Publications by Rita Cucchiara

The detection of humans in very complex scenes can be very challenging, due to the performance degradation of classical motion detection and tracking approaches. An alternative approach is the detection of human-like patterns over the whole image. The present paper follows this line by extending Tuzel et al.’s technique [1] based on covariance descriptors and LogitBoost algorithm applied over Riemannian manifolds. Our proposal represents a significant extension of it by: (a) exploiting motion information to focus the attention over areas in which motion is present or was present in the recent past; (b) enriching the human classifier by additional, dedicated cascades trained on positive and negative samples taken from the specific scene; (c) using a rough estimation of the scene perspective, to reduce false detections and improve system performance. This approach is suitable in multi-camera scenarios, since the monolithic block for human-detection remains the same for the whole system, whereas the parameter tuning and set-up of the three proposed extensions (the only camera-dependent parts of the system), are automatically computed for each camera. The approach has been tested on a construction working site in which complexity and dynamics are very high, making human detection a real challenge. The experimental results demonstrate the improvements achieved by the proposed approach.

This article presents a framework for automatic semantic annotation of video streams with an ontology that includes concepts expressed using linguistic terms and visual data.

In this paper we present a new optimization technique for the neighborhood computation in connected component labeling focused on images stored in raster scan order. This new technique is based on a 2x2 square block analysis of the image, and it exploits the fact that, when using 8-connection, the pixels of a 2x2 square are all connected to each other. This implies that they will share the same label at the end of the computation. To prove the effectiveness of our proposal, we show a comprehensive comparison of the most used and advanced connected components labeling techniques presented so far. The tests are conducted on high resolution images obtained from digitized historical manuscripts and a set of transformations is applied in order to show the algorithms behavior at different image resolutions and with a varying number of labels.

This paper proposes a system for people trajectory shape analysis by exploiting a statistical approach which accounts for sequences of both directional (the directions of the trajectory) and linear (the speeds) data. A semi-directional distribution (AWLG - Approximated Wrapped and Linear Gaussian) is used with a mixture to find main directions and speeds. A variational version of the mutual information criterion is proposed to prove the statistical dependency of the data. Then, in order to compare data sequences, we define an inexact method with a Kullback-Leibler-based distance measure and employ a global alignment technique is to handle sequences of different lengths and with local shifts or deformations. A comprehensive analysis of variable dependency and parameter estimation techniques are reported and evaluated on both synthetic and real data sets.

This paper presents a novel approach for detecting multiple instances of the same object for pick-and-place automation. The working conditions are very challenging, with complex objects, arranged at random in the scene, and heavily occluded. This approach exploits SIFT to obtain a set of correspondences between the object model and the current image. In order to segment the multiple instances of the object, the correspondences are clustered among the objects using a voting scheme which determines the best estimate of the object's center through mean shift. This procedure is compared in terms of accuracy with existing homography-based solutions which make use of RANSAC to eliminate outliers in the homography estimation.

This paper presents a novel approach for detecting multipleinstances of the same object for pick-and-place automation.The working conditions are very challenging, with complex objects, arranged at random in the scene, and heavily occluded. This approach exploits SIFT to obtain a set of correspondences between the object model and the current image. In order to segment the multiple instances of the object, the correspondences are clustered among the objects using a voting scheme which determines the best estimate of the object’s center through mean shift. This procedure is compared in terms of accuracy with existing homography-based solutions which make use of RANSAC to eliminate outliers in the homography estimation.

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.

In this work we propose a system for automatic document segmentation to extract graphical elements from historical manuscripts and then to identify significant pictures from them, removing floral and abstract decorations. The system performs a block based analysis by means of color and texture features. The Gradient Spatial Dependency Matrix, a new texture operator particularly effective for this task, is proposed. The feature vectors are processed by an embedding procedure which allows increased performance in later SVM classification. Results for both feature extraction and embedding based classification are reported, supporting the effectiveness of the proposal.

It is our great pleasure to welcome you to the 1st ACM Workshop on Multimedia in Forensics -- MiFor'09.With the proliferation of multimedia data on the web, surveillance cameras in cities, and mobile phones in everyday life we see an enormous growth in multimedia data that needs to be analyzed by forensic investigators. The sheer volume of such datasets makes manual inspection of all data impossible. Tools are needed to support the investigator in their quest for relevant clues and evidence and in their strive towards preventing crime.The multimedia community has developed new solutions for management of large collections of video footage, images, audio and other multimedia content, knowledge extraction and categorization, pattern recognition, indexing and retrieval, searching, browsing and visualization, and modeling and simulation in various domains. Due to the inherent uncertainty and complexity of forensic data, applying those techniques to forensic data is not straightforward. The time is ripe to tailor these results for forensics. Multimedia in forensics is the workshop which target is to join the research topics and the applications.The workshop aims at addressing the multimedia toolbox supporting the forensic process from the prevention of crime, capturing and annotation of the crime scene, the investigation of the data in the lab, up to the presentation of the results in court. It is a first attempt in bringing multimedia tools in to this exciting application field. The target audience consists of researchers working on innovative technology, representatives from companies developing tools, and forensic investigators in various disciplines.Despite the ambitious objective for the workshop and it being the first edition, it attracted a good number of quality submissions fairly distributed among different countries and among the different topics of the workshop. The MiFor09 Technical Program Committee includes the most experienced researchers in the related research fields, and thanks to their indispensable effort we were able to select 11 papers for oral presentation.The workshop schedules four oral sessions, named "Detection and Mining", "Multimedia forensics prototypes", "Forgery and Splicing Detection" and "Tracking". In addition, the program includes a keynote address by Professor Mohan Kankanhalli, a distinguished lecturer in the field.