Publications by Simone Calderara

We propose a method for tracking groups from single and multiple cameras with disjoint fields of view. Our formulation follows the tracking-by-detection paradigm where groups are the atomic entities and are linked over time to form long and consistent trajectories. To this end, we formulate the problem as a supervised clustering problem where a Structural SVM classifier learns a similarity measure appropriate for group entities. Multi-camera group tracking is handled inside the framework by adopting an orthogonal feature encoding that allows the classifier to learn inter- and intra-camera feature weights differently. Experiments were carried out on a novel annotated group tracking data set, the DukeMTMC-Groups data set. Since this is the first data set on the problem it comes with the proposal of a suitable evaluation measure. Results of adopting learning for the task are encouraging, scoring a +15% improvement in F1 measure over a non-learning based clustering baseline. To our knowledge this is the first proposal of this kind dealing with multi-camera group tracking.

Mankind directly controls the environment and lifestyles of several domestic species for purposes ranging from production and research to conservation and companionship. These environments and lifestyles may not offer these animals the best quality of life. Behaviour is a direct reflection of how the animal is coping with its environment. Behavioural indicators are thus among the preferred parameters to assess welfare. However, behavioural recording (usually from video) can be very time consuming and the accuracy and reliability of the output rely on the experience and background of the observers. The outburst of new video technology and computer image processing gives the basis for promising solutions. In this pilot study, we present a new prototype software able to automatically infer the behaviour of dogs housed in kennels from 3D visual data and through structured machine learning frameworks. Depth information acquired through 3D features, body part detection and training are the key elements that allow the machine to recognise postures, trajectories inside the kennel and patterns of movement that can be later labelled at convenience. The main innovation of the software is its ability to automatically cluster frequently observed temporal patterns of movement without any pre-set ethogram. Conversely, when common patterns are defined through training, a deviation from normal behaviour in time or between individuals could be assessed. The software accuracy in correctly detecting the dogs' behaviour was checked through a validation process. An automatic behaviour recognition system, independent from human subjectivity, could add scientific knowledge on animals' quality of life in confinement as well as saving time and resources. This 3D framework was designed to be invariant to the dog's shape and size and could be extended to farm, laboratory and zoo quadrupeds in artificial housing. The computer vision technique applied to this software is innovative in non-human animal behaviour science. Further improvements and validation are needed, and future applications and limitations are discussed.

Modern crowd theories agree that collective behavior is the result of the underlying interactions among small groups of individuals. In this work, we propose a novel algorithm for detecting social groups in crowds by means of a Correlation Clustering procedure on people trajectories. The affinity between crowd members is learned through an online formulation of the Structural SVM framework and a set of specifically designed features characterizing both their physical and social identity, inspired by Proxemic theory, Granger causality, DTW and Heat-maps. To adhere to sociological observations, we introduce a loss function (G-MITRE) able to deal with the complexity of evaluating group detection performances. We show our algorithm achieves state-of-the-art results when relying on both ground truth trajectories and tracklets previously extracted by available detector/tracker systems.

Despite prejudice cannot be directly observed, nonverbal behaviours provide profound hints on people inclinations. In this paper, we use recent sensing technologies and machine learning techniques to automatically infer the results of psychological questionnaires frequently used to assess implicit prejudice. In particular, we recorded 32 students discussing with both white and black collaborators. Then, we identified a set of features allowing automatic extraction and measured their degree of correlation with psychological scores. Results confirmed that automated analysis of nonverbal behaviour is actually possible thus paving the way for innovative clinical tools and eventually more secure societies.

