Alessio Del Bue

Live-cell 3D super-resolution imaging in thick biological samples

We demonstrate three-dimensional (3D) super-resolution live-cell imaging through thick specimens (50–150 μm), by coupling far-field individual molecule localization with selective plane illumination microscopy (SPIM). The improved signal-to-noise ratio of selective plane illumination allows nanometric localization of single molecules in thick scattering specimens without activating or exciting molecules outside the focal plane. We report 3D super-resolution imaging of cellular spheroids.

Factorization for non-rigid and articulated structure using metric projections

This paper describes a new algorithm for recovering the 3D shape and motion of deformable and articulated objects purely from uncalibrated 2D image measurements using an iterative factorization approach. Most solutions to non-rigid and articulated structure from motion require metric constraints to be enforced on the motion matrix to solve for the transformation that upgrades the solution to metric space. While in the case of rigid structure the metric upgrade step is simple since the motion constraints are linear, deformability in the shape introduces non-linearities. In this paper we propose an alternating least-squares approach associated with a globally optimal projection step onto the manifold of metric constraints. An important advantage of this new algorithm is its ability to handle missing data which becomes crucial when dealing with real video sequences with self-occlusions. We show successful results of our algorithms on synthetic and real sequences of both deformable and articulated data.

Social interaction discovery by statistical analysis of F-formations.

We present a novel approach for detecting social interactions in a crowded scene by employing solely visual cues. The detection of social interactions in unconstrained scenarios is a valuable and important task, especially for surveillance purposes. Our proposal is inspired by the social signaling literature, and in particular it considers the sociological notion of F-formation. An F-formation is a set of possible configurations in space that people may assume while participating in a social interaction. Our system takes as input the positions of the people in a scene and their (head) orientations; then, employing a voting strategy based on the Hough transform, it recognizes F-formations and the individuals associated with them. Experiments on simulations and real data promote our idea.

Human behavior analysis in video surveillance: A Social Signal Processing perspective

The analysis of human activities is one of the most intriguing and important open issues for the automated video surveillance community. Since few years ago, it has been handled following a mere Computer Vision and Pattern Recognition perspective, where an activity corresponded to a temporal sequence of explicit actions (run, stop, sit, walk, etc.). Even under this simplistic assumption, the issue is hard, due to the strong diversity of the people appearance, the number of individuals considered (we may monitor single individuals, groups, crowd), the variability of the environmental conditions (indoor/outdoor, different weather conditions), and the kinds of sensors employed. More recently, the automated surveillance of human activities has been faced considering a new perspective, that brings in notions and principles from the social, affective, and psychological literature, and that is called Social Signal Processing (SSP). SSP employs primarily nonverbal cues, most of them are outside of conscious awareness, like face expressions and gazing, body posture and gestures, vocal characteristics, relative distances in the space and the like. This paper is the first review analyzing this new trend, proposing a structured snapshot of the state of the art and envisaging novel challenges in the surveillance domain where the cross-pollination of Computer Science technologies and Sociology theories may offer valid investigation strategies.

Re-identification with RGB-D sensors

People re-identification is a fundamental operation for any multi-camera surveillance scenario. Until now, it has been performed by exploiting primarily appearance cues, hypothesizing that the individuals cannot change their clothes. In this paper, we relax this constraint by presenting a set of 3D soft-biometric cues, being insensitive to appearance variations, that are gathered using RGB-D technology. The joint use of these characteristics provides encouraging performances on a benchmark of 79 people, that have been captured in different days and with different clothing. This promotes a novel research direction for the re-identification community, supported also by the fact that a new brand of affordable RGB-D cameras have recently invaded the worldwide market.

A Bilinear Approach to the Position Self-Calibration of Multiple Sensors

This paper presents a novel algorithm for the automatic 3D localization of a set of sensors in an unknown environment. Given the measures of a set of time of arrival delays at each sensor, the approach simultaneously estimates the 3D position of the sensors and the sources that have generated the event. Such inference is obtained with no assumption about the sensor localization; the only assumption made is that the emission time of the sources must be known in order to evaluate the time of flight for each event. Moreover, we propose a further method that deals with the likely case of missing data in the measurements. This occurs when sensors are far apart or behind natural barriers that avoids the registration of the given event. Simulated experiments show the validity of the approach for different setups of sensors and number of events.

