Moving object detection and tracking in video surveillance systems is commonly based on background estimation and subtraction. For satisfactory performance in real world applications, robust estimators, tolerating the presence of outliers in the data, are needed. Nonparametric kernel density estimation has been successfully used in modeling the background statistics, due to its capability to perform well without making any assumption about the form of the underlying distributions. However, in real-time applications, the O(N 2) complexity of the method can be a bottleneck, preventing the object tracking and event analysis modules from having the computing time needed. In this paper, we propose a new background subtraction technique, using multiresolution and recursive density estimation with mean shift based mode tracking. An algorithm with complexity independent on N is developed for fast, real-time implementation. Comparative results with known methods are included, in order to attest the effectiveness and quality of the proposed approach.

No abstract

Citizen safety in modern urban environments is an important aspect of life quality. Implementation of a smart city approach to video surveillance depends heavily on the capability of gathering and processing huge amounts of live urban data. Analyzing data from high bandwidth surveillance video streams provided by large size distributed sensor networks is particularly challenging. We propose here an efficient method for automatic violent behavior detection designed for video sensor networks. Known solutions to real-time violence detection are not suitable for implementation in a resource-constrained environment due to the high processing power requirements. Our algorithm achieves real-time processing on a Raspberry PI-embedded architecture. To ensure separation of temporal and spatial information processing we employ a computationally effective cascaded approach. It consists of a deep neural network followed by a time domain classifier. In contrast with current approaches, the deep neural network input is fed exclusively with motion vector features extracted directly from the MPEG encoded video stream. As proven by results, we achieve state-of-the-art performance, while running on a low computational resources embedded architecture.

Distributed sensing, computing and communication capabilities of wireless sensor networks require, in most situations, an efficient node localization procedure. In the case of random deployments in harsh or hostile environments, a general localization process within global coordinates is based on a set of anchor nodes able to determine their own position using GPS receivers. In this paper we propose another anchor node localization technique that can be used when GPS devices cannot accomplish their mission or are considered to be too expensive. This novel technique is based on the fusion of video and compass data acquired by the anchor nodes and is especially suitable for video-or multimedia-based wireless sensor networks. For these types of wireless networks the presence of video cameras is intrinsic, while the presence of digital compasses is also required for identifying the cameras' orientations.

No abstract