Ricerc@Sapienza

Neural network compression has recently received much attention due to the computational requirements of modern deep models. In this work, our objective is to transfer knowledge from a deep and accurate model to a smaller one.

A desirable smart traffic-monitoring and street-safety system can elicit and support the intervention of law enforcement agencies or medical staff. Recently, there has been a dramatically higher demand for such smart systems. To this end, the International Workshop on Traffic and Street Surveillance for Safety and Security (IWT4S) was organized in conjunction with the 15th IEEE International Conference on Advanced Video and Signal-based Surveillance (AVSS 2018).

Lighting design and modelling or industrial applications like luminaire planning and commissioning rely heavily on time-consuming manual measurements or on physically coherent computational simulations. Regarding the latter, standard approaches are based on CAD modeling simulations and offline rendering, with long processing times and therefore inflexible workflows. Thus, in this paper we propose a computer vision based system to measure lighting with just a single RGBD camera.

The management of plastic debris is a serious issue due to its durability. Unfortunately, million
tons of plastic end up in the sea becoming one of the biggest current environmental problems. One way to
monitor the amount of plastic in beaches is to collect samples and visually count and sort the plastic particles
present in them. This is a very time-consuming task. In this work, we present a Computer Vision-based
system which is able to automatically count and classify microplastic particles (1-5 mm) into five different

A modern lighting system should automatically calibrate itself (light commissioning), assess its own status (which lights are on/off and how dimmed), and allow for the creation or preservation of lighting patterns (adjustability), e.g. after the sunset. Such a system does not exist today, nor (real) data, labels, or metrics are available to compare with and foster progress. In this paper we set the baselines to such a computational system, called LIT, and its applications.

Are we ready to segment consumer stereo videos? The amount of this data type is rapidly increasing and encompasses rich information of appearance, motion and depth cues. However, the segmentation of such data is still largely unexplored. First, we propose therefore a new benchmark: videos, annotations and metrics to measure progress on this emerging challenge. Second, we evaluate several state of the art segmentation methods and propose a novel ensemble method based on recent spectral theory. This combines existing image and video segmentation techniques in an efficient scheme.

Faster R-CNN has established itself as the de-facto best object detector but it remains strongly limited in two aspects: (i) it is sensitive to background clutter and its classification performance decreases when it is confronted with more noisy proposals; (ii) it suffers when the objects vary largely in scale and specifically for the small objects. We address both issues with our geometric-proposals for Faster R-CNN (GP-FRCNN), whereby we re-rank the generic object proposals with an approximate geometric estimate of the scene.

Human activity recognition and forecasting can be used as a primary cue for scene understanding. Acquiring details from the scene has vast applications in different fields such as computer vision, robotics and more recently smart lighting. This work brings together advanced research in computer vision and the most modern technology in lighting. The goal of this work is to eliminate the need for any switches for lighting, which means that each person in the office perceives the entire office as all lit, while lights, which are not visible by the person, are switched off by the system.

The rapid advances of transportation infrastructure have led to a dramatic increase in the demand for smart systems capable of monitoring traffic and street safety. Fundamental to these applications are a community-based evaluation platform and benchmark for object detection and multi-object tracking.