distributed and interactive systems logo

Follow us on: GitHub YouTube Vimeo Twitter LinkedIn

Master's Thesis Topics available at DIS

Publication date: 22-07-2019

The Distributed & Interactive Systems group at CWI has new open positions for motivated students who would like to work on their Master’s thesis as an internship in the group. Topics include smart textiles, activity recognition, physiological sensing, virtual reality, point clouds, Internet of things and web technologies. Keep reading for more information about research topics, requirements and contact information.

Objective Metrics for Point Cloud Quality Assessment

Contact: Pablo Cesar (p.s.cesar@cwi.nl)

Volumetric data captured by state of the art capture devices, in its most primitive form, consists of a collection of points called a point cloud (PC). A point cloud consists of a set of individual 3D points. Each point, in addition to having a 3D (x, y, z) position, i.e. spatial attribute, may also contain a number of other attributes such as color, reflectance, surface normal, etc. There are no spatial connections or ordering relations specified among the individual points. When a PC signal is processed, for example undergoing lossy compression to reduce its size, it is critical to be able to quantify how well the processed signal is approximating the original one, as in the perception of the end user, which is the human being who will visualize the signal. The goal of this project is to develop a new algorithm (i.e. objective full-reference quality metric) to evaluate the perceptual fidelity of a processed PC with respect to its original version. A framework implementing the objective metrics currently available in literature to assess PC visual quality, and comparing the performance to the proposed method will also be developed. Subjective feedbacks on the visual quality of the signals will be collected from users to serve as ground-truth.

Skills:

  • Good (Matlab, Python or C++) programming skills

Literature:

  • E. Torlig; E. Alexiou; T. Fonseca; R. de Queiroz; T. Ebrahimi, A novel methodology for quality assessment of voxelized point clouds”, 2018. SPIE Optical Engineering + Applications
  • E. Alexiou; T. Ebrahimi, “Benchmarking of objective quality metrics for colorless point clouds”, 2018 Picture Coding Symposium
  • S. Schwarz, M. Preda, V. Baroncini, M. Budagavi, P. Cesar, et.al. Emerging MPEG Standards for Point Cloud Compression. IEEE Journal on Emerging and Selected Topics in Circuits and Systems (IEEE JETCAS), 9(1) : pp. 133-148, 2019.

User Navigation in 6DoF Virtual Reality

Contact: Pablo Cesar (p.s.cesar@cwi.nl)

Nowadays, Virtual Reality (VR) applications are typically designed to provide an immersive experience with three Degrees of Freedom (3DoF): a user who watches a 360-degree video on a Head-Mounted Display (HMD) can choose the portion of the spherical content to view, by rotating the head to a specific direction. Nevertheless, the feeling of immersion in VR results not only from the possibility to turn the head and change the viewing direction but also from changing the viewpoint, moving within the virtual scene. VR applications allowing translations inside the virtual scene are referred to as six Degrees of Freedom (6DoF) applications.

The goal of this project is the development of a platform to capture user’s navigation patterns in 6DoF VR. First, an interface to capture user’s position in the virtual space will be implemented in Unity3D for a HMD equipped with controllers and eventually special sensors for positional tracking. Second, a user study to collect the navigation patterns of actual users in a virtual environment, such a 3D scene model, will be designed and performed. Third, the data will be analyzed to explore correlation between different user’s navigation behavior.

Skills:

  • Unity programming

Literature:

  • X Corbillon, F De Simone, G Simon, P. Frossard, “Dynamic Adaptive Streaming for Multi-Viewpoint Omnidirectional Videos”, Proceedings of the 9th ACM on Multimedia Systems Conference ACM MMsys 2018
  • A. L. Simeone et al., “Altering User Movement Behaviour in Virtual Environments”, IEEE Transactions on Visualization and Computer Graphics 2017
  • http://antilatency.com

Comparing the Performance of Mesh versus Point Cloud-based Compression

Contact: Pablo Cesar (p.s.cesar@cwi.nl)

