Christian Micheloni

Trajectory-Based Anomalous Event Detection

During the last years, the task of automatic event analysis in video sequences has gained an increasing attention among the research community. The application domains are disparate, ranging from video surveillance to automatic video annotation for sport videos or TV shots. Whatever the application field, most of the works in event analysis are based on two main approaches: the former based on explicit event recognition, focused on finding high-level, semantic interpretations of video sequences, and the latter based on anomaly detection. This paper deals with the second approach, where the final goal is not the explicit labeling of recognized events, but the detection of anomalous events differing from typical patterns. In particular, the proposed work addresses anomaly detection by means of trajectory analysis, an approach with several application fields, most notably video surveillance and traffic monitoring. The proposed approach is based on single-class support vector machine (SVM) clustering, where the novelty detection SVM capabilities are used for the identification of anomalous trajectories. Particular attention is given to trajectory classification in absence of a priori information on the distribution of outliers. Experimental results prove the validity of the proposed approach.

Active video-based surveillance system: the low-level image and video processing techniques needed for implementation

The importance of video surveillance techniques has considerably increased since the latest terrorist incidents. Safety and security have become critical in many public areas, and there is a specific need to enable human operators to remotely monitor the activity across large environments. For these reasons, multicamera systems are needed to provide surveillance coverage across a wide area, ensuring object visibility over a large range of depths. In the development of advanced visual-based surveillance systems, a number of key issues critical to its successful operation must be addressed. This article describes the low-level image and video processing techniques needed to implement a modern surveillance system. In particular, the change detection methods for both fixed and mobile cameras (pan and tilt) are introduced and the registration methods for multicamera systems with overlapping and nonoverlapping views are discussed.

Video security for ambient intelligence

Moving toward the implementation of the intelligent building idea in the framework of ambient intelligence, a video security application for people detection, tracking, and counting in indoor environments is presented in this paper. In addition to security purposes, the system may be employed to estimate the number of accesses in public buildings, as well as the preferred followed routes. Computer vision techniques are used to analyze and process video streams acquired from multiple video cameras. Image segmentation is performed to detect moving regions and to calculate the number of people in the scene. Testing was performed on indoor video sequences with different illumination conditions.

Video Analysis in Pan-Tilt-Zoom Camera Networks

Pan-tilt-zoom (PTZ) cameras are able to dynamically modify their field of view (FOV). This functionality introduces new capabilities to camera networks such as increasing the resolution of moving targets and adapting the sensor coverage. On the other hand, PTZ functionality requires solutions to new challenges such as controlling the PTZ parameters, estimating the ego motion of the cameras, and calibrating the moving cameras.This tutorial provides an overview of the main video processing techniques and the currents trends in this active field of research. Autonomous PTZ cameras mainly aim to detect and track targets with the largest possible resolution. Autonomous PTZ operation is activated once the network detects and identifies an object as sensible target and requires accurate control of the PTZ parameters and coordination among the cameras in the network. Therefore, we present cooperative localization and tracking methods, i.e., multiagentand consensus-based approaches to jointly compute the targets properties such as ground-plane position and velocity. Stereo vision exploiting wide baselines can be used to derive three-dimensional (3-D) target localization. This tutorial further presents different techniques for controlling PTZ camera handoff, configuring the network to dynamically track targets, and optimizing the network configuration to increase coverage probability. It also discusses implementation aspects for these video processing techniques on embedded smart cameras, with a special focus on data access properties.

Re-identify people in wide area camera network

Tracking individuals within a wide area camera network is a tough problem. Obtaining information across uncovered areas is an open issue that person re-identification methods deal with. A novel appearance-based method for person re-identification is proposed. The approach computes a novel discriminative signature by exploiting multiple local features. A novel signature distance measure is given by exploiting a body part division approach. The method has been compared to state-of-the-art methods using a re-identification benchmark dataset. A new dataset acquired from non-overlapping cameras has been built to validate the method against a real wide area camera network scenario. The method has proven to be robust against low resolution images, viewpoint and illumination changes, occlusions and pose variations. Results show that the proposed approach outperforms state-of-the-art methods used for comparison.

