Visual sensor networks for infomobility

Abstract

The wide availability of embedded sensor platforms and low cost cameras-together with the developments in wireless communication-make it now possible the conception of pervasive intelligent sys tems based on vision. Such systems may be understood as distributed and collaborative sensor networks, able to produce, aggregate and process images in order to understand the observed scene and communicate the relevant information found about it. In this paper, we investigate the peculiarities of visual sensor networks with respect to standard vision systems and we identify possible strategies to accomplish image processing and analysis tasks over them. Although the rather strong constraints in computational and transmission power of embedded platforms that may prevent the use of state of the art computer vision and pattern recognition methods, we argue that multi node processing methods may be envisaged to decompose a complex task into a hierarchy of computationally simpler problems to be solved over the nodes of the network. These ideas are illustrated by describing an application of visual sensor network to infomobility. In particular, we consider an experimental setting in which several views of a parking lot are acquired by the sensor nodes in the network. By integrating the various views, the network is capable to provide a description of the scene in terms of the available spaces in the parking lot.

ScanTraffic: Smart Camera Network for Traffic Information Collection

“…For the sake of brevity, we use the name "flow sensor" to denote a smart camera running the former algorithm and the name "parking sensor" to denote a smart camera running the latter. As described in [10], those algorithms achieve an overall detection rate of 95% with a false alarm rate of 0.1%.…”

“…The goal of such visual WSNs is to collect information about parking lot occupancy and traffic flow. For this purpose, we used the two embedded vision algorithms described in [10]: one algorithm counts cars passing in a road section; the other algorithm detects the occupancy status of a set of parking spaces. For the sake of brevity, we use the name "flow sensor" to denote a smart camera running the former algorithm and the name "parking sensor" to denote a smart camera running the latter.…”

An Intelligent Cooperative Visual Sensor Network for Urban Mobility

“…In car-driven approaches, object detection methods, such as [ 18 ], are employed to detect cars in the observed images, while in space-driven approaches the aim is to asses the occupancy status of a set of predefined parking spaces imaged by the sensor. Change detection is often based on background subtraction [ 19 ]. For outdoor applications, background cannot be static but it should be modeled dynamically, to cope with issues such as illumination changes, shadows and weather conditions.…”

An Intelligent Parking Management System for Urban Areas

“…The sensors used are Anisotropic Magneto-Resistive (AMR) magnetic sensors, and the wireless communication link is established by ZigBee. Magrini [ 13 ] proposed a vision sensors network to monitor available spaces in public car parks, using distributed network nodes to perform the required processing and analysis of images. Chen [ 14 ] proposed a system for locating available spaces in indoor car parks and a guidance system to locate the available space.…”