Publications by Rita Cucchiara

This paper proposes a new human-machine interface particularly conceived for people with severe disabilities (specifically tetraplegic people), that allows them to interact with the computer for their everyday life by means of mouse pointer. In this system, called FaceMouse, instead of classical pointer paradigm that requires the user to look at the point where to move, we propose to use a paradigm called derivative paradigm, where the user does not indicate the precise position, but the direction along which the mouse pointer must be moved. The proposed system is composed of a common, lowcost webcam, and by a set of computer vision techniques developed to identify the parts of the user's face (the only body part that a tetraplegic person can move) and exploit them for moving the pointer. Specifically, the implemented algorithm is based on template matching to track the nose of the user and on cross-correlation to calculate the best match. Finally, several real applications of the system are described and experimental results carried out by disabled people are reported.

A system for video surveillance purposes in wide areas based on active cameras, also capable to follow a person in the scene by keeping him framed, is presented. The proposed approach is based on the so-called direction histograms to compute the ego-motion and on frame differencing for detecting moving objects. It exploits post-processing and active contours to extract precise shape of moving objects to be fed to a probabilistic algorithm to track moving people in the scene. Person following, instead, is based on simple heuristic rules that move the camera as soon as the selected person is close to the border of the field of view. Experimental results on a live active camera demonstrate the feasibility of real-time person following.

Logging information on moving objects is crucial in video surveillance systems. Distributed multi-camera systems can provide the appearance of objects/people from different viewpoints 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 to fully 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 configuration 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.

This paper describes a complete approach to detect, localize and describe network patterns. Such texture is automatically detected with Gaussian derivative kernels and Fisher linear discriminant analysis; line closure and thinning is provided by morphological masking and line luminance profile fitting provides width estimation. Detection results on dermatological images are reported and discussed.

This paper presents an effective system for streaming over low-capacity networks (such as GPRS and EGPRS) of live videos with low latency. Existing solutions are either too complex or not suitable to our scope. For this reason, we developed a complete, ready-to-use streaming system based on H.264/AVC codec and UDP/IP stack. The system employs adaptive controls to achieve the best tradeoff between low latency and good video fluency, by keeping the UDP buffer occupancy at the decoder side between two given levels. Our experiments demonstrate that this system is able to transmit live videos at CIF format and 10 fps over GPRS/EGPRS with very low latency (1.73 sec on average, basically due to the network delay), good fluency and average quality, measured with PSNR, of 31 dB on GPRS at 23 kbps at 10 fps.

Effective usage of multimedia digital libraries has to deal with the problem of building efficient content annotation and retrieval tools. MOM (Multimedia Ontology Manager) is a complete system that allows the creation of multimedia ontologies, supports automatic annotation and creation of extended text (and audio) commentaries of video sequences, and permits complex queries by reasoning on the ontology.

A system for the automatic creation of Pictorially Enriched Ontologies is presented, that is ontologies for context-based video digital libraries, enriched by pictorial concepts for video annotation, summarization and similarity-based retrieval. Extraction of pictorial concepts with video clips clustering, ontology storing with MPEG-7, and the use of the ontology for stored video annotation are described. Re-sults on sport videos and TRECVID2005 video material are reported.

Multimedia surveillance relates to the exploitation of multimedia tools for retrieving information from surveillance data, for emerging applications such as video post-analysis for forensic purposes. Searching for all the sequences in which a certain person was present is a typical query that is carried out by means of example images. Unfortunately, surveillance cameras often have low resolution, making retrieval based on appearance difficult. This paper proposes to exploit a two-step retrieval process that merges similarity-based retrieval with multicamera tracking-based retrieval able to create consistent traces of a person from different views and, thus, different resolutions. A mixture model is used to summarize these traces into a single prototype on which retrieval is performed. Experimental results demonstrate the accuracy of the retrieval process also in the case of varying illumination conditions.

In this DEMO, we present a tool set for video digital library management that allows i) structural annotation of edited videos in MPEG-7 by automatically extracting shots and clips; ii) automatic semantic annotation based on perceptual similarity against a taxonomy enriched with pictorial concepts iii) video clip access and hierarchical summarization with stand-alone and web interface iv) access to clips from mobile platform in GPRS-UMTS videostreaming. The tools can be applied in different domain-specific Video Digital Libraries. The main novelty is the possibility to enrich the annotation with pictorial concepts that are added to a textual taxonomy in order to make the automatic annotation process more fast and often effective. The resulting multimedia ontology is described in the MPEG-7 framework. The PEANO (Perceptual Annotation of Video) tool has been tested over video art, sport (Soccer, Olimpic Games 2006, Formula 1) and news clips.

In this work, we describe in detail the MPEG-7 Shape Spectrum Descriptor and provide a set of tests with different 3D objects databases. To verify if the literature reported low performance of this descriptor were due to the comparison employed, we also used the Earth Movers Distance which allows much more detailed histograms comparisons. Finally we compare our outcomes with the best results in related work.