Publications by Costantino Grana

People tracking deals with problems of shape changes, self-occlusions and track occlusions due to other interfering tracks and fixed objects that hide parts of the people shape. These problems are more critical in indoor surveillance and in particular in home automation settings, in which the need to merge information obtained form different cameras distributed around the house calls for the integration of reliable data obtained during time. Therefore, tracking algorithms should be carefully tuned to cope with occlusions and shape changes, working not only at pixel level but also at region level. In this work we provide a novel technique for object tracking, based on probabilistic masks and appearance models. Occlusions due to other tracks or due to background objects and false occlusions are discriminated. The classification of occluded regions of the track is exploited in a selective model update. 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 to track assignment even with large occlusions. At the same time, the model update 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 different experiments of people behavior control in indoor situations.

We describe an integrated solution devised for inhouse video surveillance, to control the safety of people living in a domestic environment. The system is composed of robust moving object detection module, able to disregard shadows, a tracking module designed for large occlusion solution and of a posture detector. Shadows, large occlusions and deformable model of people are key features of inhouse surveillance. Moreover, the requirements of high speed reaction to dangerous situations and the need to implement a reliable and low cost televiewing system, led to the introduction of a new multimedia model of semantic transcoding, capable of supporting different user's requests and constraints of their devices (PDA, smart phones, ...). Our application context is the emerging area of domotics (from the Latin word domus that means "home" and informatics) and, in particular, indoor video surveillance of the house where people with some difficulties (elders and disabled people) can now live in a sufficient degree of autonomy, thanks to the strong interaction with the new technologies that can be distributed in the house with affordable costs and high reliability.

The paper presents an approach for a robust (semi-)automatic correction of radial lens distortion in images and videos. This method, based on the Hough transform, has the characteristics to be applicable also on videos from unknown cameras that, consequently, can not be a priori calibrated. We approximated the lens distortion by considering only the lower-order term of the radial distortion. Thus, the method relies on the assumption that pure radial distortion transforms straight lines into curves. The computation of the best value of the distortion parameter is performed in a multi-resolution way. The method precision depends on the scale of the multi-resolution and on the Hough space's resolution. Experiments are provided for both outdoor, uncalibrated camera and an indoor, calibrated one. The stability of the value found in different frames of the same video demonstrates the reliability of the proposed method.

The aim of this study was to provide mathematical descriptors for the border of pigmented skin lesion images and to assess their efficacy for distinction among different lesion groups. New descriptors such as lesion slope and lesion slope regularity are introduced and mathematically defined. A new algorithm based on the Catmull-Rom spline method and the computation of the gray-level gradient of points extracted by interpolation of normal direction on spline points was employed. The efficacy of these new descriptors was tested on a data set of 510 pigmented skin lesions, composed by 85 melanomas and 425 nevi, by employing statistical methods for discrimination between the two populations.

The description of the border appears to be an important feature for clinical judgement in dermatoscopy, but it is subjective and can lead to different results depending on the examiners’ experience. In order to provide mathematical descriptors for border regularity and to increase the reproducibility of clinical judgement, a method to quantify border characteristics and to automatically reproduce the B (Border) parameters of the ABCD rule was developed. 331 images of pigmented skin lesions, 113 referring to melanomas and 218 to melanocytic naevi, acquired by a digital videomicroscope with a 20× magnification were studied. Clinical evaluation: for the evaluation of border cut-off, a score ranging to 0 from 8 was attributed to each lesion on the basis of the number of segments with an abrupt edge interruption of the pigmentation. Computer elaboration: after automatic border detection, the skin lesion gradient, defined as the change in lightness values along a 30 pixel long segment centred on the lesion border, expressed as the slope of the curve, was calculated along a 30 pixel segment. Minimum and maximum values and the standard deviation were calculated for the description of border regularity. In order to compare clinical and computer evaluation, the lesion border was divided into 8 segments and a threshold for abrupt border cut-off was set on a visual basis. Melanomas presented more abrupt and inhomogeneous margins in respect of melanocytic naevi. A good correlation between clinical evaluation and computer elaboration was found for the number of borders with an abrupt cut-off (rho = 0.834; P < 0.001). Computerized image analysis appears to be able to numerically describe pigmented skin lesions and to reproduce some aspects of the clinical evaluation. Enabling an objective and reproducible description, it could represent a useful support to clinical diagnosis.