Long term tracking of people in unconstrained scenarios is still an open problem due to the absence of constant elements in the problem setting. The camera, when active, may move and both the background and the target appearance may change abruptly leading to the inadequacy of most standard tracking techniques. We propose to exploit a learning approach that considers the tracking task as a semi supervised learning (SSL) problem. Given few target samples the aim is to search the target occurrences in the video stream re-interpreting the problem as label propagation on a similarity graph. We propose a solution based on graph transduction that works iteratively frame by frame. Additionally, in order to avoid drifting, we introduce an update strategy based on an evolutionary clustering technique that chooses the visual templates that better describe target appearance evolving the model during the processing of the video. Since we model people appearance by means of covariance matrices on color and gradient information our framework is directly related to structure learning on Riemannian manifolds. Tests on publicly available datasets and comparisons with stateof- the-art techniques allow to conclude that our solution exhibit interesting performances in terms of tracking precision and recall in most of the considered scenarios.

Multimedia forensics is a new emerging discipline regarding the analysis and exploitation of digital data as support for investigation to extract probative elements. Among them, visual data about people and people activities, extracted from videos in an efficient way, are becoming day by day more appealing for forensics, due to the availability of large video-surveillance footage. Thus, many research studies and prototypes investigate the analysis of soft biometrics data, such as people appearance and people trajectories. In this work, we propose new solutions for querying and retrieving visual data in an interactive and active fashion for soft biometrics in forensics. The innovative proposal joins the capability of transductive learning for semi-supervised search by similarity and a typical multimedia methodology based on user-guided relevance feedback to allow an active interaction with the visual data of people, appearance and trajectory in large surveillance areas. Approaches proposed are very general and can be exploited independently by the surveillance setting and the type of video analytic tools.

Online Multiple Target Tracking (MTT) is often addressed within the tracking-by-detection paradigm. Detections are previously extracted independently in each frame and then objects trajectories are built by maximizing specifically designed coherence functions. Nevertheless, ambiguities arise in presence of occlusions or detection errors. In this paper we claim that the ambiguities in tracking could be solved by a selective use of the features, by working with more reliable features if possible and exploiting a deeper representation of the target only if necessary. To this end, we propose an online divide and conquer tracker for static camera scenes, which partitions the assignment problem in local subproblems and solves them by selectively choosing and combining the best features. The complete framework is cast as a structural learning task that unifies these phases and learns tracker parameters from examples. Experiments on two different datasets highlights a significant improvement of tracking performances (MOTA +10%) over the state of the art.

Leader identification is a crucial task in social analysis, crowd management and emergency planning. In this paper, we investigate a computational model for the individuation of leaders in crowded scenes. We deal with the lack of a formal definition of leadership by learning, in a supervised fashion, a metric space based exclusively on people spatiotemporal information. Based on Tarde's work on crowd psychology, individuals are modeled as nodes of a directed graph and leaders inherits their relevance thanks to other members references. We note this is analogous to the way websites are ranked by the PageRank algorithm. During experiments, we observed different feature weights depending on the specific type of crowd, highlighting the impossibility to provide a unique interpretation of leadership. To our knowledge, this is the first attempt to study leader identification as a metric learning problem

Conventional experiments on MTT are built upon the belief that fixing the detections to different trackers is sufficient to obtain a fair comparison. In this work we argue how the true behavior of a tracker is exposed when evaluated by varying the input detections rather than by fixing them. We propose a systematic and reproducible protocol and a MATLAB toolbox for generating synthetic data starting from ground truth detections, a proper set of metrics to understand and compare trackers peculiarities and respective visualization solutions.

The understanding of mutual people interaction is a key component for recognizing people social behavior, but it strongly relies on a personal point of view resulting difficult to be a-priori modeled. We propose the adoption of the unique head mounted cameras first person perspective (ego-vision) to promptly detect people interaction in different social contexts. The proposal relies on a complete and reliable system that extracts people׳s head pose combining landmarks and shape descriptors in a temporal smoothed HMM framework. Finally, interactions are detected through supervised clustering on mutual head orientation and people distances exploiting a structural learning framework that specifically adjusts the clustering measure according to a peculiar scenario. Our solution provides the flexibility to capture the interactions disregarding the number of individuals involved and their level of acquaintance in context with a variable degree of social involvement. The proposed system shows competitive performances on both publicly available ego-vision datasets and ad hoc benchmarks built with real life situations.