Publications by Roberto Vezzani

The interest of the research community in creating reference datasets for performance analysis is always very high. Although new datasets, collecting large amounts of video footage are spreading in surveillance and forensics, few bench-marks with annotation data are available for testing specific tasks and especially for 3D/multi-view analysis. In this paper we present 3DPeS, a new dataset for 3D/multi- view surveillance and forensic applications. This has been designed for discussing and evaluating research results in people re-identification and other related activities (people detection, people segmentation and people tracking). The new assessed version of the dataset contains hundreds of video sequences of 200 people taken from a multi-camera distributed surveillance system over several days, with different light conditions; each person is detected multiple times and from different points of view. In surveillance scenarios, the dataset can be exploited to evaluate people reacquisition, 3D body models and people activity reconstruction algorithms. In forensics it can be adopted too, by relaxing some constraints (e.g. real time) and neglecting some information (e.g. calibration). Some results on this new dataset are presented using state of the art methods for people re-identification as a benchmark for future comparisons.

We propose a new simplified 3D body model (called Sarc3D) for surveillance application, that can be created, updated and compared in rea-time.People are detected and tracked in each calibrated camera, and their silhouette, appearance, position and orientation are extracted and used to place, scale and orientate a 3D body model. Foreach vertex of the model a signature (color features, reliability and saliency) is computed from the 2D appearance images and exploited for mathing. This approach achieves robustness against partial occlusions, pose and viewpoint changes. The complete proposal and a full experimental evaluation is presented, using a new benchmark suite and the PETS2009 dataset.

Hidden Markov Models (HMM) have been widely used for action recognition, since they allow to easily model the temporal evolution of a single or a set of numeric features extracted from the data. The selection of the feature set and the related emission probability function are the key issues to be defined. In particular, if the training set is not sufficiently large, a manual or automatic feature selection and reduction is mandatory. In this paper we propose to model the emission probability function as a Mixture of Gaussian and the feature set is obtained from the projection histograms of the foreground mask. The projectionhistograms contain the number of moving pixel for each row and for each column of the frame and they provide sufficient information to infer the instantaneous posture of the person. Then, the HMM framework recovers the temporal evolution of the postures recognizing in such a manner the global action. The proposed method have been successfully tested on the UT-Tower and on the Weizmann Datasets.

Surveillance of wide areas with several connected cameras integrated in the same automatic system is no more a chimera, but modular, scalable and flexible architectures are mandatory to manage them. This paper points out the main issues on the development of distributed surveillance systems and proposes an integrated framework particularly suitable for research purposes. As first, exploiting a computer architecture analogy, a three layer tracking system is proposed, which copes with the integration of both overlapping and non overlapping cameras. Then, a static service oriented architecture is adopted to collect and manage the plethora of high level modules, such as face detection and recognition, posture and action classification, and so on. Finally, the overall architecture is controlled by an event driven communication infrastructure, which assures the scalability and the flexibility of the system.

In this paper, we present a new and fast techniquefor background estimation from cluttered image sequences.Most of the background initialization approaches developedso far collect a number of initial frames and then requirea slow estimation step which introduces a delay wheneverit is applied. Conversely, the proposed technique redistributesthe computational load among all the frames bymeans of a patch by patch preprocessing, which makesthe overall algorithm more suitable for real-time applications.For each patch location a prototype set is created andmaintained. The background is then iteratively estimatedby choosing from each set the most appropriate candidatepatch, which should verify a sort of frequency coherencewith its neighbors. To this aim, the Hadamard transformhas been adopted which requires less computation time thanthe commonly used DCT. Finally, a refinement step exploitsspatial continuity constraints along the patch borders toprevent erroneous patch selections. The approach has beencompared with the state of the art on videos from availabledatasets (ViSOR and CAVIAR), showing a speed up of about10 times and an improved accuracy

The availability of new techniques and tools for Video Surveillance and the capability of storing huge amounts of visual data acquired by hundreds of cameras every day call for a convergence between pattern recognition, computer vision and multimedia paradigms. A clear need for this convergence is shown by new research projects which attempt to exploit both ontology-based retrieval and video analysis techniques also in the field of surveillance.This paper presents the ViSOR (Video Surveillance Online Repository) framework, designed with the aim of establishing an open platform for collecting, annotating, retrieving, and sharing surveillance videos, as well as evaluating the performance of automatic surveillance systems. Annotations are based on a reference ontology which has been defined integrating hundreds of concepts, some of them coming from the LSCOM and MediaMill ontologies. A new annotation classification schema is also provided, which is aimed at identifying the spatial, temporal and domain detail level used.The ViSOR web interface allows video browsing, querying by annotated concepts or by keywords, compressed video previewing, media downloading and uploading.Finally, ViSOR includes a performance evaluation desk which can be used to compare different annotations.

Wide area video surveillance always requires to extract and integrate information coming from different cameras and views. Re-identification of people captured from different cameras or different views is one of most challenging problems. In this paper, we present a novel approach for people matching with vertices-based 3D human models.People are detected and tracked in each calibrated camera, and their silhouette, appearance, position and orientation are extracted and used to place, scale and orientate a 3D body model. Colour features are computed from the 2D appearance images and mapped to the 3D model vertices, generating the 3D model for each tracked person. A distance function between 3D models is defined in order to find matches among models belonging to the same person. This approach achieves robustness against partial occlusions, pose and viewpoint changes. A first experimental evaluation is conducted using images extracted from a real camera set-up.

On-line action recognition from a continuous stream of actionsis still an open problem with fewer solutions proposedcompared to time-segmented action recognition. The mostchallenging task is to classify the current action while findingits time boundaries at the same time. In this paper wepropose an approach capable of performing on-line actionsegmentation and recognition by means of batteries of HMMtaking into account all the possible time boundaries and actionclasses. A suitable Bayesian normalization is appliedto make observation sequences of different length comparableand computational optimizations are introduce to achievereal-time performances. Results on a well known actiondataset prove the efficacy of the proposed method

In this paper, we present a new approach to object tracking based on batteries of particle filter working in multicamera systems with non overlapped fields of view. In each view the moving objects are tracked with independent particle filters; each filter exploits a likelihood function based on both color and motion information. The consistent labeling of people exiting from a camera field of view and entering in a neighbor one is obtained sharing particles information for the initialization of new filtering trackers. The information exchange algorithm is based on path-nodes, which are a graph-based scene representation usually adopted in computer graphics. The approach has been tested even in case of simultaneous transitions, occlusions, and groups of people. Promising results have been obtained and here presented using a real setup of non overlapped cameras.