Signal and Image Processing Group
learning from large distributed processing, image understanding and ocean acoustics
Signal and Image Processing Group
learning from large distributed processing, image understanding and ocean acoustics
We will present a deep learning-based method that jointly detects and pairs nuclei and Golgi in 3D that outperforms classical approaches on a dataset of mouse retinal microscopy images acquired at the Vascular Biology and Disease Laboratory from Instituto Gulbenkian de Ciência.
Emergency Departments (EDs) are essential for providing prompt care but often face overcrowding issues, mainly due to non-urgent patients and seasonal spikes. Accurate forecasting of patient influx is essential for…
Automated Analysis of Multi-Modal Medical Data using Deep Belief Networks Recently, magnetic resonance and ultrasound imaging have found utility as adjuncts to mammography in the detection and management of breast…
Precision Radiology In this work, we propose new prognostic methods that predict 5-year mortality in elderly individuals using chest computed tomography (CT). The methods consist of a classifier that performs…
Started in 2014 we deployed a large scale 3D visual sensing infrastructure in Lisbon’s Airport. Currently with more than 30 depth cameras (3D sensors), became a key technology for queue…
The 2018 LARSyS Annual Meeting was a success! For two full days researchers from ISR, IN+, M-ITI and Maretec gathered at Pavilhão do Conhecimento to exchange knowledge and debate future…
Acoustic Surveillance System Underwater noise has been identified by EU as a pollutant for biological species, including marine mammals, fish, invertebrates and to biodiversity as a whole. Despite the vast…
A Learned based method to design cost functions DO is an innovative way of estimating a surrogate of the gradient of a “well behaved” cost function from data and solve…
The challenge is to count vehicles in a city-scale low resolution, low frame rate network of urban cameras. The target city is NY where 200+ cameras stream video from selected places. In this work several Deep Learning solutions are presented with unprecedented performance. In a very diverse conditions (sunny, cloudy, rainy) the deep-learning model is able to estimate the correct number of cars with errors of 1.5 cars (MAE).
