Alessandro Perina

Bounding Multiple Gaussians Uncertainty with Application to Object Tracking

This paper proves the uncertainty bound for the multiple Gaussian functions, termed multiple Gaussians Uncertainty (MGU), which significantly generalizes the uncertainty principle for the single Gaussian function. First, as a theoretical contribution, we prove that the momentum (velocity) and position for the sum of multiple Gaussians wave function are theoretically bounded. Second, as for a practical application, we show that the bound can be well exploited for object tracking to detect anomalies of local movement in an online learning framework. By integrating MGU with a given object tracker, we demonstrate that uncertainty principle can provide remarkable robustness in tracking. Extensive experiments are done to show that the proposed MGU can significantly help base trackers overcome the object drifting and reach state-of-the-art results.

Sparse representation classification with manifold constraints transfer

The fact that image data samples lie on a manifold has been successfully exploited in many learning and inference problems. In this paper we leverage the specific structure of data in order to improve recognition accuracies in general recognition tasks. In particular we propose a novel framework that allows to embed manifold priors into sparse representation-based classification (SRC) approaches. We also show that manifold constraints can be transferred from the data to the optimized variables if these are linearly correlated. Using this new insight, we define an efficient alternating direction method of multipliers (ADMM) that can consistently integrate the manifold constraints during the optimization process. This is based on the property that we can recast the problem as the projection over the manifold via a linear embedding method based on the Geodesic distance. The proposed approach is successfully applied on face, digit, action and objects recognition showing a consistently increase on performance when compared to the state of the art.

Adaptive Local Movement Modeling for Robust Object Tracking

In this paper, we present a new strategy for modeling the motion of local patches for single-object tracking that can be seamlessly applied to most part-based trackers in the literature. The proposed adaptive local movement modeling method is able to model the local movement distribution of the image patches defining the object to track and the reliability of each image patch. Given the output of a base tracking algorithm, a Gaussian mixture model (GMM) is first used to model the distribution of the movement of local patches relative to the center of gravity of the tracked object. Then, the GMM is combined with the chosen base tracker in a boosting framework, which gives an efficient integrated scheme for the tracking task. This provides a robust procedure to detect outliers in the local motion of the patches. The algorithm is highly configurable with the possibility to change the number of local patches used for tracking and to adapt to the variations of the tracked object. The extensive tracking results on standard data sets show that equipping state-of-the-art trackers with our technique remarkably improves their performance.

The Pictures We Like Are Our Image: Continuous Mapping of Favorite Pictures into Self-Assessed and Attributed Personality Traits

Flickr allows its users to tag the pictures they like as “favorite”. As a result, many users of the popular photo-sharing platform produce galleries of favorite pictures. This article proposes new approaches, based on Computational Aesthetics, capable to infer the personality traits of Flickr users from the galleries above. In particular, the approaches map low-level features extracted from the pictures into numerical scores corresponding to the Big-Five Traits, both self-assessed and attributed. The experiments were performed over 60,000 pictures tagged as favorite by 300 users (the PsychoFlickr Corpus). The results show that it is possible to predict beyond chance both self-assessed and attributed traits. In line with the state-of-the-art of Personality Computing, these latter are predicted with higher effectiveness (correlation up to 0.68 between actual and predicted traits).

Abnormality Detection with Improved Histogram of Oriented Tracklets

Recently the histogram of oriented tracklets (HOT) was shown to be an efficient video representation for abnormality detection and achieved state-of-the-arts on the available datasets. Unlike standard video descriptors that mainly employ low level motion features, e.g. optical flow, the HOT descriptor simultaneously encodes magnitude and orientation of tracklets as a mid-level representation over crowd motions. However, extracting tracklets in HOT suffers from poor salient point initialization and tracking drift in the presence of occlusion. Moreover, count-based HOT histogramming does not properly take into account the motion characteristics of abnormal motions. This paper extends the HOT by addressing these drawbacks introducing an enhanced version of HOT, named Improved HOT. First, we propose to initialize salient points in each frame instead of the first frame, as the HOT does. Second, we replace the naive count-based histogramming by the richer statistics of crowd movement (i.e., motion distribution). The evaluation of the Improved HOT on different datasets, namely UCSD, BEHAVE and UMN, yields compelling results in abnormality detection, by outperforming the original HOT and the state-of-the-art descriptors based on optical flow, dense trajectories and the social force models.

