

r.troms&hl=en (check bus stops and times)

https://play.google.com/store/apps/details?id=no.wtw.mobillett.trom

so&hl=en (buy bus tickets – credit card needed)

Map

Page|13

Pre-conference Tutorial

Sunday 11 14:00 - 15:30 Tutorial lecture (part 1) 15:30 - 16:00 Coffee break 16:00 - 17:30 Tutorial lecture (part 2) 17:30 - 18:00 Q&A and discussion 18:30 - 19:30 Ice-breaker cocktail at the Polaria museum Abstract - Deep Visual Features - Selection, Fusion, and Compression with Applications in Visual Object Tracking

The tutorial will explain how to use Deep Features for enabling state-of-the-art results in computer vision tasks, in particular visual object tracking. Visual object tracking is a difficult task in three respects, since a) it needs to be performed in real-time, b) the only available information about the object is an image region in the first frame, and c) the internal object models needs to be updated in each frame. The use of carefully chosen Deep Features gives significantly improvements regarding accuracy and robustness of the object tracker, but straightforward frame-wise updates of the object model become prohibitively slow for real-time performance. Also, state-of-the-art results require an appropriate fusion of multi-level Deep Features. By introducing a compact representation of Deep Features, smart fusion and updating mechanisms, and exploiting systematically GPU implementations for feature extraction and optimization, real-time performance is achievable without jeopardizing tracking quality. The tutorial will cover some basic theory of Deep Features, both for visual appearance and optical flow. Basics about multi-layer networks, receptive fields, convolutional layers, pooling, and invariance will be explained. The different levels of Deep Features cover respectively different aspects of the input data and it will be explained what kind of information is covered by these levels. Since the spatial resolution varies between layers, fusing of multi-level Deep Features is non-trivial and the tutorial will explain how this is achieved in an efficient way. Finally, not all feature dimensions are required to solve the addressed task and although a certain feature might be highly informative, its relevance to the addressed task might be low. In its final part, the tutorial will explain how to select relevant feature dimensions.

Page|14

Michael Felsberg received a Ph.D. degree in engineering from the University of Kiel, Germany, in 2002. Since 2008, he has been a Full Professor and the Head of the Computer Vision Laboratory, Linköping University, Sweden. His current research interests include signal processing methods for image analysis, computer and robot vision, and machine learning. He has published more than 100 reviewed conference papers, journal articles, and book contributions. He was a recipient of awards from the German Pattern Recognition Society in 2000, 2004, and 2005, from the Swedish Society for Automated Image Analysis in 2007 and 2010,

from Conference on Information Fusion in 2011 (Honorable Mention), from the CVPR Workshop on Mobile Vision 2014, and from ICPR 2016 (best scientific paper in Computer Vision). He has achieved top ranks on various challenges (VOT: 3rd 2013, 1st 2014, 2nd 2015, 1st 2016; VOT-TIR: 1st 2015 and 2016; OpenCV Tracking: 1st 2015; KITTI Stereo Odometry: 1st 2015, March). He has coordinated the EU projects COSPAL and DIPLECS, he is an Associate Editor of the Journal of Mathematical Imaging and Vision, Journal of Image and Vision Computing, Journal of Real-Time Image Processing, Frontiers in Robotics and AI. He was Publication Chair of the International Conference on Pattern Recognition 2014 and Track Chair 2016, he was the General Co-Chair of the DAGM symposium in 2011, and he will be general Chair of CAIP 2017.

Page|16

Conference Schedule

Oral Sessions

Oral session 1 – Monday 12, 09:50

Tobias Bottger, Markus Ulrich, and Carsten Steger, “Subpixel-Precise Tracking of Rigid Objects in Real-time”.

Rasmus R. Jensen, Jonathan D. Stets, Seidi Suurmets, Jesper Clement, and Henrik Aanæs, “Wearable Gaze Trackers: Mapping Visual Attention in 3D”.

Oral session 2 – Monday 12, 11:00

Tomas Pajdla and Michal Polic, “Uncertainty Computation in Large 3D Reconstruction”.