Monitoring and controlling the driver’s guidance by analyzing the rotation impressed to the steering-wheel can be a very important task in order to improve safety. This paper proposes a general-purpose method to track the steering wheel’s absolute angle by using a single camera vision system mounted inside the car. The absolute angle is computed by means of the accumulation of inter-frame relative rotations and the error propagation is prevented with an alignment process. The approach is based on the modeling of the motion of the steering wheel, as it appears perspectivelydistorted by the point of view of the un-calibrated camera. We modified the Lucas-Kanade method for an approximatively rotational motion model in order to provide the detection and tracking of significant features on the wheel. The experimental results are compared with ground-truthed data obtained with different types of sensors.

In contrast with common naevi, which generally show a homogeneous and regularly distributed pigmentation, brown to black pigment areas with irregular shape or asymmetric distribution are frequently observable in melanomas. Identification of dark areas inside a melanocytic lesion is of great importance for melanoma diagnosis, both during clinical examination and employing programs for automated image analysis. The aim of our study was to compare two different methods for the automated identification and description of dark areas in epiluminescence microscopy images of melanocytic lesions and to evaluate their diagnostic capability. 339 images of melanocytic lesions, referring to 113 melanomas and 226 melanocytic naevi, acquired by means of a polarizedlight videomicroscope (Videocap 200, DS-medica, Italy) with a 20 fold magnification were studied. Two different methods were employed for the identification of dark areas: the first permits the identification of ‘absolute’ dark areas, defined as areas which are darker than the skin. The second identifies the lesion area, the darkest with respect to the overall brightness of the lesion (‘relative’ dark areas). A set of parameters is extracted both for ‘absolute’ and ‘relative’ dark areas, in order to numerically describe the region properties, such as extension, balance, regularity and symmetry of its distribution. Significant differences in dark area distribution between melanomas and naevi were observed employing both methods, permitting a good discrimination of melanocytic lesions (diagnostic accuracy = 74.6% and 71.2% for absolute and relative dark areas, respectively). In conclusion, both methods for automated identification of dark areas are useful for melanoma diagnosis and can be implemented in programs for image analysis.

Background The assessment of colours is essential for the diagnosis of malignant melanoma ( MM), both for pattern analysis on dermoscopic images, and when employing semiquantitative methods. Objectives To develop a computer program for colour assessment in MM images mimicking the human perception of lesion colours, and to compare the automatic colour evaluation with one performed by human observers. Methods A colour palette comprising six colour groups ( black, dark brown, light brown, blue grey, red and white) was created by selecting single colour components inside melanocytic lesion images acquired by means of a digital videomicroscope, and was implemented in the image analysis program. Subsequently, colours were assessed by the computer program on 331 melanocytic lesion images composing our image database, and the results were compared with the evaluation of lesion colours performed by the clinician. Results The black, white and blue - grey colours were more frequently found in MMs than in naevi, both by the clinicians and by the computer. In MM images we observed 4.27 +/- 1.14 colours (mean +/- SD) per lesion, as opposed to 3.22 +/- 0.68 in naevi. The correlation between clinical and computer evaluation of the colours was very good, with a value of 0.781 for overall assessment. Conclusions This innovative method for automatic colour evaluation, reproducing clinical assessment of melanocytic lesion colours, may provide numerical parameters to be employed for computer-aided diagnosis of MM.

In this paper we propose an approach to indoor environment surveillance and, in particular, to people behaviour control in home automation context. The reference application is a silent and automatic control of the behaviour of people living alone in the house and specially conceived for people with limited autonomy (e.g., elders or disabled people). The aim is to detect dangerous events (such as a person falling down) and to react to these events by establishing a remote connection with low-performance clients, such as PDA (Personal Digital Assistant). To this aim, we propose an integrated server architecture, typically connected in intranet with network cameras, able to segment and track objects of interest; in the case of objects classified as people, the system must also evaluate the people posture and infer possible dangerous situations. Finally, the system is equipped with a specifically designed transcoding server to adapt the video content to PDA requirements (display area and bandwidth) and to the user's requests. The main issues of the proposal are a reliable real-time object detector and tracking module, a simple but effective posture classifier improved by a supervised learning phase, and an high performance transcoding inspired on MPEG-4 object-level standard, tailored to PDA. Results on different video sequences and performance analysis are discussed.

Background subtraction methods are widely exploited for moving object detection in videos in many applications, such as traffic monitoring, human motion capture, and video surveillance. How to correctly and efficiently model and update the background model and how to deal with shadows are two of the most distinguishing and challenging aspects of such approaches. This work proposes a general-purpose method that combines statistical assumptions with the object-level knowledge of moving objects, apparent objects (ghosts), and shadows acquired in the processing of the previous frames. Pixels belonging to moving objects, ghosts, and shadows are processed differently in order to supply an object-based selective update. The proposed approach exploits color information for both background subtraction and shadow detection to improve object segmentation and background update. The approach proves fast, flexible, and precise in terms of both pixel accuracy and reactivity to background changes.