Publications

Automatic segmentation of skin lesions in clinical images is a very challenging task; it is necessary for visual analysis of the edges, shape and colors of the lesions to support the melanoma diagnosis, but, at the same time, it is cumbersome since lesions (both naevi and melanomas) do not have regular shape, uniform color, or univocal structure. Most of the approaches adopt unsupervised color clustering. This works compares the most spread color clustering algorithms, namely median cut, k-means, fuzzy-c means and mean shift applied to a method for automatic border extraction, providing an evaluation of the upper bound in accuracy that can be reached with these approaches. Different tests have been performed to examine the influence of the choice of the parameter settings with respect to the performances of the algorithms. Then a new supervised learning phase is proposed to select the best number of clusters and to segment the lesion automatically. Examples have been carried out in a large database of medical images, manually segmented by dermatologists. From these experiments mean shift was resulted the best technique, in term of sensitivity and specificity. Finally, a qualitative evaluation of the goodness of segmentation has been validated by the human experts too, confirming the results of the quantitative comparison.

In this paper we focus on the problem of automatically registering dermatological images, because even if different products are available, most of them share the problem of a limited field of view on the skin. A possible solution is then the composition of multiple takes of the same lesion with digital software, such as that for panorama images creation.In this work, to perform an automatic selection of matching points the Harris Corner Detector is used, and to cope with outlier couples we employed the RANSAC method. Projective mapping is then used to match the two images. Given a set of correspondence points, Singular Value Decomposition was used to compute the transform parameters.At this point the two images need to be blended together. One initial assumption is often implicitly made: the aim is to merge two rectangular images. But when merging occurs between more than two images iteratively, this assumption will fail. To cope with differently shaped images, we employed the Distance Transform and provided a weighted merging of images. Different tests were conducted with dermatological images, both with standard rectangular frame and with not typical shapes, as for example a ring due to the objective and lens selection. The successive composition of different circular images with other blending functions, such as the Hat function, doesn’t correctly get rid of the border and residuals of the circular mask are still visible. By applying Distance Transform blending, the result produced is insensitive of the outer shape of the image.

This paper proposes a novel method for estimating thegeospatial trajectory of a moving camera. The proposedmethod uses a set of reference images with known GPS(global positioning system) locations to recover the trajectoryof a moving camera using geometric constraints. Theproposed method has three main steps. First, scale invariantfeatures transform (SIFT) are detected and matched betweenthe reference images and the video frames to calculatea weighted adjacency matrix (WAM) based on the numberof SIFT matches. Second, using the estimated WAM, themaximum matching reference image is selected for the currentvideo frame, which is then used to estimate the relativeposition (rotation and translation) of the video frame usingthe fundamental matrix constraint. The relative position isrecovered upto a scale factor and a triangulation amongthe video frame and two reference images is performed toresolve the scale ambiguity. Third, an outlier rejection andtrajectory smoothing (using b-spline) post processing stepis employed. This is because the estimated camera locationsmay be noisy due to bad point correspondence or degenerateestimates of fundamental matrices. Results of recoveringcamera trajectory are reported for real sequences.

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.