Markus Ylimaki, Juho Kannala, and Janne Heikkila, “Robust and Practical Depth Map Fusion for Time-of-Flight Cameras”.

Sebastian Nesgaard Jensen, Jakob Wilm, and Henrik Aanæs, “An Error Analysis of Structured Light Scanning of Biological Tissue”.

Oral session 3 – Monday 12, 15:00

Carina Jensen, Anne Sofie Korsager, Lars Boesen, Lasse Riis Østergaard, and Jesper Carl, “Computer Aided Detection of Prostate Cancer on Biparametric MRI using a Quadratic Discriminant Model”.

Gabriel Eilertsen, Per-Erik Forssen, and Jonas Unger, “BriefMatch: Dense binary feature matching for real-time optical flow estimation”.

Arun Mukundan, Giorgos Tolias, and Ondrej Chum, “Robust Data Whitening as an Iteratively Re-weighted Least Squares Problem”.

Oral session 4 – Monday 12, 16:00

Ian E. Nordeng, Ahmad Hasan, Doug Olsen, Jeremiah Neubert, “DEBC Detection with Deep Learning”.

Mikko Lauri and Simone Frintrop, “Object proposal generation applying the distance dependent Chinese restaurant process”.

Rao Muhammad Anwer, Fahad Shahbaz Khan, Joost van de Weijer, Jorma Laaksonen, “Top-Down Deep Appearance Attention for Action Recognition”.

Page|17

Oral session 5 – Tuesday 13, 09:50

Karsten Vogt and Jorn Ostermann, “Soft Margin Bayes-Point-Machine Classification via Adaptive Direction Sampling”.

Karl Skretting and Kjersti Engan, “Sparse Approximation by Matching Pursuit using Shift-Invariant Dictionary”.

Oral session 6 – Tuesday 13, 11:00

Malte S. Nissen, Oswin Krause, Kristian Almstrup, Søren Kjærulff, Torben T. Nielsen, and Mads Nielsen, “Convolutional neural networks for segmentation and object detection of human semen”.

Michael Kampffmeyer, Sigurd Løkse, Filippo M. Bianchi, Robert Jenssen, and Lorenzo Livi, “Deep Kernelized Autoencoders”.

Rasmus R. Paulsen, Kasper Korsholm Marstal, Søren Laugesen, and Stine Harder, “Creating ultra dense point correspondence over the entire human head”.

Oral session 7 – Tuesday 13, 16:00

Gary A. Atkinson, “Two-source surface reconstruction using polarization”.

Aidin Hassanzadeh, Arto Kaarna, and Tuomo Kauranne, “Unsupervised Multi-Manifold Classification of Hyperspectral Remote Sensing Images with Contractive Autoencoder”.

Arnt-Børre Salberg, Øivind Due Trier, and Michael Kampffmeyer, “Large-scale mapping of small roads in lidar images using deep convolutional neural networks”.

Oral session 8 – Tuesday 13, 17:00

Georg Radow, Michael Breuß, Laurent Hoeltgen, and Thomas Fischer, “Optimised Anisotropic Poisson Denoising”.

Johannes Meyer, Thomas Langle, and Jurgen Beyerer, “General Cramér-von Mises, a Helpful Ally for Transparent Object Inspection using Deflection Maps?”.

Gilles Pitard, Gaetan Le Goıc, Alamin Mansouri, Hugues Favreliere, Maurice Pillet, Sony George, and Jon Yngve Hardeberg, “Robust anomaly detection using Reflectance Transformation Imaging for surface quality inspection”.

Oral session 9 – Wednesday 14, 09:50

Jukka Kaipala, Miguel Bordallo López, Simo Saarakkala, and Jérôme Thevenot, “Automatic Segmentation of Bone Tissue

Page|18

from Computed Tomography Using a Volumetric Local Binary Patterns Based Method”.

Sahar Zafari, Tuomas Eerola, Jouni Sampo, Heikki Kalviainen, and Heikki Haario, “Comparison of Concave Point Detection Methods for Overlapping Convex Objects Segmentation”.