Optimizing interaction force for global anomaly detection in crowded scenes

This paper presents a novel method for global anomaly detection in crowded scenes. The proposed method introduces the Particle Swarm Optimization (PSO) method as a robust algorithm for optimizing the interaction force computed using the Social Force Model (SFM). The main objective of the proposed method is to drift the population of particles towards the areas of the main image motion. Such displacement is driven by the PSO fitness function aimed at minimizing the interaction force, so as to model the most diffused and typical crowd behavior. Experiments are extensively conducted on public available datasets, namely, UMN and PETS 2009, and also on a challenging dataset of videos taken from Internet. The experimental results revealed that the proposed scheme outperforms all the available state-of-the-art algorithms for global anomaly detection.

Piecewise quadratic reconstruction of non-rigid surfaces from monocular sequences

In this paper we present a new method for the 3D reconstruction of highly deforming surfaces (for instance a flag waving in the wind) viewed by a single orthographic camera. We assume that the surface is described by a set of feature points which are tracked along an image sequence. Most non-rigid structure from motion algorithms assume a global deformation model where a rigid mean shape component accounts for most of the motion and the deformation modes are small deviations from it. However, in the case of strongly deforming objects, the deformations become more complex and a global model will often fail to explain the intricate deformations which are no longer small linear deviations from a strong mean component. Our proposed algorithm divides the surface into overlapping patches, reconstructs each of these patches individually using a quadratic deformation model and finally registers them imposing the constraint that points shared by patches must correspond to the same 3D points in space. We show good results on challenging motion capture and real video sequences with strong deformations where global methods fail to achieve good reconstructions.

A closed form solution to the microphone position self-calibration problem

This paper presents a novel algorithm for the automatic 3D localization of a set of microphones in an unknown environment. Given the times of arrival at each microphone of a set of sound events, the approach simultaneously estimates the 3D positions of the sensors and the sources that have generated the events. The only assumption made is that the emission time of the sound events must be known in order to measure the time of flight for each event. A closed form solution is also proposed whenever a sound event coincides with a microphone position. Simulated and real experiments show the validity of the approach for different setups of sensors and number of events.

Optimal Metric Projections for Deformable and Articulated Structure-from-Motion

This paper describes novel algorithms for recovering the 3D shape and motion of deformable and articulated objects purely from uncalibrated 2D image measurements using a factorisation approach. Most approaches to deformable and articulated structure from motion require to upgrade an initial affine solution to Euclidean space by imposing metric constraints on the motion matrix. While in the case of rigid structure the metric upgrade step is simple since the constraints can be formulated as linear, deformability in the shape introduces non-linearities. In this paper we propose an alternating bilinear approach to solve for non-rigid 3D shape and motion, associated with a globally optimal projection step of the motion matrices onto the manifold of metric constraints. Our novel optimal projection step combines into a single optimisation the computation of the orthographic projection matrix and the configuration weights that give the closest motion matrix that satisfies the correct block structure with the additional constraint that the projection matrix is guaranteed to have orthonormal rows (i.e. its transpose lies on the Stiefel manifold). This constraint turns out to be non-convex. The key contribution of this work is to introduce an efficient convex relaxation for the non-convex projection step. Efficient in the sense that, for both the cases of deformable and articulated motion, the proposed relaxations turned out to be exact (i.e. tight) in all our numerical experiments. The convex relaxations are semi-definite (SDP) or second-order cone (SOCP) programs which can be readily tackled by popular solvers. An important advantage of these new algorithms is their ability to handle missing data which becomes crucial when dealing with real video sequences with self-occlusions. We show successful results of our algorithms on synthetic and real sequences of both deformable and articulated data. We also show comparative results with state of the art algorithms which reveal that our new methods outperform existing ones.