Recent advances in 3D capturing technologies enable the generation of dynamic and static volumetric visual signals from real-world scenes and objects, opening the way to a huge number of applications using this data, from robotics to immersive communications. Volumetric signals are typically represented as polygon meshes or point clouds and can be visualized from any viewpoint, providing six Degrees of Freedom (6DoF) viewing capabilities. They represent a key enabling technology for Augmented and Virtual Reality (AR and VR) applications, which are receiving a lot of attention from main technological innovation players, both in academic and industrial communities. Volumetric signals are extremely high rate, thus require efficient compression algorithms able to remove the visual redundancy in the data while preserving the perceptual quality of the processed visual signal. Existing compression technologies for mesh-based signals include open source libraries such a Draco (https://github.com/google/draco ). Compression of point clouds signals is currently under standardization. The goal of this project is the development of a platform to compare the performance of mesh versus point cloud based compression algorithms in terms of visual quality of the resulting compressed volumetric object. Starting from a set of high quality point cloud (or mesh) volumetric objects, the corresponding mesh (or point cloud) representations of the same objects are extracted. Each representation is then compressed using a point cloud/mesh-based codec, and the resulting compressed signals are evaluated in terms of objective and subjective quality.

Skills:

  • Good programming skills
  • Computer graphics basics

Literature:

  • Kyriaki Christaki, et al, “Subjective Visual Quality Assessment of Immersive 3D Media Compressed by Open-Source Static 3D Mesh Codecs”, preprint, 2018
  • Gauthier Lafruit et al., “MPEG-I coding performance in immersive VR/AR applications”, IBC 2018
  • M. Berger et al., “A Survey of Surface Reconstruction from Point Clouds”, Computer Graphics Forum 2016
  • https://github.com/google/draco

Human Perception of Volumes

Contact: Pablo Cesar (p.s.cesar@cwi.nl)

Recent advances in 3D capturing technologies enable the generation of dynamic and static volumetric visual signals from real-world scenes and objects, opening the way to a huge number of applications using this data, from robotics to immersive communications. Volumetric signals are typically represented as polygon meshes or point clouds and can be visualized from any viewpoint, providing six Degrees of Freedom (6DoF) viewing capabilities. They represent a key enabling technology for Augmented and Virtual Reality (AR and VR) applications, which are receiving a lot of attention from main technological innovation players, both in academic and industrial communities. The goal of this project is to design and perform a set of psychovisual experiments, using VR technology and visualization via a Head Mounted Display (HMD), in which the impact on human perception of different properties of the volumetric signal representation via point clouds or meshes, such as the convexity and concavity of a surface, the resolution, the illumination and color, are analyzed. First, a review of the state of the art on the perception of volumetric objects will be performed, second a set of open research questions will be chosen and a set of experiments will be designed and performed, and the collected data will be analysed in order to answer the research question.

Skills:

  • Unity programming
  • Interest in human perception analysis

Literature:

  • C. J. Wilson and A. Soranzo, “The Use of Virtual Reality in Psychology: A Case Study in Visual Perception”, Computational and Mathematical Methods in Medicine, 2015
  • J. Zhang et al., “A subjective quality evaluation for 3d point cloud models”, in Proc. of the 2014 International Conference on Audio, Language and Image Processing
  • J. Thorn et al., “Assessing 3d scan quality through paired-comparisons psychophysics test”, in Proc. of the 2016 ACM Conference on Multimedia

Low-Resolution facial Emotion Micro-expression Recognition in the Wild

Contact: Abdallah El Ali (aea@cwi.nl), Pablo Cesar (p.s.cesar@cwi.nl)

Low-resolution (LR) face recognition is a challenging task, especially when the low resolution faces are captured under non-ideal conditions (e.g. mobile settings). Such face images are often contaminated by blur, non-uniform lighting, and non-frontal face pose. While there is work that investigates a variety of techniques (e.g. super resolution) for dealing with LR face images, it is unclear to what extent such methods can be useful for facial micro expression emotion recognition. This project will involve working with existing micro-expression datasets (e.g. CASME II, CAS(ME)2), and exploring different super resolution techniques on both real and artificially downsampled LR images.

Skills:

  • Required: computer vision, machine learning
  • Recommended: deep learning, generative models

Literature:

ThermalEmotions: Exploring thermal cameras for pose-invariant emotion recognition while mobile

Contact: Abdallah El Ali (aea@cwi.nl), Pablo Cesar (p.s.cesar@cwi.nl)

Thermal cameras have the unique advantage of being able to capture thermal signatures (heat radiation) from energy-emitting entities. Previous work has shown the potential of such cameras for cognitive load estimation, even under high pose variance. In this project, you will explore (using a standard computer vision approach) the potential for mobile (FLIR) (or possibly higher resolution) thermal cameras for pose-invariant emotion recognition while users are mobile. The idea is that the emotional signature on a user’s face allows such recognition, when coupled with standard facial expression features even under computer vision challenging conditions. You will use/collect a mobile thermal face dataset, and explore different types of SOTA deep neural network architectures to perform such supervised emotion classification.

