close

Press Release

CVC NewsPress Release

New automatic fall detector for the elderly through Computer Vision

Senior-Logo-v2-1
  • First results of the automatic fall detector developed by the Center de Visió per Computador and the company Sensing & Control.
  • The system will offer peace of mind both to elderly people living in isolation in times of COVID-19, as well as to their families.
  • The project has been funded by the Ministry of Science, Innovation and Universities with the RETOS program.

The number of older people living in isolation at home during the COVID-19 pandemic has increased significantly, as they cannot receive visits from family or friends because they are people at extreme risk for this disease. This also increases the chances that if an emergency occurs, it will take time to be detected. With this problem in mind, the SENIOR project, funded by the Ministry of Science, Innovation and Universities with the RETOS program (RTC-2017-6618-1), has presented the results of the automatic fall detector developed by the research team in the automatic analysis of human behavior of the Center de Visió per Computador, lead by Dr. Sergio Escalera, and which is being integrated into the Smart home enControlTM developed by the Sensing & Control company.

The key is to be able to act as quickly as possible after the fall has occurred, in order to minimize damage and increase the chances of a successful recovery. For this, and through the use of technologies such as the Internet of Things and Artificial Intelligence, a non-invasive system has been created, based on a depth camera, which allows the generation of 3D images, and a thermal camera. Once the images have been obtained, and applying Artificial Intelligence techniques on them, the system is capable of automatically and non-invasively detecting falls of elderly people living alone, sending an alert to their caregivers in the event of an alert. Unlike most of the existing solutions on the market, this solution does not compromise the privacy of the user, since there are no cameras with video images, nor is any action required by the user. Within the framework of the project, a new interface aimed at caregivers has also been developed that also makes it easy to monitor the activities of older people such as time spent in stays. This continuous monitoring has also been shown to be useful for detecting the first stages and evolution of diseases such as Alzheimer’s, as mentioned by numerous investigations published in scientific journals.

It is expected to be able to commercialize this software, aimed at professional caregivers and families of people who live alone, during the year 2022.

 

Este proyecto ha sido subvencionado por el programa nacional RETOS-Colaboración 2017 con número de expediente: RTC-2017-6618-1.

read more
ConferencesCVC NewsPress Release

New advances in fair face recognition algorithms

FairFace Challenge at ECCV 2020(1)

Face recognition has been routinely utilized by both private and governmental organizations around the world. Automatic face recognition can be used for legitimate and beneficial purposes (e.g. to improve security) but at the same time its power and ubiquity heightens a potential negative impact unfair methods can have for the society (e.g. discrimination against ethnic minorities). Although not sufficient, a necessary condition for a legitimate deployment of face recognition algorithms is equal accuracy for all demographic groups.

With this purpose in mind, researchers from the Human Pose Recovery and Behavior Analysis Group at the Computer Vision Center (CVC) – University of Barcelona, led by Dr. Sergio Escalera, organized a challenge within the European Conference of Computer Vision (ECCV) 2020. The results, recently published in Computer Vision – ECCV 2020 Workshops, evaluated the accuracy and bias in gender and skin colour of the submitted algorithms by the participants on the task of face verification in the presence of other confounding attributes.

The challenge was a success since “it attracted 151 participants, who made more than 1.8K submissions in total, exceeding our expectations regarding the number of participants and submissions” explained Dr. Sergio Escalera.

The participants used an image dataset not balanced, which simulates a real world scenario where AI-based models supposed to be trained and evaluated on imbalanced data (considerably more white males that dark females). In total, thy worked with 152,917 images from 6,139 identities.

The images were annotated for two protected attributes: gender and skin colour; and five legitimate attributes: age group (0-34, 35-64, 65+), head pose (frontal, other), image source (still image, video frame), wearing glasses and a bounding box size.

The obtained results were very promising. Top winning solutions exceeded 0.999 of accuracy while achieving very low scores in the proposed bias metrics, which can be considered a step toward the development of fairer face recognition methods. The analysis of top-10 teams shows higher false positive rates for females with dark skin tone and for samples where both individuals wear glasses. In contrast there were higher false negative rates for males with light skin tone and for samples where both individuals are younger than 35 years. “This was not a surprise as the adopted dataset was not balanced with respect to different demographic attributes. However, it shows that overall accuracy is not enough when the goal is to build fair face recognition methods, and that future works on the topic must take into account accuracy and bias mitigation together”, concluded Dr. Julio C. S. Jacques Jr, researcher at the CVC and at the Universitat Oberta de Catalunya.

