Real-time video-shot detection for scene surveillance applications

Abstract

In this paper, a surveillance system with automatic video-shot detection and indexing capabilities is presented. The proposed system aims at detecting the presence of abandoned objects in a guarded environment and at automatically performing online semantic video segmentation in order to facilitate the human operator's task of retrieving the cause of an alarm. The former task is performed by operating image segmentation based on temporal rank-order filtering, followed by classification in order to reduce false alarms. The latter task is performed by operating temporal video segmentation when an alarm is detected. In the clips of interest, the key frame is the one depicting a person leaving a dangerous object, and is determined on the basis of a feature indicating the movement around the dangerous region. Experimental results are reported in terms of static region detection, classification, clip and key-frame detection errors versus different levels of complexity of the guarded environment, in order to establish the performance that can be expected from the system in different situations.

Scenario-based query processing for video-surveillance archives

“…Existing systems generally support textual searches for event queries (Shet et al, 2005;Stringa and Regazzoni, 2000). Some systems also support object queries to some extent (Hampapur et al, 2005).…”

Automatic Classification of Abandoned Objects for Surveillance of Public Premises

“…Generally, there are three main approaches to classification: shape-based classification (e.g., [1,[8][9][10]12]), motion-based classification (e.g., [3]) or combined shape-motion classification (e.g., [2,6,13]). …”

“…To date, in the visual surveillance research area, the literature reports attempts to analyze four main categories of objects, namely, person, vehicle, group of people, and package (e.g., [1,2,6,[8][9][10][12][13]). …”

“…In [1,10], the focus is on the classification of abandoned objects. In order to classify abandoned objects, only shape features can be used because the objects are static and no motion occurs.…”

Static Background Extraction and Updating Algorithm based on Adaptive Weights

“…The inter frame difference method has the advantage of less computation, strong robustness, and strong adaptability. The disadvantage is that it is difficult to extract the pixel point from the moving target, which is easier to produce void pixel [7] . The background difference method, as a method widely used in motion detection, is a key part of computer vision, effective segmentation of background and prospects for the follow-up tracking, object recognition, and behavior classification.…”