Alessandro Ortis

An Advanced Bio-Inspired PhotoPlethysmoGraphy (PPG) and ECG Pattern Recognition System for Medical Assessment

Physiological signals are widely used to perform medical assessment for monitoring an extensive range of pathologies, usually related to cardio-vascular diseases. Among these, both PhotoPlethysmoGraphy (PPG) and Electrocardiography (ECG) signals are those more employed. PPG signals are an emerging non-invasive measurement technique used to study blood volume pulsations through the detection and analysis of the back-scattered optical radiation coming from the skin. ECG is the process of recording the electrical activity of the heart over a period of time using electrodes placed on the skin. In the present paper we propose a physiological ECG/PPG “combo” pipeline using an innovative bio-inspired nonlinear system based on a reaction-diffusion mathematical model, implemented by means of the Cellular Neural Network (CNN) methodology, to filter PPG signal by assigning a recognition score to the waveforms in the time series. The resulting “clean” PPG signal exempts from distortion and artifacts is used to validate for diagnostic purpose an EGC signal simultaneously detected for a same patient. The multisite combo PPG-ECG system proposed in this work overpasses the limitations of the state of the art in this field providing a reliable system for assessing the above-mentioned physiological parameters and their monitoring over time for robust medical assessment. The proposed system has been validated and the results confirmed the robustness of the proposed approach.

Organizing egocentric videos of daily living activities

Abstract Egocentric videos are becoming popular since the possibility to observe the scene flow from the user’s point of view (First Person Vision). Among the different applications of egocentric vision is the daily living monitoring of a user wearing the camera. We propose a system able to automatically organize egocentric videos acquired by the user over different days. Through an unsupervised temporal segmentation, each egocentric video is divided in chapters by considering the visual content. The obtained video segments related to the different days are hence connected according to the scene context in which the user acts. Experiments on a challenging egocentric video dataset demonstrate the effectiveness of the proposed approach that outperforms with a good margin the state of the art in accuracy and computational time.

Adaptive Compression of Stereoscopic Images

Nowadays the growing availability of stereo cameras for common applications is becoming a commodity. This paper addresses the problem of stereoscopic images data compression proposing an innovative algorithm for compressing Multi Picture Object coded stereopairs. By means of self organizing reconstruction algorithm based on image redundancy we are able to reduce the size of the enclosed JPEG images. The overall perceived (and measured) quality is managed by considering that a stereoscopic image represents the same scene acquired from two different perspectives. In particular we achieve some compression gain just encoding the two images with different quality factors. The reported results and test benchmarks show the robustness and efficiency of the proposed algorithm.

Advanced Bio-Inspired System for Noninvasive Cuff-Less Blood Pressure Estimation from Physiological Signal Analysis

Blood Pressure (BP) is one of the most important physiological indicators that provides useful information in the field of health-care monitoring. Blood pressure may be measured by both invasive and non-invasive methods. A novel algorithmic approach is presented to estimate systolic and diastolic blood pressure accurately in a way that does not require any explicit user calibration, i.e., it is non-invasive and cuff-less. The approach herein described can be applied in a medical device, as well as in commercial mobile smartphones by an ad hoc developed software based on the proposed algorithm. The authors propose a system suitable for blood pressure estimation based on the PhotoPlethysmoGraphy (PPG) physiological signal sampling time-series. Photoplethysmography is a simple optical technique that can be used to detect blood volume changes in the microvascular bed of tissue. It is non-invasive since it takes measurements at the skin surface. In this paper, the authors present an easy and smart method to measure BP through careful neural and mathematical analysis of the PPG signals. The PPG data are processed with an ad hoc bio-inspired mathematical model that estimates systolic and diastolic pressure values through an innovative analysis of the collected physiological data. We compared our results with those measured using a classical cuff-based blood pressure measuring device with encouraging results of about 97% accuracy.