Reference:

Sixta T., Jacques Junior J.C.S., Buch-Cardona P., Vazquez E., Escalera S. (2020) FairFace Challenge at ECCV 2020: Analyzing Bias in Face Recognition. Computer Vision – ECCV 2020 Workshops. ECCV 2020. Lecture Notes in Computer Science, vol 12540. Springer, Cham. DOI: 10.1007/978-3-030-65414-6_32

In the media

Diario Libre: Detectan algoritmos más precisos de reconocimiento facial según tono de piel

El Desconcierto: Inteligencia artificial: Detectan algoritmos más precisos de reconocimiento facial según tono de piel

Ámbito: Detectan algoritmos que diferencian el tono de piel en el reconocimiento facial

Diario San Rafael: Detectan algoritmos que diferencian el tono de piel en el reconocimiento facial

Mirage news: New advances in detection of bias in face recognition algorithms

Marktechpost: Researchers From Computer Vision Center (CVC) And The University Of Barcelona Conducted A Study That Results In Improved Accuracy On Face Verification Tasks In The Presence Of Other Confounding Attributes

read more
In the media

The role of the CVC in the fight against Covid-19 and lung cancer

Foto IAM4B

La Vanguardia -in its printed edition- and Univadis Spain, featured the CVC research aimed to develop a digital biopsia that may be used in the diagnosis of Covid-19 and lung cancer.

Members of the Interactive Augmented Modelling for Biomedicine (IAM4B) leaded by Dr. Dèbora Gil and Dr. Carles Sánchez, in collaboration with researchers from the Germans Trias i Pujol Research Institute (IGTP) leaded by the Dr. Antoni Rosell, Thorax Area Clinical Director, were using a technique called radiomics for the diagnosis of lung cancer combining PET and TAC scanners.

IAM4B researchers (CVC). From left to right and from top to bottom: Dr. Carles Sánchez, Guillermo Torres, Dr. Thomas Batard, Dr. Aura Hernández, Roger Domingo Espinós, Esmitt Ramírez, Dr. Dèbora Gil (IAM4B Director) and José Elías Yauri.

 

Hospital Germans Trias i Pujol researchers. From left to right and from top to the bottom: Dr. Jordi Deportos, Dr. Antoni Rosell (Thorax Area Clinical Director), Dr. Sonia Baeza, Dr. Gloria Moragas and Dr. Maite Salcedo

However, with the Covid-19 pandemic emergence, they tried to transfer all the knowledge they accumulated during their studies in cancer lung to Covid-19, concretely to the early detection of microstrokes provoked by bilateral pneumonia asociated to Covid-19 infection. For achieving this purpose they used again radiomics with TAC and SPECT (instead PET) scanners.

The system has been retrospectively tested with 63 Covid-19 patients for the first pandemic wave and 70 non-Covid-19 patients, including healthy controls and non-Covid-19 pneumonia (bacterial pneumonia), reaching a 93% accuracy in the detection of Covid-19 microinfarcts. The results are therefore very encouraging.

You can read the full articles here (in Spanish): Digital biopsia (La Vanguardia) and Univadis España

 

This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No 712949 (TECNIOspring PLUS) and from the Agency for Business Competitiveness of the Government of Catalonia.

read more
Events & CommunityPress Release

El projecte Tasta i Testeja Tecnologia impulsa les vocacions STEM a instituts del Vallès.

_DSC9597

Bellaterra, 29 de Gener 2020, avui s’ha donat el tret de sortida del projecte 3Ts (Tasta i Testeja Tecnologia) impulsat pels Ajuntaments de Sant Quirze del Vallès, Barberà del Vallès i Sabadell, des de les àrees de promoció econòmica de cada municipi, i amb finançament de la Diputació de Barcelona dins la línia de projectes singulars de dinamització del Teixit productiu del catàleg de serveis 2019. Per part de Sant Quirze, hi participa el Servei a l’empresa. Per part del municipi de Barberà, hi participa el centre de negocis Nodus Barberà, i per part de Sabadell, la seva oficina d’Atenció a l’empresa i l’autònom. Amb la missió de fomentar la innovació des d’una òptica supramunicipal, els membres organitzadors del projecte 3Ts pretenen fer una transferència directa del coneixement a través del foment de les vocacions STEM a l’àrea del Vallès.