Skills:

  • Required: computer vision, machine learning
  • Recommended: human computer interaction

Literature:

Thermal Facial Micro-expression Emotion Recognition

Contact: Gerard Pons (gerard@cwi.nl), Pablo Cesar (p.s.cesar@cwi.nl)

Thermal cameras have the unique advantage of being able to capture thermal signatures (heat radiation) from energy-emitting entities. This project will involve working with existing micro-expression datasets (e.g. CASME II, CAS(ME)2) for pretraining, and collecting a thermal face dataset for exploring different DNN techniques applied to thermal images as a means to capture and quantify facial emotion expressions. This project can also be geared towards thermally detecting differences between spontaneous versus posed facial emotion expressions.

Skills:

  • Required: computer vision, machine learning
  • Recommended: deep learning

Literature:

Exploring DNNs for Music Emotion Recognition and Recommendation

Contact: Abdallah El Ali (aea@cwi.nl), Pablo Cesar (p.s.cesar@cwi.nl)

This project focuses on the emotional analysis of music, and how such techniques can enable better music recommendations. You will likely work on existing datasets (e.g. PMEmo dataset), however you can choose to collect your own if it aligns better with your research interests. You will investigate how DNNs can be used for music emotion recognition, and explore fusion methods for fusing multimodal music data (e.g. tags, waveforms).

Skills:

  • Required: audio signal processing, machine learning
  • Recommended: deep learning

Literature:

Design and Development of a Steering Wheel for Continuous Emotion Annotation

Contact: Abdallah El Ali (aea@cwi.nl), Pablo Cesar (p.s.cesar@cwi.nl), Kaspar Jansen (Design Engineering - TU Delft)

Emotion recognition has moved away from the desktop, and on to the road, whether in automated or non-automated vehicles. This requires collecting precise ground truth labels in such settings, that do not pose driver distraction (whether the primary task is driving or situation monitoring in the case of automated driving). This project asks: How can drivers continuously annotate how they are feeling while driving? How can we ensure that providing such annotation is not distracting from their primary task (e.g. driving)? Initial explorations can include grip / pressure sensing on the steering wheel, possibly rotary knobs, motion-based 3D gesture interaction, and/or the use of ambient light for real-time state feedback. This is a joint project with the Design Engineering department at TU Delft. It will require prototyping emotion input techniques on the steering wheel, and evaluating them in a desktop-based driving simulator study to ensure high usability of the wheel concept and high quality of the collected annotations.

Skills:

  • Required: Hardware and software prototyping (e.g. Arduino), sensors and input techniques, design engineering methods
  • Recommended: Controlled user studies, Unity programming, statistics

Literature:

Comparing AR/VR Emotion Capture Methods for Real-time continuous Emotion Annotation

Contact: Abdallah El Ali (aea@cwi.nl), Pablo Cesar (p.s.cesar@cwi.nl)

Emotion recognition has moved away from the desktop, and on to virtual environments. This requires collecting ground truth labels in such settings. This project asks: How can we continuously annotate how we are feeling while immersed in a mixed or fully virtual environment? What kind of scenarios does this work in, and which scenarios do not? Can we leverage gaze and head movement, and other non-verbal input methods? This project will require prototyping emotion input techniques, and evaluating them in AR or VR environments to ensure high usability and high quality of collected ground truth data.

Skills:

  • Required: programming, prototyping, controlled user studies, statistics
  • Recommended: Unity programming

Literature:

TextileEmotionSensing: Exploring smart Textiles for Emotion Recognition in mobile Interactions

Contact: Abdallah El Ali (aea@cwi.nl), Pablo Cesar (p.s.cesar@cwi.nl)

Can the clothes we wear or chairs we sit on know how we’re feeling? In this project, you will explore a range of smart textiles (e.g. capacitive pressure sensors) for emotion recognition across mobile interactions. Should the textile be embedded in a couch? Should it be attached to the users, and if so, where? Can we robustly detect affective states such as arousal, valence, joy, anger, etc.? This project will require knowledge and know-how of hardware prototyping, and use of fabrication techniques for embedding sensors in such fabrics. It will involve running controlled user studies to collect (and later analyze) such biometric data.

