Publications

-

In this paper we address the problem of human posture classification, in particular focusing to an indoor surveillance application. The approach was initially inspired to a previous works of Haritaoglou et al. [5] that uses histogram projections to classify people’s posture. Projection histograms are here exploited as the main feature for the posture classification, but, differently from [5], we propose a supervised statistical learning phase to create probability maps adopted as posture templates. Moreover, camera calibration and homography are included to solve perspective problems and to improve the precision of the classification. Furthermore, we make use of a finite state machine to detect dangerous situations as falls and to activate a suitable alarm generator. The system works on-line on standard workstations with network cameras.

-

This paper proposes the use of an approach of video transcoding driven by the video content and providedwith the adaptive quantization of MPEG standards.Computer vision techniques can extract semanticsfrom videos according with user's interests: the videosemantics is exploited to adapt the video in order tomeet the device's capabilities and the user'srequirements and preserve the best quality possible. Well assessed video analysis techniques are used to segment the video into objects grouped in classes ofrelevance to which the user can assign a weight proportional to their relevance. This weight is used todecide the quantization values to be applied in theMPEG-2 encoding to each macroblock. A modified version of the PSNR (Peak Signal-to-Noise Ratio) is used as performance metric and comparativeevaluation is reported with respect to other codingstandards such as JPEG, JPEG 2000, (basic) MPEG-2, and MPEG-4. Experimental results are provided on different situations, one indoor and oneoutdoor. Keywords:Videotranscoding, adaptive quantization, motion detection

This paper describes our approach to real-time detection of camera motion and moving object segmentation in videos acquired from moving cameras. As far as we know, none of the proposals reported in the literature are able to meet real-time requirements. In this work, we present an approach based on a color segmentation followed by a region-merging on motion through Markov Random Fields (MRFs). The technique we propose is inspired to a work of Gelgon and Bouthemy (Pattern Recognition 33 (2000) 725-40), that has been modified to reduce computational cost in order to achieve a fast segmentation (about 10 frame per second). To this aim a modified region matching algorithm (namely Partitioned Region Matching) and an innovative arc-based MRF optimization algorithm with a suitable definition of the motion reliability are proposed. Results on both synthetic and real sequences are reported to confirm validity of our solution.

This work presents a novel people tracking approach, able to cope with frequent shape changes and large occlusions. In particular, the tracks are described by means of probabilistic masks and appearance models. Occlusions due to other tracks or due to background objects and false occlusions are discriminated. The tracking system is general enough to be applied with any motion segmentation module, it can track people interacting each other and it maintains the pixel assignment to track even with large occlusions. At the same time, the update model is very reactive, so as to cope with sudden body motion and silhouette's shape changes. Due to its robustness, it has been used in many experiments of people behavior control in indoor situations.

Atypical nevi share some dermoscopic features with early melanoma, and computer elaboration of digital images could represent a useful support to diagnosis. The aim of our study was to automatically assess colors in atypical nevi, and to compare the data with those referring to clearly benign nevi and melanomas. Dermoscopic images of 459 melanocytic lesions, referring to 76 atypical nevi, 288 clearly benign nevi and 95 melanomas, were acquired by means of a digital videomicroscope (Videocap 100, DS-Medica, Italy) employing a 20-fold magnification. An image analysis program, based on an approach, which shares some similarities with the human perception of colors, was employed. For the evaluation of colors in melanocytic lesion images, the identification of the six main color groups (black, dark brown, light brown, red, white and blue-gray) and the numerical description of color areas were obtained. Black, white and blue-gray were more frequently found in atypical nevi than in clearly benign nevi, but less frequently than in melanomas. Color area values significantly differed between the three groups, showing increasing irregularity in color distribution from benign lesions to atypical nevi and melanomas. The clinical–morphological interpretation of the numerical data, based on the mathematical description of the aspect and distribution of different color areas in different lesion types may contribute to the characterization of atypical nevi and their distinction from melanomas.

The assessment of asymmetry is essential for melanoma (MM) diagnosis, both when using a heuristic approach and when employing semiquantitative methods on dermoscopic images. The aim of our study was to develop and validate a software for assessment of asymmetry in melanocytic lesion images, based on evaluation of color symmetry, and to compare the automatic evaluation to the one performed by human observers. An image analysis program enabling the numerical assessment of asymmetry in melanocytic lesions, based on evaluation and comparison of RGB color components inside image color blocks, was employed on 459 videomicroscopic digital images, referring to 95 melanomas (MMs), 76 atypical nevi (AN) and 288 clearly benign nevi (BN). Clinical evaluation of asymmetry on dermoscopic images was performed on the same image set employing a 0–1 scoring system. Asymmetry judgement was expressed by the clinicians for 12.8% of BN, 44.7% of AN, and for 64.2% of MMs, whereas the computer identified 6.9% of BN, 27.6% of AN, and 87.4% of MMs as asymmetric. Sensitivity and specificity of clinical judgement were 64.2 and 80.5%, respectively, whereas for computer evaluation, a sensitivity of 87.5% and a specificity of 85.7% were obtained. Numerical parameters (mean RGB distance, variance and maximum distance) referring to MMs were significantly higher both with respect to BN and AN. This innovative method for automatic asymmetry evaluation, based on the mathematical description of color distribution in different image blocks, provides numerical parameters for employment in computer-aided melanoma diagnosis.