Violence detection in crowded scenes using substantial derivative

This paper presents a novel video descriptor based on substantial derivative, an important concept in fluid mechanics, that captures the rate of change of a fluid property as it travels through a velocity field. Unlike standard approaches that only use temporal motion information, our descriptor exploits the spatio-temporal characteristic of substantial derivative. In particular, the spatial and temporal motion patterns are captured by respectively the convective and local accelerations. After estimating the convective and local field from the optic flow, we followed the standard bag-of-word procedure for each motion pattern separately, and we concatenated the two resulting histograms to form the final descriptor. We extensively evaluated the effectiveness of the proposed method on five benchmarks, including three standard datasets (Violence in Movies, Violence In Crowd, and BEHAVE), and two new video-survelliance sequences downloaded from Youtube. Our experiments show how the proposed approach sets the new state-of-the-art on all benchmarks and how the structural information captured by convective acceleration is essential to detect violent episodes in crowded scenarios.

Crowd motion monitoring using tracklet-based commotion measure.

Abnormal detection in crowd is a challenging vision task due to the scarcity of real-world training examples and the lack of a clear definition of abnormality. To tackle these challenges, we propose a novel measure to capture the commotion of a crowd motion for the task of abnormality detection in crowd. The unsupervised nature of the proposed measure allows to detect abnormality adaptively (i.e. context dependent) with no training cost. The extensive experiments on three different levels (e.g. pixel, frame and video) show the superiority of the proposed approach compared to the state of the arts.

Detecting Abnormal Behavioral Patterns in Crowd Scenarios

This Chapter presents a framework for the the task of abnormality detection in crowded scenes based on the analysis of trajectories, build up upon a novel video descriptor, called Histogram of Oriented Tracklets. Unlike standard approaches that employ low level motion features, e.g. optical flow, to form video descriptors, we propose to exploit mid-level features extracted from long-range motion trajectories called tracklets, which have been successfully applied for action modeling and video analysis. Following standard procedure, a video sequence is divided into spatio-temporal cuboids within which we collect statistics of the tracklets passing through them. Specifically, tracklets orientation and magnitude are quantized in a two-dimensional histogram which encodes the actual motion patterns in each cuboid. These histograms are then fed into machine learning models (e.g., Latent Dirichlet allocation and Support Vector Machines) to detect abnormal behaviors in video sequences. The evaluation of the proposed descriptor on different datasets, namely UCSD, BEHAVE, UMN and Violence in Crowds, yields compelling results in abnormality detection, by setting new state-of-the-art and outperforming former descriptors based on the optical flow, dense trajectories and social force models.

Personal Aesthetics for Soft Biometrics: A Generative Multi-resolution Approach

Are we recognizable by our image preferences? This paper answers affirmatively the question, presenting a soft biometric approach where the preferred images of an individual are used as his personal signature in identification tasks. The approach builds a multi-resolution latent space, formed by multiple Counting Grids, where similar images are mapped nearby. On this space, a set of preferred images of a user produces an ensemble of intensity maps, highlighting in an intuitive way his personal aesthetic preferences. These maps are then used for learning a battery of discriminative classifiers (one for each resolution), which characterizes the user and serves to perform identification. Results are promising: on a dataset of 200 users, and 40K images, using 20 preferred images as biometric template gives 66% of probability of guessing the correct user. This makes the personal aesthetics a very hot topic for soft biometrics, while its usage in standard biometric applications seems to be far from being effective, as we show in a simple user study.

A comparison of crowd commotion measures from generative models

Detecting abnormal events in video sequences is a challenging task that has been broadly investigated over the last decade. The main challenges come from the lack of a clear definition of abnormality and from the scarcity, often absence, of abnormal training samples. To address these two shortages, the computer vision community made use of generative models to learn normal behavioral patterns in videos. Then, for each test observation, a (crowd) commotion measure is computed quantifying the deviation from the normal model. In this paper, we evaluated two different families of generative models, namely topic models, representing the standard choice, and the most recent Counting Grids which have never been considered for this task. Moreover, we also extended the 2D Counting Grid, introduced for the analysis of images, to three dimensions, making the model able to capture the spatial-temporal relationships of the videos. In the experimental section, we compared all the approaches on five challenging sequences showing the superiority of the 3-D counting grid.