Skills:

  • Required: hardware prototyping (e.g. Arduino, soldering), signal processing, interest in human computer interaction and fabrication
  • Recommended: applied machine learning

Literature:

Developing and comparing Emotion/Mood Induction Methods across Domains

Contact: Abdallah El Ali (aea@cwi.nl), Pablo Cesar (p.s.cesar@cwi.nl)

Affect is a fundamental aspect of internal and external human behavior and processes. While much research has been done on eliciting emotions, it remains a challenge what is the most effective method(s) for inducing emotions, and under which context. In this project, you will design, develop, and test different affect induction procedures, across a range of contexts that involve HMDs, driving simulators, and/or smartphone interaction. Techniques can be visual, auditory, haptic, but also may explore newer techniques such as electrical muscle stimulation.

Skills:

  • Hardware prototyping (e.g. Arduino), experiment design (controlled, field), statistics, interest in human computer interaction

Literature:

ThermalWear II: Exploring Wearable Thermal Displays to Augment Human-Machine Interactions with Affect

Contact: Abdallah El Ali (aea@cwi.nl), Pablo Cesar (p.s.cesar@cwi.nl)

Thermal stimulation is an intrinsic aspect of sensory and perceptual experience, and is tied with several experience facets, including cognitive, emotional, and social phenomena. The capability of thermal stimuli to evoke emotions has been demonstrated in isolation, or to augment media. This project will build on a prior master’s thesis, and extended our ThermalWear prototype in one of several ways: (1) deriving a user calibration model to ensure users have personalized thermal feedback in accordance with their own thermal sensitivities (2) explore thermal feedback across multiple body locations (3) explore how spoken conversations can be augmented with affect (4) explore other directions involving thermal feedback, e.g. multimodal feedback. The project should result in tangible prototypes, and evaluated in a controlled study or in the field.

Skills:

  • Hardware prototyping (e.g. Arduino), human computer interaction, fabrication, thermal and/or multimodal output.

Literature:

PhysiologicalFashion: Visualizing group (emotional) biometric data for smart fashion

Contact: Abdallah El Ali (aea@cwi.nl), Pablo Cesar (p.s.cesar@cwi.nl)

Wearable biotech fashion is becoming a recent trend, however we still know very little on what the best means of visualizing such biometric data. How and when should a necklace visualize a user’s heartbeat? Should a person’s clothe indicate their body heat emission? How should such on-body wearable sensors look like, and should they actuate in the same or a different place? This is a project to explore the intersection between fashion, aesthetics, and wearable biotech sensors. One idea is to focus on visualizing shared biometric synchrony in multi-party settings. The project should result in a series of smart wearable fashion prototypes, and evaluated in the field.

Skills:

  • Hardware prototyping (e.g. Arduino), human computer interaction, fabrication, multimodal output.

Literature:

Discrete or continuous? Designing a Emotion Self-report Collection Approach.

Contact: Surjya Ghosh (surjya@cwi.nl), Pablo Cesar (p.s.cesar@cwi.nl)

Objective: The objective of this project is to find the correlation between two popular emotion models - Ekman’s discrete emotion model, Russell’s circumplex model.

Firstly, users report one of the six discrete emotions, while in the second case, users represent emotion as a combination of activeness and arousal (in continuous scale). However, it is often unknown, whether one model is preferred over the other for usability, simplicity and accuracy. In this project, we aim to find answers to these questions.

Brief Approach: Towards this objective, we design an Android application, which collects self-reports following both these models. It schedules a fixed number of probes (4 to 5) a day and asks user to report their emotion. The emotion collection UI should have two screens - in one screen, users report emotion following discrete model, while in the other one, users report emotion following circumplex model.

We need to collect data over significant period (say one month) from large number of participants (may be 20). We assume that participants do not have idea emotion model. This is necessary otherwise, users may bias the findings.

It is known that every discrete emotion can be expressed as a combination of activeness and pleasure. So, each discrete emotion reported must map to the appropriate quadrant of the circumplex plane. We also need to perform post-study participant survey to compare self-reporting using both the models (mainly qualitative questions).