Evaluation of Levenberg–Marquardt neural networks and stacked autoencoders clustering for skin lesion analysis, screening and follow-up

Traditional methods for early detection of melanoma rely on the visual analysis of the skin lesions performed by a dermatologist. The analysis is based on the so-called ABCDE (Asymmetry, Border irregularity, Colour variegation, Diameter, Evolution) criteria, although confirmation is obtained through biopsy performed by a pathologist. The proposed method exploits an automatic pipeline based on morphological analysis and evaluation of skin lesion dermoscopy images. Preliminary segmentation and pre-processing of dermoscopy image by SC-cellular neural networks is performed, in order to obtain ad-hoc grey-level skin lesion image that is further exploited to extract analytic innovative hand-crafted image features for oncological risks assessment. In the end, a pre-trained Levenberg–Marquardt neural network is used to perform ad-hoc clustering of such features in order to achieve an efficient nevus discrimination (benign against melanoma), as well as a numerical array to be used for follow-up rate definition and assessment. Moreover, the authors further evaluated a combination of stacked autoencoders in lieu of the Levenberg–Marquardt neural network for the clustering step.

A System for Autonomous Landing of a UAV on a Moving Vehicle

This paper describes the approach employed to implement the autonomous landing of an Unmanned Aerial Vehicle (UAV) upon a moving ground vehicle. We consider an application scenario in which a target, made of a visual pattern, is mounted on the top of a ground vehicle which roams in an arena using a certain path and velocity; the UAV is asked to find the ground vehicle, by detecting the visual pattern, and then to track it in order to perform the approach and finalize the landing. To this aim, Computer Vision is adopted to perform both detection and tracking of the visual target; the algorithm used is based on the TLD (Tracking-Learning-Detection) approach, suitably integrated with an Hough Transform able to improve the precision of the identification of the 3D coordinates of the pattern. The output of the Computer Vision algorithm is then exploited by a Kalman filter which performs the estimation of the trajectory of the ground vehicle in order to let the UAV track, follow and approach it. The paper describes the software and hardware architecture of the overall application running on the UAV. The application described has been practically used with success in the context of the “Mohamed Bin Zayed” International Robotic Challenge (MBZIRC) which took place in March 2017 in Abu Dhabi.

Organizing Videos Streams for Clustering and Estimation of Popular Scenes

The huge diffusion of mobile devices with embedded cameras has opened new challenges in the context of the automatic understanding of video streams acquired by multiple users during events, such as sport matches, expos, concerts. Among the other goals there is the interpretation of which visual contents are the most relevant and popular (i.e., where users look). The popularity of a visual content is an important cue exploitable in several fields that include the estimation of the mood of the crowds attending to an event, the estimation of the interest of parts of a cultural heritage, etc. In live social events people capture and share videos which are related to the event. The popularity of a visual content can be obtained through the “visual consensus” among multiple video streams acquired by the different users devices. In this paper we address the problem of detecting and summarizing the “popular scenes” captured by users with a mobile camera during events. For this purpose, we have developed a framework called RECfusion in which the key popular scenes of multiple streams are identified over time. The proposed system is able to generate a video which captures the interests of the crowd starting from a set of the videos by considering scene content popularity. The frames composing the final popular video are automatically selected from the different video streams by considering the scene recorded by the highest number of users’ devices (i.e., the most popular scene).

The Social Picture

We present The Social Picture, a framework to collect and explore huge amount of crowdsourced social images about public events, cultural heritage sites and other customized private events.The Social Picture aims to create social communities of users that contribute to the creation of image collections about common interests. The collections can be explored through a number of advanced Computer Vision and Machine Learning algorithms, able to capture the visual content of images in order to organize them in a semantic way. The interfaces of The Social Picture allow the users to create customized collections by exploiting semantic filters based on visual features, social network tags, geolocation, and other information related to the images.

A new fast matching method for adaptive compression of stereoscopic images

In the last few years, due to the growing use of stereoscopic images, much effort has been spent by the scientific community to develop algorithms for stereoscopic image compression. Stereo images represent the same scene from two different views, and therefore they typically contain a high degree of redundancy. It is then possible to implement some compression strategies devoted to exploit the intrinsic characteristics of the two involved images that are typically embedded in a MPO (Multi Picture Object) data format. MPO files represents a stereoscopic image by building a list of JPEG images. Our previous work introduced a simple block-matching approach to compute local residual useful to reconstruct during the decoding phase, stereoscopic images that maintain high perceptual quality; this allows to the encoder to force high level of compression at least for one of the two involved images. On the other hand the matching approach, based only on the similarity of the blocks, results rather inefficient. Starting from this point, the main contribution of this paper focuses on the improvement of both matching step effectiveness and its computational cost. Such alternative approach aims to greatly enhance matching step by exploiting the geometric properties of a pair of stereoscopic images. In this way we significantly reduce the complexity of the method without affecting results in terms of quality.