El projecte compta amb professorat de secundària, que rebrà formació tècnica per part de l’Escola d’Enginyeria de la Universitat Autònoma de Barcelona i el Centre de Visió per Computador, ajudant a definir les activitats que treballaran els estudiants a les aules. Els estudiants (i els professors participants) seran de quart de la ESO, uns 80 en total, de tres instituts: l’Institut Pau Vila de Sabadell, l’Institut Bitàcola de Barberà del Vallès i de l’Institut Salas i Xandri de Sant Quirze del Vallès. Els alumnes treballaran continguts relacionats amb el currículum de secundària: programació i robòtica, matemàtiques i estadística, així com una introducció a la Intel·ligència Artificial i la visió per computador. Amb l’ús de cotxes de muntatge propi (jetson bots), es farà un platooning (cotxes en filera seguint-se els uns als altres) el més llarg possible entre tots els cotxes participants.

Aquest foment de les vocacions STEM des de l’àmbit de secundària, amb especial èmfasi en les noies, busca impulsar la participació de les generacions futures en l’àmbit tecnològic. A més a més, el projecte també pretén donar a conèixer la recerca i l’educació universitària disponible a Catalunya en l’àmbit de l’enginyeria i les ciències de la computació. D’aquesta manera, es busca donar resposta a la creixent demanda laboral en el sector TIC i poder nodrir les empreses innovadores de l’àrea del Vallès que aposten per les noves tecnologies, essent el projecte una eina perfecta per a la visibilització d’aquestes entitats empresarials.

Més informació: www.3ts.cat

 

Per contacte de premsa:

Alexandra Canet

acanet@cvc.uab.es

 

 

read more
CVC NewsEvents & CommunityPress Release

Second edition of the symposium that will highlight Barcelona as a key player of Artificial Intelligence in Europe

unnamed

The Deep Learning Symposium (DLBCN) 2019 is expected to display the potential of Barcelona in the field of Artificial Intelligence. The symposium will have the presence of global experts in Deep Learning that will meet once again in Barcelona on December 19-20th.

Barcelona will host this December the second edition of the Deep Learning Barcelona Symposium (DLBCN). Deep Learning has greatly revolutionised Artificial Intelligence, boosting this technology across the globe. According to Forbes magazine, the business value created by AI will reach $3.9T in 2022 in the USA. What’s more, it estimates an increase of 20% of Europe’s economy within 10 years due to the implementation of AI. The Deep Learning Barcelona Symposium has the aim to highlight the research developed in Barcelona, bringing together top-level researchers who are either currently developing their research in the city, or have pursued part of their academic career here.

Alphastar project leader Oriol Vinyals will be one of the main speakers. He is currently a researcher at Google DeepMind (London), from where he developed the Alphastar algorithm. This project made the front page of Nature magazine, and was considered a major milestone for the development of Artificial Intelligence. DeepMind’s algorithm won 10-1 against two top professional players of the Starcraft II video game. This technology tested new types of AI.  In order to beat the Starcraft players, it had to combine long term planning with real-time decision making, along with the ability to acquire and make use of abstract information in a setting with no fixed rules.

The symposium will also have the presence of Facebook AI’s research leader, Cristian Canton, or Marta Ruiz, UPC researcher, who has actively worked within the field of data biases in language, a hot topic impacting gender diversity in AI.

This unique meeting gathers multidisciplinary researchers in the field of Deep Learning and highlights the potential of Barcelona to become the hub of AI in the South of Europe. The symposium is organised by leading universities and local research centres in the field of Machine Learning: the Universitat Politècnica de Catalunya (UPC), the Computer Vision Centre, the Barcelona Supercomputing Center (BSC), the Universitat Oberta de Catalunya (UOC), the Universitat Pompeu Fabra (UPF), the Universitat de Barcelona (UB), Dolby Laboratories and Telefonica Research.

For further details: http://deeplearning.barcelona

read more
1 2
Page 1 of 2