Re-Identification in the Function Space of Feature Warps

Person re-identification in a non-overlapping multicamera scenario is an open challenge in computer vision because of the large changes in appearances caused by variations in viewing angle, lighting, background clutter, and occlusion over multiple cameras. As a result of these variations, features describing the same person get transformed between cameras. To model the transformation of features, the feature space is nonlinearly warped to get the “warp functions”. The warp functions between two instances of the same target form the set of feasible warp functions while those between instances of different targets form the set of infeasible warp functions. In this work, we build upon the observation that feature transformations between cameras lie in a nonlinear function space of all possible feature transformations. The space consisting of all the feasible and infeasible warp functions is the warp function space (WFS). We propose to learn a discriminating surface separating these two sets of warp functions in the WFS and to re-identify persons by classifying a test warp function as feasible or infeasible. Towards this objective, a Random Forest (RF) classifier is employed which effectively chooses the warp function components according to their importance in separating the feasible and the infeasible warp functions in the WFS. Extensive experiments on five datasets are carried out to show the superior performance of the proposed approach over state-of-the-art person re-identification methods. We show that our approach outperforms all other methods when large illumination variations are considered. At the same time it has been shown that our method reaches the best average performance over multiple combinations of the datasets, thus, showing that our method is not designed only to address a specific challenge posed by a particular dataset.

Self-Reconfigurable Smart Camera Networks

Camera networks that reconfigure while performing multiple tasks have unique requirements, such as concurrent task allocation with limited resources, the sharing of data among fields of view across the network, and coordination among heterogeneous devices.

Generalized neural trees for pattern classification

In this paper, a new neural tree (NT) model, the generalized NT (GNT), is presented. The main novelty of the GNT consists in the definition of a new training rule that performs an overall optimization of the tree. Each time the tree is increased by a new level, the whole tree is reevaluated. The training rule uses a weight correction strategy that takes into account the entire tree structure, and it applies a normalization procedure to the activation values of each node such that these values can be interpreted as a probability. The weight connection updating is calculated by minimizing a cost function, which represents a measure of the overall probability of correct classification. Significant results on both synthetic and real data have been obtained by comparing the classification performances among multilayer perceptrons (MLPs), NTs, and GNTs. In particular, the GNT model displays good classification performances for training sets having complex distributions. Moreover, its particular structure provides an easily probabilistic interpretation of the pattern classification task and allows growing small neural trees with good generalization properties.

Stereo rectification of uncalibrated and heterogeneous images

In this paper, an algorithm for rectifying heterogeneous and uncalibrated pairs of stereo images is presented. In particular, a pair of images is captured by using a combination of static and dynamic cameras at unequal zoom, thus having different focal lengths and/or image resolutions. The rectification of such pairs of images is made in two steps. In the first step, image shrinking based on focal ratios is performed for compensating the effect of unequal zoom levels followed by a zero padding on the smaller image for making the images of equal size. In the second step, rectification transformations are calculated by solving a nonlinear constrained optimization problem for a given set of pairs of corresponding points (SIFT descriptors) between stereo images. Experiments are performed to evaluate the performance of the proposed method and assess the improvements of the proposed method over direct rectification.

A balanced neural tree for pattern classification

This paper proposes a new neural tree (NT) architecture, balanced neural tree (BNT), to reduce tree size and improve classification with respect to classical NTs. To achieve this result, two main innovations have been introduced: (a) perceptron substitution and (b) pattern removal. The first innovation aims to balance the structure of the tree. If the last-trained perceptron largely misclassifies the given training set into a reduced number of classes, then this perceptron is substituted with a new perceptron. The second novelty consists of the introduction of a new criterion for the removal of tough training patterns that generate the problem of over-fitting. Finally, a new error function based on the depth of the tree is introduced to reduce perceptron training time. The proposed BNT has been tested on various synthetic and real datasets. The experimental results show that the proposed BNT leads to satisfactory results in terms of both tree depth reduction and classification accuracy.