Skills:

  • Android programming (UI design, data collection, scheduling service)
  • Basic data analysis (data cleaning, statistical testing, plotting)

Ambient Holodeck: Exploring Ambient Multisensory VR Environments

Contact: Alina Striner (alina.striner@cwi.nl), Pablo Cesar (p.s.cesar@cwi.nl)

How might we create a portable or compartmentalized ambient multisensory environment (wind, smell, humidity, temperature) for VR? How does ambient multisensory stimuli affect players’ experience of video games or viewers experience of movies? In this project you will help build and test a compartmentalized ambient multisensory system capable of being integrated into VR entertainment experiences.

This project will require knowledge and know-how of working with Arduino-style environments. The project will involve running controlled studies to collect (and later analyze) data about user experiences in these environments.

Skills:

  • Required: Experience with electronics and prototyping using Arduino or similar microprocessors. Familiarity with hardware prototyping (eg. 3D printing). Interest in human computer interaction and tangible interfaces
  • Recommended: Experience with Unity, VR/AR development

Literature:

  • Sensing the future of HCI: touch, taste, and smell user interfaces. Marianna Obrist, Carlos Velasco, Chi Vi, Nimesha Ranasinghe, Ali Israr, Adrian Cheok, Charles Spence, and Ponnampalam Gopalakrishnakone. 2016. interactions 23, 5 (2016), 40–49. https://dl.acm.org/citation.cfm?id=2973568
  • Multisensory presence in virtual reality: possibilities & limitations. Alberto Gallace, Mary K Ngo, John Sulaitis, and Charles Spence, 2012. In Multiple sensorial media advances and applications: New developments in MulSeMedia. IGI Global, 1–38.
  • Mulsemedia: State of the art, perspectives, and challenges. Gheorghita Ghinea, Christian Timmerer, Weisi Lin, and Stephen R Gulliver. 2014. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 11, 1s (2014), 17.

Generative Models for Mobile Emotion Recognition using Physiological Signals

Contact: Tianyi Zhang (tianyi@cwi.nl), Pablo Cesar (p.s.cesar@cwi.nl)

Nowadays, in order to recognise physiological emotion, participants need to wear intrusive sensors (e.g. electroencephalograph). This project focuses on the research and development of a highly accurate emotion recognition system using a variety of wearable physiological sensors in mobile environments based on deep learning methods.

The rise of deep learning methods has shown that many difficult recognition problems can be solved by deep neural networks such as Convolutional Neural Networks (CNNs), Deep Belief Networks (DBN) and Recurrent Neural Networks (RNN). However, a system based on deep learning models requires a large amount of data for training. For emotion recognition based on physiological sensors, it is costly to collect physiological sensor data since we need to recruit users for experiments. In addition, it is also difficult to equip a large number of users with multiple physiological sensors. Thus, the challenge is how to automatically augment data with suitable artificial samples for emotion recognition when the amount of data is limited.

A Generative Model is a powerful way of learning data distribution using unsupervised learning and it has achieved tremendous success in just a few years. The target of this thesis is to develop a generative model to augment the physiological signals for precise emotion recognition in mobile environments. The work includes collecting data in mobile environments, adapting generative models to augment the collected dataset and developing deep neural networks for emotion recognition.

Skills:

  • Required: Knowledge about machine learning, especially about generative models (e.g. GAN, VAE), deep learning networks (e.g. CNN, LSTM, DBN) and traditional machine learning models (e.g. SVM, KNN, Bayesian network), good Python programming skills
  • Recommended: Physiological signal processing, basic knowledge about statistical models and emotion models, programming skills in R

Literature:

  • Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y. Generative adversarial nets. InAdvances in neural information processing systems 2014 (pp. 2672-2680).
  • Kingma DP, Welling M. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114. 2013 Dec 20.
  • Le Meur O, Liu Z. Saccadic model of eye movements for free-viewing condition. Vision research. 2015 Nov 1;116:152-64.

Designing and implementing a new compression solution for light field contents

Contact: Irene Viola (irene.viola@cwi.nl), Pablo Cesar (p.s.cesar@cwi.nl)

Among the 3D acquisition and rendering technologies, light field has emerged as a promising solution, due to its ability to capture not only the intensity, but also the direction of light flowing through a scene. This allows to visualise the 3D scene from different points of view, as well as to change viewing parameters such as depth of field or focal plane. However, efficient compression solutions are needed to reduce the vast amount of data generated during the acquisition.