Oral session 10 – Wednesday 14, 11:00

Mohammad A. Haque, Kamal Nasrollahi, and Thomas B. Moeslund, “Estimation of Heartbeat Peak Locations and Heartbeat Rate from Facial Video”.

Aleksei Tiulpin, Jerome Thevenot, Esa Rahtu, and Simo Saarakkala, “A novel method for automatic localization of joint area on knee plain radiographs”.

Anne Krogh Nøhr, Louise Pedersen Pilgaard, Bolette Dybkjær Hansen, Rasmus Nedergaard, Heidi Haavik, Rene Lindstroem, Maciej Plocharski, and Lasse Riis Østergaard, “Semi-Automatic Method for Intervertebral Kinematics Measurement in the Cervical Spine”.

Oral session 11- Wednesday 14, 15:00

Christian Herrmann, Dieter Willersinn, and Jurgen Beyerer, “Residual vs. Inception vs. Classical Networks for Low-Resolution Face Recognition”.

Radim Spetlık, Jan Cech, Vojtech Franc, and Jirı Matas, “Visual Language Identification from Facial Landmarks”.

Sigurd Løkse, Filippo M. Bianchi, Arnt-Børre Salberg, and Robert Jenssen, “Spectral Clustering using PCKID - A Probabilistic Cluster Kernel for Incomplete Data”.

Oral session 12 – Wednesday 14, 16:00

Melanie Pohl, Dimitri Bulatov, and Jochen Meidow, “Simplification of Polygonal Chains by Enforcing Few Distinctive Edge Directions”.

Måns Larsson, Jennifer Alven, and Fredrik Kahl, “Max-Margin Learning of Deep Structured Models for Semantic Segmentation”.

Øyvind Meinich-Bache, Kjersti Engan, Trygve Eftestøl, and Ivar Austvoll, “Detecting Chest Compression Depth using a Smartphone Camera and Motion Segmentation”.

Copyright @ All Rights Reserved

Page|19

Poster Sessions Schedule Poster session 1 – Monday 12, 13:50

Averaging three-dimensional time-varying sequences of rotations: application to preprocessing of motion capture data

Plane Refined Structure from Motion A Time-Efficient Optimisation Framework for Parameters of Optical Flow

Methods Image processing of leaf movements in Mimosa pudica using Matlab Evaluation of Visual Tracking Algorithms for Embedded Devices Multimodal Neural Networks: RGB-D for Semantic Segmentation and

Object Detection Structure from Motion by Artificial Neural Networks Pipette Hunter: patch-clamp pipette detection Framework for machine vision based traffic sign inventory Copy-Move Forgery Detection Using the Segment Gradient Orientation

Histogram Object Tracking via Pixel-wise and Block-wise Sparse Representation Supervised Approaches for Function Prediction of Proteins Contact

Networks from Topological Structure Information

Poster session 2 – Tuesday 13, 13.50

ConvNet Regression for Fingerprint Orientations Domain Transfer for Delving into Deep Networks Capacity to De-Abstract

Art Foreign Object Detection in Multispectral X-ray Images Diagnosis of Broiler Livers by Classifying Image Patches Historical Document Binarization Combining Semantic Labeling and

Graph Cuts Convolutional Neural Networks for False Positive Reduction of

Automatically Detected Cilia in Low Magnification TEM Images Automatic Emulation by Adaptive Relevance Vector Machines Deep Learning for Polar Bear Detection Crowd Counting Based on MMCNN in Still Images Generation and Authoring of Augmented Reality Terrains Through Real-

Time Analysis of Map Images

Poster session 3 – Tuesday 13, 15:00

Solution of Pure Scattering Radiation Transport Equation (RTE) using Finite Difference Method (FDM)

Page|20

Augmented Reality Interfaces for Additive Manufacturing Dynamic Exploratory Search in Content-Based Image Retrieval Block-Permutation-Based Encryption Scheme with Enhanced Color

Scrambling Synthetic Aperture Radar (SAR) monitoring of avalanche activity: An

automated detection scheme Canonical Analysis of Sentinel-1 Radar and Sentinel-2 Optical Data A Noncentral and Non-Gaussian Probability Model for SAR Data A clustering approach to heterogeneous change detection

