Katarzyna Gościewska

SmartMonitor: an approach to simple, intelligent and affordable visual surveillance system

The paper provides fundamental information about the SmartMonitor --- an innovative surveillance system based on video content analysis. We present a short introduction to the characteristics of the developed system and a brief review of methods commonly applied in surveillance systems nowadays. The main goal of the paper is to describe planned basic system parameters as well as to explain the reason for creating it. SmartMonitor is being currently developed but some experiments have already been performed and their results are provided as well.

SmartMonitor--an intelligent security system for the protection of individuals and small properties with the possibility of home automation.

“SmartMonitor” is an intelligent security system based on image analysis that combines the advantages of alarm, video surveillance and home automation systems. The system is a complete solution that automatically reacts to every learned situation in a pre-specified way and has various applications, e.g., home and surrounding protection against unauthorized intrusion, crime detection or supervision over ill persons. The software is based on well-known and proven methods and algorithms for visual content analysis (VCA) that were appropriately modified and adopted to fit specific needs and create a video processing model which consists of foreground region detection and localization, candidate object extraction, object classification and tracking. In this paper, the “SmartMonitor” system is presented along with its architecture, employed methods and algorithms, and object analysis approach. Some experimental results on system operation are also provided. In the paper, focus is put on one of the aforementioned functionalities of the system, namely supervision over ill persons.

Application of foreground object patterns analysis for event detection in an innovative video surveillance system

SmartMonitor is an innovative surveillance system based on video content analysis. It is a modular solution that can work in several predefined scenarios mainly concerned with home/surrounding protection against unauthorized intrusion, supervision over ill person and crime detection. Each scenario is associated with several actions and conditions, which imply the utilization of algorithms with various input parameters. In this paper, focus is put on the analysis of foreground object patterns for the purposes of event recognition, as well as the experimental investigation of selected methods and algorithms which were developed and employed for the SmartMonitor system prototype. The prototype performs three main tasks: detection and localization of foreground regions using adaptive background modelling based on Gaussian Mixture Models, candidate objects extraction and classification using Haar and HOG descriptors, and tracking using Mean-Shift algorithm. The main goal of the work described here is to match system parameters with each scenario to provide the highest effectiveness and to decrease the number of false alarms.

Extraction of the Foreground Regions by Means of the Adaptive Background Modelling Based on Various Colour Components for a Visual Surveillance System

Intelligent monitoring systems based on visual content analysis are often composed of three main modules — background modelling, object extraction and object tracking. This paper describes a method for adaptive background modelling utilizing Gaussian Mixture Models (GMM) and various colour components. The description is based on the experimental results obtained during the development of the SmartMonitor — an innovative security system based on video content analysis. In this paper the main characteristics of the system are introduced. An explanation of GMM algorithm and a presentation of its main advantages and drawbacks is provided. Finally, some experimentally obtained images containing foreground regions extracted with the use of various background models are presented.

The Removal of False Detections from Foreground Regions Extracted Using Adaptive Background Modelling for a Visual Surveillance System

For recent surveillance systems, the false detection removal process is an important step which succeeds the extraction of foreground regions and precedes the classification of object silhouettes. This paper describes the false object removal process when applied to the ’SmartMonitor’ system — i.e. an innovative monitoring system based on video content analysis that is currently being developed to ensure the safety of people and assets within small areas. This paper firstly briefly describes the basic characteristics and advantages of the system. A description of the methods used for background modelling and foreground extraction is also given. The paper then goes on to explain the artefacts removal process using various background models. Finally the paper presents some experimental results alongside a concise explanation of them.

Automatic Analysis of Vehicle Trajectory Applied to Visual Surveillance

In this paper we discuss a problem of automatic analysis of vehicles trajectories in the context of illegal movements. It is crucial to detect restricted or security critical behaviour on roads, especially for safety protection and fluent traffic. Here, we propose an vision-based algorithm for vehicle detection and tracking, which is later employed to recognize patterns in resultant trajectories. Experiments were performed on real video streams. They gave encouraging results.

Applying Image Features and AdaBoost Classification for Vehicle Detection in the ‘SM4Public’ System

The main goal of works described in the paper is to test and select algorithms to be implemented in the ‘SM4Public’ security system for public spaces. The paper describes the use of cascading approaches in the scenario concerning the detection of vehicles in static images. Three feature extractors were used along with benchmark datasets in order to prepare eight various cascades of classifiers. The algorithms selected for feature extraction are Histogram of Oriented Gradients, Local Binary Patterns and Haar-like features. AdaBoost was used as a classifier. The paper briefly introduces the ‘SM4Public’ system characteristics, characterizes the employed algorithms and presents sample experimental results.

Application of 2D Fourier Descriptors and Similarity Measures to the General Shape Analysis Problem

The General Shape Analysis (GSA) is a problem of finding the most similar basic shape to the test one. It is close to traditional recognition or retrieval of shapes. Main difference is that GSA does not aim at the identification of an exact object shape but at the indication of one or few most similar to it general templates --- simple shape figures, e.g. rectangle, circle or triangle. By comparing more complicated shapes with simple ones it is possible to determine the most general information about a particular object. In order to perform the comparison using the template matching approach it is necessary to define methods for the representation and similarity estimation of shapes. In this paper the attention is paid to two-dimensional Fourier Descriptor applied for the representation of a shape and two matching methods, namely Euclidean distance and correlation. The effectiveness of the shape descriptor is estimated as a convergence between the experimental results and results provided by humans through the inquiry forms concerning the same GSA task. Performed experiments allowed us to determine the influence of the matching method on the final effectiveness of the approach applying Fourier Descriptors. Selection of the absolute spectrum subpart size is also discussed.

Moment Shape Descriptors Applied for Action Recognition in Video Sequences

Algorithms for recognition of human activities have found application in many computer vision systems, for example in visual content analysis approaches and in video surveillance systems, where they can be employed for the recognition of single gestures, simple actions, interactions and even behaviour. In this paper an approach for human action recognition based on shape analysis is presented. Set of binary silhouettes extracted from video sequences representing a person performing an action are used as input data. The developed approach is composed of several algorithms including those for shape representation and matching. It can deal with sequences of different number of frames and none of them has to be removed. The paper provides some initial experimental results on classification using proposed approach and moment shape description algorithms, namely the Zernike Moments, Moment Invariants and Contour Sequence Moments.

Action Recognition Using Silhouette Sequences and Shape Descriptors

The paper provides an approach for human action recognition based on shape analysis. The developed approach is intended for specific type of data, namely sequences of binary silhouettes representing a person performing an action, and consists of several processing steps including shape description as well as similarity or dissimilarity estimation. The approach can deal with sequences of different length without removing any frames. The paper also provides some experimental results showing the classification accuracy and overall recognition effectiveness of the proposed approach using several popular shape description algorithms, namely the Two-Dimensional Fourier Descriptor, Generic Fourier Descriptor, Point Distance Histogram and UNL-Fourier Descriptor.