In recent years, several compression schemes have been presented to exploit the redundancies in the light field data. Among others, view synthesis and disparity estimation seem to be promising solutions to reduce the size of the data while maintaining an acceptable visual quality. The goal of this project is to research, design and implement a new disparity estimation and prediction method to perform compression on light field data. The new method will be tested against state of the art solutions to assess its coding efficiency.

Skills:

  • Knowledge of image processing
  • Good programming skills (Matlab, Python or C++)

Literature:

  • “WaSP: Hierarchical Warping, Merging, and Sparse Prediction for Light Field Image Compression.” Astola, P. & Tabus, I., Nov 2018, 2018 7th European Workshop on Visual Information Processing (EUVIP). IEEE
  • “Light field image coding via linear approximation prior.” Zhao, S. & Chen, Z., 2017, IEEE International Conference on Image Processing (ICIP). IEEE
  • “A graph learning approach for light field image compression.” Viola, I., Petric Maretic, H., Frossard, P. & Ebrahimi, T., 2018, Applications of Digital Image Processing XLI. SPIE Optical Engineering + Applications

ShareMyView: Comparing Collaborative Interaction Methods in VR

Contact: Jie Li (j.li@cwi.nl), Alina Striner (alina.striner@cwi.nl), Pablo Cesar (p.s.cesar@cwi.nl)

What joint-attention and control challenges exist in collaborative VR? How might we design for collaborative attention and control in VR exploration and co-creation? In this project you will identify different collaborative challenges in VR, and create and test models in Unity to address these challenges.

Examples of Collaborative Scenarios:

  • Exploring a 360° or 3D outdoor environment
  • Teaching physical tasks, like sculpting
  • Co-creating together in VR, such as baking a cake together

This project will require knowledge of Unity and C#. It will involve building 3D interaction models and running controlled studies to collect (and later analyze) data about user experiences in these environments.

Skills:

  • Required: programming/prototyping (C#/Unity)
  • Recommended: Running user studies, quantitative and qualitative analysis methods

Literature:

  • Scott W Greenwald, Alexander Kulik, André Kunert, Stephan Beck, Bernd Fröhlich, Sue Cobb, Sarah and others. 2017. Technology and applications for collaborative learning in virtual reality. Philadelphia, PA: International Society of the Learning Sciences
  • Jan Gugenheimer, Evgeny Stemasov, Julian Frommel, and Enrico Rukzio. 2017. Sharevr: Enabling co-located experiences for virtual reality between hmd and non-hmd users. In Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems. ACM, 4021–4033
  • Hikaru Ibayashi, Yuta Sugiura, Daisuke Sakamoto, Natsuki Miyata, Mitsunori Tada, Takashi Okuma, Takeshi Kurata, Masaaki Mochimaru, and Takeo Igarashi. 2015. Dollhouse vr: a multi-view, multi-user collaborative design workspace with vr technology. In SIGGRAPH Asia 2015 Emerging Technologies. ACM, 8

Reconstructing High Frame Rate Point Clouds of Human Bodies

Contact: Pablo Cesar (p.s.cesar@cwi.nl)

Volumetric sensing, based on range-sensing technology, allows to capture the depth of on object or an entire scene, in addition to its color information. A format that has recently become widespread to represent volumetric signals captured by  such sensors, such as the Intel Real Sense camera, is the point cloud. A point cloud is a set of individual points in the 3D space, each associated with attributes, such as a color triplet. With respect to other volumetric representations, such as polygon meshes, the point cloud content generation implies much less computational processing, thus it is suitable for live capture and transmission. The goal of this project is the development of a machine learning-based approach to interpolate the point clouds representing a human body captured at different instants in time, in order to increase the frame rate of dynamic point cloud capturing a user’s body. The core of the project will be on the design of the network. The second main goal will be the collection of training data produced by using a capture set-up made of multiple Intel Real Sense sensors, in order to train the neural network aiming at learning how the point cloud signal representing body movement evolves in time.

Skills:

  • Machine learning
  • Good programming skills

Literature:

Contact

Group leader: Pablo Cesar

Science Park 123
1089 XG, Amsterdam
The Netherlands

Centrum Wiskunde & Informatica

Distributed & Interactive Systems (DIS) is a research group at CWI

Follow us...

© 2021 Distributed & Interactive Systems | Last update: 2024-04-25 15:49