Francesco Ziliani

Image analysis for video surveillance based on spatial regularization of a statistical model-based change detection

Advanced video surveillance applications require two successive steps: image analysis and content understanding. The first step analyses and extracts the characteristics of the video sequence. It defines the regions or the objects of interest according to their spatial/temporal properties. This analysis results in a segmentation of the video sequence. This is interpreted by the content understanding step according to the specific scenario and surveillance requirements. This paper addresses the image analysis problem for a video surveillance system. We use a statistical model-based change detection technique that defines the areas of interest in the image. Each area is analyzed separately by integrating spatial and temporal descriptors in a multi-feature clustering algorithm. The selective procedure we propose minimizes the computational load and significantly improves the results provided by the change detection technique. We test this method on both indoor and outdoor surveillance sequences. All the results show a correct segmentation of the scene. Moreover each object defined in the segmentation is described in terms of its spatial and temporal properties. These results can represent a valid input for a later content understanding procedure in several surveillance scenarios.

Performance evaluation of event detection solutions: the CREDS experience

In video surveillance projects, automatic and real-time event detection solutions are required to guarantee an efficient and cost-effective use of the infrastructure. Many solutions have been proposed to automatically detect a variety of events of interest. However, not all solutions and technologies may satisfy all the requirements of the surveillance scenario. For this reason, performance evaluation of existing event detection solutions becomes an important step in the deployment of video surveillance projects. In this paper, we propose a practical approach that aims at minimizing the ground truth generation problem and the expertise required to evaluate and compare the results by introducing specific requirements of specific event detection scenarios. This approach is believed to be applicable for an initial evaluation of candidate solutions to a specific surveillance scenario before more exhaustive tests in an integrated environment. The proposed method is under evaluation in the framework of the challenge of real-time event detection solutions (CREDS).

Image Analysis for Video Surveillance Based on Spatial Regularization of a Statistical Model-Based Change Detection

Advanced video surveillance applications require two successive phases: image analysis and content understanding. The first phase analyzes and extracts the characteristics of the video sequence. It defines the regions or the objects of interest according to their spatial/temporal properties. This image analysis results in a segmentation of the video sequence. This is interpreted by the content understanding phase according to the specific scenario and surveillance requirements. This paper addresses the image analysis problem for a video surveillance system. We apply a statistical model-based change detection technique that defines the areas of interest in the image. This method provides a reliable detection of the moving areas in the scene. It does not require fine tuning of any threshold along the sequence and it is computationally efficient. However, it is not able to provide an accurate spatial descriptions of the objects. In particular it fails in distinguishing shadows and reflections from real moving objects. In order to improve the spatial coherence of the change detection results, each area detected as changed is analyzed separately. Its spatial and temporal descriptors are integrated in a multi-feature clustering algorithm. This is able to distinguish the regions belonging to real objects from the regions representing their shadows and/or reflections. A successive refinement labels as background all those regions that are sufficiently similar to the background. The selective procedure we propose minimizes the computational load since only the changed areas in the image are processed. We test this method on both indoor and outdoor surveillance sequences. All the results show a correct segmentation of the scene. Moreover, each object defined in the segmentation is described in terms of its spatial and temporal properties. These results represent a valid input for a later content understanding procedure in several surveillance scenarios.

Object Oriented Motion-Segmentation for Video-Compression in the CNN-UM

Object-oriented motion segmentation is a basic step of the effective coding of image-series. Following the MPEG-4 standard we should define such objects. In this paper, a fully parallel and locally connected computation model is described for segmenting frames of image sequences based on spatial and motion information. The first type of the algorithm is called early segmentation. It is based on spatial information only and aims at providing an over-segmentation of the frame in real-time. Even if the obtained results do not minimize the number of regions, it is a good starting point for higher level post processing, when the decision on how to regroup regions in object can rely on both spatial and temporal information. In the second type of the algorithm stochastic optimization methods are used to form homogenous dense optical vector fields which act directly on motion vectors instead of 2D or 3D motion parameters. This makes the algorithm simple and less time consuming than many other relaxation methods. Then we apply morphological operators to handle disocclusion effects and to map the motion field to the spatial content. Computer simulations of the CNN architecture demonstrate the usefulness of our methods. All solutions in our approach suggest a fully parallel implementation in a newly developed CNN-UM VLSI chip architecture.

Image Analysis for Advanced Video Surveillance

More and more cameras are available on the market and their prices continuously decrease. This cost effectiveness lets a video surveillance system be easily adopted. Moreover the spread of cameras for surveillance purposes increases dramatically the visual data to be analyzed. The great amount of visual material to be viewed and the limit of the human attention in front of a monitor require automatic methods to interpret the content of surveillance video sequences. Because of the variety of scenarios, an automatic system has to behave differently according to the particular application. In the case of surveillance of banks, for instance, an intrusion has to be detected. Consequently the system is expected to generate an alarm for the intervention of a human operator. In the case of highway surveillance, on the other hand, the target is to compute statistics about the traffic and to generate alarms in case of an emergency or anomalous situations. The events leading to an alarm are of different nature, i.e. an accident, a traffic jam, a vehicle stopped on the emergency lane.