Audio surveillance is gaining in the last years wide interest. This is due to the large number of situations in which this kind of systems can be used, either alone or combined with video-based algorithms. In this paper we propose a deep learning method to automatically recognize events of interest in the context of audio surveillance (namely screams, broken glasses and gun shots). The audio stream is represented by a gammatonegram image. We propose a 21-layer CNN to which we feed sections of the gammatonegram representation. At the output of this CNN there are units that correspond to the classes. We trained the CNN, called AReN, by taking advantage of a problemdriven data augmentation, which extends the training dataset with gammatonegram images extracted by sounds acquired with different signal to noise ratios. We experimented it with three datasets freely available, namely SESA, MIVIA Audio Events and MIVIA Road Events and we achieved 91.43%, 99.62% and 100% recognition rate, respectively. We compared our method with other state of the art methodologies based both on traditional machine learning methodologies and deep learning. The comparison confirms the effectiveness of the proposed approach, which outperforms the existing methods in terms of recognition rate.We experimentally prove that the proposed network is resilient to the noise, has the capability to significantly reduce the false positive rate and is able to generalize in different scenarios. Furthermore, AReN is able to process 5 audio frames per second on a standard CPU and, consequently, it is suitable for real audio surveillance applications.

This paper aims at dynamically understanding the properties of a scene from the analysis of moving object trajectories. Two different applications are proposed: the former is devoted to identify abnormal behaviors, while the latter allows to extract the k, most of the similar trajectories to the one hand-drawn by an human operator. A set of normal trajectories' models is extracted using a novel unsupervised learning technique: the scene is adaptively partitioned into zones using the distribution of the training set and each trajectory is represented as a sequence of symbols by considering positional information (the zones crossed in the scene), speed, and shape. The main novelty is the use of a kernel-based approach for evaluating the similarity between the trajectories. Furthermore, we define a novel and efficient kernel-based clustering algorithm, aimed at obtaining groups of normal trajectories. Experimentations, conducted over three standard data sets, confirm the effectiveness of the proposed approach.

Gender recognition has been among the most investigated problems in the last years; although several contributions have been proposed, gender recognition in unconstrained environments is still a challenging problem and a definitive solution has not been found yet. Furthermore, Deep Convolutional Neural Networks (DCNNs) achieve very interesting performance, but they typically require a huge amount of computational resources (CPU, GPU, RAM, storage), that are not always available in real systems, due to their cost or to specific application constraints (when the application needs to be installed directly on board of low-power smart cameras, e.g. for digital signage). In the latest years the Machine Learning community developed an interest towards optimizing the efficiency of Deep Learning solutions, in order to make them portable and widespread. In this work we propose a compact DCNN architecture for Gender Recognition from face images that achieves approximately state of the art accuracy at a highly reduced computational cost (almost five times). We also perform a sensitivity analysis in order to show how some changes in the architecture of the network can influence the tradeoff between accuracy and speed. In addition, we compare our optimized architecture with popular efficient CNNs on various common benchmark dataset, widely adopted in the scientific community, namely LFW, MIVIA-Gender, IMDB-WIKI and Adience, demonstrating the effectiveness of the proposed solution.

Visual tracking supported by unmanned aerial vehicles (UAVs) has generated a lot of interest in recent years, especially in application domains such as surveillance, search for missing persons and traffic monitoring. The major challenges in visual tracking with small UAVs arise in the form of target representation, target appearance change, target detection and localization in real time computation. Reliable target detection depends on factors such as occlusions, image noise, illumination and pose changes, or image blur that may compromise the object labeling. To mitigate these issues, this paper proposes a hybrid solution: along with the tracked objects, scenes are completely depicted by adding contextual information, i.e., data describing places, natural features, or in general points of interest. Each scenario indeed is semantically described by ontological statements that define the context and then, by inference, support the object tracking task in the object identification and labeling. The synergy between the tracking methods and semantic modeling can bridge the object labeling gap, enhancing the scene understanding and awareness when alarming situations are discovered. Experimental results are promising and confirm the applicability of the proposed framework in supporting drones in object identification and critical situation detection tasks.