ODONE , Francesca

In this paper we deal with pedestrian detection and propose the use of group lasso to learn from data a compact and meaningful representation out of a high dimensional dictionary of local features. Group lasso, a regularized method with a sparsity-enforcing penalty term, has the very nice property of performing feature selection while...

In this paper, we describe an efficient pipeline for real-time text detection to be implemented on different architectures, with particular reference to smart phones. The text detection pipeline is based on a rather standard segmentation followed by a classification of each segmented connected component. Segmentation is performed by a linear...

In this work we consider a machine learning setting where data are represented as graphs. First, we derive a kernel function which evaluates the similarity between graphs, while capturing pair-wise constraints between graph nodes. Second, we apply it to the problem of classifying collective activities: on this respect we first represent groups...

In this paper we consider the problem of classifying people spatial orientation with respect to the camera viewpoint from 2D images. Structured multi-class feature selection allows us to control the amount of redundancy of our input data, while semi-supervised learning helps us coping with the intrinsic ambiguity of output labels. We model the...

In this work we consider the problem of modeling and recognizing collective activities performed by groups of people sharing a common purpose. For this aim we take into account the social contextual information of each person, in terms of the relative orientation and spatial distribution of people groups. We propose a method able to process a...

This paper is about extracting knowledge from large sets of videos, with a particular reference to the video-surveillance application domain. We consider an unsupervised framework and address the specific problem of modeling common behaviors from long-term collection of instantaneous observations. Specifically, such data describe dynamic events...

In this work we present a prototype application for modelling common behaviours from long-time observations of a scene. The core of the system is based on the method proposed in (Noceti and Odone, 2012), an adaptive technique for profiling patterns of activities on temporal data - coupling a string-based representation and an unsupervised...

This paper proposes a new approach for embedding spatial information into a Bag of Features image descriptor, primarily meant for image retrieval. The method is conceptually related to Spatial Pyramids but instead of requiring fixed and arbitrary sub-regions where to compute region-based BoF, it relies on an adaptive procedure based on multiple...

In the statistical learning framework, the use of appropriate kernels may be the key for substantial improvement in solving a given problem. In essence, a kernel is a similarity mea- sure between input points satisfying some mathematical requirements and possibly capturing the domain knowledge. In this paper, we focus on kernels for images: we...

No description

In this paper we propose a motion-based people counting al- gorithm that relies on a weak camera calibration and produces a smooth estimate of the number of people in the scene. The method performs an analysis of the severity of possible occlu- sions and the integration of instantaneous observations over time. The key features of the algorithm...

No description

No description

No description

No description

We address the problem of multi-view association of articulated objects observed by potentially moving and handheld cameras. Starting from trajectory data, we encode the temporal evolution of the objects and perform matching without making assumptions on scene geometry and with only weak assumptions on the field-of-view overlaps. After...

In this paper we propose a real time face recognition method that combines face matching and identity verification modules in a feedback loop, exploiting the temporal efficiency of matching and the performances of SVM classifiers. Our approach represents an ad-hoc solution for settings characterized by variable quantity, quality and...

We propose a video alignment method based on observing the actions of a set of articulated objects. Given ob- ject association information, the proposed video synchronization method is applicable to general and unconstrained scenarios in a way that is not feasible with current state-of-the-art approaches: the proposed method does not impose...

This paper considers view-based 3D object recognition in videos The availability of video sequences allows us to address recognition exploiting both space and time information to build models of the object that are robust to view-point variations. In order to limit the amount of information potentially available in a video we adopt a...