Publications by Rita Cucchiara

In this paper, we propose a system for automatic video summarization at sub-shot level. Our work covers two main aspects: the first is the sub-shot detection, which is performed without a priori constraints on the number or length of the shots. The algorithm is based on color histograms and motion features, and employs fuzzy c-means with variable number of clusters. The second aspect is an in depth discussion on the annotation of summaries with the MPEG-7 standard. Results on mixed genres TV material, from TRECVID videos, are reported.

Logging information on moving objects is crucial in video surveillance systems. Distributed multi-camera systems can provide the appearance of objects/people from differentviewpoints and at different resolutions, allowing a more complete and precise logging of the information. This is achieved through consistent labeling to correlate collected information of the same person. This paper proposes a novel approach to consistent labeling also capable tofully characterize groups of people and to manage miss segmentations. The ground-plane homography and the epipolar geometry are automatically learned and exploited to warp objects’ principal axes between overlapped cameras. A MAP estimator that exploits two contributions (forward and backward) is used to choose the most probable label con£guration to be assigned at the handoff of a new object. Extensive experiments demonstrate the accuracy of the proposed method in detecting single and simultaneous handoffs, miss segmentations, and groups.

What approach or combination of approaches did you test in each of your submitted runs?TRECVID2005_UNIMORE_??.xml: the same linear transition detector (LTD) was tested forevery run, with ten uniformly spaced thresholds for the detection.What if any significant differences (in terms of what measures) did you find among theruns?The system behaved as expected: the higher the threshold the better the recall. Of course theprecision lowered correspondently. Interesting enough, it seems that we cannot overcome theoverall limit around 80% for recall and 88% for precision, independently of the other parameter.Based on the results, can you estimate the relative contribution of each component of yoursystem/approach to its effectiveness?One of the main objective of our system was to test the performance of a single algorithm forboth cuts and gradual transitions. So all the merit and the demerits are related to our LTD.Overall, what did you learn about runs/approaches and the research question(s) thatmotivated them?The use of a single algorithm allows the system to be run without training. Just a singleparameter may be employed to tune the sensibility of the system, thus allowing its use in generalpurpose/user friendly systems.

In this paper, we present a system for the assisted creation of Pictorially Enriched Ontologies, that is ontologies for context-based digital libraries enriched by pictorial concepts for video annotation, summarization and similarity based retrieval. Here we detail the approach for video clips clustering and pictorial concepts extraction together with the approach for storing the ontology within the MPEG-7 framework. The clustering is performed by Complete Link hierarchical clustering on color histograms and motion features. Results on Formula 1 TV material are reported.

In this paper, we approach the problem of detecting editing features suitable for video annotation, by paying attention to artifacts and effects introduced in video editing. In particular, a linear transition detection algorithm is presented, which can characterize the transition center and length with high precision. The technique works with sub-frame granularity and is able to include both abrupt cuts and longer dissolves in a single approach. Theoretical justification for the algorithm is provided with an optimization technique for real cases. We present results obtained exploiting the editing features on a Formula 1 video digital library, detecting replays and providing pre classification hints for automatic shot annotation.

In this paper, we address the exploitation of computervision techniques to develop multimedia services andautomatic monitoring systems related to the securityand the privacy in public areas. The research is part ofa two-year ltalian project called LAICA, intended toprovide advanced services for citizens and publicofficers. Citizens want fast and friendly web access topublic places, to see the environment in real-timewithout violating the privacy laws. Public officers andpolicy centres want a fast and reactive monitoringsystem, capable to automatically detect dangeroussituations, given the huge amount of cameras that cannot be monitored simultaneously by human operators.In this work, we describe the project and the definedmethodologies in multi-camera video mosaicing,people tracking and consistent labelling, and access toprocessed data with face obscuration.

This paper reports advances achieved within a project called LAICA (Laboratorio di Ambient Intelligence per una Città Amica) on Ambient Intelligence in urban environments. The overall LAICA architecture is described and the unified operative centre developed by Regulus SpA (partner of the project) to collect and correlate data from different sensors and prototypes is depicted. Moreover, the paper describes the results obtained in developing a system for video surveillance in public parks, devoted to create a mosaic image of the scene and to extract and track moving people. Moreover, the system takes the privacy issues into account, proposing a method for face detection and tracking able to obscure faces in order to protect people’s identity.

Tools for the interpretation of significant events from video and video clip adaptation can effectively support automatic extraction and distribution of relevant content from video streams. In fact, adaptation can adjust meaningful content, previously detected and extracted, to the user/client capabilities and requirements. The integration of these two functions is increasingly important, due to the growing demand of multimedia data from remote clients with limited resources (PDAs, HCCs, Smart phones). In this paper we propose an unified framework for event-based and object-based semantic extraction from video and semantic on-line adaptation. Two cases of application, highlight detection and recognition from soccer videos and people behavior detection in domotic* applications, are analyzed and discussed.

In this paper we present a people posture classificationapproach especially devoted to cope with occlusions. Inparticular, the approach aims at assessing temporal coherenceof visual data over probabilistic models. A mixed predictiveand probabilistic tracking is proposed: a probabilistictracking maintains along time the actual appearance ofdetected people and evaluates the occlusion probability; anadditional tracking with Kalman prediction improves the estimationof the people position inside the room. ProbabilisticProjection Maps (PPMs) created with a learning phaseare matched against the appearance mask of the track. Finally,an Hidden Markov Model formulation of the posturecorrects the frame-by-frame classification uncertainties andmakes the system reliable even in presence of occlusions.Results obtained over real indoor sequences are discussed.

This paper addresses auto-iris compensation. Auto-iris can be really troublesome for motion detection and tracking techniques based on background or frame differencing,since it can change quickly the average intensity of thecurrent frame. To cope with this, we introduced a two-step autoiris compensation approach in our traffic monitoring system. First, the auto-iris detection is based on the computation of the average of the luminance difference obtained by background suppression. Then, if an auto-iris is detected, the compensation phase is started. In this phase, the auto-iris’ behaviour is empirically modelled and, thus, compensated. Experimental results demonstrate the accuracy of the proposed approach, with both quantitative measures and visual analysis.