Poster session 4 – Wednesday 14, 13:00

Local Adaptive Wiener Filtering for Class Averaging in Single Particle Reconstruction

Decoding gene expression in 2D and 3D Segmentation of multiple structures in chest radiographs using multi-

task fully convolutional networks Memory effects in subjective quality assessment of x-ray images Multispectral constancy based on spectral adaptation transform Classification of Fingerprints Captured Using Optical Coherence

Tomography State estimation of the performance of gravity tables using multispectral

image analysis Interpolation from Grid Lines: Linear, Transfinite and Weighted Method Automated Pain Assessment in Neonates Enhancement of Cilia Sub-structures by Multiple Instance Registration

and Super-resolution Reconstruction

Poster session 5 – Wednesday 14, 13:50

Leaflet Free Edge Detection for the Automatic Analysis of Prosthetic Heart Valve Opening and Closing Motion Patterns from High Speed Video Recordings

Robust Abdominal Organ Segmentation Using Regional Convolutional Neural Networks

Non-reference image quality assessment for fingervein presentation attack detection

Feature space clustering for trabecular bone segmentation Airway-Tree Segmentation in Subjects with Acute

Respiratory Distress Syndrome Context Aware Query Image Representation for Particular

Object Retrieval

Page|21

Granulometry-Based Trabecular Bone Segmentation Automatic Segmentation of Abdominal Fat in MRI-Scans, using Graph-

Cuts and Image Derived Energies HDR imaging pipeline for spectral filter array cameras Thistle detection An image-based method for objectively assessing injection moulded

plastic quality Collaborative Representation of Statistically Independent Filters’

Response: An Application to Face Recognition under Illicit Drug Abuse Alterations

Page|22

Keynote Speakers

Klaus Robert Müller (IAPR Invited Speaker)

Klaus-Robert Müller received the Diploma degree in mathematical physics in 1989 and the Ph.D. in theoretical computer science in 1992, both from University of Karlsruhe, Germany. From 1992 to 1994 he worked as a Postdoctoral fellow at GMD FIRST, in Berlin where he started to built up the intelligent data analysis (IDA) group. From 1994 to 1995 he was a European Community STP Research Fellow at University of Tokyo in Prof. Amari's Lab. From 1995 until 2008 he was head of department of the IDA group at GMD FIRST

(since 2001 Fraunhofer FIRST) in Berlin and since 1999 he holds a joint associate Professor position of GMD and University of Potsdam. In 2003 he became a full professor at University of Potsdam, in 2006 he became chair of the machine learning department at TU Berlin. He has been lecturing at Humboldt University, Technical University Berlin and University of Potsdam. In 1999 he received the annual national prize for pattern recognition (Olympus Prize) awarded by the German pattern recognition society DAGM, in 2006 the SEL Alcatel communication award and in 2014 he was granted the Science Prize of Berlin awarded by the Governing Mayor of Berlin. Since 2012 he is Member of the German National Academy of Sciences Leopoldina and he holds a distinguished professorship at Korea University in Seoul. He serves in the editorial boards of Computational Statistics, IEEE Transactions on Biomedical Engineering, Journal of Machine Learning Research and in program and organization committees of various international conferences.(services) His research areas include statistical learning theory for neural networks, support vector machines and ensemble learning techniques. He contributed to the field of signal processing working on time-series analysis, statistical denoising methods and blind source separation. His present application interests are expanded to the analysis of biomedical data, most recently to brain computer interfacing, genomic data analysis, computational chemistry and atomistic simulations.

Page|23

Machine learning and AI for the sciences -- towards understanding

Abstract

In recent years machine learning (ML) and Artificial Intelligence (AI) methods have begun to play a more and more enabling role in the sciences and in industry.

In particular the advent of large and/or complex data corpora has given rise to new technological challenges and possibilities.

The talk will touch upon the topic of ML applications in sciences, here, in Neuroscience and Physics and discuss possibilities for extracting information from machine learning models for furthering our understanding by explaining nonlinear ML models.

Finally briefly perspectives and limits will be outlined.

Page|24

Henrik Christensen

Dr. Henrik I. Christensen is a Professor of Computer Science at Dept. of Computer Science and Engineering UC San Diego. He is also the director of the Institute for Contextual Robotics. Prior to UC San Diego he was the founding director of Institute for Robotics and Intelligent machines (IRIM) at Georgia Institute of Technology (2006-2016). Dr. Christensen does research on systems integration, human-robot interaction, mapping and robot vision. The research is performed within the Cognitive Robotics Laboratory. He has published more than 350 contributions across AI,

robotics and vision. His research has a strong emphasis on "real problems with real solutions". A problem needs a theoretical model, implementation, evaluation, and translation to the real world. He is actively engaged in the setup and coordination of robotics research in the US (and worldwide). Dr. Christensen received the Engelberger Award 2011, the highest honor awarded by the robotics industry. He was also awarded the "Boeing Supplier of the Year 2011" with 3 other colleagues at Georgia Tech. Dr. Christensen is a fellow of American Association for Advancement of Science (AAAS) and Institute of Electrical and Electronic Engineers (IEEE). He recieved an honorary doctorate in engineering from Aalborg University 2014. He collaborates with institutions and industries across three continents. His research has been featured in major media such as CNN, NY Times, and BBC.

Vision of everyday service tasks

Abstract

There is now an abundance of cameras in the world. The cost of a camera in volume is about $1. The opportunity to recognize everyday objects, perform servoing to interact with objects, recognize people and estimate their pose opens many interesting opportunities for designing systems for use in manufacturing, service and healthcare applications. In this presentation we will present embedded vision applications for daily tasks and outline how progress on recognition, pose estimation, 3D model estimation opens many avenues for increased use of camera system to design of intelligent systems.

Page|25

Jeremy Wolfe Dr. Jeremy Wolfe is Professor of Ophthalmology and Professor of Radiology at Harvard Medical School. He is Director of the Visual Attention Lab and the Center for Advanced Medical Imaging at Brigham and Women's Hospital. Wolfe received an AB in Psychology in 1977 from Princeton and his PhD in Psychology in 1981 from MIT under the supervision of Richard Held. His research focuses on visual search and visual attention with a particular interest in socially important search tasks in areas such as medical image perception (e.g. cancer screening), security (e.g. baggage screening), and intelligence. He is

Immediate Past-Chair of the Psychonomic Society and just ended his term as Editor of Attention, Perception, and Psychophysics.

The Incidental Gorilla: What can the science of visual attention tell us about the art of radiology?

Abstract

We cannot simultaneously recognize every object in our field of view. As a result we deploy attention from object to object or place to place, searching for what we need. This is true whether we are looking for the cat in the bedroom or nodules in a lung CT. We do not search at random. Our attention is guided by the features of the targets we seek and the structure of the scenes in which those targets are embedded; again, whether that scene is the bedroom or the lung. Unfortunately, our search engine does not work perfectly and we sometimes fail to find what we seek. When those missed targets are such things as tumors or bombs, these errors are socially significant, worth understanding and, if possible, correcting. In this talk, I will illustrate some of the basic principles of human visual attention and I will present data showing how those principles play out in the realm of medical image perception.

Page|26

Gustau Camps-Valls

Gustau Camps-Valls is an associate professor (hab. Full professor) in the Department of Electronics Engineering. He is a research coordinator in the Image and Signal Processing (ISP) group. He has been Visiting Researcher at the Remote Sensing Laboratory (Univ. Trento, Italy) in 2002, the Max Planck Institute for Biological Cybernetics (Tübingen, Germany) in 2009, and as Invited Professor at the Laboratory of Geographic Information Systems of the École Polytechnique Fédérale de Lausanne (Lausanne, Switzerland) in 2013.

He is interested in the development of machine learning algorithms for

geoscience and remote sensing data analysis. He is an author of 120 journal papers, more than 150 conference papers, 20 international book chapters, and editor of the books "Kernel methods in bioengineering, signal and image processing" (IGI, 2007), "Kernel methods for remote sensing data analysis" (Wiley & Sons, 2009), and "Remote Sensing Image Processing" (MC, 2011). He's a co-editor of the forthcoming book "Digital Signal Processing with Kernel Methods" (Wiley & sons, 2015). He holds a Hirsch's index h=48 (see Google Scholar page), entered the ISI list of Highly Cited Researchers in 2011, and Thomson Reuters ScienceWatch identified one of his papers on kernel-based analysis of hyperspectral images as a Fast Moving Front research. In 2015, he obtained the prestigious European Research Council (ERC) consolidator grant on Statistical learning for Earth observation data analysis. He is a referee and Program Committee member of many international journals and conferences.

Since 2007 he is member of the Data Fusion technical committee of the IEEE GRSS, and since 2009 of the Machine Learning for Signal Processing Technical Committee of the IEEE SPS. He is member of the MTG-IRS Science Team (MIST) of EUMETSAT. He is Associate Editor of the IEEE Transactions on Signal Processing, IEEE Signal Processing Letters, IEEE Geoscience and Remote Sensing Letters, and invited guest editor for IEEE Journal of Selected Topics in Signal Processing (2012) and IEEE Geoscience and Remote Sensing Magazine (2015).

Page|27

Physics-Aware Gaussian Processes for Earth Observation

Abstract

Earth observation from satellite sensory data pose challenging problems, where machine learning is currently a key player. In recent years, Gaussian Process (GP) regression and other kernel methods have excelled in biophysical parameter estimation tasks from space. GP regression is based on solid Bayesian statistics, and generally yield efficient and accurate parameter estimates. However, GPs are typically used for inverse modeling based on concurrent observations and in situ measurements only. Very often a forward model encoding the well-understood physical relations is available though. In this talk, we introduce three GP models that respect and learn the physics of the underlying processes in the context of inverse modeling. First, we will introduce a Joint GP (JGP) model that combines in situ measurements and simulated data in a single GP model. Second, we present a latent force model (LFM) for GP modeling that encodes ordinary differential equations to blend data-driven modeling and physical models of the system. The LFM performs multi-output regression, adapts to the signal characteristics, is able to cope with missing data in the time series, and provides explicit latent functions that allow system analysis and evaluation. Finally, we present an Automatic Gaussian Process Emulator (AGAPE) that learns the unknown forward physical model in a compact form. AGAPE exploits interpolation and smart acquisition functions that favor sampling in low density regions and flatness of the approximating function. Empirical evidence of the performance of these models will be presented through illustrative examples of vegetation monitoring and atmospheric modeling.

Informationabout

SCIA2017

sponsors

Norsk Regnesentral • Postboks 114 Blindern • NO-0314 Oslo • http://www.nr.no

Norsk Regnesentral (Norwegian Computing Center, NR) is a private and independant, non-profit research foundation.

NR carries out contract research and development for national and international clients from industrial, commercial, and public service organizations.

Our department of Statistical Analysis, Machine Learning and Image Analysis (SAMBA) with 36 research scientists carry out research in many fields covered by the SCIA conference and has a long tradition in supporting the work of The Norwegian Society for Image Processing and Pattern Recognition.

Pho

to: i

stoc

kpho

to.c

om

Intelligent Applied Computer Vision

With an annual turnover of 6,1 M€ and a team of 37 scientists, SINTEF’s Smart Sensor Systems department is the leading independent contract research group within the fields of image analysis, computer vision and applied optics in Norway.

Our core fields are 3D imaging, image and video analysis, robot vision and machine learning.

We develop innovative computer vision systems for industrial use. Our competence in both sensors and computer vision enable us to buildcomplete systems for a wide specter of applications.

Examples include video conferencing, 3D subsea cameras, bin picking, qualitycontrol and drone vision for sense and avoid.

We are applied researchers and our main business is developing robust prototypes for customers.

SINTEF is the largest independent research organisation in Scandinavia. We create value and innovation through knowledge generation and development of technological solutions that are brought into practical use.

SINTEF employs 2000 staff from 75 different countries.

Contact: Research Manager Helene Schulerud Helene.Schulerud@sintef.no

Picture: SINTEF